Article(id=1200070551147479770, tenantId=1146029695717560320, journalId=1189918454225211397, issueId=1200070543870357634, articleNumber=null, orderNo=null, doi=10.20104/j.cnki.1674-6546.20230397, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=null, receivedDateStr=null, revisedDate=1695312000000, revisedDateStr=2023-09-22, acceptedDate=null, acceptedDateStr=null, onlineDate=1764048715625, onlineDateStr=2025-11-25, pubDate=1710432000000, pubDateStr=2024-03-15, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1764048715625, onlineIssueDateStr=2025-11-25, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1764048715625, creator=13701087609, updateTime=1764048715625, updator=13701087609, issue=Issue{id=1200070543870357634, tenantId=1146029695717560320, journalId=1189918454225211397, year='2024', volume='', issue='3', pageStart='1', pageEnd='48', issueExtLink='null', onlineDate='null', pubDate='null', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=null, createTime=1764048713891, creator=13701087609, updateTime=1764049195679, updator=13701087609, preIssue=null, nextIssue=null, ext={EN=IssueExt(id=1200072564690219870, tenantId=1146029695717560320, journalId=1189918454225211397, issueId=1200070543870357634, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1200072564690219871, tenantId=1146029695717560320, journalId=1189918454225211397, issueId=1200070543870357634, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null}, startPage=43, endPage=48, ext={EN=ArticleExt(id=1200070551499801341, articleId=1200070551147479770, tenantId=1146029695717560320, journalId=1189918454225211397, language=EN, title=Research on Fuel Consumption Prediction of Heavy-Duty Diesel Vehicles Based on Neural Network, columnId=null, journalTitle=Automotive Engineer, columnName=null, runingTitle=null, highlight=null, articleAbstract=

To establish an accurate fuel consumption prediction model of heavy-duty diesel vehicles, this paper firstly used the dataset collected by heavy-duty diesel vehicles in real road driving, and Pearson correlation coefficient to calculate the correlation between different factors and fuel consumption, then selected 7 factors with strong correlation with fuel consumption, and used Back Propagation (BP) neural network and Long Short-Term Memory (LSTM) neural network to establish fuel consumption prediction models for heavy-duty diesel vehicles. The prediction results of different driving sections show that the prediction accuracy of BP neural network for fuel consumption values in different road sections differs sharply, and the generalization of the model is low, while the prediction of different road sections of the LSTM model is very accurate, and the model generalization is strong.

, 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=Changhai Liu), CN=ArticleExt(id=1200070554263846920, articleId=1200070551147479770, tenantId=1146029695717560320, journalId=1189918454225211397, language=CN, title=基于神经网络的重型柴油车油耗预测研究, columnId=0, journalTitle=汽车工程师, columnName=, runingTitle=null, highlight=null, articleAbstract=

为建立准确的重型柴油车油耗预测模型,使用重型柴油车实际道路行驶数据集,利用皮尔逊相关系数计算了不同因素与油耗的相关性,选取与油耗相关性较强的7个因素,利用反向传播(BP)神经网络、长短时记忆(LSTM)神经网络分别建立重型柴油车油耗预测模型。对不同行驶路段的预测结果表明,BP神经网络对各路段油耗的预测准确性存在很大差异,模型泛化能力差,LSTM神经网络模型对各路段的预测均十分准确,模型泛化能力强。

, correspAuthors=null, authorNote=null, correspAuthorsNote=null, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=iq74e8r/dSyXk9s+5EzGNg==, magXml=7lq0mJUCrtD41Wpeg8T+SQ==, pdfUrl=null, pdf=xnIPoDWGLzU2unZ78WLfxA==, pdfFileSize=898904, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=AR0ZqSx7diNj7AaA5TkOsw==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=4zzi5jDFmgiaGgrrL0XxLg==, mapNumber=null, authorCompany=null, fund=null, authors=null, authorsList=刘昌海)}, authors=[Author(id=1200407190482842087, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070551147479770, 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=1200407190591893998, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070551147479770, authorId=1200407190482842087, language=EN, stringName=Changhai Liu, firstName=Changhai, middleName=null, lastName=Liu, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=Chongqing Jiaotong University, Chongqing 400074, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1200407190679974391, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070551147479770, authorId=1200407190482842087, language=CN, stringName=刘昌海, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=重庆交通大学, 重庆 400074, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1200407190348624347, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070551147479770, xref=null, ext=[AuthorCompanyExt(id=1200407190357012956, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070551147479770, companyId=1200407190348624347, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=Chongqing Jiaotong University, Chongqing 400074), AuthorCompanyExt(id=1200407190365401565, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070551147479770, companyId=1200407190348624347, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=重庆交通大学, 重庆 400074)])])], keywords=[Keyword(id=1200407190872912390, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070551147479770, language=EN, orderNo=1, keyword=Heavy-duty diesel vehicles), Keyword(id=1200407190981964304, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070551147479770, language=EN, orderNo=2, keyword=Fuel consumption prediction), Keyword(id=1200407191082627609, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070551147479770, language=EN, orderNo=3, keyword=Back Propagation (BP) neural network), Keyword(id=1200407191191679524, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070551147479770, language=EN, orderNo=4, keyword=Long Short-Term Memory (LSTM) neural network), Keyword(id=1200407191292342832, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070551147479770, language=CN, orderNo=1, keyword=重型柴油车), Keyword(id=1200407191376228918, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070551147479770, language=CN, orderNo=2, keyword=油耗预测), Keyword(id=1200407191523029568, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070551147479770, language=CN, orderNo=3, keyword=BP神经网络), Keyword(id=1200407191619498574, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070551147479770, language=CN, orderNo=4, keyword=LSTM神经网络)], refs=[Reference(id=1200407194974941937, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070551147479770, doi=null, pmid=null, pmcid=null, year=2016, volume=35, issue=7, pageStart=689, pageEnd=694, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=邵良杉, 赵藤野, 温廷新, journalName=辽宁工程技术大学学报(自然科学版), refType=null, unstructuredReference=邵良杉, 赵藤野, 温廷新, 等. PSO-BP神经网络在露天矿卡车油耗预测中的应用[J]. 辽宁工程技术大学学报(自然科学版), 2016, 35(7): 689-694., articleTitle=PSO-BP神经网络在露天矿卡车油耗预测中的应用, refAbstract=null), Reference(id=1200407195104965372, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070551147479770, doi=null, pmid=null, pmcid=null, year=2016, volume=35, issue=7, pageStart=689, pageEnd=694, url=null, language=null, rfNumber=[1], rfOrder=1, authorNames=SHAO L S, ZHAO T Y, WEN T X, journalName=Journal of Liaoning Technical University (Natural Science), refType=null, unstructuredReference=SHAO L S, ZHAO T Y, WEN T X, et al. PSO and BP Neural Network Application in Open-Pit Mine Truck Fuel Consumption Forecast[J]. Journal of Liaoning Technical University (Natural Science), 2016, 35(7): 689-694., articleTitle=PSO and BP Neural Network Application in Open-Pit Mine Truck Fuel Consumption Forecast, refAbstract=null), Reference(id=1200407195209822978, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070551147479770, doi=null, pmid=null, pmcid=null, year=2021, volume=41, issue=8, pageStart=161, pageEnd=166, url=null, language=null, rfNumber=[2], rfOrder=2, authorNames=顾清华, 王骞, 江松, journalName=矿业研究与开发, refType=null, unstructuredReference=顾清华, 王骞, 江松, 等. 基于PSOGA-SVM的露天矿卡车油耗预测研究[J]. 矿业研究与开发, 2021, 41(8): 161-166., articleTitle=基于PSOGA-SVM的露天矿卡车油耗预测研究, refAbstract=null), Reference(id=1200407195331457803, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070551147479770, doi=null, pmid=null, pmcid=null, year=2021, volume=41, issue=8, pageStart=161, pageEnd=166, url=null, language=null, rfNumber=[2], rfOrder=3, authorNames=GU Q H, WANG Q, JIANG S, journalName=Mining Research and Development, refType=null, unstructuredReference=GU Q H, WANG Q, JIANG S, et al. Research on Fuel Consumption Prediction of Truck in Open-Pit Mine Based on PSOGA-SVM[J]. Mining Research and Development, 2021, 41(8): 161-166., articleTitle=Research on Fuel Consumption Prediction of Truck in Open-Pit Mine Based on PSOGA-SVM, refAbstract=null), Reference(id=1200407195457286931, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070551147479770, doi=null, pmid=null, pmcid=null, year=2023, volume=40, issue=3, pageStart=186, pageEnd=191, url=null, language=null, rfNumber=[3], rfOrder=4, authorNames=邹智宏, 李超, 邓聚才, journalName=计算机仿真, refType=null, unstructuredReference=邹智宏, 李超, 邓聚才, 等. 基于mRMR特征优化算法的油耗预测建模研究[J]. 计算机仿真, 2023, 40(3): 186-191+301., articleTitle=基于mRMR特征优化算法的油耗预测建模研究, refAbstract=null), Reference(id=1200407195583116056, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070551147479770, doi=null, pmid=null, pmcid=null, year=2023, volume=40, issue=3, pageStart=186, pageEnd=191, url=null, language=null, rfNumber=[3], rfOrder=5, authorNames=ZOU Z H, LI C, DENG J C, journalName=Computer Simulation, refType=null, unstructuredReference=ZOU Z H, LI C, DENG J C, et al. Research on Fuel Consumption Prediction Modeling Based on Max-Relevance and Min-Redundancy Feature Optimization Algorithm[J]. Computer Simulation, 2023, 40(3): 186-191+301., articleTitle=Research on Fuel Consumption Prediction Modeling Based on Max-Relevance and Min-Redundancy Feature Optimization Algorithm, refAbstract=null), Reference(id=1200407195687973663, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070551147479770, doi=null, pmid=null, pmcid=null, year=2016, volume=16, issue=3, pageStart=200, pageEnd=206, url=null, language=null, rfNumber=[4], rfOrder=6, authorNames=朱广宇, 赵蕾, 黄达, journalName=交通运输系统工程与信息, refType=null, unstructuredReference=朱广宇, 赵蕾, 黄达, 等. 基于决策树方法的车辆油耗估计模型[J]. 交通运输系统工程与信息, 2016, 16(3): 200-206., articleTitle=基于决策树方法的车辆油耗估计模型, refAbstract=null), Reference(id=1200407195809608483, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070551147479770, doi=null, pmid=null, pmcid=null, year=2016, volume=16, issue=3, pageStart=200, pageEnd=206, url=null, language=null, rfNumber=[4], rfOrder=7, authorNames=ZHU G Y, ZHAO L, HUANG D, journalName=Journal of Transportation Systems Engineering and Information Technology, refType=null, unstructuredReference=ZHU G Y, ZHAO L, HUANG D, et al. A Method of Vehicle Fuel Consumption Estimation Based on Decision Tree[J]. Journal of Transportation Systems Engineering and Information Technology, 2016, 16(3): 200-206., articleTitle=A Method of Vehicle Fuel Consumption Estimation Based on Decision Tree, refAbstract=null), Reference(id=1200407195939631914, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070551147479770, doi=null, pmid=null, pmcid=null, year=2019, volume=120, issue=null, pageStart=436, pageEnd=447, url=null, language=null, rfNumber=[5], rfOrder=8, authorNames=KANARACHOS S, MATHEW J, FITZPATRICK E M, journalName=Expert Systems with Applications, refType=null, unstructuredReference=KANARACHOS S, MATHEW J, FITZPATRICK E M. Instantaneous Vehicle Fuel Consumption Estimation using Smartphones and Recurrent Neural Networks[J]. Expert Systems with Applications, 2019, 120: 436-447., articleTitle=Instantaneous Vehicle Fuel Consumption Estimation using Smartphones and Recurrent Neural Networks, refAbstract=null), Reference(id=1200407196061266736, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070551147479770, doi=null, pmid=null, pmcid=null, year=2023, volume=null, issue=3, pageStart=121, pageEnd=126, url=null, language=null, rfNumber=[6], rfOrder=9, authorNames=王一婷, 行本贝, 李彬, journalName=计算机与现代化, refType=null, unstructuredReference=王一婷, 行本贝, 李彬, 等. 基于Shared-LSTM的重型卡车不同加速驾驶行为油耗预测方法[J]. 计算机与现代化, 2023(3): 121-126., articleTitle=基于Shared-LSTM的重型卡车不同加速驾驶行为油耗预测方法, refAbstract=null), Reference(id=1200407196199678770, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070551147479770, doi=null, pmid=null, pmcid=null, year=2023, volume=null, issue=3, pageStart=121, pageEnd=126, url=null, language=null, rfNumber=[6], rfOrder=10, authorNames=WANG Y T, XING B B, LI B, journalName=Computer and Modernization, refType=null, unstructuredReference=WANG Y T, XING B B, LI B, et al. Fuel Consumption Prediction Method of Heavy Trucks with Different Acceleration Driving Behaviors Based on Shared-LSTM[J]. Computer and Modernization, 2023(3): 121-126., articleTitle=Fuel Consumption Prediction Method of Heavy Trucks with Different Acceleration Driving Behaviors Based on Shared-LSTM, refAbstract=null), Reference(id=1200407196317119290, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070551147479770, doi=null, pmid=null, pmcid=null, year=2013, volume=30, issue=6, pageStart=55, pageEnd=58, url=null, language=null, rfNumber=[7], rfOrder=11, authorNames=陈静杰, 邹迎欢, journalName=计算机仿真, refType=null, unstructuredReference=陈静杰, 邹迎欢. 油耗预测中显著影响参数提取方法的仿真[J]. 计算机仿真, 2013, 30(6): 55-58., articleTitle=油耗预测中显著影响参数提取方法的仿真, refAbstract=null), Reference(id=1200407196472308543, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070551147479770, doi=null, pmid=null, pmcid=null, year=2013, volume=30, issue=6, pageStart=55, pageEnd=58, url=null, language=null, rfNumber=[7], rfOrder=12, authorNames=CHEN J J, ZOU Y H, journalName=Computer Simulation, refType=null, unstructuredReference=CHEN J J, ZOU Y H. Simulation for Significant Impact Parameter Extraction Method in Fuel Consumption Estimation[J]. Computer Simulation, 2013, 30(6): 55-58., articleTitle=Simulation for Significant Impact Parameter Extraction Method in Fuel Consumption Estimation, refAbstract=null), Reference(id=1200407196610720579, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070551147479770, doi=null, pmid=null, pmcid=null, year=2023, volume=45, issue=3, pageStart=241, pageEnd=246, url=null, language=null, rfNumber=[8], rfOrder=13, authorNames=吴明兴, 谷昊霖, 别佩, journalName=沈阳工业大学学报, refType=null, unstructuredReference=吴明兴, 谷昊霖, 别佩, 等. 基于萤火虫算法改进BP神经网络的电力用能行为预测方法[J]. 沈阳工业大学学报, 2023, 45(3): 241-246., articleTitle=基于萤火虫算法改进BP神经网络的电力用能行为预测方法, refAbstract=null), Reference(id=1200407196736549704, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070551147479770, doi=null, pmid=null, pmcid=null, year=2023, volume=45, issue=3, pageStart=241, pageEnd=246, url=null, language=null, rfNumber=[8], rfOrder=14, authorNames=WU M X, GU H L, BIE P, journalName=Journal of Shenyang University of Technology, refType=null, unstructuredReference=WU M X, GU H L, BIE P, et al. Improved BP Neural Network Based on Firefly Algorithm for Predicting Electricity Energy Consumption Behavior[J]. Journal of Shenyang University of Technology, 2023, 45(3): 241-246., articleTitle=Improved BP Neural Network Based on Firefly Algorithm for Predicting Electricity Energy Consumption Behavior, refAbstract=null), Reference(id=1200407196895933264, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070551147479770, doi=null, pmid=null, pmcid=null, year=2022, volume=69, issue=1, pageStart=93, pageEnd=100, url=null, language=null, rfNumber=[9], rfOrder=15, authorNames=JAGRUTHI H, KAVITHA C, MULIMANI M, journalName=International Journal of Computer Applications in Technology, refType=null, unstructuredReference=JAGRUTHI H, KAVITHA C, MULIMANI M. Network Intrusion Detection Using Fusion Features and Convolutional Bidirectional Recurrent Neural Network[J]. International Journal of Computer Applications in Technology, 2022, 69(1): 93-100., articleTitle=Network Intrusion Detection Using Fusion Features and Convolutional Bidirectional Recurrent Neural Network, refAbstract=null), Reference(id=1200407197017568085, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070551147479770, doi=null, pmid=null, pmcid=null, year=2022, volume=16, issue=4, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[10], rfOrder=16, authorNames=FATEMEHALSADAT M, KAREM C, RACHID L, journalName=The Cryosphere, refType=null, unstructuredReference=FATEMEHALSADAT M, KAREM C, RACHID L, et al. Convolutional Neural Network and Long Short-Term Memory Models for Ice-Jam Predictions[J]. The Cryosphere, 2022, 16(4)., articleTitle=Convolutional Neural Network and Long Short-Term Memory Models for Ice-Jam Predictions, refAbstract=null)], funds=null, companyList=[AuthorCompany(id=1200407190348624347, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070551147479770, xref=null, ext=[AuthorCompanyExt(id=1200407190357012956, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070551147479770, companyId=1200407190348624347, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=Chongqing Jiaotong University, Chongqing 400074), AuthorCompanyExt(id=1200407190365401565, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070551147479770, companyId=1200407190348624347, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=重庆交通大学, 重庆 400074)])], figs=[ArticleFig(id=1200407191934071404, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070551147479770, language=EN, label=null, caption=null, figureFileSmall=Rf0bG87Z/tqDhNYh4bZm6g==, figureFileBig=uMWdrOdnu+2cQv5lICJtIw==, tableContent=null), ArticleFig(id=1200407192101843577, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070551147479770, language=CN, label=图1, caption=BP神经网络结构, figureFileSmall=Rf0bG87Z/tqDhNYh4bZm6g==, figureFileBig=uMWdrOdnu+2cQv5lICJtIw==, tableContent=null), ArticleFig(id=1200407192219284105, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070551147479770, language=EN, label=null, caption=null, figureFileSmall=PIRKqCtJShGHWXWkWBOWQQ==, figureFileBig=xdLifgZ+DZGsUKil19g7fw==, tableContent=null), ArticleFig(id=1200407192315753105, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070551147479770, language=CN, label=图2, caption=RNN展开示意, figureFileSmall=PIRKqCtJShGHWXWkWBOWQQ==, figureFileBig=xdLifgZ+DZGsUKil19g7fw==, tableContent=null), ArticleFig(id=1200407192437387932, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070551147479770, language=EN, label=null, caption=null, figureFileSmall=bDN7fACmdSGqXd5Cg5jHrQ==, figureFileBig=2r25yPZBTz3yBHz+QvGrhQ==, tableContent=null), ArticleFig(id=1200407192563217059, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070551147479770, language=CN, label=图3, caption=LSTM神经元结构示意, figureFileSmall=bDN7fACmdSGqXd5Cg5jHrQ==, figureFileBig=2r25yPZBTz3yBHz+QvGrhQ==, tableContent=null), ArticleFig(id=1200407193712456360, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070551147479770, language=EN, label=null, caption=null, figureFileSmall=rCyuePCtzkddznyTxczPvA==, figureFileBig=QyxapwmcMrgYqQFg1W1zSw==, tableContent=null), ArticleFig(id=1200407193838285491, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070551147479770, language=CN, label=图4, caption=城市路段BP和LSTM神经网络模型预测结果对比, figureFileSmall=rCyuePCtzkddznyTxczPvA==, figureFileBig=QyxapwmcMrgYqQFg1W1zSw==, tableContent=null), ArticleFig(id=1200407193930560183, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070551147479770, language=EN, label=null, caption=null, figureFileSmall=yngdtMAXYSrc38LGX4O4+A==, figureFileBig=87fMlHcJXbUK3n0s4nJd9A==, tableContent=null), ArticleFig(id=1200407194048000706, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070551147479770, language=CN, label=图5, caption=郊区路段BP和LSTM神经网络模型预测结果对比, figureFileSmall=yngdtMAXYSrc38LGX4O4+A==, figureFileBig=87fMlHcJXbUK3n0s4nJd9A==, tableContent=null), ArticleFig(id=1200407194173829831, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070551147479770, language=EN, label=null, caption=null, figureFileSmall=babTrzfvA0/PjAB3m4NYGA==, figureFileBig=StOTUQCRAj2iqT5uOHOTTA==, tableContent=null), ArticleFig(id=1200407194299658958, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070551147479770, language=CN, label=图6, caption=高速路段BP和LSTM神经网络模型预测结果对比, figureFileSmall=babTrzfvA0/PjAB3m4NYGA==, figureFileBig=StOTUQCRAj2iqT5uOHOTTA==, tableContent=null), ArticleFig(id=1200407194404516563, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070551147479770, language=EN, label=null, caption=null, figureFileSmall=null, figureFileBig=null, tableContent=
因素 相关系数 因素 相关系数
发动机扭矩 0.96 坡度 0.51
发动机进气量 0.92 加速度 0.46
车辆比功率 0.92 冷却液温度 0.35
发动机转速 0.72 环境温度 0.15
车速 0.67 环境湿度 -0.13
), ArticleFig(id=1200407194500985564, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070551147479770, language=CN, label=表1, caption=

各因素与油耗的皮尔逊相关系数

, figureFileSmall=null, figureFileBig=null, tableContent=
因素 相关系数 因素 相关系数
发动机扭矩 0.96 坡度 0.51
发动机进气量 0.92 加速度 0.46
车辆比功率 0.92 冷却液温度 0.35
发动机转速 0.72 环境温度 0.15
车速 0.67 环境湿度 -0.13
), ArticleFig(id=1200407194605843169, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070551147479770, language=EN, label=null, caption=null, figureFileSmall=null, figureFileBig=null, tableContent=
评价指标 BP神经网络模型 LSTM神经网络模型
MAE RMSE R2/% MAE RMSE R2/%
城市路段 0.085 1 0.114 7 89.92 0.056 5 0.077 4 95.41
郊区路段 0.075 0 0.108 4 94.81 0.074 2 0.096 2 95.91
高速路段 0.127 8 0.192 3 97.38 0.172 3 0.213 7 96.77
), ArticleFig(id=1200407194752643813, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070551147479770, language=CN, label=表2, caption=

BP和LSTM神经网络模型预测结果评价指标对比

, figureFileSmall=null, figureFileBig=null, tableContent=
评价指标 BP神经网络模型 LSTM神经网络模型
MAE RMSE R2/% MAE RMSE R2/%
城市路段 0.085 1 0.114 7 89.92 0.056 5 0.077 4 95.41
郊区路段 0.075 0 0.108 4 94.81 0.074 2 0.096 2 95.91
高速路段 0.127 8 0.192 3 97.38 0.172 3 0.213 7 96.77
)], attaches=null, journal=Journal(id=1189918244568731652, delFlag=0, nameCn=汽车工程师, nameEn=Automotive Engineer, nameHistory1=null, nameHistory2=null, issn=1674-6546, eissn=null, cn=22-1432/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=+bJsKkKt/pjz9u6EwhnksQ==, journalPrice=null, startedYear=null, abbrevIsoEn=null, journalRemark=null, publicationField=null, createdTime=1761628217121, updatedTime=1761735708780, createdBy=18614031015, updatedBy=13701087609, firstLetterCn=A, firstLetterEn=A, subjectCode=Engineering, subjectName=Engineering, subjectCodeEn=Engineering, subjectNameEn=null, picCn=+bJsKkKt/pjz9u6EwhnksQ==, picEn=O3Sn3tnYYrh/jm6emnnMWA==, jcr=null, cjcr=null, exts=[JournalExt(id=1190369097415233706, language=CN, name=汽车工程师, 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=1761735708812, updatedTime=1761735708812, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=https://tjqc.cbpt.cnki.net/index.aspx?t=1, submissionEditorUrl=https://tjqc.cbpt.cnki.net/index.aspx?t=3, submissionReviewUrl=https://tjqc.cbpt.cnki.net/index.aspx?t=2, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""}), JournalExt(id=1190369097553645739, language=EN, name=Automotive Engineer, 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=1761735708845, updatedTime=1761735708845, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=https://tjqc.cbpt.cnki.net/index.aspx?t=1, submissionEditorUrl=https://tjqc.cbpt.cnki.net/index.aspx?t=3, submissionReviewUrl=https://tjqc.cbpt.cnki.net/index.aspx?t=2, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""})], databaseList=null, tenantJournalId=1189918454225211397, websiteList=[Website(id=1189918982430847716, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1189918454225211397, 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/qcgcs/CN, language=CN, createTime=1761628393037, createBy=18614031015, updateTime=1761628422913, updateBy=18614031015, name=汽车工程师-中文, tplId=1146099689490845704, title=汽车工程师, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1189919800185917791, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189918982430847716, code=articleTextType, value=kx, createTime=1761628588005, updateTime=1761628588005, creator=18614031015, updator=18614031015), WebsiteProps(id=1189919800164946268, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189918982430847716, code=banner, value=null, createTime=1761628588000, updateTime=1761628588000, creator=18614031015, updator=18614031015), WebsiteProps(id=1189919800211083618, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189918982430847716, code=grayFlag, value=0, createTime=1761628588011, updateTime=1761628588011, creator=18614031015, updator=18614031015), WebsiteProps(id=1189919800156557659, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189918982430847716, code=logo, value=https://castjournals.cast.org.cn/joweb/qcgcs/CN/file/pic?fileId=yiZ96RYoYcnGnRMuWdmkWA==, createTime=1761628587998, updateTime=1761628587998, creator=18614031015, updator=18614031015), WebsiteProps(id=1189919800223666532, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189918982430847716, code=minRunFlag, value=0, createTime=1761628588014, updateTime=1761628588014, creator=18614031015, updator=18614031015), WebsiteProps(id=1189919800181723486, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189918982430847716, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/qcgcs/CN/file/pic, createTime=1761628588004, updateTime=1761628588004, creator=18614031015, updator=18614031015), WebsiteProps(id=1189919800215277923, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189918982430847716, code=silenceFlag, value=0, createTime=1761628588012, updateTime=1761628588012, creator=18614031015, updator=18614031015), WebsiteProps(id=1189919800173334877, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189918982430847716, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1761628588002, updateTime=1761628588002, creator=18614031015, updator=18614031015), WebsiteProps(id=1189919800194306400, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189918982430847716, code=themeColor, value=null, createTime=1761628588007, updateTime=1761628588007, creator=18614031015, updator=18614031015), WebsiteProps(id=1189919800202695009, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189918982430847716, code=themeStyle, value=null, createTime=1761628588009, updateTime=1761628588009, creator=18614031015, updator=18614031015)]), Website(id=1189918982527316711, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1189918454225211397, 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/qcgcs/EN, language=EN, createTime=1761628393061, createBy=18614031015, updateTime=1761628543075, updateBy=18614031015, name=汽车工程师-英文, tplId=1146101810881728533, title=Automotive Engineer, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1189919837561352952, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189918982527316711, code=articleTextType, value=kx, createTime=1761628596916, updateTime=1761628596916, creator=18614031015, updator=18614031015), WebsiteProps(id=1189919837540381429, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189918982527316711, code=banner, value=null, createTime=1761628596911, updateTime=1761628596911, creator=18614031015, updator=18614031015), WebsiteProps(id=1189919837582324475, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189918982527316711, code=grayFlag, value=0, createTime=1761628596921, updateTime=1761628596921, creator=18614031015, updator=18614031015), WebsiteProps(id=1189919837527798516, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189918982527316711, code=logo, value=https://castjournals.cast.org.cn/joweb/qcgcs/EN/file/pic?fileId=yiZ96RYoYcnGnRMuWdmkWA==, createTime=1761628596908, updateTime=1761628596908, creator=18614031015, updator=18614031015), WebsiteProps(id=1189919837594907389, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189918982527316711, code=minRunFlag, value=0, createTime=1761628596924, updateTime=1761628596924, creator=18614031015, updator=18614031015), WebsiteProps(id=1189919837557158647, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189918982527316711, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/qcgcs/EN/file/pic, createTime=1761628596915, updateTime=1761628596915, creator=18614031015, updator=18614031015), WebsiteProps(id=1189919837586518780, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189918982527316711, code=silenceFlag, value=0, createTime=1761628596922, updateTime=1761628596922, creator=18614031015, updator=18614031015), WebsiteProps(id=1189919837548770038, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189918982527316711, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_en_623/, createTime=1761628596913, updateTime=1761628596913, creator=18614031015, updator=18614031015), WebsiteProps(id=1189919837569741561, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189918982527316711, code=themeColor, value=null, createTime=1761628596918, updateTime=1761628596918, creator=18614031015, updator=18614031015), WebsiteProps(id=1189919837573935866, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189918982527316711, code=themeStyle, value=null, createTime=1761628596919, updateTime=1761628596919, creator=18614031015, updator=18614031015)])], journalTitle=汽车工程师, weixinUrl=null, journalUrl=https://tjqc.cbpt.cnki.net/, iacademicId=null, status=1, seqNo=null, journalTitleEn=Automotive Engineer, journalPhotoCn=+bJsKkKt/pjz9u6EwhnksQ==, journalPhotoEn=O3Sn3tnYYrh/jm6emnnMWA==, 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/qcgcs/CN/10.20104/j.cnki.1674-6546.20230397, detailUrlEn=https://castjournals.cast.org.cn/joweb/qcgcs/EN/10.20104/j.cnki.1674-6546.20230397, pdfUrlCn=https://castjournals.cast.org.cn/joweb/qcgcs/CN/PDF/10.20104/j.cnki.1674-6546.20230397, pdfUrlEn=https://castjournals.cast.org.cn/joweb/qcgcs/EN/PDF/10.20104/j.cnki.1674-6546.20230397, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
基于神经网络的重型柴油车油耗预测研究
收藏切换
PDF下载
刘昌海
汽车工程师 | 2024,(3): 43-48
收起
收藏切换
汽车工程师 | 2024, (3): 43-48
基于神经网络的重型柴油车油耗预测研究
全屏
刘昌海
作者信息
  • 重庆交通大学, 重庆 400074
Research on Fuel Consumption Prediction of Heavy-Duty Diesel Vehicles Based on Neural Network
Changhai Liu
Affiliations
  • Chongqing Jiaotong University, Chongqing 400074
出版时间: 2024-03-15 doi: 10.20104/j.cnki.1674-6546.20230397
文章导航
收藏切换

为建立准确的重型柴油车油耗预测模型,使用重型柴油车实际道路行驶数据集,利用皮尔逊相关系数计算了不同因素与油耗的相关性,选取与油耗相关性较强的7个因素,利用反向传播(BP)神经网络、长短时记忆(LSTM)神经网络分别建立重型柴油车油耗预测模型。对不同行驶路段的预测结果表明,BP神经网络对各路段油耗的预测准确性存在很大差异,模型泛化能力差,LSTM神经网络模型对各路段的预测均十分准确,模型泛化能力强。

重型柴油车  /  油耗预测  /  BP神经网络  /  LSTM神经网络

To establish an accurate fuel consumption prediction model of heavy-duty diesel vehicles, this paper firstly used the dataset collected by heavy-duty diesel vehicles in real road driving, and Pearson correlation coefficient to calculate the correlation between different factors and fuel consumption, then selected 7 factors with strong correlation with fuel consumption, and used Back Propagation (BP) neural network and Long Short-Term Memory (LSTM) neural network to establish fuel consumption prediction models for heavy-duty diesel vehicles. The prediction results of different driving sections show that the prediction accuracy of BP neural network for fuel consumption values in different road sections differs sharply, and the generalization of the model is low, while the prediction of different road sections of the LSTM model is very accurate, and the model generalization is strong.

Heavy-duty diesel vehicles  /  Fuel consumption prediction  /  Back Propagation (BP) neural network  /  Long Short-Term Memory (LSTM) neural network
刘昌海. 基于神经网络的重型柴油车油耗预测研究. 汽车工程师, 2024 , (3) : 43 -48 . DOI: 10.20104/j.cnki.1674-6546.20230397
Changhai Liu. Research on Fuel Consumption Prediction of Heavy-Duty Diesel Vehicles Based on Neural Network[J]. Automotive Engineer, 2024 , (3) : 43 -48 . DOI: 10.20104/j.cnki.1674-6546.20230397
我国公路货物运输量逐年提高,同时,也使能源消耗量逐年增加,准确的燃油消耗量估算对于量化运输过程中产生的能源成本十分重要。
针对重型车辆的油耗估算问题,邵良杉等[1]提出了一种基于粒子群优化反向传播(Back Propagation,BP)神经网络的油耗预测方法,并基于仿真数据验证了该算法的有效性。顾清华等[2]提出了一种基于粒子群优化支持向量机(Particle Swarm Optimization-Support Vector Machine,PSO-SVM)的油耗预测算法,解决了传统算法易陷入局部最优解的问题。但上述研究工作主要基于仿真数据开展。邹智宏等[3]针对油耗预测建模过程中数据输入的冗余问题,提出一种基于最大相关最小冗余算法与主成分分析方法相结合的冗余特征优化算法,并基于BP神经网络建立了一种高速道路车辆油耗预测模型,可准确实现对高速路段运输车辆的燃油消耗量预测。朱广宇等[4]利用主成分分析法获取了车辆油耗的关键影响因素,随后,基于改进的C4.5决策树构建车辆油耗估计模型,使用高速公路场景下车辆油耗的典型样本数据进行测试,证明了该模型的有效性和实用性。Kanarachos等[5]基于移动设备收集到的不同驾驶条件下的油耗数据,利用循环神经网络(Recurrent Neural Network,RNN)对车辆的瞬时油耗进行预测,实现了对车辆油耗的间接监控,但传统的RNN容易出现梯度爆炸和梯度消失的问题,从而导致模型失效。王一婷等[6]定量分析了车辆的不同加速驾驶行为,基于一种共享权重的长短时记忆(Long Short-Term Memory,LSTM)神经网络建立了车辆的油耗预测模型,实现了较为准确的油耗预测。
上述车辆油耗模型研究中,部分研究未使用真实的车辆行驶数据建模,模型并不能完全反映真实工况下油耗的变化情况,部分研究仅针对部分路段建立模型并进行了验证,而由于车辆在不同路段的行驶状态存在很大差异,模型的泛化能力有限。
为此,本文针对重型柴油车实测数据进行相关性分析,分别建立BP神经网络油耗模型和LSTM神经网络油耗模型,并分析2种模型在不同行驶路段的油耗预测效果。
本文使用的重型柴油车运行状态数据及油耗数据基于实际道路驾驶测试采集获得,试验路线位于重庆市,该路线包含了城市道路、市郊道路和高速道路。根据已有的研究和现有的试验数据采集设备,采集的重型车行驶数据主要包括车速、发动机转速、发动机扭矩、环境温度、经度、纬度、海拔、燃油消耗率、环境湿度、冷却液温度,数据采集频率为1 Hz。在该路线进行了2次实际道路驾驶试验,分别采集数据9 955条和10 583条。
受数据采集仪器的精度和行驶时交通状况的限制,采集到的行驶工况数据往往存在质量问题,需要对数据进行预处理,将异常、重复数据删除,补齐缺失数据。试验路线属于山地丘陵地段,使用采集的数据分别计算道路坡度、瞬态加速度和车辆比功率(Vehicle Specific Power,VSP):
ij=hj/xj
aj=vj+1-vj
Pvsj=vj[mgf+mgij+maj(1+δ)+CDAρvj2/2]/m
式中:ijj时刻的道路坡度;hjj时刻的高度差;xjj时刻的水平方向位移;ajvj分别为j时刻车辆的加速度、速度;Pvsjj时刻车辆比功率;v为车速;m为车辆质量,本文取3 100 kg;g=9.8 m/s2为重力加速度;f为滚动阻力系数;δ为旋转质量因子,取δ=0.2;CD为空气阻力系数,取CD=0.9;A为迎风面积,取A=4 m2ρ=1.225 kg/m3为空气密度。
将式(3)简化可得:
Pvsj=(9.8(f+ij)+1.2aj)vj+2.205vj3/3 100
其中:
f=0.007 6+0.000 056vj
车辆行驶过程中,直接或间接影响油耗的因素很多,因此,提取油耗的显著影响因素非常重要[7]。皮尔逊相关系数r是确定变量间是否具有线性关系的一种计算方法:
$r=\frac{{\sum }_{i=1}^{n}({x}_{i}-\overline{x})({y}_{i}-\overline{y})}{\sqrt{\sum _{i=1}^{n}\left({x}_{i}{-\overline{x})}^{2}\right({y}_{i}-{\overline{y)}}^{2}}}$
式中:n为样本数量,xiyi分别为2个变量的取值,$\overline{x}$$\overline{y}$分别为xiyi的平均值。
r的取值范围为[-1,1]:r=0时,变量间不具有相关性;|r|∈(0,0.3)时,变量间具有非常弱的相关性;|r|∈[0.3,0.6)时,变量间具有中相关性;|r|∈[0.6,0.8)时,变量间具有强相关性;|r|∈[0.8,1.0)时,变量间具有极强相关性;当|r|=1时,两变量完全线性变化。表1所示为不同影响因素与油耗间的皮尔逊相关系数,可以看出,发动机扭矩、发动机进气量、车辆比功率、发动机转速及车速均与油耗具有强相关性,加速度和坡度与油耗间的相关性不强,但对研究燃油消耗率是有意义的,而冷却液温度、环境温度和湿度与油耗的相关系数很小。因此,使用发动机扭矩、发动机进气量、车辆比功率、发动机转速、车速、坡度及加速度构建油耗预测模型。
BP神经网络是一种信号前向传播、误差反向传播的多层前馈神经网络,其能够有效识别特征间的非线性关系[8]。该神经网络包括输入层、中间层和输出层,输入层负责接收数据样本矩阵,中间层负责数据样本计算,输出层负责输出数据。如图1所示,各层结构内和各神经元层结构之间连接紧密,各层结构之间采用全连接,网络模型训练过程主要可通过不断地动态地调整模型权重及阈值等实现。
前向传播计算公式为:
${H}_{j}=L\left({\sum }_{i=1}^{n}{w}_{ij}{x}_{i}-{b}_{j}\right)$
式中:Hj为隐含层第j个节点输出,L为激活函数,wij为第j个节点输入与输出间的权值,bj为第j个节点的阈值。
得到输出值后,计算网络的输出y′与实际输出y间的误差e
e=y-y'
最后,采用误差反向传播算法,根据实际输出与期望输出间的误差更新神经网络每两层间的权值和阈值。
RNN是一种链式连接的递归神经网络[9],由输入层、隐含层和输出层构成,RNN结构展开如图2所示。
RNN在传播的过程中权重是共享的,每个时刻的输入都包含当前的数据和上一阶段输出的特征,可对数据特征进行更加充分的学习,但也会导致数据的多次计算,从而增加模型的训练时间。为解决这一问题,研究人员在RNN中添加了3个门机制,形成了LSTM神经网络。
LSTM神经网络在反向传播的过程中不会进行多余的计算,它可以解决RNN无法处理长时依赖的问题,不会出现梯度消失。图3所示为LSTM神经元结构,主要包含遗忘门、输入门、输出门和1个记忆单元,神经元会对模型中的数据进行特征提取和筛选,从而改善模型的效果[10]
LSTM神经网络信息传递过程主要为以下几个步骤:
a. 遗忘门对当前时间段输入的数据xt和上个时间段输出的隐藏状态的数据信息ht-1进行筛选,然后将其输入Sigmoid函数,输出0~l范围内的数值,利用该数值决定信息是否被保留,遗忘门的计算公式为:
ft=σ(Wf[ht-1,xt]+bf)
式中:σ为Sigmoid激活函数,Wfbf分别为遗忘门权重、遗忘门偏置项。
b. 输入门根据输入xt和隐藏状态ht-1更新信息,利用tanh激活函数新增候选记忆单元,输入门计算公式为:
it=σ(Wi[ht-1,xt]+bi)
${{\tilde{C}}_{t}}=\tanh \left( {{W}_{c}}\left[ {{h}_{t}}_{-1},{{x}_{t}} \right]+{{b}_{c}} \right)$
式中:it、${{\tilde{C}}_{t}}$分别为需要记忆的信息和候选记忆单元,WiWc分别为it、${{\tilde{C}}_{t}}$的权重,bibc分别为it${\tilde{C}}_{t}$的偏置项。
c. 更新记忆单元:
${{C}_{t}}={{f}_{t}}{{C}_{t}}_{-1}+{{i}_{t}}{{\tilde{C}}_{t}}$
d. 输出门根据ht-1xt计算输出信息,tanh激活函数结合输出门信息ot得到当前隐藏层状态:
ot=σ(Wo[ht-1,xt]+bo)
ht=ot·tanh(Ct)
式中:Wo为输出门权重,bo为输出门偏置项。
由于本文数据属性涉及范围广,不同特征维度的数据范围不同,为了降低识别误差,首先需对数据进行标准化处理,将其转换为无量纲数据,便于不同单位的指标间进行比较和加权。本文采用Min-Max归一化对网络输入数据进行处理:
x=(x′-xmin)/(xmax-xmin)
式中:x′、x分别为原始数据和经标准化后的数据,xmaxxmin分别为原始数据x′中的最大值和最小值。
通过相关性分析选取了7个与油耗相关性较强的因素,因此模型的输入数据样本维度为7,输出数据维度为1,经尝试并参考经验公式,选取隐藏层数量为2层,神经单元数量为12个,故模型的模式为7-12-12-1。选择Sigmoid函数为BP神经网络模型隐含层的激活函数,选择Purelin函数为输出层激活函数。
设定最大迭代次数为500次,模型学习率设置为0.3,模型误差大小设置为不小于0.5,模型误差低于设定值或超过最大迭代次数时终止训练,否则继续执行。采用小批量梯度下降法,批量尺寸设置为128。
将LSTM神经网络模型的时间步长设置为10,即用前10个历史时间段的车辆运行状态数据对下一时刻的油耗进行预测,同样使用2个隐含层,隐含层节点数分别设置为128个、64个,经多次试验,选择tanh函数为隐含层激活函数,选择Purelin函数作为输出层激活函数。
设定最大迭代次数为500次,模型学习率为0.000 5,30次内模型误差没有降低或超过最大迭代次数时终止训练,否则继续执行。模型的优化器采用Adam优化算法,批量尺寸设置为128。
常见的回归评价指标有平均绝对误差(Mean Absolute Error,MAE)、均方根误差(Root Mean Squared Error,RMSE)、决定系数R2等。MAE用于表示整体模型的预测值的误差;RMSE代表整体模型的预测值与实际值相互间的偏离程度;R2反映预测数据对实际数据的拟合效果。其中,决定系数值越接近1、MAE和RMSE越小,表明预测效果越好。
将2次试验的车辆轨迹数据进行预处理后,使用第1次全行程数据共9 955条输入到BP神经网络模型与LSTM神经网络模型分别进行训练,保存各自结果最好的模型。由于不同路段的行驶工况存在很大差异,导致各路段间油耗差异很大,因此选取第2次试验路线中城市、郊区和高速路段各1 000条数据来验证2种模型的预测性能,图4~图6表2所示为各路段的预测结果,其中,真实值为实际驾驶时采集的燃油消耗率,预测值是使用相关性分析得到的影响因素作为输入,通过训练好的BP神经网络模型和LSTM神经网络模型预测得到的结果。
根据使用同一数据集训练得到的BP神经网络油耗模型与LSTM神经网络油耗模型对不同路段的预测结果可以看出,BP神经网络模型的MAE、RMSE在城市、郊区路段均较LSTM神经网络高,只有高速路段的MAE、RMSE较LSTM神经网络模型低。比较2种模型在3种路段的R2结果可知:BP神经网络模型对3种路段重型柴油车燃油消耗率的预测值与实际值的决定系数存在很大的差异,城市路段的R2仅为89.92%,高速路段的R2达到97.38%,郊区路段的R2在两者之间;LSTM神经网络模型对3种路段预测结果差异不大,3种路段的R2都达到了95%以上。由以上结果可得,在使用相同的数据集训练模型时,LSTM神经网络模型更为稳定、泛化能力更强。
本文使用重型柴油车实际道路行驶数据,选取与车辆油耗相关性较强的因素,建立了BP神经网络油耗模型与LSTM神经网络油耗模型,通过对比2种油耗模型在不同路段的燃油消耗率预测结果表明:LSTM神经网络油耗模型对重型柴油车在城市、郊区路段下行驶时的油耗预测能力较BP神经网络油耗模型强,BP神经网络油耗模型仅在高速路段下预测能力略强于LSTM神经网络油耗模型,但LSTM神经网络模型对3种路段下行驶时的油耗预测值与真实值的R2均超过95%,而BP神经网络模型的预测结果仅在高速路段R2>95%。重型柴油车实际驾驶中涉及的道路类型多样,因此,使用LSTM神经网络油耗模型能够获得更为准确的油耗预测结果。
由于本文仅采用了一种类型的车辆开展燃油消耗率数据实测,研究对象相对单一。在未来的研究中,将考虑采用更多类型车辆数据,进一步提升模型的适用性。
参考文献 引证文献
排序方式:
[1]
邵良杉, 赵藤野, 温廷新, 等. PSO-BP神经网络在露天矿卡车油耗预测中的应用[J]. 辽宁工程技术大学学报(自然科学版), 2016, 35(7): 689-694.
SHAO L S, ZHAO T Y, WEN T X, et al. PSO and BP Neural Network Application in Open-Pit Mine Truck Fuel Consumption Forecast[J]. Journal of Liaoning Technical University (Natural Science), 2016, 35(7): 689-694.
[2]
顾清华, 王骞, 江松, 等. 基于PSOGA-SVM的露天矿卡车油耗预测研究[J]. 矿业研究与开发, 2021, 41(8): 161-166.
GU Q H, WANG Q, JIANG S, et al. Research on Fuel Consumption Prediction of Truck in Open-Pit Mine Based on PSOGA-SVM[J]. Mining Research and Development, 2021, 41(8): 161-166.
[3]
邹智宏, 李超, 邓聚才, 等. 基于mRMR特征优化算法的油耗预测建模研究[J]. 计算机仿真, 2023, 40(3): 186-191+301.
ZOU Z H, LI C, DENG J C, et al. Research on Fuel Consumption Prediction Modeling Based on Max-Relevance and Min-Redundancy Feature Optimization Algorithm[J]. Computer Simulation, 2023, 40(3): 186-191+301.
[4]
朱广宇, 赵蕾, 黄达, 等. 基于决策树方法的车辆油耗估计模型[J]. 交通运输系统工程与信息, 2016, 16(3): 200-206.
ZHU G Y, ZHAO L, HUANG D, et al. A Method of Vehicle Fuel Consumption Estimation Based on Decision Tree[J]. Journal of Transportation Systems Engineering and Information Technology, 2016, 16(3): 200-206.
[5]
KANARACHOS S, MATHEW J, FITZPATRICK E M. Instantaneous Vehicle Fuel Consumption Estimation using Smartphones and Recurrent Neural Networks[J]. Expert Systems with Applications, 2019, 120: 436-447.
[6]
王一婷, 行本贝, 李彬, 等. 基于Shared-LSTM的重型卡车不同加速驾驶行为油耗预测方法[J]. 计算机与现代化, 2023(3): 121-126.
WANG Y T, XING B B, LI B, et al. Fuel Consumption Prediction Method of Heavy Trucks with Different Acceleration Driving Behaviors Based on Shared-LSTM[J]. Computer and Modernization, 2023(3): 121-126.
[7]
陈静杰, 邹迎欢. 油耗预测中显著影响参数提取方法的仿真[J]. 计算机仿真, 2013, 30(6): 55-58.
CHEN J J, ZOU Y H. Simulation for Significant Impact Parameter Extraction Method in Fuel Consumption Estimation[J]. Computer Simulation, 2013, 30(6): 55-58.
[8]
吴明兴, 谷昊霖, 别佩, 等. 基于萤火虫算法改进BP神经网络的电力用能行为预测方法[J]. 沈阳工业大学学报, 2023, 45(3): 241-246.
WU M X, GU H L, BIE P, et al. Improved BP Neural Network Based on Firefly Algorithm for Predicting Electricity Energy Consumption Behavior[J]. Journal of Shenyang University of Technology, 2023, 45(3): 241-246.
[9]
JAGRUTHI H, KAVITHA C, MULIMANI M. Network Intrusion Detection Using Fusion Features and Convolutional Bidirectional Recurrent Neural Network[J]. International Journal of Computer Applications in Technology, 2022, 69(1): 93-100.
[10]
FATEMEHALSADAT M, KAREM C, RACHID L, et al. Convolutional Neural Network and Long Short-Term Memory Models for Ice-Jam Predictions[J]. The Cryosphere, 2022, 16(4).
2024年第卷第3期
PDF下载
181
68
引用本文
BibTeX
文章信息
doi: 10.20104/j.cnki.1674-6546.20230397
  • 首发时间:2025-11-25
  • 出版时间:2024-03-15
补充材料
相关文章
文章信息
作者
出版历史
  • 修回日期:2023-09-22
基金
作者信息
    重庆交通大学, 重庆 400074
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/qcgcs/CN/10.20104/j.cnki.1674-6546.20230397
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