基于深度神经网络的数据驱动虚拟传感器在汽车半主动悬架实时控制中的应用

IF 1.3 4区 工程技术 Q3 TRANSPORTATION SCIENCE & TECHNOLOGY
Paulius Kojis, E. Šabanovič, Viktor Skrickij
{"title":"基于深度神经网络的数据驱动虚拟传感器在汽车半主动悬架实时控制中的应用","authors":"Paulius Kojis, E. Šabanovič, Viktor Skrickij","doi":"10.3846/transport.2022.16919","DOIUrl":null,"url":null,"abstract":"This research presents a data-driven Neural Network (NN)-based Virtual Sensor (VS) that estimates vehicles’ Unsprung Mass (UM) vertical velocity in real-time. UM vertical velocity is an input parameter used to control a vehicle’s semi-active suspension. The extensive simulation-based dataset covering 95 scenarios was created and used to obtain training, validation and testing data for Deep Neural Network (DNN). The simulations have been performed with an experimentally validated full vehicle model using software for advanced vehicle dynamics simulation. VS was developed and tested, taking into account the Root Mean Square (RMS) of Sprung Mass (SM) acceleration as a comfort metric. The RMS was calculated for two cases: using actual UM velocity and estimations from the VS as input to the suspension controller. The comparison shows that RMS change is less than the difference threshold that vehicle occupants could perceive. The achieved result indicates the great potential of using the proposed VS in place of the physical sensor in vehicles.","PeriodicalId":23260,"journal":{"name":"Transport","volume":"40 1","pages":""},"PeriodicalIF":1.3000,"publicationDate":"2022-05-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":"{\"title\":\"DEEP NEURAL NETWORK BASED DATA-DRIVEN VIRTUAL SENSOR IN VEHICLE SEMI-ACTIVE SUSPENSION REAL-TIME CONTROL\",\"authors\":\"Paulius Kojis, E. Šabanovič, Viktor Skrickij\",\"doi\":\"10.3846/transport.2022.16919\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"This research presents a data-driven Neural Network (NN)-based Virtual Sensor (VS) that estimates vehicles’ Unsprung Mass (UM) vertical velocity in real-time. UM vertical velocity is an input parameter used to control a vehicle’s semi-active suspension. The extensive simulation-based dataset covering 95 scenarios was created and used to obtain training, validation and testing data for Deep Neural Network (DNN). The simulations have been performed with an experimentally validated full vehicle model using software for advanced vehicle dynamics simulation. VS was developed and tested, taking into account the Root Mean Square (RMS) of Sprung Mass (SM) acceleration as a comfort metric. The RMS was calculated for two cases: using actual UM velocity and estimations from the VS as input to the suspension controller. The comparison shows that RMS change is less than the difference threshold that vehicle occupants could perceive. The achieved result indicates the great potential of using the proposed VS in place of the physical sensor in vehicles.\",\"PeriodicalId\":23260,\"journal\":{\"name\":\"Transport\",\"volume\":\"40 1\",\"pages\":\"\"},\"PeriodicalIF\":1.3000,\"publicationDate\":\"2022-05-13\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"2\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Transport\",\"FirstCategoryId\":\"5\",\"ListUrlMain\":\"https://doi.org/10.3846/transport.2022.16919\",\"RegionNum\":4,\"RegionCategory\":\"工程技术\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"TRANSPORTATION SCIENCE & TECHNOLOGY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Transport","FirstCategoryId":"5","ListUrlMain":"https://doi.org/10.3846/transport.2022.16919","RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"TRANSPORTATION SCIENCE & TECHNOLOGY","Score":null,"Total":0}
引用次数: 2

摘要

该研究提出了一种基于数据驱动的神经网络(NN)的虚拟传感器(VS),可以实时估计车辆的非簧载质量(UM)垂直速度。UM垂直速度是用于控制车辆半主动悬架的输入参数。建立了涵盖95个场景的广泛模拟数据集,并用于获取深度神经网络(DNN)的训练、验证和测试数据。利用先进的车辆动力学仿真软件,对一个经过实验验证的整车模型进行了仿真。VS的开发和测试,考虑到弹簧质量(SM)加速度的均方根(RMS)作为舒适度量。RMS计算了两种情况:使用实际的UM速度和来自VS的估计作为悬架控制器的输入。对比结果表明,均方根变化小于车辆乘员能感知到的差异阈值。实现的结果表明,在车辆中使用所提出的VS代替物理传感器的巨大潜力。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
DEEP NEURAL NETWORK BASED DATA-DRIVEN VIRTUAL SENSOR IN VEHICLE SEMI-ACTIVE SUSPENSION REAL-TIME CONTROL
This research presents a data-driven Neural Network (NN)-based Virtual Sensor (VS) that estimates vehicles’ Unsprung Mass (UM) vertical velocity in real-time. UM vertical velocity is an input parameter used to control a vehicle’s semi-active suspension. The extensive simulation-based dataset covering 95 scenarios was created and used to obtain training, validation and testing data for Deep Neural Network (DNN). The simulations have been performed with an experimentally validated full vehicle model using software for advanced vehicle dynamics simulation. VS was developed and tested, taking into account the Root Mean Square (RMS) of Sprung Mass (SM) acceleration as a comfort metric. The RMS was calculated for two cases: using actual UM velocity and estimations from the VS as input to the suspension controller. The comparison shows that RMS change is less than the difference threshold that vehicle occupants could perceive. The achieved result indicates the great potential of using the proposed VS in place of the physical sensor in vehicles.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
Transport
Transport Engineering-Mechanical Engineering
CiteScore
3.40
自引率
5.90%
发文量
19
审稿时长
4 months
期刊介绍: At present, transport is one of the key branches playing a crucial role in the development of economy. Reliable and properly organized transport services are required for a professional performance of industry, construction and agriculture. The public mood and efficiency of work also largely depend on the valuable functions of a carefully chosen transport system. A steady increase in transportation is accompanied by growing demands for a higher quality of transport services and optimum efficiency of transport performance. Currently, joint efforts taken by the transport experts and governing institutions of the country are required to develop and enhance the performance of the national transport system conducting theoretical and empirical research. TRANSPORT is an international peer-reviewed journal covering main aspects of transport and providing a source of information for the engineer and the applied scientist. The journal TRANSPORT publishes articles in the fields of: transport policy; fundamentals of the transport system; technology for carrying passengers and freight using road, railway, inland waterways, sea and air transport; technology for multimodal transportation and logistics; loading technology; roads, railways; airports, ports, transport terminals; traffic safety and environment protection; design, manufacture and exploitation of motor vehicles; pipeline transport; transport energetics; fuels, lubricants and maintenance materials; teamwork of customs and transport; transport information technologies; transport economics and management; transport standards; transport educology and history, etc.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信