Article(id=1324427132184702992, tenantId=1146029695717560320, journalId=1240685776644648972, issueId=1324426994615727048, articleNumber=null, orderNo=null, doi=10.3969/j.issn.1007-7294.2026.09.006, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=1773590400000, receivedDateStr=2026-03-16, revisedDate=null, revisedDateStr=null, acceptedDate=null, acceptedDateStr=null, onlineDate=1793697634978, onlineDateStr=2026-11-03, pubDate=1789401600000, pubDateStr=2026-09-15, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1793697634978, onlineIssueDateStr=2026-11-03, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1793697634978, creator=13701087609, updateTime=1793697634978, updator=13701087609, issue=Issue{id=1324426994615727048, tenantId=1146029695717560320, journalId=1240685776644648972, year='2026', volume='30', issue='9', pageStart='1397', pageEnd='1576', issueExtLink='null', onlineDate='null', pubDate='1789401600000', pubDateStr='2026-09-15', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=1, specialIssue=null, createTime=1793697602180, creator='13701087609', updateTime=1793699937016, updator='13701087609', preIssue=null, nextIssue=null, articleTotal=null, ext={EN=IssueExt(id=1324436787699000005, tenantId=1146029695717560320, journalId=1240685776644648972, issueId=1324426994615727048, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1324436787699000006, tenantId=1146029695717560320, journalId=1240685776644648972, issueId=1324426994615727048, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null, downloadFileDto=null}, startPage=1461, endPage=1472, ext={EN=ArticleExt(id=1324427132839014417, articleId=1324427132184702992, tenantId=1146029695717560320, journalId=1240685776644648972, language=EN, title=Compensation design of ship attitude based on CNN-BiLSTM prediction, columnId=1241023037940748650, journalTitle=Journal of Ship Mechanics, columnName=Hydrodynamics, runingTitle=null, highlight=null, articleAbstract=

During maritime operations, ships are subject to wave-induced disturbances, resulting in complex multi-degree-of-freedom motions that severely affect the stability of ships during offshore operations. To address this challenge, this study proposes a CNN-BiLSTM hybrid prediction model for real-time ship attitude forecasting and designs a dual-layer Stewart platform compensation mechanism to mitigate ship motion effects. To overcome sensor latency and noise interference, 2011 ship attitude samples collected in the South China Sea were first filtered using a Savitzky-Golay (SG) filter. The processed data were then fed into the CNN-BiLSTM hybrid prediction model, which significantly improved the accuracy of attitude prediction. Furthermore, a platform kinematic model was established using the closed-loop vector method. The predicted data were utilized to compensate the dual-layer Stewart platform, enabling coordinated control between the lower platform (simulating wave disturbances) and the upper platform (performing dynamic compensation). Experimental results demonstrate that the proposed approach achieves effective ship attitude compensation and provides a feasible solution for stable landing operations of unmanned aerial vehicles (UAVs) at sea.

, authors=Juan WANG1, 2, Zong-bing JIANG1, 3, Qiu-xia QU1, Peng LI2, authorsList=Juan WANG, Zong-bing JIANG, Qiu-xia QU, Peng LI, authorCompany=null, correspAuthors=null, authorNote=null, correspAuthorsNote=null, copyrightStatement=Copyright ©2026 Journal of Ship Mechanics. All rights reserved., copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=null, magXml=null, pdfUrl=null, pdf=null, pdfFileSize=null, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=null, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=null, mapNumber=null, fund=null), CN=ArticleExt(id=1324427164183048431, articleId=1324427132184702992, tenantId=1146029695717560320, journalId=1240685776644648972, language=CN, title=基于CNN-BiLSTM预测的船舶姿态补偿设计, columnId=1241023038087549292, journalTitle=船舶力学, columnName=流体力学, runingTitle=null, highlight=null, articleAbstract=

船舶在海上作业时会受到波浪的扰动,造成船舶多自由度的复合运动,极大影响船舶在海上作业时的稳定性。因此,本文提出一种CNN-BiLSTM融合的预测模型,对船舶姿态进行实时预测,并设计双层Stewart平台补偿机构,以实现对船舶运动的有效补偿。为消除传感器延时与噪声的干扰,首先用SG滤波器(Savitzky-Golay)对南海采集到的2011个船舶姿态样本数据进行滤波,并使用CNN-BiLSTM融合预测模型对姿态数据进行预测,该模型显著提升了船舶姿态预测的精度。进一步通过闭环矢量法构建平台运动学模型,利用预测后的数据对双层Stewart平台进行补偿,实现底层平台模拟波浪扰动与顶层平台动态补偿的协同控制。实验数据表明,该研究能够取得良好的船舶姿态补偿效果,为海上无人机平稳降落提供了可行的解决方案。

, authors=王娟1, 2, 江宗兵1, 3, 屈秋霞1, 李鹏2, authorsList=王娟, 江宗兵, 屈秋霞, 李鹏, authorCompany=null, correspAuthors=null, authorNote=

王 娟(1984–),女,博士,副教授,E-mail:

, correspAuthorsNote=null, copyrightStatement=版权所有©《船舶力学》编辑部2026, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=kaHFZA1eeaUeABC7Y1yz8w==, magXml=JOD/1JZIsQYAVx75YCy/+g==, pdfUrl=null, pdf=XJpRoxpFVRqJLIEasBxLcg==, pdfFileSize=2311231, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=Ah5cUpDoKgswuqxkuQS5IA==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=ms2Zr6rOK9xEZhWrkdKPvQ==, mapNumber=null, fund=null)}, authors=[Author(id=1324427312120332665, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=wangjuan@sjzu.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1324427312279716220, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, authorId=1324427312120332665, language=EN, stringName=Juan WANG, firstName=Juan, middleName=null, lastName=WANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1School of Electrical and Control Engineering, Shenyang Jianzhu University, Shenyang 110168, China
2State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110169, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1324427312405545341, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, authorId=1324427312120332665, language=CN, stringName=王娟, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1沈阳建筑大学 电气与控制工程学院,沈阳 110168
2中国科学院沈阳自动化研究所 机器人学国家重点实验室,沈阳 110169, bio={"content":"

王 娟(1984–),女,博士,副教授,E-mail:

"}, bioImg=null, bioContent=

王 娟(1984–),女,博士,副教授,E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1324427311830925679, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, xref=1, ext=[AuthorCompanyExt(id=1324427311843508592, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, companyId=1324427311830925679, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1School of Electrical and Control Engineering, Shenyang Jianzhu University, Shenyang 110168, China), AuthorCompanyExt(id=1324427311864480113, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, companyId=1324427311830925679, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1沈阳建筑大学 电气与控制工程学院,沈阳 110168)]), AuthorCompany(id=1324427311931588978, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, xref=2, ext=[AuthorCompanyExt(id=1324427311939977587, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, companyId=1324427311931588978, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110169, China), AuthorCompanyExt(id=1324427311948366196, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, companyId=1324427311931588978, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2中国科学院沈阳自动化研究所 机器人学国家重点实验室,沈阳 110169)])]), Author(id=1324427312522985855, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1324427312627843458, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, authorId=1324427312522985855, language=EN, stringName=Zong-bing JIANG, firstName=Zong-bing, middleName=null, lastName=JIANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 3, address=1School of Electrical and Control Engineering, Shenyang Jianzhu University, Shenyang 110168, China
3Taiyuan Heavy Machinery Group Yuci Hydraulic Industry (Jinan) Co., Ltd., Automation Department, Jinan 250100, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1324427312745283971, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, authorId=1324427312522985855, language=CN, stringName=江宗兵, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 3, address=1沈阳建筑大学 电气与控制工程学院,沈阳 110168
3太重集团榆次液压工业(济南)有限公司 自动化部,济南 250100, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1324427311830925679, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, xref=1, ext=[AuthorCompanyExt(id=1324427311843508592, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, companyId=1324427311830925679, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1School of Electrical and Control Engineering, Shenyang Jianzhu University, Shenyang 110168, China), AuthorCompanyExt(id=1324427311864480113, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, companyId=1324427311830925679, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1沈阳建筑大学 电气与控制工程学院,沈阳 110168)]), AuthorCompany(id=1324427312040640885, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, xref=3, ext=[AuthorCompanyExt(id=1324427312049029494, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, companyId=1324427312040640885, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3Taiyuan Heavy Machinery Group Yuci Hydraulic Industry (Jinan) Co., Ltd., Automation Department, Jinan 250100, China), AuthorCompanyExt(id=1324427312057418103, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, companyId=1324427312040640885, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3太重集团榆次液压工业(济南)有限公司 自动化部,济南 250100)])]), Author(id=1324427312820781445, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, orderNo=2, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1324427312908861831, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, authorId=1324427312820781445, language=EN, stringName=Qiu-xia QU, firstName=Qiu-xia, middleName=null, lastName=QU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1School of Electrical and Control Engineering, Shenyang Jianzhu University, Shenyang 110168, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1324427312988553608, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, authorId=1324427312820781445, language=CN, stringName=屈秋霞, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1沈阳建筑大学 电气与控制工程学院,沈阳 110168, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1324427311830925679, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, xref=1, ext=[AuthorCompanyExt(id=1324427311843508592, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, companyId=1324427311830925679, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1School of Electrical and Control Engineering, Shenyang Jianzhu University, Shenyang 110168, China), AuthorCompanyExt(id=1324427311864480113, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, companyId=1324427311830925679, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1沈阳建筑大学 电气与控制工程学院,沈阳 110168)])]), Author(id=1324427313068245386, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, orderNo=3, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1324427313164714380, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, authorId=1324427313068245386, language=EN, stringName=Peng LI, firstName=Peng, middleName=null, lastName=LI, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110169, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1324427313244406157, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, authorId=1324427313068245386, language=CN, stringName=李鹏, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2中国科学院沈阳自动化研究所 机器人学国家重点实验室,沈阳 110169, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1324427311931588978, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, xref=2, ext=[AuthorCompanyExt(id=1324427311939977587, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, companyId=1324427311931588978, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110169, China), AuthorCompanyExt(id=1324427311948366196, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, companyId=1324427311931588978, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2中国科学院沈阳自动化研究所 机器人学国家重点实验室,沈阳 110169)])])], keywords=[Keyword(id=1324427315022791054, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, language=EN, orderNo=1, keyword=ship attitude prediction), Keyword(id=1324427315123454351, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, language=EN, orderNo=2, keyword=dual-layer Stewart platform compensation system), Keyword(id=1324427315211534736, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, language=EN, orderNo=3, keyword=CNN-BiLSTM prediction), Keyword(id=1324427315274449297, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, language=CN, orderNo=1, keyword=船舶姿态预测), Keyword(id=1324427315341558162, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, language=CN, orderNo=2, keyword=双层Stewart平台补偿系统), Keyword(id=1324427315412861331, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, language=CN, orderNo=3, keyword=CNN-BiLSTM预测)], refs=[Reference(id=1324427321037423039, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=1, rfOrder=0, authorNames=null, journalName=null, refType=null, unstructuredReference=Chen N, Huang D L, et al. A novel inertial parameter identification method for the ship-mounted Stewart platform based on a wave compensation platform[J]. Measurement, 2025, 242: 116010., articleTitle=null, refAbstract=null), Reference(id=1324427321104531904, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=2, rfOrder=1, authorNames=null, journalName=null, refType=null, unstructuredReference=Tang G, Lei J, et al. A modified 6-DOF hybrid serial–parallel platform for ship wave compensation[J]. Ocean Engineering, 2023, 280: 114336., articleTitle=null, refAbstract=null), Reference(id=1324427321196806593, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=3, rfOrder=2, authorNames=null, journalName=null, refType=null, unstructuredReference=Li D, Wang S, et al. A BP-Neural-Network-based PID control algorithm of shipborne Stewart platform for wave compensation[J]. Journal of Marine Science and Engineering, 2024, 12(12): 2160., articleTitle=null, refAbstract=null), Reference(id=1324427321293275586, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=4, rfOrder=3, authorNames=null, journalName=null, refType=null, unstructuredReference=Cai Y, Zheng S, et al. Sliding-mode control of ship-mounted Stewart platforms for wave compensation using velocity feedforward[J]. Ocean Engineering, 2021, 236: 109477., articleTitle=null, refAbstract=null), Reference(id=1324427321368773059, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=5, rfOrder=4, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhou Y, She J, et al. Disturbance rejection for Stewart platform based on integration of equivalent-input-disturbance and sliding-mode control methods[J]. IEEE/ASME Transactions on Mechatronics, 2023, 28(4): 2364-2374., articleTitle=null, refAbstract=null), Reference(id=1324427321456853444, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=6, rfOrder=5, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhang Q, Wang X, et al. Wave heave compensation based on an optimized backstepping control method[J]. China Ocean Engineering, 2022, 36(6): 959-968., articleTitle=null, refAbstract=null), Reference(id=1324427321532350917, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=7, rfOrder=6, authorNames=null, journalName=null, refType=null, unstructuredReference=张 琴, 蔡慧茹, 等. 基于改进麻雀优化PID的波浪补偿控制方法[J]. 工程科学与技术, 2024, 56(1): 22‒34., articleTitle=null, refAbstract=null), Reference(id=1324427321670762950, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=7, rfOrder=7, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhang Q, Cai H R, et al. An improved sparrow search algorithm optimized control strategy for active wave compensation[J]. Advanced Engineering Sciences, 2024, 56(1): 22‒34. (in Chinese), articleTitle=null, refAbstract=null), Reference(id=1324427321754649031, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=8, rfOrder=8, authorNames=null, journalName=null, refType=null, unstructuredReference=常宗瑜, 刘 波. 基于Stewart机构的船载运动补偿装置的动力学模拟[J]. 机械设计, 2019, 36(S2): 37‒40., articleTitle=null, refAbstract=null), Reference(id=1324427321830146504, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=8, rfOrder=9, authorNames=null, journalName=null, refType=null, unstructuredReference=Chang Z Y, Liu B. Dynamic simulation of shipboard motion compensation device based on Stewart platform[J]. Journal of Machine Design, 2019, 36(S2): 37‒40. (in Chinese), articleTitle=null, refAbstract=null), Reference(id=1324427321930809801, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=9, rfOrder=10, authorNames=null, journalName=null, refType=null, unstructuredReference=Gong M, Yan C, et al. Short-term wind power forecasting model based on temporal convolutional network and informer[J]. Energy, 2023, 283: 129171., articleTitle=null, refAbstract=null), Reference(id=1324427322014695882, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=10, rfOrder=11, authorNames=null, journalName=null, refType=null, unstructuredReference=尚凡成, 李传庆, 等. 改进LSTM神经网络在极短期波浪时序预报中的应用[J]. 上海交通大学学报, 2023, 57(6): 659‒665., articleTitle=null, refAbstract=null), Reference(id=1324427322090193355, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=10, rfOrder=12, authorNames=null, journalName=null, refType=null, unstructuredReference=Shang F C, Li C Q, et al. Application of improved LSTM neural network in time-series prediction of extreme short-term wave[J]. Journal of Shanghai Jiao Tong University, 2023, 57(6): 659‒665. (in Chinese), articleTitle=null, refAbstract=null), Reference(id=1324427322190856652, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=11, rfOrder=13, authorNames=null, journalName=null, refType=null, unstructuredReference=张 彪, 彭秀艳, 等. 基于ELM-EMD-LSTM组合模型的船舶运动姿态预测[J]. 船舶力学, 2020, 24(11): 1413‒1421., articleTitle=null, refAbstract=null), Reference(id=1324427323851801037, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=11, rfOrder=14, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhang B, Peng X Y, et al. Ship motion attitude prediction based on ELM-EMD-LSTM integrated model[J]. Journal of Ship Mechanics, 2020, 24(11): 1413‒1421. (in Chinese), articleTitle=null, refAbstract=null), Reference(id=1324427323923104206, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=12, rfOrder=15, authorNames=null, journalName=null, refType=null, unstructuredReference=陈占阳, 占正勇, 等. 长短期记忆神经网络在船舶迎浪运动多时间尺度实时预测中的应用研究[J]. 船舶力学, 2024, 28(12): 1803‒1819., articleTitle=null, refAbstract=null), Reference(id=1324427324002795983, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=12, rfOrder=16, authorNames=null, journalName=null, refType=null, unstructuredReference=Chen Z Y, Zhan Z Y, et al. A framework of LSTM neural network model in multi-time scale real-time prediction of ship motions in head waves[J]. Journal of Ship Mechanics, 2024, 28(12): 1803‒1819. (in Chinese), articleTitle=null, refAbstract=null), Reference(id=1324427324069904848, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=13, rfOrder=17, authorNames=null, journalName=null, refType=null, unstructuredReference=Wang Y C, Wang H, et al. Ship roll prediction algorithm based on Bi-LSTM-TPA combined model[J]. Journal of Marine Science and Engineering, 2021, 9(4): 387-387., articleTitle=null, refAbstract=null), Reference(id=1324427324162179537, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=14, rfOrder=18, authorNames=null, journalName=null, refType=null, unstructuredReference=朱沛樵, 丁 军, 等. 基于GRU模型的船舶运动与载荷快速预报研究[J]. 船舶力学, 2025, 29(3): 337‒350., articleTitle=null, refAbstract=null), Reference(id=1324427324229288402, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=14, rfOrder=19, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhu P Q, Ding J, et al. Rapid prediction of ship motion and load based on GRU neural network[J]. Journal of Ship Mechanics, 2025, 29(3): 337‒350. (in Chinese), articleTitle=null, refAbstract=null), Reference(id=1324427324308980179, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=15, rfOrder=20, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhang W, Wu P, et al. Roll motion prediction of unmanned surface vehicle based on coupled CNN and LSTM[J]. Future Internet, 2019, 11(11): 243., articleTitle=null, refAbstract=null), Reference(id=1324427324380283348, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=16, rfOrder=21, authorNames=null, journalName=null, refType=null, unstructuredReference=Yuan P Y, Zhao W G, et al. Intelligent prediction algorithm of ship roll and pitch motion based on SSA-optimized BiLSTM network[J]. Ocean Engineering, 2025, 320: 120331., articleTitle=null, refAbstract=null), Reference(id=1324427324443197909, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=17, rfOrder=22, authorNames=null, journalName=null, refType=null, unstructuredReference=Liu W, Cao Y. Research on offshore vessel trajectory prediction based on PSO-CNN-RGRU-attention[J]. Applied Sciences, 2025, 15(7): 3625-3625., articleTitle=null, refAbstract=null), Reference(id=1324427324501918166, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=18, rfOrder=23, authorNames=null, journalName=null, refType=null, unstructuredReference=Chang S W, Lyu Z, et al. Automated six-degree-of-freedom Stewart platform for heavy floor tiling[J]. Automation in Construction, 2025, 170: 105932., articleTitle=null, refAbstract=null), Reference(id=1324427324573221335, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=19, rfOrder=24, authorNames=null, journalName=null, refType=null, unstructuredReference=Wen S R, Jing J Y, et al. Vibration isolation of a double-layered Stewart platform with local oscillators[J]. Mechanics of Advanced Materials and Structures, 2022, 29(27): 6685-6693., articleTitle=null, refAbstract=null), Reference(id=1324427324648718808, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=20, rfOrder=25, authorNames=null, journalName=null, refType=null, unstructuredReference=Wen S Q, Zhang W R, et al. An enhanced principal component analysis method with Savitzky-Golay filter and clustering algorithm for sensor fault detection and diagnosis[J]. Applied Energy, 2023, 337., articleTitle=null, refAbstract=null), Reference(id=1324427324715827673, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=21, rfOrder=26, authorNames=null, journalName=null, refType=null, unstructuredReference=孔杰杰, 王检耀, 等. 一种新型多旋翼无人机着舰装置及安全边界评估方法[J]. 中国舰船研究, 2024, 19(1): 272‒279., articleTitle=null, refAbstract=null), Reference(id=1324427324774547930, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=21, rfOrder=27, authorNames=null, journalName=null, refType=null, unstructuredReference=Kong J J, Wang J Y, et. al. A new multi-rotor UAV landing device and safety boundary assessment method[J]. Chinese Journal of Ship Research, 2024, 19(1): 272‒279. (in Chinese), articleTitle=null, refAbstract=null)], funds=[Fund(id=1324427320848679358, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, awardId=null, language=CN, fundingSource=机器人学国家重点实验室开放基金(2024-O22);辽宁省国际产业技术研发项目(2025JH2/101900038), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1324427311830925679, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, xref=1, ext=[AuthorCompanyExt(id=1324427311843508592, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, companyId=1324427311830925679, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1School of Electrical and Control Engineering, Shenyang Jianzhu University, Shenyang 110168, China), AuthorCompanyExt(id=1324427311864480113, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, companyId=1324427311830925679, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1沈阳建筑大学 电气与控制工程学院,沈阳 110168)]), AuthorCompany(id=1324427311931588978, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, xref=2, ext=[AuthorCompanyExt(id=1324427311939977587, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, companyId=1324427311931588978, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110169, China), AuthorCompanyExt(id=1324427311948366196, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, companyId=1324427311931588978, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2中国科学院沈阳自动化研究所 机器人学国家重点实验室,沈阳 110169)]), AuthorCompany(id=1324427312040640885, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, xref=3, ext=[AuthorCompanyExt(id=1324427312049029494, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, companyId=1324427312040640885, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3Taiyuan Heavy Machinery Group Yuci Hydraulic Industry (Jinan) Co., Ltd., Automation Department, Jinan 250100, China), AuthorCompanyExt(id=1324427312057418103, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, companyId=1324427312040640885, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3太重集团榆次液压工业(济南)有限公司 自动化部,济南 250100)])], figs=[ArticleFig(id=1324427315609993620, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, language=EN, label=Fig.1, caption=Model prediction process, figureFileSmall=UDFuDcmhTN87lC1MH/3Tnw==, figureFileBig=Ah5cUpDoKgswuqxkuQS5IA==, tableContent=null), ArticleFig(id=1324427315744211349, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, language=CN, label=图1, caption=模型预测流程图, figureFileSmall=UDFuDcmhTN87lC1MH/3Tnw==, figureFileBig=Ah5cUpDoKgswuqxkuQS5IA==, tableContent=null), ArticleFig(id=1324427315857457558, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, language=EN, label=Fig.2, caption=Double-layered Stewart platform, figureFileSmall=03ujpTPLt966uGJcWdWjUA==, figureFileBig=HOt7A1Ua+B5WEoKGBZKAzw==, tableContent=null), ArticleFig(id=1324427315932955031, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, language=CN, label=图2, caption=双层Stewart平台结构图, figureFileSmall=03ujpTPLt966uGJcWdWjUA==, figureFileBig=HOt7A1Ua+B5WEoKGBZKAzw==, tableContent=null), ArticleFig(id=1324427316008452504, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, language=EN, label=Fig.3, caption=Coordinate system of stewart platform, figureFileSmall=T9lJlmueOrjSd9eqowKrXA==, figureFileBig=MWecRWlB5qBxop/zjLdU6Q==, tableContent=null), ArticleFig(id=1324427316155253145, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, language=CN, label=图3, caption=双层Stewart平台坐标系, figureFileSmall=T9lJlmueOrjSd9eqowKrXA==, figureFileBig=MWecRWlB5qBxop/zjLdU6Q==, tableContent=null), ArticleFig(id=1324427316239139226, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, language=EN, label=Fig.4, caption=Compensation platform joints in the coordinate system, figureFileSmall=hKF3d/tJNrWmnI078XYclw==, figureFileBig=Nw/cmdVl04iycusSgxmm5w==, tableContent=null), ArticleFig(id=1324427316314636699, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, language=CN, label=图4, caption=补偿平台铰点在坐标系中的位置图, figureFileSmall=hKF3d/tJNrWmnI078XYclw==, figureFileBig=Nw/cmdVl04iycusSgxmm5w==, tableContent=null), ArticleFig(id=1324427316394328476, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, language=EN, label=Fig.5, caption=Moving platform joints in the coordinate system, figureFileSmall=IDZdPfs8hRFHsE/0ZNJwow==, figureFileBig=q4Q8OL97fUzhEb8pi5x28A==, tableContent=null), ArticleFig(id=1324427316469825949, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, language=CN, label=图5, caption=干扰平台铰点在坐标系中的位置图, figureFileSmall=IDZdPfs8hRFHsE/0ZNJwow==, figureFileBig=q4Q8OL97fUzhEb8pi5x28A==, tableContent=null), ArticleFig(id=1324427316557906334, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, language=EN, label=Fig.6, caption=Schematic diagram of SG filter fitting, figureFileSmall=YS36v1g/DRkH9vj0le8TEg==, figureFileBig=D8J7O4TaUL8hBEc4gGOYDw==, tableContent=null), ArticleFig(id=1324427316625015199, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, language=CN, label=图6, caption=SG滤波器原理图, figureFileSmall=YS36v1g/DRkH9vj0le8TEg==, figureFileBig=D8J7O4TaUL8hBEc4gGOYDw==, tableContent=null), ArticleFig(id=1324427316708901280, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, language=EN, label=Fig.7, caption=Comparison of data before and after filtering, figureFileSmall=alnpN1qtxPMIe5CduUVeNw==, figureFileBig=oY63jwMo0/a76Pf2km0png==, tableContent=null), ArticleFig(id=1324427316771815841, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, language=CN, label=图7, caption=滤波前后对比, figureFileSmall=alnpN1qtxPMIe5CduUVeNw==, figureFileBig=oY63jwMo0/a76Pf2km0png==, tableContent=null), ArticleFig(id=1324427316859896226, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, language=EN, label=Fig.8, caption=LSTM prediction results for pitch attitude, figureFileSmall=5Bl/p/6AXNNeOo907arv2w==, figureFileBig=e9XIkvY8qUP2WfyAyFCuKg==, tableContent=null), ArticleFig(id=1324427316952170915, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, language=CN, label=图8, caption=LSTM模型俯仰姿态预测结果, figureFileSmall=5Bl/p/6AXNNeOo907arv2w==, figureFileBig=e9XIkvY8qUP2WfyAyFCuKg==, tableContent=null), ArticleFig(id=1324427317057028516, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, language=EN, label=Fig.9, caption=BiLSTM prediction results for pitch attitude, figureFileSmall=AD+sW6pcEqInTlBrKV74xA==, figureFileBig=SsQMBE7KSqsXcVwVQ/3Nxw==, tableContent=null), ArticleFig(id=1324427317132525989, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, language=CN, label=图9, caption=BiLSTM模型俯仰姿态预测结果, figureFileSmall=AD+sW6pcEqInTlBrKV74xA==, figureFileBig=SsQMBE7KSqsXcVwVQ/3Nxw==, tableContent=null), ArticleFig(id=1324427317199634854, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, language=EN, label=Fig.10, caption=CNN-BiLSTM prediction results for pitch attitude, figureFileSmall=XLijEusw8CStLpFqcL0Wxg==, figureFileBig=NTMZfGuh58+PYFFXnkAtQQ==, tableContent=null), ArticleFig(id=1324427317283520935, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, language=CN, label=图10, caption=CNN-BiLSTM模型俯仰姿态预测结果, figureFileSmall=XLijEusw8CStLpFqcL0Wxg==, figureFileBig=NTMZfGuh58+PYFFXnkAtQQ==, tableContent=null), ArticleFig(id=1324427317367407016, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, language=EN, label=Fig.11, caption=CNN-BiLSTM prediction results for roll attitude, figureFileSmall=5hv5fkB6otHsykBWYaKaKg==, figureFileBig=IxhySu4iu4mt00wT49ur+g==, tableContent=null), ArticleFig(id=1324427317430321577, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, language=CN, label=图11, caption=CNN-BiLSTM模型横滚姿态预测结果, figureFileSmall=5hv5fkB6otHsykBWYaKaKg==, figureFileBig=IxhySu4iu4mt00wT49ur+g==, tableContent=null), ArticleFig(id=1324427317493236138, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, language=EN, label=Fig.12, caption=CNN-BiLSTM prediction results for yaw attitude, figureFileSmall=CFe4++V9pZfBz19RlBibww==, figureFileBig=dmqHtwLlpOyKV7Q8Cnc5Dg==, tableContent=null), ArticleFig(id=1324427317572927915, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, language=CN, label=图12, caption=CNN-BiLSTM模型偏航姿态预测结果, figureFileSmall=CFe4++V9pZfBz19RlBibww==, figureFileBig=dmqHtwLlpOyKV7Q8Cnc5Dg==, tableContent=null), ArticleFig(id=1324427317631648172, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, language=EN, label=Fig.13, caption=Comparison of pitch direction compensation results, figureFileSmall=DfxJPIfkAW8jVBQz2eKgqQ==, figureFileBig=2ET+g0LHLjBcZ4iNPox3hg==, tableContent=null), ArticleFig(id=1324427317711339949, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, language=CN, label=图13, caption=俯仰方向补偿结果对比, figureFileSmall=DfxJPIfkAW8jVBQz2eKgqQ==, figureFileBig=2ET+g0LHLjBcZ4iNPox3hg==, tableContent=null), ArticleFig(id=1324427317786837422, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, language=EN, label=Fig.14, caption=Comparison of roll direction compensation results, figureFileSmall=6hidwKeDEruUJjHOiyFN1w==, figureFileBig=h0MgMDc5AbU6ME/LQiHQcQ==, tableContent=null), ArticleFig(id=1324427319619748271, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, language=CN, label=图14, caption=横滚方向补偿结果对比, figureFileSmall=6hidwKeDEruUJjHOiyFN1w==, figureFileBig=h0MgMDc5AbU6ME/LQiHQcQ==, tableContent=null), ArticleFig(id=1324427319682662832, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, language=EN, label=Fig.15, caption=Comparison of yaw direction compensation results, figureFileSmall=LoKA1MN9mk7XNxZ31zfUvQ==, figureFileBig=80kOwdYCMTcD8FnpRbq35w==, tableContent=null), ArticleFig(id=1324427319758160305, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, language=CN, label=图15, caption=偏航方向补偿结果对比, figureFileSmall=LoKA1MN9mk7XNxZ31zfUvQ==, figureFileBig=80kOwdYCMTcD8FnpRbq35w==, tableContent=null), ArticleFig(id=1324427319825269170, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, language=EN, label=Fig.16, caption=Comparison of pitch direction before and after compensation, figureFileSmall=Jfxe5iSM8A5owydeUG0VMw==, figureFileBig=l6WTXH7D2PhJLPahQX7Rgg==, tableContent=null), ArticleFig(id=1324427319921738163, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, language=CN, label=图16, caption=俯仰方向补偿前后对比, figureFileSmall=Jfxe5iSM8A5owydeUG0VMw==, figureFileBig=l6WTXH7D2PhJLPahQX7Rgg==, tableContent=null), ArticleFig(id=1324427319997235636, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, language=EN, label=Fig.17, caption=Comparison of pitch direction before and after compensation under Sea State 5, figureFileSmall=mgDmj7R7J/0CdWvBQ+ioMQ==, figureFileBig=PB8s8BsqYsIkI0VguP3k5Q==, tableContent=null), ArticleFig(id=1324427320068538805, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, language=CN, label=图17, caption=五级海况下俯仰方向补偿前后对比, figureFileSmall=mgDmj7R7J/0CdWvBQ+ioMQ==, figureFileBig=PB8s8BsqYsIkI0VguP3k5Q==, tableContent=null), ArticleFig(id=1324427320139841974, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, language=EN, label=Fig.18, caption=Comparison of roll direction before and after compensation under Sea State 5, figureFileSmall=0jVGrmDTZcWqumgBYIpItg==, figureFileBig=FKgm/cd/RYXFqCxgmm0KKw==, tableContent=null), ArticleFig(id=1324427320206950839, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, language=CN, label=图18, caption=五级海况下横滚方向补偿前后对比, figureFileSmall=0jVGrmDTZcWqumgBYIpItg==, figureFileBig=FKgm/cd/RYXFqCxgmm0KKw==, tableContent=null), ArticleFig(id=1324427320286642616, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, language=EN, label=Fig.19, caption=Comparison of yaw direction before and after compensation under Sea State 5, figureFileSmall=1fbHH2sXVsUZbVeYYtZA7w==, figureFileBig=y/+GZtNST++MOnodb7qmEg==, tableContent=null), ArticleFig(id=1324427320366334393, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, language=CN, label=图19, caption=五级海况下偏航方向补偿前后对比, figureFileSmall=1fbHH2sXVsUZbVeYYtZA7w==, figureFileBig=y/+GZtNST++MOnodb7qmEg==, tableContent=null), ArticleFig(id=1324427320433443258, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, language=EN, label=Fig.20, caption=Visualization of compensation effect, figureFileSmall=7Id8ucIjbC8ZVksSsyJjSw==, figureFileBig=mkySfREkOwF5kYQatofJFQ==, tableContent=null), ArticleFig(id=1324427320517329339, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, language=CN, label=图20, caption=补偿可视化, figureFileSmall=7Id8ucIjbC8ZVksSsyJjSw==, figureFileBig=mkySfREkOwF5kYQatofJFQ==, tableContent=null), ArticleFig(id=1324427320580243900, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, language=EN, label=Tab.1, caption=

Analysis of attitude prediction error

, figureFileSmall=null, figureFileBig=null, tableContent=
姿态评估指标/%LSTMBiLSTMCNN-BiLSTM(本文)
PitchRMSE6.675.343.43
MAE5.124.262.45
RollRMSE7.025.613.78
MAE5.434.512.69
YawRMSE6.315.023.55
MAE4.984.032.51
), ArticleFig(id=1324427320643158461, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, language=CN, label=表1, caption=

姿态预测误差分析

, figureFileSmall=null, figureFileBig=null, tableContent=
姿态评估指标/%LSTMBiLSTMCNN-BiLSTM(本文)
PitchRMSE6.675.343.43
MAE5.124.262.45
RollRMSE7.025.613.78
MAE5.434.512.69
YawRMSE6.315.023.55
MAE4.984.032.51
)], attaches=null, journal=Journal(id=1240685663704625163, delFlag=0, nameCn=船舶力学, nameEn=Journal of Ship Mechanics, nameHistory1=null, nameHistory2=null, issn=1007-7294, eissn=null, cn=32-1468/U, coden=null, periodic=0, language=CN, oaType=null, ccby=null, superviseOffice=null, ownerOffice=null, pubOffice=null, editorOffice=null, officeType=null, aims=null, clcCode=null, officeProv=null, officeCity=null, officeAddr=null, officeZip=null, officeEmail=null, officePhone=null, editDirector=null, officeDirector=null, officeDirectorPhone=null, officeStaffNum=null, officeEmpNum=null, coverPicUrl=8VABIsgSw5I4HF/4goaIlA==, journalPrice=null, startedYear=null, abbrevIsoEn=Journal of Ship Mechanics, journalRemark=null, publicationField=null, createdTime=1773732113054, updatedTime=1788949655820, createdBy=18614031015, updatedBy=13041195026, firstLetterCn=C, firstLetterEn=C, subjectCode=Mechanics, subjectName=null, subjectCodeEn=Mechanics, subjectNameEn=null, picCn=8VABIsgSw5I4HF/4goaIlA==, picEn=Ve/8A/FRYceS/z8o7GCJ5g==, jcr=null, cjcr=null, exts=[JournalExt(id=1304512665783656728, language=CN, name=船舶力学, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=, createdTime=1788949656196, updatedTime=1788949656196, createdBy=13041195026, updatedBy=13041195026, submissionGuidelinesUrl=, submissionAuthorUrl=https://cblx.cbpt.cnki.net/EditorD3N/index.aspx?t=1, submissionEditorUrl=https://cblx.cbpt.cnki.net/EditorD3N/index.aspx?t=3, submissionReviewUrl=https://cblx.cbpt.cnki.net/EditorD3N/index.aspx?t=2, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""}), JournalExt(id=1304512665829794073, language=EN, name=Journal of Ship Mechanics, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=, createdTime=1788949656207, updatedTime=1788949656207, createdBy=13041195026, updatedBy=13041195026, submissionGuidelinesUrl=, submissionAuthorUrl=https://cblx.cbpt.cnki.net/EditorD3N/index.aspx?t=1, submissionEditorUrl=https://cblx.cbpt.cnki.net/EditorD3N/index.aspx?t=3, submissionReviewUrl=https://cblx.cbpt.cnki.net/EditorD3N/index.aspx?t=2, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""})], databaseList=null, tenantJournalId=1240685776644648972, websiteList=[Website(id=1240686760611607145, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1240685776644648972, journalNameCn=null, journalNameEn=null, grayFlag=null, tenantId=1146029695717560320, platformId=null, journalGroupId=null, journalGroupNameCn=null, journalGroupNameEn=null, type=1, domain=https://castjournals.cast.org.cn/joweb/cblx/CN, language=CN, createTime=1773732374576, createBy=18614031015, updateTime=1773732394922, updateBy=18614031015, name=船舶力学-中文, tplId=1146099689490845704, title=船舶力学, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1240687166741869216, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1240686760611607145, code=articleTextType, value=kx, createTime=1773732471404, updateTime=1773732471404, creator=18614031015, updator=18614031015), WebsiteProps(id=1240687166725091997, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1240686760611607145, code=banner, value=null, createTime=1773732471400, updateTime=1773732471400, creator=18614031015, updator=18614031015), WebsiteProps(id=1240687166758646435, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1240686760611607145, code=grayFlag, value=0, createTime=1773732471408, updateTime=1773732471408, creator=18614031015, updator=18614031015), WebsiteProps(id=1240687166716703388, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1240686760611607145, code=logo, value=https://castjournals.cast.org.cn/joweb/cblx/CN/file/pic?fileId=/ZVjg3ao2vf5wYxw5Kn1Uw==, createTime=1773732471398, updateTime=1773732471398, creator=18614031015, updator=18614031015), WebsiteProps(id=1240687166771229349, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1240686760611607145, code=minRunFlag, value=0, createTime=1773732471411, updateTime=1773732471411, creator=18614031015, updator=18614031015), WebsiteProps(id=1240687166737674911, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1240686760611607145, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/cblx/CN/file/pic, createTime=1773732471403, updateTime=1773732471403, creator=18614031015, updator=18614031015), WebsiteProps(id=1240687166767035044, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1240686760611607145, code=silenceFlag, value=0, createTime=1773732471410, updateTime=1773732471410, creator=18614031015, updator=18614031015), WebsiteProps(id=1240687166729286302, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1240686760611607145, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1773732471401, updateTime=1773732471401, creator=18614031015, updator=18614031015), WebsiteProps(id=1240687166750257825, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1240686760611607145, code=themeColor, value=null, createTime=1773732471406, updateTime=1773732471406, creator=18614031015, updator=18614031015), WebsiteProps(id=1240687166754452130, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1240686760611607145, code=themeStyle, value=null, createTime=1773732471407, updateTime=1773732471407, creator=18614031015, updator=18614031015)]), Website(id=1240686760674521707, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1240685776644648972, journalNameCn=null, journalNameEn=null, grayFlag=null, tenantId=1146029695717560320, platformId=null, journalGroupId=null, journalGroupNameCn=null, journalGroupNameEn=null, type=1, domain=https://castjournals.cast.org.cn/joweb/cblx/EN, language=EN, createTime=1773732374590, createBy=18614031015, updateTime=1773732413338, updateBy=18614031015, name=船舶力学-英文, tplId=1146101810881728533, title=Journal of Ship Mechanics, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1240687194269078438, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1240686760674521707, code=articleTextType, value=kx, createTime=1773732477967, updateTime=1773732477967, creator=18614031015, updator=18614031015), WebsiteProps(id=1240687194248106915, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1240686760674521707, code=banner, value=null, createTime=1773732477962, updateTime=1773732477962, creator=18614031015, updator=18614031015), WebsiteProps(id=1240687194285855657, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1240686760674521707, code=grayFlag, value=0, createTime=1773732477971, updateTime=1773732477971, creator=18614031015, updator=18614031015), WebsiteProps(id=1240687194239718306, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1240686760674521707, code=logo, value=https://castjournals.cast.org.cn/joweb/cblx/EN/file/pic?fileId=/ZVjg3ao2vf5wYxw5Kn1Uw==, createTime=1773732477960, updateTime=1773732477960, creator=18614031015, updator=18614031015), WebsiteProps(id=1240687194302632875, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1240686760674521707, code=minRunFlag, value=0, createTime=1773732477975, updateTime=1773732477975, creator=18614031015, updator=18614031015), WebsiteProps(id=1240687194260689829, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1240686760674521707, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/cblx/EN/file/pic, createTime=1773732477965, updateTime=1773732477965, creator=18614031015, updator=18614031015), WebsiteProps(id=1240687194294244266, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1240686760674521707, code=silenceFlag, value=0, createTime=1773732477973, updateTime=1773732477973, creator=18614031015, updator=18614031015), WebsiteProps(id=1240687194256495524, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1240686760674521707, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_en_623/, createTime=1773732477964, updateTime=1773732477964, creator=18614031015, updator=18614031015), WebsiteProps(id=1240687194277467047, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1240686760674521707, code=themeColor, value=null, createTime=1773732477969, updateTime=1773732477969, creator=18614031015, updator=18614031015), WebsiteProps(id=1240687194281661352, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1240686760674521707, code=themeStyle, value=null, createTime=1773732477970, updateTime=1773732477970, creator=18614031015, updator=18614031015)])], journalTitle=船舶力学, weixinUrl=null, journalUrl=https://cblx.cbpt.cnki.net/, iacademicId=null, status=1, seqNo=null, journalTitleEn=Journal of Ship Mechanics, journalPhotoCn=8VABIsgSw5I4HF/4goaIlA==, journalPhotoEn=Ve/8A/FRYceS/z8o7GCJ5g==, journalFirstLetter=C, journalRecommend=null, journalNew=null, journalCollection=null, jcrJf=null, cjcrJf=null, jcrJfStr=null, cjcrJfStr=null, submissionFirstDecision=null, sciSubjectClassification=null, casSubjectClassification=null, citeScore=null, totalCitationFrequency=null, icpCode=null, psCode=null, advertisingLicenseCode=null, copyrightInformation=null, country=null, option=, provinceCode=null, provinceName=null, collectFlag=false, interPubPlatform=, interPubPlatformUrl=null), detailUrlCn=https://castjournals.cast.org.cn/joweb/cblx/CN/10.3969/j.issn.1007-7294.2026.09.006, detailUrlEn=https://castjournals.cast.org.cn/joweb/cblx/EN/10.3969/j.issn.1007-7294.2026.09.006, pdfUrlCn=https://castjournals.cast.org.cn/joweb/cblx/CN/PDF/10.3969/j.issn.1007-7294.2026.09.006, pdfUrlEn=https://castjournals.cast.org.cn/joweb/cblx/EN/PDF/10.3969/j.issn.1007-7294.2026.09.006, aliStartDate=0, aliEndDate=0, collectionFlag=false, citedCount=null, citedUrl=null, previewStatus=0, delFlag=0, hasFullText=1, orderTime=1789401600000, fullTextJson=null, articleText=null, reference=null)
收藏切换
基于CNN-BiLSTM预测的船舶姿态补偿设计
收藏切换
PDF下载
王娟 1, 2 , 江宗兵 1, 3 , 屈秋霞 1 , 李鹏 2
船舶力学 | 流体力学 2026,30(9): 1461-1472
收起
收藏切换
船舶力学 |流体力学 2026 , 30 (9) : 1461 -1472
基于CNN-BiLSTM预测的船舶姿态补偿设计
全屏
[Author(id=1324427312120332665, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=wangjuan@sjzu.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1324427312279716220, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, authorId=1324427312120332665, language=EN, stringName=Juan WANG, firstName=Juan, middleName=null, lastName=WANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1School of Electrical and Control Engineering, Shenyang Jianzhu University, Shenyang 110168, China
2State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110169, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1324427312405545341, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, authorId=1324427312120332665, language=CN, stringName=王娟, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1沈阳建筑大学 电气与控制工程学院,沈阳 110168
2中国科学院沈阳自动化研究所 机器人学国家重点实验室,沈阳 110169, bio={"content":"

王 娟(1984–),女,博士,副教授,E-mail:

"}, bioImg=null, bioContent=

王 娟(1984–),女,博士,副教授,E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1324427311830925679, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, xref=1, ext=[AuthorCompanyExt(id=1324427311843508592, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, companyId=1324427311830925679, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1School of Electrical and Control Engineering, Shenyang Jianzhu University, Shenyang 110168, China), AuthorCompanyExt(id=1324427311864480113, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, companyId=1324427311830925679, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1沈阳建筑大学 电气与控制工程学院,沈阳 110168)]), AuthorCompany(id=1324427311931588978, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, xref=2, ext=[AuthorCompanyExt(id=1324427311939977587, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, companyId=1324427311931588978, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110169, China), AuthorCompanyExt(id=1324427311948366196, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, companyId=1324427311931588978, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2中国科学院沈阳自动化研究所 机器人学国家重点实验室,沈阳 110169)])]), Author(id=1324427312522985855, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1324427312627843458, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, authorId=1324427312522985855, language=EN, stringName=Zong-bing JIANG, firstName=Zong-bing, middleName=null, lastName=JIANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 3, address=1School of Electrical and Control Engineering, Shenyang Jianzhu University, Shenyang 110168, China
3Taiyuan Heavy Machinery Group Yuci Hydraulic Industry (Jinan) Co., Ltd., Automation Department, Jinan 250100, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1324427312745283971, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, authorId=1324427312522985855, language=CN, stringName=江宗兵, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 3, address=1沈阳建筑大学 电气与控制工程学院,沈阳 110168
3太重集团榆次液压工业(济南)有限公司 自动化部,济南 250100, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1324427311830925679, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, xref=1, ext=[AuthorCompanyExt(id=1324427311843508592, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, companyId=1324427311830925679, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1School of Electrical and Control Engineering, Shenyang Jianzhu University, Shenyang 110168, China), AuthorCompanyExt(id=1324427311864480113, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, companyId=1324427311830925679, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1沈阳建筑大学 电气与控制工程学院,沈阳 110168)]), AuthorCompany(id=1324427312040640885, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, xref=3, ext=[AuthorCompanyExt(id=1324427312049029494, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, companyId=1324427312040640885, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3Taiyuan Heavy Machinery Group Yuci Hydraulic Industry (Jinan) Co., Ltd., Automation Department, Jinan 250100, China), AuthorCompanyExt(id=1324427312057418103, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, companyId=1324427312040640885, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3太重集团榆次液压工业(济南)有限公司 自动化部,济南 250100)])]), Author(id=1324427312820781445, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, orderNo=2, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1324427312908861831, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, authorId=1324427312820781445, language=EN, stringName=Qiu-xia QU, firstName=Qiu-xia, middleName=null, lastName=QU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1School of Electrical and Control Engineering, Shenyang Jianzhu University, Shenyang 110168, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1324427312988553608, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, authorId=1324427312820781445, language=CN, stringName=屈秋霞, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1沈阳建筑大学 电气与控制工程学院,沈阳 110168, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1324427311830925679, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, xref=1, ext=[AuthorCompanyExt(id=1324427311843508592, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, companyId=1324427311830925679, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1School of Electrical and Control Engineering, Shenyang Jianzhu University, Shenyang 110168, China), AuthorCompanyExt(id=1324427311864480113, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, companyId=1324427311830925679, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1沈阳建筑大学 电气与控制工程学院,沈阳 110168)])]), Author(id=1324427313068245386, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, orderNo=3, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1324427313164714380, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, authorId=1324427313068245386, language=EN, stringName=Peng LI, firstName=Peng, middleName=null, lastName=LI, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110169, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1324427313244406157, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, authorId=1324427313068245386, language=CN, stringName=李鹏, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2中国科学院沈阳自动化研究所 机器人学国家重点实验室,沈阳 110169, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1324427311931588978, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, xref=2, ext=[AuthorCompanyExt(id=1324427311939977587, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, companyId=1324427311931588978, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110169, China), AuthorCompanyExt(id=1324427311948366196, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1324427132184702992, companyId=1324427311931588978, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2中国科学院沈阳自动化研究所 机器人学国家重点实验室,沈阳 110169)])])]
王娟1, 2 , 江宗兵1, 3, 屈秋霞1, 李鹏2
作者信息
  • 1沈阳建筑大学 电气与控制工程学院,沈阳 110168
  • 2中国科学院沈阳自动化研究所 机器人学国家重点实验室,沈阳 110169
  • 3太重集团榆次液压工业(济南)有限公司 自动化部,济南 250100
作者简介:

王 娟(1984–),女,博士,副教授,E-mail:

Compensation design of ship attitude based on CNN-BiLSTM prediction
Juan WANG1, 2 , Zong-bing JIANG1, 3, Qiu-xia QU1, Peng LI2
Affiliations
  • 1School of Electrical and Control Engineering, Shenyang Jianzhu University, Shenyang 110168, China
  • 2State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110169, China
  • 3Taiyuan Heavy Machinery Group Yuci Hydraulic Industry (Jinan) Co., Ltd., Automation Department, Jinan 250100, China
出版时间: 2026-09-15 doi: 10.3969/j.issn.1007-7294.2026.09.006
文章导航
收藏切换

船舶在海上作业时会受到波浪的扰动,造成船舶多自由度的复合运动,极大影响船舶在海上作业时的稳定性。因此,本文提出一种CNN-BiLSTM融合的预测模型,对船舶姿态进行实时预测,并设计双层Stewart平台补偿机构,以实现对船舶运动的有效补偿。为消除传感器延时与噪声的干扰,首先用SG滤波器(Savitzky-Golay)对南海采集到的2011个船舶姿态样本数据进行滤波,并使用CNN-BiLSTM融合预测模型对姿态数据进行预测,该模型显著提升了船舶姿态预测的精度。进一步通过闭环矢量法构建平台运动学模型,利用预测后的数据对双层Stewart平台进行补偿,实现底层平台模拟波浪扰动与顶层平台动态补偿的协同控制。实验数据表明,该研究能够取得良好的船舶姿态补偿效果,为海上无人机平稳降落提供了可行的解决方案。

船舶姿态预测  /  双层Stewart平台补偿系统  /  CNN-BiLSTM预测

During maritime operations, ships are subject to wave-induced disturbances, resulting in complex multi-degree-of-freedom motions that severely affect the stability of ships during offshore operations. To address this challenge, this study proposes a CNN-BiLSTM hybrid prediction model for real-time ship attitude forecasting and designs a dual-layer Stewart platform compensation mechanism to mitigate ship motion effects. To overcome sensor latency and noise interference, 2011 ship attitude samples collected in the South China Sea were first filtered using a Savitzky-Golay (SG) filter. The processed data were then fed into the CNN-BiLSTM hybrid prediction model, which significantly improved the accuracy of attitude prediction. Furthermore, a platform kinematic model was established using the closed-loop vector method. The predicted data were utilized to compensate the dual-layer Stewart platform, enabling coordinated control between the lower platform (simulating wave disturbances) and the upper platform (performing dynamic compensation). Experimental results demonstrate that the proposed approach achieves effective ship attitude compensation and provides a feasible solution for stable landing operations of unmanned aerial vehicles (UAVs) at sea.

ship attitude prediction  /  dual-layer Stewart platform compensation system  /  CNN-BiLSTM prediction
王娟, 江宗兵, 屈秋霞, 李鹏. 基于CNN-BiLSTM预测的船舶姿态补偿设计. 船舶力学, 2026 , 30 (9) : 1461 -1472 . DOI: 10.3969/j.issn.1007-7294.2026.09.006
Juan WANG, Zong-bing JIANG, Qiu-xia QU, Peng LI. Compensation design of ship attitude based on CNN-BiLSTM prediction[J]. Journal of Ship Mechanics, 2026 , 30 (9) : 1461 -1472 . DOI: 10.3969/j.issn.1007-7294.2026.09.006
船舶在波浪中的运动具有低频、大幅值、多自由度耦合的特点,其俯仰、横滚和偏航运动对舰载无人机海上降落会造成极大干扰,船舶姿态补偿技术可以提升作业的安全性和效率[1−3]。为解决此问题,Cai等[4]设计了一种基于速度前馈补偿器的滑模双闭环控制器,通过对位姿的高精度跟踪控制提高了Stewart平台的动态性能。Zhou等[5]针对舰载Stewart平台设计了一种基于滤波的滑模反步控制器,有效地抑制了舰船运动引起的扰动。Zhang等[6]设计了一种跟踪船舶升沉运动的反演控制方法,并采用粒子群算法对控制参数进行优化,显著提高了姿态补偿的效率。张琴等[7]采用改进麻雀搜索算法(CCRSSA)优化PID控制方法,该方法更适合用于复杂海况下船舶姿态补偿平台的控制。常宗瑜等[8]建立的模型考虑到了液压部件的动态性能,并利用PID控制算法进行仿真,该方法能将纵摇角度补偿到1°以下,证明了该方法的有效性。
然而,船舶姿态传感器及平台执行机构固有的测量噪声与延时,会导致测量姿态滞后于真实姿态,因此在进行船舶姿态补偿之前,对船舶姿态进行预测,可以主动抵消延迟带来的影响。Gong等[9]使用LSTM模型对风速进行预测,解决了长时间序列的梯度消失和梯度爆炸问题。尚凡成等[10]提出一种生成式对抗思想的LSTM模型,预测精度优于传统的AR模型与LSTM模型。张彪等[11]提出了基于极限学习机、经验模态分解和长短期记忆神经网络的组合预测模型,实现对船舶运动姿态更加准确的预测。陈占阳等[12]采用LSTM模型对船舶运动进行实时预测,该方法在非线性船舶运动预测方面表现良好。Wang等[13]提出了Bi-LSTM-TPA混合模型,该模型同时提取正、反向横摇角序列的特征,提高了对船舶横摇角的预测精度。朱沛樵等[14]采用两个独立的GRU对船舶纵摇和垂荡进行预测,预测结果表明在超前预报时间达到10 s时,仍可以保持很高的预测精度。Zhang等[15]融入了注意力机制,并改进了耦合的卷积神经网络与长短期记忆网络架构,用于预测无人艇的横摇运动。Yuan等[16]提出麻雀搜索算法优化的BiLSTM,能够准确捕获全局最优的解决方案,提高船舶运动预测的准确性。这些预测模型虽能有效提升预测精度,但大多未能与波浪补偿系统结合进行验证。
综上所述,一方面,单一的控制方法受限于传感器及补偿系统执行机构存在的延迟,导致补偿系统可能出现补偿信号迟滞;另一方面,普通LSTM预测模型难以准确对船舶姿态实现精准预测,且姿态预测模型未充分与补偿机构结合。因此,本文研究了波浪扰动环境下船舶姿态预测控制问题,设计了基于CNN-BiLSTM预测的双层Stewart平台船舶姿态补偿系统。具体贡献如下:
(1)将卷积神经网络(CNN)与BiLSTM进行融合,强化对数据特征提取的能力和对数据前后文的感知力,实现对船舶姿态的准确预测。(2)对Stewart平台进行运动学分析,并在Simulink Multibody中构建双层Stewart可视化模型,顶层的补偿平台能够根据底层干扰平台的扰动实时运动,实现船舶姿态补偿,保证了补偿平台的稳定性。(3)将CNN-BiLSTM预测模型与双层Stewart补偿系统进行集成,预测模型根据期望位姿与实际位姿的差值调整预测步长,从而减小传感器噪声及执行机构延迟的影响,实现对船舶姿态的精确补偿。
本文首先构建了基于CNN-BiLSTM的姿态预测模型。在实验中采用滤波器对南海采集到的2011个船舶姿态数据进行滤波,然后使用该预测模型对船舶姿态进行预测,预测结果显示该模型显著提高了船舶姿态预测的精度。通过对船舶姿态进行实时预测,可以减轻补偿信号滞后对补偿机构的影响,进一步使用闭环矢量法构建双层Stewart平台,利用预测后的数据对双层Stewart平台进行补偿,实现底层平台模拟波浪扰动与顶层平台动态补偿的协同控制,为进一步测试补偿系统在其他场景下的表现,采用MSS工具箱模拟了五级海况下的船舶姿态并进行补偿,补偿结果验证了系统的有效性。
为消除姿态传感器带来的延时和传感器噪声的影响,本文设计CNN-BiLSTM融合模型对船舶姿态数据进行短时预测,使Stewart船舶姿态补偿系统能够实现对船舶姿态变化的快速响应,从而达到精确补偿的目的。
在卷积神经网络中,卷积层为CNN的核心部分,卷积层通过卷积核滑动进行卷积操作,自动学习并提取局部特征[17]。卷积计算公式如下
$ {Y}_{j}=f\left(\sum {W}_{ij}\otimes {X}_{i}+{b}_{j}\right) $
式中:$ {X}_{i} $、$ {Y}_{j} $分别为输入矩阵和输出矩阵,$ f $为激活函数,$ {W}_{ij} $为卷积核,$ {b}_{j} $为偏置项,$ \otimes $为卷积操作。
池化层可以实现卷积层输出的降采样,降低中间隐含层的维度,能够在减少接下来各层计算量的同时保留重要特征。池化层一般采用最大池化或平均池化,本文采用最大池化,公式为
$ {p}_{l(i,j)}={\max }_{(j-1)w \lt t \lt jw}\left({a}_{l(i,t)}\right) $
式中:$ {a}_{l(i,t)} $表示第$ l $层中第$ i $个特征图的第$ t $个神经元;$ w $表示卷积核的宽度;$ j $表示第$ j $个池化核,$ {p}_{l(i,j)} $表示经过池化后,该特征图在第$ j $个池化窗口内的输出值。池化操作在时间维度上以窗口 $ w $为步长滑动,且窗口内的位置$ t $满足 $ \left(j-1\right)w \lt t \lt jw $。
BiLSTM是一种循环神经网络(Recurrent Neural Network, RNN)的变体,它能够在处理序列数据时考虑前后信息。其基本结构是由两个LSTM组成的,一个按时间步从前到后处理序列(前向LSTM),另一个按时间步从后到前处理序列(后向LSTM)。这样,每个时间步的输入将同时考虑过去和未来的上下文信息。BiLSTM在LSTM运算的基础上对正向LSTM与反向LSTM的隐藏状态进行合并,通常的合并方法是将正向与反向的隐藏状态拼接为一个更大的向量求平均,来获得$ {Y}_{t} $作为当前时间步的最终输出值。计算过程如下
$ {Y}_{t}={\overrightarrow{\boldsymbol{W}}}_{t}\cdot{\overrightarrow{{h}}}_{t}+{\overleftarrow{\boldsymbol{W}}}_{t}\cdot \overleftarrow{h_t} +{b}_{Y} $
式中:$ {\overrightarrow{\boldsymbol{W}}}_{t} $、$ {\overleftarrow{\boldsymbol{W}}}_{t} $分别为$ t $时间步正向隐藏状态$ {\overrightarrow{{h}}}_{t} $与反向隐藏状态$ \overleftarrow{h_t} $的合并权重矩阵,$ {b}_{Y} $为合并偏置项。通过可学习的权重对两个方向的信息进行组合,使模型能够在船舶姿态急剧变化时,后向 LSTM 提供的逆向预测有助于模型感知后续走势,从而修正前向 LSTM 可能产生的滞后偏差。
CNN-BiLSTM融合模型在船舶姿态预测中的核心原理是通过CNN对船舶运动数据的局部动态特征进行多尺度感知,并结合双向BiLSTM对数据上下文的全方位建模,从而实现对船舶姿态复杂非线性演化规律的高精度捕捉。CNN-BiLSTM预测模型基本结构如图1所示。
预测具体流程如下:首先,原始船舶姿态数据(以俯仰数据为例)经过归一化处理后,通过滑动窗口构建为时间片段样本。CNN层利用一维卷积核在时间维度上滑动,提取船舶姿态的局部波动,卷积后的高维特征通过池化层压缩冗余信息,保留关键姿态状态。随后BiLSTM层接收CNN提取的时序特征,通过前向LSTM从历史到未来方向建模船舶姿态的变化趋势,同时后向LSTM从未来到历史方向逆向挖掘隐含的时序关系。BiLSTM进一步通过全连接层映射为未来时刻的姿态预测值,最终得到船舶姿态的预测结果。
超参数的选择对模型预测结果的精度有直接的影响。CNN-BiLSTM模型超参数包含卷积层数、卷积核大小、学习率、迭代次数等。
时间序列预测中,采用一维卷积层可以很好地让模型学习到复杂的时序特征,且更大的感受野可以捕捉更长时间跨度的依赖关系,过多的层数会增加模型复杂程度及参数体量,加大训练难度,并带来较高的过拟合风险。在实验中,一维卷积层采用两层,卷积核大小为3。训练集与测试集划分的比例为8∶2,选择Adam作为优化器,学习率为0.001,选择MSE作为损失函数,Batch size设置为32,最大迭代次数设定为100次。
采用CNN-BiLSTM预测模型对船舶姿态进行预测,可以有效减小传感器及补偿平台执行机构延迟造成的补偿信号迟滞影响,将预测后的数据输入到补偿系统,从而验证补偿的稳定性。
Gough-Stewart平台通常简称为Stewart平台,是一种具有六自由度的并联机械系统,在仿真和精密领域应用广泛[18]。本文提出了一种基于双层Stewart机构的船舶姿态补偿系统。该系统的核心结构由上下两个六自由度Stewart平台构成,其中底层平台用于模拟波浪扰动下的船舶姿态,称作干扰平台;而顶层平台则负责对底层运动进行实时监测与动态补偿,称作补偿平台[19]。结构如图2所示:
每层Stewart平台由下平台、上平台和6个执行机构组成。干扰平台固定在基座上,上平台通过6个执行机构与下平台相连。控制6个执行机构伸缩可以驱动干扰平台产生六自由度的运动,模拟海浪对补偿平台的扰动。补偿平台与干扰平台的结构相同,同样由上平台、下平台和6个执行机构组成。通过对干扰平台的位姿反解,实时调节执行机构的运动状态,使补偿平台产生与干扰平台相反的位姿变化,最终达到运动补偿的目的。
当补偿平台绕$ X $轴、$ Y $轴、$ Z $轴做俯仰、横滚、偏航运动时,可通过坐标旋转矩阵将干扰坐标系中的点在补偿坐标系中表示出来,基坐标系以基座圆心为原点建立,以便在同一坐标系下运算。旋转矩阵R可以表示为
$ {\boldsymbol{R}}={{\boldsymbol{R}}}_{x}(\alpha ){{\boldsymbol{R}}}_{y}(\beta ){{\boldsymbol{R}}}_{z}(\gamma )=\left[\begin{matrix}c\beta c\gamma & s\alpha s\beta c\gamma -c\alpha s\gamma & c\alpha s\beta c\gamma +s\alpha s\gamma \\c\beta s\gamma & s\alpha s\beta c\gamma +c\alpha s\gamma & c\alpha s\beta c\gamma -s\alpha s\gamma \\-s\beta & s\alpha c\beta & c\alpha c\beta \end{matrix}\right] $
式中:$ c\alpha =\cos \alpha , s\alpha =\sin \alpha $。
为建立双层Stewart平台的运动学模型,需要确定其坐标系。双层Stewart平台的坐标系如图3所示。在Stewart的干扰平台上建立干扰坐标系{$ B $};基座平台上建立基坐标系{$ G $};上层Stewart补偿平台上建立补偿坐标系{$ P $}。补偿平台和干扰平台的直径均为1200 mm,电动缸的初始长度为1764 mm。
由此可得补偿平台各铰点在补偿坐标系中的位置关系如图4所示,执行机构通过球铰固定在平台上。上平台各铰点的坐标为
$ \begin{array}{ll}{P}_{1}=(-424.59,-424.59,-50)&{P}_{2}=(424.59,-424.59,-50)\\{P}_{3}=(580,-155.41,-50)&{P}_{4}=(155.41,580,-50)\\{P}_{5}=(-155.41,580,-50)&{P}_{6}=(-580,-155.41,-50)\end{array} $
同理可得干扰平台各铰点在干扰坐标系中的位置关系如图5所示。干扰平台各铰点的坐标为
$ \begin{array}{ll}{B}_{1}=(-155.41,-580,50)&{B}_{2}=(155.41,-580,50)\\{B}_{3}=(580,155.41,50)&{B}_{4}=(424.59,424.59,50)\\{B}_{5}=(-424.59,424.59,50)&{B}_{6}=(-580,155.41,50)\end{array} $
因此,补偿平台$ \{P\} $上一点$ {P}_{i} $在干扰平台$ \{B\} $下的表示为$ {}^{{\mathrm{B}}}R{}_{{\mathrm{P}}}{}^{{\mathrm{P}}}p{}_{i} $。Stewart平台运动学逆解是已知平台姿态求各个杆的长度,最常用的运动学逆解方法为闭环矢量法。船舶姿态补偿系统的第$ i $根电动缸的杆向量可以通过图3分析获得,表达式如下
$ {l}_{i}={}^{{\mathrm{B}}}p{}_{i}-{}^{{\mathrm{B}}}b{}_{i}={}^{{\mathrm{B}}}{\boldsymbol{R}}{}_{{\mathrm{P}}}{}^{{\mathrm{P}}}p{}_{i}+{}^{{\mathrm{B}}}O{}_{{\mathrm{P}}}-{}^{{\mathrm{B}}}b{}_{i} $
式中:$ {l}_{i} $为补偿系统中第$ i $根执行机构的杆向量;$ {}^{{\mathrm{B}}}{\boldsymbol{R}}{}_{{\mathrm{P}}} $为坐标系旋转矩阵;$ {}^{{\mathrm{P}}}p{}_{i} $为补偿平台虎克铰点的坐标;$ {}^{{\mathrm{B}}}b{}_{i} $为干扰平台上的虎克铰点的坐标;$ {}^{{\mathrm{B}}}O{}_{{\mathrm{P}}} $为补偿平面原点。
假设传感器检测到的干扰平台实时位姿为$ {\theta }_{{\mathrm{B}}} $,动平台的期望位姿为$ {\theta }_{{\mathrm{P}}} $,根据补偿需求,$ {\theta }_{{\mathrm{B}}} $和$ {\theta }_{{\mathrm{P}}} $的关系应为
$ {\theta }_{{\mathrm{P}}}=-{\theta }_{{\mathrm{B}}} $
将期望位姿$ {\theta }_{{\mathrm{P}}} $代入式(5)所建立的运动学逆解方程可求得补偿平台的执行机构的期望长度$ {l}_{{\mathrm{P}}} $为
$ {l}_{{\mathrm{P}}}=f\left({\theta }_{{\mathrm{P}}}\right),\;\;\left(i=1,2,\cdots 6\right) $
设此时补偿平台的实际位姿为$ {\theta }_{{\mathrm{T}}} $,当前时刻为$ {t}_{0} $,由于系统存在延迟,因此$ {\theta }_{{\mathrm{P}}} $会滞后于$ {\theta }_{{\mathrm{B}}} $,则期望位姿与实际位姿的差$ \Delta \theta $为
$ \Delta \theta ={\theta }_{{\mathrm{T}}}-{\theta }_{{\mathrm{P}}} $
CNN-BiLSTM模型的预测步长$ \Delta N $为
$ \Delta N={f}_{0}\cdot \left({t}_{0}\right) $
式中:$ {f}_{0} $为CNN-BiLSTM模型的输入调整函数,该函数负责计算输入CNN-BiLSTM模型数据的间隔大小,以实现对CNN-BiLSTM模型预测步长的调整。
CNN-BiLSTM模型的预测输出为$ \theta \left({t}_{0}+\Delta N\right) $,则此时姿态预测模型的输出补偿量为
$ {\theta }_{{\mathrm{C}}}=\theta ({t}_{0}+\Delta N) $
所以,要实现对船舶运动的实时补偿,在$ {t}_{0} $时刻输入给运动学逆解模型的位姿数据应为
$ {\theta }_{{\mathrm{I}}}={\theta }_{{\mathrm{C}}} $
CNN-BiLSTM预测模型会根据补偿平台期望位姿与实际位姿的差,进行实时预测,从而减小系统延迟对补偿性能的影响。预测后的姿态数据代入式(5),从而求出六个驱动机构的长度矢量,进而求得期望的驱动机构长度。
通过上述分析,已经得到了用于姿态预测的CNN-BiLSTM模型,并且完成了对Stewart平台的运动学建模,下面首先以船舶俯仰姿态(Pitch)作为示例进行预测。船舶运动姿态的数据是由飞控(PX4)传感器在我国南海一艘11000吨级的海巡船上采集得到。数据选取100 s内的2011个样本值,其中训练样本占比80%。
传感器在数据采集过程中会受到干扰,所以首先对原始数据进行滤波操作。SG(Savitzky-Golay)滤波器是一种数字信号滤波方法,广泛应用于数据分析、信号处理等领域[20]。其基本原理是以滑动窗口的形式在信号上移动,在每个窗口中通过拟合多项式来估计窗口中心数据的数值,工作原理如图6所示。
假设$ X\left[n\right] $表示信号的多个样本,对于窗口内$ 2M+1 $个数据点可以用最小二乘法来拟合一个$ P $次多项式
$ P(n)=\sum \limits_{p=0}^{{{P}}}\left({a}_{0}+{a}_{1}n+{a}_{2}{n}^{2}+\cdots +{a}_{p}{n}^{p}\right) $
式中:$ {a}_{p} $是$ P $次多项式第$ p $项的系数。原始数据$ X\left[n\right] $和滤波后数据的残差为
$ {\varepsilon }_{n}=\sum \limits_{n=-M}^{M}{\left(P(n)-x[n]\right)}^{2}=\sum \limits_{n=-M}^{M}{\left(\sum \limits_{p=0}^{{{P}}}{a}_{p}{n}^{p}-x[n]\right)}^{2} $
式中:实验中设置SG滤波器的滤波阶次$ P=3 $,$ 2M+1 $设为21。滤波前后的数据对比如图7所示。
本文选用均方根误差(Root Mean Squared Error, RMSE)和平均绝对误差(Mean Absolute Error, MAE)作为相关模型预测精度的评价指标。
(1)均方根误差的计算公式如下式所示
$ {\mathrm{RMSE}}=\sqrt{\frac{1}{m}\sum \limits_{i=1}^{m}{\left({y}_{i}-{\hat{y}}_{i}\right)}^{2}} $
(2)平均绝对误差的计算公式如下式所示
$ {\mathrm{MAE}}=\frac{1}{m}\sum \limits_{i=1}^{m}\left| {y}_{i}-{\hat{y}}_{i}\right| $
式中:$ m $为样本数,$ {y}_{i} $为真实值,$ {\hat{y}}_{i} $为预测结果。由上式可知,RMSE与MAE越小则表明预测结果与真实值越吻合。
通过分析图8~10及表1可知,在预测俯仰角的实验中,CNN-BiLSTM融合模型相对于传统LSTM模型和BiLSTM模型,在RMSE上分别降低了3.24%和1.91%,在MAE上分别降低了2.67%和1.81%。结果表明,相较于LSTM模型和BiLSTM模型,CNN-BiLSTM融合模型有更好的预测精度,用上述方法同样对横滚(Roll)和偏航(Yaw)数据进行预测,表1同样给出了完整的误差对比,实验表明CNN-BiLSTM预测模型具有很高的预测精度,结果如图11~12所示。
通过对姿态的预测可以提高补偿系统的响应速度及补偿精度,将预测后的俯仰、横滚、偏航姿态数据输入到Stewart补偿平台,原始数据输入到干扰平台,并在Simulink-Multibody中进行可视化仿真,图13~15为采用“Transform Sensor”模块导出的平台姿态数据,补偿前Stewart平台在俯仰方向上的角度变化范围为−2.5°~2°,补偿后变化范围缩小至±0.3°以内;补偿前在横滚方向上的角度变化范围为−7°~2°,补偿后变化范围缩小至±0.3°以内;补偿前在偏航方向上的角度变化范围为−3°~2.5°,补偿后变化范围缩小至±0.5°以内,结果均显示姿态预测补偿系统的补偿能力良好。通常无人机降落要求姿态角在2°以内,因此验证了补偿的有效性[21]。图16表示的是在第30秒时加入补偿信号,系统在极短时间内达到补偿效果。
为了验证补偿系统在不同工况下的表现,采用MATLAB中的海洋工具箱(Marine Systems Simulator, MSS)模拟了五级海况下的船舶姿态变化,并进行预测与补偿实验,根据图17~19可以看出,五级海况下三个方向的姿态角度在±10°左右,最大可达±12°,补偿后的俯仰和横滚方向的姿态基本可以稳定在±0.5°以内,偏航方向的姿态可以稳定在±0.8°以内。可视化仿真的动画效果以附件形式提供,图20是在可视化模拟过程中的某同一时刻截取的补偿前后效果对比图。
本文设计了一种基于CNN-BiLSTM姿态预测的双层Stewart船舶姿态补偿系统。通过该预测模型对船舶姿态进行实时预测,从而减小补偿信号迟滞对Stewart补偿机构的影响,该模型结合了卷积神经网络对船舶姿态数据特征的提取能力和双向LSTM对数据前后的感知能力,显著提高了姿态预测的准确性。然后对Stewart姿态补偿系统进行运动学分析,并通过模拟实验证明了该方法良好的船舶姿态补偿性能,为舰载无人机在海上着陆时的稳定性和安全性提供了可靠保障。
本文初步验证了姿态预测与补偿系统的有效性,后续可加入其他控制算法,以进一步提高补偿精度。本文仅在Simulink-Multibody中进行仿真验证,下一步可搭建实物Stewart补偿平台,进行海上试验,验证系统在实际环境中的性能与可靠性。
  • 机器人学国家重点实验室开放基金(2024-O22);辽宁省国际产业技术研发项目(2025JH2/101900038)
参考文献 引证文献
排序方式:
1
Chen N, Huang D L, et al. A novel inertial parameter identification method for the ship-mounted Stewart platform based on a wave compensation platform[J]. Measurement, 2025, 242: 116010.
2
Tang G, Lei J, et al. A modified 6-DOF hybrid serial–parallel platform for ship wave compensation[J]. Ocean Engineering, 2023, 280: 114336.
3
Li D, Wang S, et al. A BP-Neural-Network-based PID control algorithm of shipborne Stewart platform for wave compensation[J]. Journal of Marine Science and Engineering, 2024, 12(12): 2160.
4
Cai Y, Zheng S, et al. Sliding-mode control of ship-mounted Stewart platforms for wave compensation using velocity feedforward[J]. Ocean Engineering, 2021, 236: 109477.
5
Zhou Y, She J, et al. Disturbance rejection for Stewart platform based on integration of equivalent-input-disturbance and sliding-mode control methods[J]. IEEE/ASME Transactions on Mechatronics, 2023, 28(4): 2364-2374.
6
Zhang Q, Wang X, et al. Wave heave compensation based on an optimized backstepping control method[J]. China Ocean Engineering, 2022, 36(6): 959-968.
7
张 琴, 蔡慧茹, 等. 基于改进麻雀优化PID的波浪补偿控制方法[J]. 工程科学与技术, 2024, 56(1): 22‒34.
Zhang Q, Cai H R, et al. An improved sparrow search algorithm optimized control strategy for active wave compensation[J]. Advanced Engineering Sciences, 2024, 56(1): 22‒34. (in Chinese)
8
常宗瑜, 刘 波. 基于Stewart机构的船载运动补偿装置的动力学模拟[J]. 机械设计, 2019, 36(S2): 37‒40.
Chang Z Y, Liu B. Dynamic simulation of shipboard motion compensation device based on Stewart platform[J]. Journal of Machine Design, 2019, 36(S2): 37‒40. (in Chinese)
9
Gong M, Yan C, et al. Short-term wind power forecasting model based on temporal convolutional network and informer[J]. Energy, 2023, 283: 129171.
10
尚凡成, 李传庆, 等. 改进LSTM神经网络在极短期波浪时序预报中的应用[J]. 上海交通大学学报, 2023, 57(6): 659‒665.
Shang F C, Li C Q, et al. Application of improved LSTM neural network in time-series prediction of extreme short-term wave[J]. Journal of Shanghai Jiao Tong University, 2023, 57(6): 659‒665. (in Chinese)
11
张 彪, 彭秀艳, 等. 基于ELM-EMD-LSTM组合模型的船舶运动姿态预测[J]. 船舶力学, 2020, 24(11): 1413‒1421.
Zhang B, Peng X Y, et al. Ship motion attitude prediction based on ELM-EMD-LSTM integrated model[J]. Journal of Ship Mechanics, 2020, 24(11): 1413‒1421. (in Chinese)
12
陈占阳, 占正勇, 等. 长短期记忆神经网络在船舶迎浪运动多时间尺度实时预测中的应用研究[J]. 船舶力学, 2024, 28(12): 1803‒1819.
Chen Z Y, Zhan Z Y, et al. A framework of LSTM neural network model in multi-time scale real-time prediction of ship motions in head waves[J]. Journal of Ship Mechanics, 2024, 28(12): 1803‒1819. (in Chinese)
13
Wang Y C, Wang H, et al. Ship roll prediction algorithm based on Bi-LSTM-TPA combined model[J]. Journal of Marine Science and Engineering, 2021, 9(4): 387-387.
14
朱沛樵, 丁 军, 等. 基于GRU模型的船舶运动与载荷快速预报研究[J]. 船舶力学, 2025, 29(3): 337‒350.
Zhu P Q, Ding J, et al. Rapid prediction of ship motion and load based on GRU neural network[J]. Journal of Ship Mechanics, 2025, 29(3): 337‒350. (in Chinese)
15
Zhang W, Wu P, et al. Roll motion prediction of unmanned surface vehicle based on coupled CNN and LSTM[J]. Future Internet, 2019, 11(11): 243.
16
Yuan P Y, Zhao W G, et al. Intelligent prediction algorithm of ship roll and pitch motion based on SSA-optimized BiLSTM network[J]. Ocean Engineering, 2025, 320: 120331.
17
Liu W, Cao Y. Research on offshore vessel trajectory prediction based on PSO-CNN-RGRU-attention[J]. Applied Sciences, 2025, 15(7): 3625-3625.
18
Chang S W, Lyu Z, et al. Automated six-degree-of-freedom Stewart platform for heavy floor tiling[J]. Automation in Construction, 2025, 170: 105932.
19
Wen S R, Jing J Y, et al. Vibration isolation of a double-layered Stewart platform with local oscillators[J]. Mechanics of Advanced Materials and Structures, 2022, 29(27): 6685-6693.
20
Wen S Q, Zhang W R, et al. An enhanced principal component analysis method with Savitzky-Golay filter and clustering algorithm for sensor fault detection and diagnosis[J]. Applied Energy, 2023, 337.
21
孔杰杰, 王检耀, 等. 一种新型多旋翼无人机着舰装置及安全边界评估方法[J]. 中国舰船研究, 2024, 19(1): 272‒279.
Kong J J, Wang J Y, et. al. A new multi-rotor UAV landing device and safety boundary assessment method[J]. Chinese Journal of Ship Research, 2024, 19(1): 272‒279. (in Chinese)
2026年第30卷第9期
PDF下载
15
7
引用本文
BibTeX
文章信息
doi: 10.3969/j.issn.1007-7294.2026.09.006
  • 接收时间:2026-03-16
  • 首发时间:2026-11-03
  • 出版时间:2026-09-15
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2026-03-16
基金
机器人学国家重点实验室开放基金(2024-O22);辽宁省国际产业技术研发项目(2025JH2/101900038)
作者信息
    1沈阳建筑大学 电气与控制工程学院,沈阳 110168
    2中国科学院沈阳自动化研究所 机器人学国家重点实验室,沈阳 110169
    3太重集团榆次液压工业(济南)有限公司 自动化部,济南 250100
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/cblx/CN/10.3969/j.issn.1007-7294.2026.09.006
分享至
全文二维码

扫描看全文

引用本文
BibTeX
本文的引用情况
2种不同金属材料的力学参数
科
Family
属数
Number of
genus
种数
Number of
species
占总种数比例
Percentage of
total species (%)
属
Genus
种数
Number of
species
占总种数比例
Percentage of total
species (%)
鹅膏菌科Amanitaceae 2 11 5.26 鹅膏菌属 Amanita 10 4.78
小菇科 Mycenaceae 2 12 5.74 丝盖伞属 Inocybe 5 2.39
多孔菌科 Polyporaceae 8 14 6.70 蜡蘑属 Laccaria 5 2.39
红菇科 Russulaceae 3 23 11.00 小皮伞属 Marasmius 6 2.87
小菇属 Mycena 11 5.26
光柄菇属 Pluteus 5 2.39
红菇属 Russula 17 8.13
栓菌属 Trametes 5 2.39
关闭全屏