Article(id=1194640796998673296, tenantId=1146029695717560320, journalId=1189645257101713411, issueId=1194640796491162512, articleNumber=null, orderNo=null, doi=10.19822/j.cnki.1671-6329.20240283, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=research-article, receivedDate=null, receivedDateStr=null, revisedDate=null, revisedDateStr=null, acceptedDate=null, acceptedDateStr=null, onlineDate=1762754161356, onlineDateStr=2025-11-10, pubDate=1743782400000, pubDateStr=2025-04-05, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1762754161356, onlineIssueDateStr=2025-11-10, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1762754161356, creator=13701087609, updateTime=1762754161356, updator=13701087609, issue=Issue{id=1194640796491162512, tenantId=1146029695717560320, journalId=1189645257101713411, year='2025', volume='', issue='4', pageStart='1', pageEnd='62', issueExtLink='null', onlineDate='null', pubDate='null', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=null, createTime=1762754161236, creator=13701087609, updateTime=1762754161236, updator=13701087609, preIssue=null, nextIssue=null, ext=null, issueFiles=null}, startPage=42, endPage=47, ext={EN=ArticleExt(id=1194640797275497363, articleId=1194640796998673296, tenantId=1146029695717560320, journalId=1189645257101713411, language=EN, title=Estimation of Road Adhesion Coefficient Based on PSO-RF, columnId=1194640797204194193, journalTitle=Automotive Digest, columnName=Special Issue on Reviews of Frontiers in Automotive Technologies by Fujian University of Technology, runingTitle=null, highlight=null, articleAbstract=

When using the Random Forest (RF) algorithm to estimate the road adhesion coefficient, there are issues such as insufficient optimization of feature selection during model construction and insufficient diversity in the ensemble of decision trees. To address this issue, a method based on Particle Swarm Optimization (PSO) algorithm to improve RF is proposed, and the algorithmic process is presented. An RF model for estimating the road adhesion coefficient is established, and the PSO algorithm is used to optimize the parameter configuration of RF, including key factors such as the number of features of each tree and the number of trees, so as to enhance the diversity and generalization capabilities of the model. At last, a joint simulation model is built on the MATLAB/Simulink platform for experiments. The comparative experimental results show that the random forest road adhesion coefficient estimation method based on PSO-RF can overcome the limitations of the traditional RF methods, and both the estimation accuracy and stability have been significantly improved.

, correspAuthors=null, authorNote=null, correspAuthorsNote=null, copyrightStatement=null, 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, authorCompany=null, fund=null, authors=null, authorsList=Xun Huang, Yunfei Zha), CN=ArticleExt(id=1194640994793660514, articleId=1194640796998673296, tenantId=1146029695717560320, journalId=1189645257101713411, language=CN, title=基于PSO-RF的路面附着系数估计, columnId=1194640797338411924, journalTitle=汽车文摘, columnName=福建理工大学汽车前瞻技术综述论文专刊, runingTitle=null, highlight=null, articleAbstract=

在利用随机森林算法(RF)进行路面附着系数估计时,存在模型构建过程中特征选择不够优化以及决策树集成的多样性不足等问题。为此,提出一种基于粒子群优化算法(PSO)对RF进行改进的方法,并给出算法流程。建立路面附着系数估计RF模型,使用PSO算法用于优化RF的参数配置,包括每棵树的特征数量、树的数量等关键因素,以增强模型的多样性和泛化能力。最后,在MATLAB/Simulink平台上搭建了联合仿真模型进行试验,对比试验结果表明:基于PSO-RF的随机森林路面附着系数估计方法能够克服传统RF方法中存在的局限性,其估计精度和稳定性均得到显著提升。

, correspAuthors=null, authorNote=null, correspAuthorsNote=null, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=059qzrZyBVUmGjdwrhqcsg==, magXml=MdoA4vASbzJkua8d2kkTQw==, pdfUrl=null, pdf=Qq6TpIzD+3Lpf/i0AWtlPA==, pdfFileSize=820200, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=K0MLBoGieRfrjJi6jmggpg==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=+Yebq90MftF8vAZHNZ7nkw==, mapNumber=null, authorCompany=null, fund=null, authors=null, authorsList=黄逊, 查云飞)}, authors=[Author(id=1194655903501750726, tenantId=1146029695717560320, journalId=1189645257101713411, articleId=1194640796998673296, orderNo=0, 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=1194655903560470984, tenantId=1146029695717560320, journalId=1189645257101713411, articleId=1194640796998673296, authorId=1194655903501750726, language=EN, stringName=Xun Huang, firstName=Xun, middleName=null, lastName=Huang, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=Fujian University of Technology, Fuzhou 350118, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1194655903627579849, tenantId=1146029695717560320, journalId=1189645257101713411, articleId=1194640796998673296, authorId=1194655903501750726, language=CN, stringName=黄逊, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=福建理工大学, 福州 350118, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1194655903426253250, tenantId=1146029695717560320, journalId=1189645257101713411, articleId=1194640796998673296, xref=null, ext=[AuthorCompanyExt(id=1194655903434641859, tenantId=1146029695717560320, journalId=1189645257101713411, articleId=1194640796998673296, companyId=1194655903426253250, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=Fujian University of Technology, Fuzhou 350118), AuthorCompanyExt(id=1194655903438836164, tenantId=1146029695717560320, journalId=1189645257101713411, articleId=1194640796998673296, companyId=1194655903426253250, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=福建理工大学, 福州 350118)])]), Author(id=1194655903686300107, tenantId=1146029695717560320, journalId=1189645257101713411, articleId=1194640796998673296, 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=1194655903757603277, tenantId=1146029695717560320, journalId=1189645257101713411, articleId=1194640796998673296, authorId=1194655903686300107, language=EN, stringName=Yunfei Zha, firstName=Yunfei, middleName=null, lastName=Zha, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=Fujian University of Technology, Fuzhou 350118, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1194655903820517838, tenantId=1146029695717560320, journalId=1189645257101713411, articleId=1194640796998673296, authorId=1194655903686300107, language=CN, stringName=查云飞, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=福建理工大学, 福州 350118, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1194655903426253250, tenantId=1146029695717560320, journalId=1189645257101713411, articleId=1194640796998673296, xref=null, ext=[AuthorCompanyExt(id=1194655903434641859, tenantId=1146029695717560320, journalId=1189645257101713411, articleId=1194640796998673296, companyId=1194655903426253250, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=Fujian University of Technology, Fuzhou 350118), AuthorCompanyExt(id=1194655903438836164, tenantId=1146029695717560320, journalId=1189645257101713411, articleId=1194640796998673296, companyId=1194655903426253250, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=福建理工大学, 福州 350118)])])], keywords=[Keyword(id=1194655903954735567, tenantId=1146029695717560320, journalId=1189645257101713411, articleId=1194640796998673296, language=EN, orderNo=1, keyword=Road adhesion coefficient), Keyword(id=1194655904005067216, tenantId=1146029695717560320, journalId=1189645257101713411, articleId=1194640796998673296, language=EN, orderNo=2, keyword=Random Forest (RF)), Keyword(id=1194655904059593169, tenantId=1146029695717560320, journalId=1189645257101713411, articleId=1194640796998673296, language=EN, orderNo=3, keyword=Particle swarm optimization (PSO)), Keyword(id=1194655904126702034, tenantId=1146029695717560320, journalId=1189645257101713411, articleId=1194640796998673296, language=EN, orderNo=4, keyword=State estimation), Keyword(id=1194655904193810899, tenantId=1146029695717560320, journalId=1189645257101713411, articleId=1194640796998673296, language=CN, orderNo=1, keyword=路面附着系数), Keyword(id=1194655904252531156, tenantId=1146029695717560320, journalId=1189645257101713411, articleId=1194640796998673296, language=CN, orderNo=2, keyword=随机森林), Keyword(id=1194655904307057109, tenantId=1146029695717560320, journalId=1189645257101713411, articleId=1194640796998673296, language=CN, orderNo=3, keyword=粒子群优化), Keyword(id=1194655904361583063, tenantId=1146029695717560320, journalId=1189645257101713411, articleId=1194640796998673296, language=CN, orderNo=4, keyword=状态估计)], refs=[Reference(id=1194655906093830642, tenantId=1146029695717560320, journalId=1189645257101713411, articleId=1194640796998673296, doi=null, pmid=null, pmcid=null, year=2024, volume=46, issue=8, pageStart=1357, pageEnd=1369, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=邓浩楠, 赵治国, 赵坤, journalName=汽车工程, refType=null, unstructuredReference=邓浩楠, 赵治国, 赵坤, 等. 四驱车辆交互式多模型自适应无迹卡尔曼滤波路面附着系数估计[J]. 汽车工程, 2024, 46(8): 1357-1369., articleTitle=四驱车辆交互式多模型自适应无迹卡尔曼滤波路面附着系数估计, refAbstract=null), Reference(id=1194655906148356595, tenantId=1146029695717560320, journalId=1189645257101713411, articleId=1194640796998673296, doi=null, pmid=null, pmcid=null, year=2018, volume=47, issue=2, pageStart=1, pageEnd=4, url=null, language=null, rfNumber=[2], rfOrder=1, authorNames=袁朝春, 张龙飞, 陈龙, journalName=机械制造与自动化, refType=null, unstructuredReference=袁朝春, 张龙飞, 陈龙. 路面附着系数识别方法发展现状综述及展望[J]. 机械制造与自动化, 2018, 47(2): 1-4,7., articleTitle=路面附着系数识别方法发展现状综述及展望, refAbstract=null), Reference(id=1194655906228048372, tenantId=1146029695717560320, journalId=1189645257101713411, articleId=1194640796998673296, doi=null, pmid=null, pmcid=null, year=2024, volume=24, issue=18, pageStart=29135, pageEnd=29148, url=null, language=null, rfNumber=[3], rfOrder=2, authorNames=LI B, WEN J E, FENG T, journalName=IEEE Sensors Journal, refType=null, unstructuredReference=LI B, WEN J E, FENG T, et al. Road Adhesion Coefficient Estimation Based on LiDAR Reflectance Intensity[J]. IEEE Sensors Journal, 2024, 24(18): 29135-29148., articleTitle=Road Adhesion Coefficient Estimation Based on LiDAR Reflectance Intensity, refAbstract=null), Reference(id=1194655906290962933, tenantId=1146029695717560320, journalId=1189645257101713411, articleId=1194640796998673296, doi=null, pmid=null, pmcid=null, year=2022, volume=null, issue=1, pageStart=55, pageEnd=59, url=null, language=null, rfNumber=[4], rfOrder=3, authorNames=吕小龙, 查云飞, 马芳武, journalName=汽车工业研究, refType=null, unstructuredReference=吕小龙, 查云飞, 马芳武, 等. 基于Kalman滤波的路面附着系数估计算法综述[J]. 汽车工业研究, 2022(1): 55-59., articleTitle=基于Kalman滤波的路面附着系数估计算法综述, refAbstract=null), Reference(id=1194655907326956022, tenantId=1146029695717560320, journalId=1189645257101713411, articleId=1194640796998673296, doi=null, pmid=null, pmcid=null, year=2015, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[5], rfOrder=4, authorNames=ARIPIN M K, GHAZALI R, SAM Y M, journalName=Uncertainty Modelling and High Performance Robust Controller for Active Front Steering Control, refType=null, unstructuredReference=ARIPIN M K, GHAZALI R, SAM Y M, et al. Uncertainty Modelling and High Performance Robust Controller for Active Front Steering Control[C]//2015 10th Asian Control Conference (ASCC). Malaysia: IEEE, 2015., articleTitle=null, refAbstract=null), Reference(id=1194655907381481975, tenantId=1146029695717560320, journalId=1189645257101713411, articleId=1194640796998673296, doi=null, pmid=null, pmcid=null, year=2015, volume=25, issue=1, pageStart=62, pageEnd=67, url=null, language=null, rfNumber=[6], rfOrder=5, authorNames=WANG F, FAN X, ZHANG Y, journalName=Computer Aided Drafting, Design and Manufacturing, refType=null, unstructuredReference=WANG F, FAN X, ZHANG Y, et al. Fuzzy Identification Based on Tire/Road Adhesion Feature[J]. Computer Aided Drafting, Design and Manufacturing, 2015, 25(1): 62-67., articleTitle=Fuzzy Identification Based on Tire/Road Adhesion Feature, refAbstract=null), Reference(id=1194655907444396536, tenantId=1146029695717560320, journalId=1189645257101713411, articleId=1194640796998673296, doi=null, pmid=null, pmcid=null, year=2017, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[7], rfOrder=6, authorNames=宋涛, journalName=轮毂驱动电动车的路面附着系数估计方法研究, refType=null, unstructuredReference=宋涛. 轮毂驱动电动车的路面附着系数估计方法研究[D]. 哈尔滨: 哈尔滨工业大学, 2017., articleTitle=null, refAbstract=null), Reference(id=1194655907528282617, tenantId=1146029695717560320, journalId=1189645257101713411, articleId=1194640796998673296, doi=null, pmid=null, pmcid=null, year=2023, volume=46, issue=3, pageStart=118, pageEnd=128, url=null, language=null, rfNumber=[8], rfOrder=7, authorNames=伍文广, 张凡皓, 徐孟龙, journalName=重庆大学学报, refType=null, unstructuredReference=伍文广, 张凡皓, 徐孟龙. 基于Elman神经网络的路面附着系数识别[J]. 重庆大学学报, 2023, 46(3): 118-128., articleTitle=基于Elman神经网络的路面附着系数识别, refAbstract=null), Reference(id=1194655907578614266, tenantId=1146029695717560320, journalId=1189645257101713411, articleId=1194640796998673296, doi=null, pmid=null, pmcid=null, year=2023, volume=45, issue=3, pageStart=134, pageEnd=138, url=null, language=null, rfNumber=[9], rfOrder=8, authorNames=黄开启, 韩伟, 陈俊杰, journalName=制造业自动化, refType=null, unstructuredReference=黄开启, 韩伟, 陈俊杰. 果蝇优化BP神经网络路面附着系数估计[J]. 制造业自动化, 2023, 45(3): 134-138., articleTitle=果蝇优化BP神经网络路面附着系数估计, refAbstract=null), Reference(id=1194655907666694651, tenantId=1146029695717560320, journalId=1189645257101713411, articleId=1194640796998673296, doi=null, pmid=null, pmcid=null, year=2023, volume=45, issue=6, pageStart=1010, pageEnd=1021, url=null, language=null, rfNumber=[10], rfOrder=9, authorNames=查云飞, 吕小龙, 陈慧勤, journalName=汽车工程, refType=null, unstructuredReference=查云飞, 吕小龙, 陈慧勤, 等. 基于路面附着系数估计的车辆轨迹跟踪控制[J]. 汽车工程, 2023, 45(6): 1010-1021+1039., articleTitle=基于路面附着系数估计的车辆轨迹跟踪控制, refAbstract=null), Reference(id=1194655907729609212, tenantId=1146029695717560320, journalId=1189645257101713411, articleId=1194640796998673296, doi=null, pmid=null, pmcid=null, year=2018, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[11], rfOrder=10, authorNames=董建凯, journalName=基于机器学习神经网络的路面附着系数实时分类算法的研究, refType=null, unstructuredReference=董建凯. 基于机器学习神经网络的路面附着系数实时分类算法的研究[D]. 上海: 同济大学, 2018., articleTitle=null, refAbstract=null), Reference(id=1194655907788329469, tenantId=1146029695717560320, journalId=1189645257101713411, articleId=1194640796998673296, doi=null, pmid=null, pmcid=null, year=2012, volume=null, issue=9, pageStart=16, pageEnd=20, url=null, language=null, rfNumber=[12], rfOrder=11, authorNames=郑香美, 高兴旺, 赵志忠, journalName=机械与电子, refType=null, unstructuredReference=郑香美, 高兴旺, 赵志忠. 基于“魔术公式”的轮胎动力学仿真分析[J]. 机械与电子, 2012(9): 16-20., articleTitle=基于“魔术公式”的轮胎动力学仿真分析, refAbstract=null), Reference(id=1194655907859632638, tenantId=1146029695717560320, journalId=1189645257101713411, articleId=1194640796998673296, doi=null, pmid=null, pmcid=null, year=2001, volume=45, issue=1, pageStart=5, pageEnd=32, url=null, language=null, rfNumber=[13], rfOrder=12, authorNames=BREIMAN L, journalName=Machine Learnings, refType=null, unstructuredReference=BREIMAN L. Random Forests[J]. Machine Learnings, 2001, 45(1): 5-32., articleTitle=Random Forests, refAbstract=null), Reference(id=1194655907914158591, tenantId=1146029695717560320, journalId=1189645257101713411, articleId=1194640796998673296, doi=null, pmid=null, pmcid=null, year=2021, volume=57, issue=12, pageStart=74, pageEnd=86, url=null, language=null, rfNumber=[14], rfOrder=13, authorNames=林棻, 王少博, 赵又群, 蔡亦璋, journalName=机械工程学报, refType=null, unstructuredReference=林棻, 王少博, 赵又群, 蔡亦璋. 基于改进Keras模型的路面附着系数估计[J]. 机械工程学报, 2021, 57(12): 74-86., articleTitle=基于改进Keras模型的路面附着系数估计, refAbstract=null), Reference(id=1194655907972878848, tenantId=1146029695717560320, journalId=1189645257101713411, articleId=1194640796998673296, doi=null, pmid=null, pmcid=null, year=2024, volume=45, issue=8, pageStart=849, pageEnd=859, url=null, language=null, rfNumber=[15], rfOrder=14, authorNames=葛杰, 曹绮欣, 张晓鹏, journalName=中国农业气象, refType=null, unstructuredReference=葛杰, 曹绮欣, 张晓鹏, 等. 基于PSO-RF模型的汉江流域参考作物蒸散量模拟研究[J]. 中国农业气象, 2024, 45(8): 849-859., articleTitle=基于PSO-RF模型的汉江流域参考作物蒸散量模拟研究, refAbstract=null)], funds=null, companyList=[AuthorCompany(id=1194655903426253250, tenantId=1146029695717560320, journalId=1189645257101713411, articleId=1194640796998673296, xref=null, ext=[AuthorCompanyExt(id=1194655903434641859, tenantId=1146029695717560320, journalId=1189645257101713411, articleId=1194640796998673296, companyId=1194655903426253250, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=Fujian University of Technology, Fuzhou 350118), AuthorCompanyExt(id=1194655903438836164, tenantId=1146029695717560320, journalId=1189645257101713411, articleId=1194640796998673296, companyId=1194655903426253250, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=福建理工大学, 福州 350118)])], figs=[ArticleFig(id=1194655904541938140, tenantId=1146029695717560320, journalId=1189645257101713411, articleId=1194640796998673296, language=EN, label=null, caption=null, figureFileSmall=VPpfVDJTMWVr+pY9F4tk2A==, figureFileBig=qEt2GC5RHth0v6+NbofXXw==, tableContent=null), ArticleFig(id=1194655904604852702, tenantId=1146029695717560320, journalId=1189645257101713411, articleId=1194640796998673296, language=CN, label=图1, caption=七自由度模型, figureFileSmall=VPpfVDJTMWVr+pY9F4tk2A==, figureFileBig=qEt2GC5RHth0v6+NbofXXw==, tableContent=null), ArticleFig(id=1194655904730681824, tenantId=1146029695717560320, journalId=1189645257101713411, articleId=1194640796998673296, language=EN, label=null, caption=null, figureFileSmall=r5c/K77UN/nQis01sOiZUg==, figureFileBig=b1meLLZIdZbyH7ZblLqNaA==, tableContent=null), ArticleFig(id=1194655904789402081, tenantId=1146029695717560320, journalId=1189645257101713411, articleId=1194640796998673296, language=CN, label=图2, caption=RF算法流程, figureFileSmall=r5c/K77UN/nQis01sOiZUg==, figureFileBig=b1meLLZIdZbyH7ZblLqNaA==, tableContent=null), ArticleFig(id=1194655904906842594, tenantId=1146029695717560320, journalId=1189645257101713411, articleId=1194640796998673296, language=EN, label=null, caption=null, figureFileSmall=lyKjCgDhIwsswv6yGjEWEQ==, figureFileBig=37Hr/XO5F+JhA+mD9gCyBg==, tableContent=null), ArticleFig(id=1194655904969757155, tenantId=1146029695717560320, journalId=1189645257101713411, articleId=1194640796998673296, language=CN, label=图3, caption=PSO-RF算法流程, figureFileSmall=lyKjCgDhIwsswv6yGjEWEQ==, figureFileBig=37Hr/XO5F+JhA+mD9gCyBg==, tableContent=null), ArticleFig(id=1194655905032671716, tenantId=1146029695717560320, journalId=1189645257101713411, articleId=1194640796998673296, language=EN, label=null, caption=null, figureFileSmall=NEz5G1K/NVB6k6UHX9IMlQ==, figureFileBig=EzgvA0MpHZuB7n7YSp4G6A==, tableContent=null), ArticleFig(id=1194655905103974885, tenantId=1146029695717560320, journalId=1189645257101713411, articleId=1194640796998673296, language=CN, label=图4, caption=RF算法训练效果, figureFileSmall=NEz5G1K/NVB6k6UHX9IMlQ==, figureFileBig=EzgvA0MpHZuB7n7YSp4G6A==, tableContent=null), ArticleFig(id=1194655905242386918, tenantId=1146029695717560320, journalId=1189645257101713411, articleId=1194640796998673296, language=EN, label=null, caption=null, figureFileSmall=K4ByJwcwJbxcn07JIWv3TA==, figureFileBig=7WkbmPZhvH2tCFABZPDmTw==, tableContent=null), ArticleFig(id=1194655905301107175, tenantId=1146029695717560320, journalId=1189645257101713411, articleId=1194640796998673296, language=CN, label=图5, caption=基于PSO-RF适应度曲线, figureFileSmall=K4ByJwcwJbxcn07JIWv3TA==, figureFileBig=7WkbmPZhvH2tCFABZPDmTw==, tableContent=null), ArticleFig(id=1194655905380798952, tenantId=1146029695717560320, journalId=1189645257101713411, articleId=1194640796998673296, language=EN, label=null, caption=null, figureFileSmall=trt77j7Uexh3r0NGk8Ps6Q==, figureFileBig=a+1a4apCvRRVia28R6wppQ==, tableContent=null), ArticleFig(id=1194655905460490729, tenantId=1146029695717560320, journalId=1189645257101713411, articleId=1194640796998673296, language=CN, label=图6, caption=PSO-RF算法估计训练效果对比, figureFileSmall=trt77j7Uexh3r0NGk8Ps6Q==, figureFileBig=a+1a4apCvRRVia28R6wppQ==, tableContent=null), ArticleFig(id=1194655905523405290, tenantId=1146029695717560320, journalId=1189645257101713411, articleId=1194640796998673296, language=EN, label=null, caption=null, figureFileSmall=24Wa+w2bDpEmZX6U3w2GQQ==, figureFileBig=rc7yMQKeXtmYs4NtswBWng==, tableContent=null), ArticleFig(id=1194655905603097067, tenantId=1146029695717560320, journalId=1189645257101713411, articleId=1194640796998673296, language=CN, label=图7, caption=对接路面下路面附着系数估计结果, figureFileSmall=24Wa+w2bDpEmZX6U3w2GQQ==, figureFileBig=rc7yMQKeXtmYs4NtswBWng==, tableContent=null), ArticleFig(id=1194655905661817324, tenantId=1146029695717560320, journalId=1189645257101713411, articleId=1194640796998673296, language=EN, label=null, caption=null, figureFileSmall=null, figureFileBig=null, tableContent=
车辆参数 数值
质心到前轴距离lf /m 0.9
质心到后轴距离lr/m 1.1
转动惯量Iz/kg·m-2 1 343.1
整车质量m/kg 720
前轮侧偏刚度Cαf /N·rad-1 48 000
前轮侧偏刚度Cαr /N·rad-1 43 000
), ArticleFig(id=1194655905724731885, tenantId=1146029695717560320, journalId=1189645257101713411, articleId=1194640796998673296, language=CN, label=表1, caption=

车辆参数

, figureFileSmall=null, figureFileBig=null, tableContent=
车辆参数 数值
质心到前轴距离lf /m 0.9
质心到后轴距离lr/m 1.1
转动惯量Iz/kg·m-2 1 343.1
整车质量m/kg 720
前轮侧偏刚度Cαf /N·rad-1 48 000
前轮侧偏刚度Cαr /N·rad-1 43 000
), ArticleFig(id=1194655905787646446, tenantId=1146029695717560320, journalId=1189645257101713411, articleId=1194640796998673296, language=EN, label=null, caption=null, figureFileSmall=null, figureFileBig=null, tableContent=
驾驶工况 路面附着系数 行驶速度/km·h-1
直线工况 0.1~1 匀速 20~110
匀加速 20~80
单移线工况 0.1~1 匀速 20~110
匀加速 20~80
双移线工况 0.1~1 匀速 20~110
匀加速 20~80
), ArticleFig(id=1194655905846366703, tenantId=1146029695717560320, journalId=1189645257101713411, articleId=1194640796998673296, language=CN, label=表2, caption=

数据采集仿真工况设置

, figureFileSmall=null, figureFileBig=null, tableContent=
驾驶工况 路面附着系数 行驶速度/km·h-1
直线工况 0.1~1 匀速 20~110
匀加速 20~80
单移线工况 0.1~1 匀速 20~110
匀加速 20~80
双移线工况 0.1~1 匀速 20~110
匀加速 20~80
), ArticleFig(id=1194655905896698352, tenantId=1146029695717560320, journalId=1189645257101713411, articleId=1194640796998673296, language=EN, label=null, caption=null, figureFileSmall=null, figureFileBig=null, tableContent=
算法 MAE MAPE RMSE R2
PSO-RF 0.000 284 87 0.000 424 64 0.001 790 3 0.999 85
RF 0.008 450 6 0.012 672 0.016 432 0.987 77
XGBoost 0.072 448 0.106 36 0.105 13 0.499 52
LSBoost 0.016 783 0.026 314 0.029 022 0.961 86
), ArticleFig(id=1194655905955418609, tenantId=1146029695717560320, journalId=1189645257101713411, articleId=1194640796998673296, language=CN, label=表3, caption=

测试集不同算法训练结果

, figureFileSmall=null, figureFileBig=null, tableContent=
算法 MAE MAPE RMSE R2
PSO-RF 0.000 284 87 0.000 424 64 0.001 790 3 0.999 85
RF 0.008 450 6 0.012 672 0.016 432 0.987 77
XGBoost 0.072 448 0.106 36 0.105 13 0.499 52
LSBoost 0.016 783 0.026 314 0.029 022 0.961 86
)], attaches=null, journal=Journal(id=1149694111122235398, delFlag=0, nameCn=汽车文摘, nameEn=Automotive Digest, nameHistory1=null, nameHistory2=null, issn=1671-6329, eissn=null, cn=22-1112/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=luiJW6+BcEXciylORYcumg==, journalPrice=null, startedYear=null, abbrevIsoEn=null, journalRemark=null, publicationField=null, createdTime=1752038036376, updatedTime=1761735682597, createdBy=18614031015, updatedBy=13701087609, firstLetterCn=A, firstLetterEn=A, subjectCode=Engineering, subjectName=Engineering, subjectCodeEn=Engineering, subjectNameEn=null, picCn=luiJW6+BcEXciylORYcumg==, picEn=O+ZP75C19YktWcRPOtyJBw==, jcr=null, cjcr=null, exts=[JournalExt(id=1190368987570606240, language=CN, name=汽车文摘, 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=1761735682623, updatedTime=1761735682623, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=https://qcwz.cbpt.cnki.net/index.aspx?t=1, submissionEditorUrl=https://qcwz.cbpt.cnki.net/index.aspx?t=3, submissionReviewUrl=https://qcwz.cbpt.cnki.net/index.aspx?t=2, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""}), JournalExt(id=1190368987625132193, language=EN, name=Automotive Digest, 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=1761735682636, updatedTime=1761735682636, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=https://qcwz.cbpt.cnki.net/index.aspx?t=1, submissionEditorUrl=https://qcwz.cbpt.cnki.net/index.aspx?t=3, submissionReviewUrl=https://qcwz.cbpt.cnki.net/index.aspx?t=2, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""})], databaseList=null, tenantJournalId=1189645257101713411, websiteList=[Website(id=1189645359124066938, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1189645257101713411, 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/qcwz/CN, language=CN, createTime=1761563156157, createBy=18614031015, updateTime=1761563183518, updateBy=18614031015, name=汽车文摘-中文, tplId=1146099689490845704, title=汽车文摘, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1189645933336867479, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189645359124066938, code=articleTextType, value=kx, createTime=1761563293060, updateTime=1761563293060, creator=18614031015, updator=18614031015), WebsiteProps(id=1189645933315895956, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189645359124066938, code=banner, value=null, createTime=1761563293055, updateTime=1761563293055, creator=18614031015, updator=18614031015), WebsiteProps(id=1189645933353644698, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189645359124066938, code=grayFlag, value=0, createTime=1761563293064, updateTime=1761563293064, creator=18614031015, updator=18614031015), WebsiteProps(id=1189645933307507347, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189645359124066938, code=logo, value=https://castjournals.cast.org.cn/joweb/qcwz/CN/file/pic?fileId=wLaOR3KnYrzJXN7hXuyp1Q==, createTime=1761563293053, updateTime=1761563293053, creator=18614031015, updator=18614031015), WebsiteProps(id=1189645933366227612, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189645359124066938, code=minRunFlag, value=0, createTime=1761563293067, updateTime=1761563293067, creator=18614031015, updator=18614031015), WebsiteProps(id=1189645933332673174, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189645359124066938, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/qcwz/CN/file/pic, createTime=1761563293059, updateTime=1761563293059, creator=18614031015, updator=18614031015), WebsiteProps(id=1189645933362033307, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189645359124066938, code=silenceFlag, value=0, createTime=1761563293066, updateTime=1761563293066, creator=18614031015, updator=18614031015), WebsiteProps(id=1189645933324284565, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189645359124066938, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1761563293057, updateTime=1761563293057, creator=18614031015, updator=18614031015), WebsiteProps(id=1189645933345256088, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189645359124066938, code=themeColor, value=null, createTime=1761563293062, updateTime=1761563293062, creator=18614031015, updator=18614031015), WebsiteProps(id=1189645933349450393, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189645359124066938, code=themeStyle, value=null, createTime=1761563293063, updateTime=1761563293063, creator=18614031015, updator=18614031015)]), Website(id=1189645359224730237, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1189645257101713411, 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/qcwz/EN, language=EN, createTime=1761563156181, createBy=18614031015, updateTime=1761563214005, updateBy=18614031015, name=汽车文摘-英文, tplId=1146101810881728533, title=Automotive Digest, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1189645970888471201, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189645359224730237, code=articleTextType, value=kx, createTime=1761563302013, updateTime=1761563302013, creator=18614031015, updator=18614031015), WebsiteProps(id=1189645970871693982, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189645359224730237, code=banner, value=null, createTime=1761563302009, updateTime=1761563302009, creator=18614031015, updator=18614031015), WebsiteProps(id=1189645970905248420, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189645359224730237, code=grayFlag, value=0, createTime=1761563302017, updateTime=1761563302017, creator=18614031015, updator=18614031015), WebsiteProps(id=1189645970863305373, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189645359224730237, code=logo, value=https://castjournals.cast.org.cn/joweb/qcwz/EN/file/pic?fileId=wLaOR3KnYrzJXN7hXuyp1Q==, createTime=1761563302007, updateTime=1761563302007, creator=18614031015, updator=18614031015), WebsiteProps(id=1189645970917831334, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189645359224730237, code=minRunFlag, value=0, createTime=1761563302020, updateTime=1761563302020, creator=18614031015, updator=18614031015), WebsiteProps(id=1189645970884276896, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189645359224730237, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/qcwz/EN/file/pic, createTime=1761563302012, updateTime=1761563302012, creator=18614031015, updator=18614031015), WebsiteProps(id=1189645970913637029, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189645359224730237, code=silenceFlag, value=0, createTime=1761563302019, updateTime=1761563302019, creator=18614031015, updator=18614031015), WebsiteProps(id=1189645970880082591, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189645359224730237, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_en_623/, createTime=1761563302011, updateTime=1761563302011, creator=18614031015, updator=18614031015), WebsiteProps(id=1189645970892665506, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189645359224730237, code=themeColor, value=null, createTime=1761563302014, updateTime=1761563302014, creator=18614031015, updator=18614031015), WebsiteProps(id=1189645970896859811, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189645359224730237, code=themeStyle, value=null, createTime=1761563302015, updateTime=1761563302015, creator=18614031015, updator=18614031015)])], journalTitle=汽车文摘, weixinUrl=null, journalUrl=https://qcwz.cbpt.cnki.net/, iacademicId=null, status=1, seqNo=null, journalTitleEn=Automotive Digest, journalPhotoCn=luiJW6+BcEXciylORYcumg==, journalPhotoEn=O+ZP75C19YktWcRPOtyJBw==, journalFirstLetter=A, 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), detailUrlCn=https://castjournals.cast.org.cn/joweb/qcwz/CN/10.19822/j.cnki.1671-6329.20240283, detailUrlEn=https://castjournals.cast.org.cn/joweb/qcwz/EN/10.19822/j.cnki.1671-6329.20240283, pdfUrlCn=https://castjournals.cast.org.cn/joweb/qcwz/CN/PDF/10.19822/j.cnki.1671-6329.20240283, pdfUrlEn=https://castjournals.cast.org.cn/joweb/qcwz/EN/PDF/10.19822/j.cnki.1671-6329.20240283, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
基于PSO-RF的路面附着系数估计
收藏切换
PDF下载
黄逊 , 查云飞
汽车文摘 | 福建理工大学汽车前瞻技术综述论文专刊 2025,(4): 42-47
收起
收藏切换
汽车文摘 | 福建理工大学汽车前瞻技术综述论文专刊 2025, (4): 42-47
基于PSO-RF的路面附着系数估计
全屏
黄逊, 查云飞
作者信息
  • 福建理工大学, 福州 350118
Estimation of Road Adhesion Coefficient Based on PSO-RF
Xun Huang, Yunfei Zha
Affiliations
  • Fujian University of Technology, Fuzhou 350118
出版时间: 2025-04-05 doi: 10.19822/j.cnki.1671-6329.20240283
文章导航
收藏切换

在利用随机森林算法(RF)进行路面附着系数估计时,存在模型构建过程中特征选择不够优化以及决策树集成的多样性不足等问题。为此,提出一种基于粒子群优化算法(PSO)对RF进行改进的方法,并给出算法流程。建立路面附着系数估计RF模型,使用PSO算法用于优化RF的参数配置,包括每棵树的特征数量、树的数量等关键因素,以增强模型的多样性和泛化能力。最后,在MATLAB/Simulink平台上搭建了联合仿真模型进行试验,对比试验结果表明:基于PSO-RF的随机森林路面附着系数估计方法能够克服传统RF方法中存在的局限性,其估计精度和稳定性均得到显著提升。

路面附着系数  /  随机森林  /  粒子群优化  /  状态估计

When using the Random Forest (RF) algorithm to estimate the road adhesion coefficient, there are issues such as insufficient optimization of feature selection during model construction and insufficient diversity in the ensemble of decision trees. To address this issue, a method based on Particle Swarm Optimization (PSO) algorithm to improve RF is proposed, and the algorithmic process is presented. An RF model for estimating the road adhesion coefficient is established, and the PSO algorithm is used to optimize the parameter configuration of RF, including key factors such as the number of features of each tree and the number of trees, so as to enhance the diversity and generalization capabilities of the model. At last, a joint simulation model is built on the MATLAB/Simulink platform for experiments. The comparative experimental results show that the random forest road adhesion coefficient estimation method based on PSO-RF can overcome the limitations of the traditional RF methods, and both the estimation accuracy and stability have been significantly improved.

Road adhesion coefficient  /  Random Forest (RF)  /  Particle swarm optimization (PSO)  /  State estimation
黄逊, 查云飞. 基于PSO-RF的路面附着系数估计. 汽车文摘, 2025 , (4) : 42 -47 . DOI: 10.19822/j.cnki.1671-6329.20240283
Xun Huang, Yunfei Zha. Estimation of Road Adhesion Coefficient Based on PSO-RF[J]. Automotive Digest, 2025 , (4) : 42 -47 . DOI: 10.19822/j.cnki.1671-6329.20240283
路面附着系数作为车辆主动控制系统的必要输入参数,直接影响汽车的附着力水平,并且能间接反映车辆发生滑移的可能性,较高的路面附着系数意味着车辆滑移风险更低。因此,在汽车主动安全系统中,路面附着系数是决策控制时需要考量的关键因素[1]。目前,对于路面附着系数的估算技术主要分为2类:基于原因(Cause-based)的方法和基于效果(Effect-based)的方法[2]。基于原因(Cause-based)的识别方法着眼于分析影响路面附着系数的各种物理因素[3],这类方法通常采用光学或激光传感器来监测相关变量,并构建数学模型以表达这些因素与路面附着系数之间的关系。通过测量这些关键参数,并应用所建立的数学模型,可以计算出路面附着系数的具体数值。然而,这种方法存在局限性,如较高的成本和复杂的硬件配置。此外,该方法的精度很大程度上取决于传感器信号的质量,当车辆行驶在不平坦路面上或遇到信号严重衰减的情况时,其预估准确性可能会大幅下降。基于效果(Effect-based)的识别方法通过分析车辆对路面变化的动力学响应来估计路面附着系数。这种方法对工作环境的要求相对较低,只需对车辆进行动力学分析即可实现路面附着系数的辨识,且涵盖了多种技术手段,例如卡尔曼滤波估计器[4]、滑模观测器[5]和神经网络等[6-8]
与卡尔曼滤波估计器和滑模观测器相比,神经网络在处理非线性关系方面展现出更强的能力,并且具备更高的容错性能。文献[9]采用了径向基(Radial Basis Function, RBF)神经网络,利用其出色的分类能力来估计路面的附着系数。此外,通过插值方法优化了RBF神经网络的参数设置,从而提升了路面附着系数估计的精确度。文献[10]中提出了一种基于遗传算法改进的BP神经网络方法,旨在防止训练过程中陷入局部最小值的问题,进而提高路面附着系数估计的准确性。文献[11]通过对数据的预处理来改进随机森林(Random Forest, RF)模型,将路面附着系数预测误差控制在一定范围。上述机器学习模型在应用过程中均有不足,如神经网络模型易陷入局部极值和过拟合等问题。近年来,由于RF算法具有分类性能优异、特征个数对结果影响较小、训练效率高等优点,能有效解决多参数间的非线性映射问题[12]。因此,本文采用RF算法进行路面附着系数的识别,以此提高整体模型的泛化能力。
针对汽车在不同行驶状态和路面条件下,传统RF算法可能导致路面附着系数预测不准确,从而影响车辆控制性能的问题,本文设计了基于PSO-RF的路面附着系数估计方法。该方法使用随机森林的超参数设置为初始粒子群,并以训练数据集上的绝对误差作为适应度函数来调整粒子位置,最终确定最优的超参数组合,实现模型配置的优化,旨在提升路面附着系数估计的精度。
构建如图1所示的7自由度车辆动力学模型,其中OXY为惯性坐标系,oxy为车辆坐标系。
图1所示,由力和力矩平衡可得到车辆纵向、侧向和横摆的动力学方程为:

$\left\{\begin{array}{l}m\ddot{x}=m\dot{y}\dot{\varphi }+({F}_{xfl}+{F}_{xfr})cos{\delta }_{f}-({F}_{yfl}+{F}_{yfr})sin{\delta }_{f}+{F}_{xrl}+{F}_{xrr}\\ m\ddot{y}=-m\dot{x}\dot{\varphi }+({F}_{xfl}+{F}_{xfr})sin{\delta }_{f}+({F}_{yfl}+{F}_{yfr})cos{\delta }_{f}+{F}_{yrl}+{F}_{yrr}\\ \begin{array}{l}{I}_{t}\varphi ={l}_{f}\left[\right({F}_{xfl}+{F}_{xfr})sin{\delta }_{f}+({F}_{yfl}+{F}_{yfr}\left)cos{\delta }_{f}\right]-{l}_{r}({F}_{yfl}+{F}_{yfr})+\\         \frac{{l}_{w}}{2}[- ({F}_{xfl}+{F}_{xfr})cos{\delta }_{f}+({F}_{yfl}+{F}_{yfr})sin{\delta }_{f}-{F}_{xfl}+{F}_{xfr}]\end{array}\end{array}\right.$

惯性坐标系OXY中车辆质心平面运动方程为:
$\left\{\begin{array}{c}\dot{X}=\dot{x}cos\varphi -\dot{y}sin\varphi \\ \dot{Y}=\dot{x}sin\varphi +\dot{y}cos\varphi \end{array}\right.$
式中:${\delta }_{f}$为前轮转角,$\dot{x}$$\dot{y}$分表示车辆质心处的纵向速度与侧向速度,$\dot{X}$$\dot{Y}$则是在惯性坐标系中车辆沿X轴和Y轴的速度分量,$\varphi $为横摆角度,It为车辆转动惯量,FxijFyij(其中ij=fl, fr, rl, rr,分别对应于前左、前右、后左、后右车轮)表示作用在四个车轮上的纵向力和侧向力,lflr分别为从车辆质心到前轴和后轴的距离,m为整车质量,lw为轮距。
车轮的纵向力Fxij和侧向力Fyij可以通过复杂的非线性函数来描述,这些函数依赖于多个参数。具体来说,它们与车轮纵向刚度Cxij及侧偏刚度Cyij、垂向载荷Fzij、路面附着系数μ、轮胎侧偏角αij、滑移率sij以及轮胎的状态参数有关,可表示为:
$\left\{\begin{array}{c}{F}_{xij}={f}_{x}({C}_{xij}, {s}_{ij}, \mu, {F}_{zij}, {\alpha }_{ij})\\ {F}_{yij}={f}_{y}({C}_{yij}, {s}_{ij}, \mu, {F}_{zij}, {\alpha }_{ij})\end{array}\right.$
综合式(1)~式(3),可得描述车辆非线性方程为:
${\dot{x}}_{dyn}={f}_{dyn}({x}_{dyn},{u}_{dyn})$
式中:状态量${x}_{dyn}={[\dot{y}, \dot{x}, \varphi, \dot{\varphi }, Y, X]}^{T}$,系统控制量${u}_{dyn}=\left[{\delta }_{f}\right]$
当车辆处于正常行驶过程中,地面施加于车辆的作用力通过轮胎传递。轮胎模型的精度直接影响车辆的动力学特性,因此构建一个精确的轮胎模型对于研究车辆的操控稳定性能至关重要。鉴于轮胎结构复杂且表现出的非线性特征,本文采用了魔术公式(Magic Formula)轮胎模型来描述轮胎的各种物理和结构属性[13]。该模型采用组合三角函数表达式来体现轮胎在不同条件下的表现,包括横向力、纵向力以及与滑移率和侧偏角相关的特性,可表示为:
$\left\{\begin{array}{l}{y}_{t}=Dsin\left\{Carctan\right[B{x}_{t}-E(B{x}_{t}-arctanB{x}_{t})\left]\right\}\\ {Y}_{t}={y}_{t}+{S}_{V}\\ {x}_{t}={X}_{t}+{S}_{H}\end{array}\right.$
式中:Xt为车轮的纵向滑移率或车轮侧偏角,Yt为轮胎所承受的纵向力或侧向力,B为刚度因子,C为形状参数,D为峰值因素,E为曲率系数。SVSH分别表示曲线垂直方向漂移与水平方向漂移。
通过使用MATLAB/Simulink软件对汽车的动态特性进行建模,收集所需的数据集。车辆运动状态相关参数如表1所示。在CarSim与MATLAB/Simulink联合仿真平台中设置多种工况,包括不同路面附着条件和行驶速度,用以收集车辆动力学相关数据。通过文献[14]可知,路面附着系数与车辆状态参数具有非线性函数关系,故选用纵向加速度、侧向加速度、纵向速度及横摆角速度等10个车辆动力学参数作为PSO-RF算法的训练样本输入,以路面附着系数作为输出。
表2所示,在直线、单移线、双移线这3种工况下,路面附着系数设定为0.1~1,每隔0.1取一个值。车辆速度分为2种:匀速行驶,范围为20~110 km/h,每间隔10 km/h取一个值;匀加速行驶,从20 km/h匀加速至80 km/h,仿真时间为20 s,采样频率为5 Hz,共收集了33 000条数据样本。并结合实车测试数据,按8∶1∶1比例划分为训练集、验证集与测试集。
为解决传统RF算法在估计路面附着系数时预估不准确的问题,本文提出了一种基于变权重PSO-RF算法的新型路面附着系数估计方法,旨在提升车辆控制效果。
RF算法是一种由多个决策树构成的预测模型,包含多个决策树的分类回归器[15],其核心理念是集成学习方法。此算法通过创建一系列独立的决策树,并引入了随机性来构建每棵树,从而增强了模型的整体稳定性和准确性。在预测时,随机森林通过对所有个体决策树预测结果进行综合考量,以确定最终输出。
其工作流程如下:
a. 通过Bootstrap抽样方法从大小为N的训练集样本中抽取若干个子集;
b. 对于每一个子集,从M个特征中随机选取m个特征作为分裂特征子集;
c. 在此过程中,每棵树都允许自由生长而不进行剪枝操作;
d. 重复上述步骤以形成一系列决策树,形成一个“森林”;
e. 通过对所有决策树的结果进行投票来决定新样本的回归或分类。
算法流程如图2所示。
PSO算法是一种受到鸟类群体觅食行为启发的用于解决优化问题的群体智能方法[14]。在该算法中,每个粒子都具备2个关键属性:位置与速度。其中,位置表示为待解决问题的一个候选解,而适应度函数则用来评估这个解的质量,即计算出相应的适应度值。粒子的速度会在每次迭代时依据自身历史最优位置及整个群体的历史最优位置进行动态调整,这种调整决定了粒子在下一次迭代中移动的方向和距离,进而逐步搜索到全局最优解或满意解。计算公式如下:
${v}_{id}^{(k+1)}=w{v}_{id}^{\left(k\right)}+{s}_{1}{r}_{1}({P}_{id}^{\left(k\right)}-{X}_{id}^{\left(k\right)})+{s}_{2}{r}_{2}({P}_{gd}^{\left(k\right)}-{X}_{id}^{\left(k\right)})$
${X}_{id}^{(k+1)}={X}_{id}^{\left(k\right)}+{v}_{id}^{(k+1)}$
式中:${v}_{id}^{\left(k\right)}$${X}_{id}^{\left(k\right)}$${P}_{id}^{\left(k\right)}$分别为粒子i在第d维搜索空间经历第k次迭代后的速度、位置和个体极值,${P}_{gd}^{\left(k\right)}$为种群在第d维搜索空间经历第k次迭代后的全局极值,s1s2为非负的加速度因子,r1r2为[0,1]之间的随机数,w为惯性权重。经过多次迭代更新后,便可在解空间中实现参数的优化。
由于人工设定方式难以精准选取随机森林最佳子树棵数(ntree)和分裂特征数(mfeature),且参数的选择对随机森林性能有很大影响。针对这一问题,本文采用粒子群算法对随机森林进行参数寻优。基于PSO-RF的路面附着系数估计识别算法流程如图3所示。
步骤1:设定迭代的最大轮次和群体的粒子数目,并初始化粒子的位置与速度。搜索空间的维度取决于所需优化参数的数量。为确保搜索过程的有效性,为粒子每一维度上的位置和速度设定上下限。
步骤2:采用均方误差作为评价指标(即适应度函数),依据粒子的位置信息计算出每个粒子的初始适应度。初始适应度值将被记作个体最佳值,当前个体最优值为全局极值。
步骤3:计算各粒子适应度,比较当前迭代步各粒子适应度与自身极值以及全局极值,从而更新个体最佳位置与全局最优位置及其对应的适应度值。
步骤4:检查是否达到结束标准,即是否完成最大迭代次数。如已达上限,则输出全局体最优适应度值,此位置即代表随机森林模型的最优参数配置;反之,则重复步骤3直到满足终止条件。
采用人工设定的参数(ntree=10,mfeature=2)构建随机森林模型,并对该模型使用测试数据集进行了样本仿真,仿真结果如图4所示。这里选取了800个路面附着系数为0.5附近的数据点作为示例来展示仿真结果。图4中,“RF预测”代表通过RF算法得到的估计值,其绝对误差平均值(Mean Absolute Error, MAE)为0.008 450 6。
改用PSO算法来确定RF回归模型中的ntreemfeature,提高RF算法模型性能。图5展示了PSO-RF算法的适应度曲线,其中,粒子群迭代次数设定为50次,同时最大种群规模限制在20个。经过训练后,最终得到本研究适用的参数配置ntree=66,mfeature=3。
使用PSO寻优后的RF算法模型对其测试集样本进行评估,其仿真结果如图6所示(与图5采用相同的样本集)。图6中的“PSO-RF估计”代表通过PSO优化后的RF算法得到的估计值,其MAE为0.000 284 87。
为了验证基于PSO-RF的路面附着系数识别算法的有效性,分别对PSO-RF、RF、极端梯度提升算法(XGBoost)、最小梯度提升算法(LSBoost)的路面附着系数估计测试集的各误差值进行了对比,并使用MATLAB软件完成相关仿真计算,如表3所示。同时,为保证仿真结果的一致性,各模型采用相同的测试集,并通过相同的评价指标,如平均绝对误差(MAE)、平均相对误差(MAPE)、均方根误差(RMSE)、R方系数(R2)来评估模型的有效性。
表3中可以看出,与未经优化的RF算法相比,PSO-RF模型的误差均更低,且R2值更接近1,模型估计值与实际值之间更吻合。对比各方法的误差可知,PSO-RF算法误差更低,更优于其他模型,因此更适合用于路面附着系数的识别。
使用Simulink与CarSim进行联合仿真,验证PSO-RF算法的有效性,并获得实时估计数据。为验证本文设计的路面附着系数估计器的表现,考虑仿真工况与训练数据样本不重合,在双移线为仿真工况下设置变附着路面,其从0.8突变至0.5。同时车辆起始速度为90 km/h,并在2 s后以5 m/s2的加速度减速至45 km/h。仿真试验中,将RF算法作为对照组,用于展示设计的附着系数估计器的有效性,仿真结果如图7所示。
双移线复杂工况的预测过程存在预测值的抖数情况,根据仿真结果可知:RF算法的路面附着系数估计结果的最大误差为0.062 1,平均绝对百分比误差MAPE为2.052%;与RF算法相比,PSO-RF算法从开始就能很好地预测,其估计结果的最大误差为0.042 7,平均绝对百分比误差MAPE为1.068%。由仿真结果可知,训练出来的PSO-RF算法模型更适用于复杂工况。
通过PSO算法调整RF模型关键参数(子树棵数ntree与分裂特征数mfeature)进行优化,解决了传统依赖手动选取这些参数的问题,提高了估计效果。相比RF算法、LSBoost算法、XGBoost算法的估计性能,PSO-RF 模型在路面附着系数估计中具有更好的估计效果,平均绝对误差低至0.000 284 87,且在复杂工况下也具有较好的泛用性。研究表明,子树棵树和分裂特征数参数对随机森林算法预测效果有显著影响,人工选取以上参数不仅不严谨,而且在估计过程中也可能降低估计预测效果。本文提出采用PSO对参数进行优选,显著改进了随机森林算法的估计效果。
参考文献 引证文献
排序方式:
[1]
邓浩楠, 赵治国, 赵坤, 等. 四驱车辆交互式多模型自适应无迹卡尔曼滤波路面附着系数估计[J]. 汽车工程, 2024, 46(8): 1357-1369.
[2]
袁朝春, 张龙飞, 陈龙. 路面附着系数识别方法发展现状综述及展望[J]. 机械制造与自动化, 2018, 47(2): 1-4,7.
[3]
LI B, WEN J E, FENG T, et al. Road Adhesion Coefficient Estimation Based on LiDAR Reflectance Intensity[J]. IEEE Sensors Journal, 2024, 24(18): 29135-29148.
[4]
吕小龙, 查云飞, 马芳武, 等. 基于Kalman滤波的路面附着系数估计算法综述[J]. 汽车工业研究, 2022(1): 55-59.
[5]
ARIPIN M K, GHAZALI R, SAM Y M, et al. Uncertainty Modelling and High Performance Robust Controller for Active Front Steering Control[C]//2015 10th Asian Control Conference (ASCC). Malaysia: IEEE, 2015.
[6]
WANG F, FAN X, ZHANG Y, et al. Fuzzy Identification Based on Tire/Road Adhesion Feature[J]. Computer Aided Drafting, Design and Manufacturing, 2015, 25(1): 62-67.
[7]
宋涛. 轮毂驱动电动车的路面附着系数估计方法研究[D]. 哈尔滨: 哈尔滨工业大学, 2017.
[8]
伍文广, 张凡皓, 徐孟龙. 基于Elman神经网络的路面附着系数识别[J]. 重庆大学学报, 2023, 46(3): 118-128.
[9]
黄开启, 韩伟, 陈俊杰. 果蝇优化BP神经网络路面附着系数估计[J]. 制造业自动化, 2023, 45(3): 134-138.
[10]
查云飞, 吕小龙, 陈慧勤, 等. 基于路面附着系数估计的车辆轨迹跟踪控制[J]. 汽车工程, 2023, 45(6): 1010-1021+1039.
[11]
董建凯. 基于机器学习神经网络的路面附着系数实时分类算法的研究[D]. 上海: 同济大学, 2018.
[12]
郑香美, 高兴旺, 赵志忠. 基于“魔术公式”的轮胎动力学仿真分析[J]. 机械与电子, 2012(9): 16-20.
[13]
BREIMAN L. Random Forests[J]. Machine Learnings, 2001, 45(1): 5-32.
[14]
林棻, 王少博, 赵又群, 蔡亦璋. 基于改进Keras模型的路面附着系数估计[J]. 机械工程学报, 2021, 57(12): 74-86.
[15]
葛杰, 曹绮欣, 张晓鹏, 等. 基于PSO-RF模型的汉江流域参考作物蒸散量模拟研究[J]. 中国农业气象, 2024, 45(8): 849-859.
2025年第卷第4期
PDF下载
236
97
引用本文
BibTeX
文章信息
doi: 10.19822/j.cnki.1671-6329.20240283
  • 首发时间:2025-11-10
  • 出版时间:2025-04-05
补充材料
相关文章
文章信息
作者
出版历史
基金
作者信息
    福建理工大学, 福州 350118
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/qcwz/CN/10.19822/j.cnki.1671-6329.20240283
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

Family
属数
Number of
genus
种数
Number of
species
占总种数比例
Percentage of
total species (%)

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