A novel recurrent neural network soft sensor via a differential evolution training algorithm for the tire contact patch.pdfVIP

下载本文档

4
0
约5.56万字
约 12页
2017-03-16 发布于天津
举报
版权申诉

A novel recurrent neural network soft sensor via a differential evolution training algorithm for the tire contact patch.pdf

1、本文档共12页，可阅读全部内容。
2、原创力文档（book118）网站文档一经付费（服务费），不意味着购买了该文档的版权，仅供个人/单位学习、研究之用，不得用于商业用途，未经授权，严禁复制、发行、汇编、翻译或者网络传播等，侵权必究。
3、本站所有内容均由合作方或网友上传，本站不对文档的完整性、权威性及其观点立场正确性做任何保证或承诺！文档内容仅供研究参考，付费前请自行鉴别。如您付费，意味着您自己接受本站规则且自行承担风险，本站不退款、不进行额外附加服务；查看《如何避免下载的几个坑》。如果您已付费下载过本站文档，您可以点击这里二次下载。
4、如文档侵犯商业秘密、侵犯著作权、侵犯人身权等，请点击“版权申诉”（推荐），也可以打举报电话：400-050-0827(电话支持时间：9:00-18:30)。
5、该文档为VIP文档，如果想要下载，成为VIP会员后，下载免费。
6、成为VIP后，下载本文档将扣除1次下载权益。下载后，不支持退款、换文档。如有疑问请联系我们。
7、成为VIP后，您将拥有八大权益，权益包括：VIP文档下载权益、阅读免打扰、文档格式转换、高级专利检索、专属身份标志、高级客服、多端互通、版权登记。
8、VIP文档为合作方或网友上传，每下载1次，网站将根据用户上传文档的质量评分、类型等，对文档贡献者给予高额补贴、流量扶持。如果你也想贡献VIP文档。上传文档

A novel recurrent neural network soft sensor via a differential evolution training algorithm for the tire contact patch.pdf

Neurocomputing 235 (2017) 71–82 Contents lists available at ScienceDirect Neurocomputing journal homepage: /locate/neucom A novel recurrent neural network soft sensor via a di?erential evolution training algorithm for the tire contact patch Carlos A. Duchanoya,?, Marco A. Moreno-Armendáriza, Leopoldo Urbinaa, Carlos A. Cruz-Villarb, Hiram Calvoa, J. de J. Rubioc a Instituto Politécnico Nacional, Centro de Investigación en Computación, Av. Juan de Dios Bátiz s/n, Ciudad de México 07738, Mexico b Sección de Mecatrónica, CINVESTAV, Av. Instituto Politécnico Nacional 2508, Apdo Postal 14740, Ciudad de México, Mexico c Sección de Estudios de Posgrado e Investigación, ESIME Azcapotzalco, Instituto Politécnico Nacional, Ciudad de México, Mexico MARK ARTICLE INFO Communicated by W. Yu Keywords: Recurrent Neuronal Networks Soft sensor Di?erential evolution Tire contact patch ABSTRACT In this paper we propose a novel Recurrent Neural Network Soft Sensor designed to estimate and predict the contact area that tires of a car are making with the ground. This is one of the most critical issues regarding car modelling for improving its performance. The proposed sensor is particularly useful for an active suspension because it allows its suspension to be prepared instead of reacting to a disturbance. The recurrent neural network enables the Soft Sensor to have a correct prediction of the contact area of the tire. This sensor uses data from 11 sensors mounted on the car while the tire contact patch is obtained by means of frustrated total internal re?ection phenomenon. The training process of the Recurrent Neuronal Network presents several di?culties caused by the existence of spurious valleys. For this reason, we address this problem as an optimization problem, solved by using a modi?ed di?erential evolution algorithm. Our Soft Sensor performance is successfully validated by physical experiments under real operation. 1. Introduction Tires have become a critical component for safety