Health Monitoring of Automotive Suspensions: A LSTM Network Approach

In the automotive industry, one of the critical issues is to develop a health monitoring system for condition assessment and remaining fatigue life estimation of key load-bearing components including automotive suspension. However, considering the difficulty to obtain expert knowledge and nonlinear...

Full description

Saved in:
Bibliographic Details
Main Authors: Haoju Hu, Huan Luo, Xiaoqiang Deng
Format: Article
Language:English
Published: Wiley 2021-01-01
Series:Shock and Vibration
Online Access:http://dx.doi.org/10.1155/2021/6626024
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849682908877422592
author Haoju Hu
Huan Luo
Xiaoqiang Deng
author_facet Haoju Hu
Huan Luo
Xiaoqiang Deng
author_sort Haoju Hu
collection DOAJ
description In the automotive industry, one of the critical issues is to develop a health monitoring system for condition assessment and remaining fatigue life estimation of key load-bearing components including automotive suspension. However, considering the difficulty to obtain expert knowledge and nonlinear dynamics in large-scale sensory data, health monitoring of automotive suspension is a challenging work. With the development of deep learning based sequence models in recent years, a long short-term memory (LSTM) network has been proved to capture long-term dependencies in time-series prediction without additional expert knowledge. In this paper, a novel health monitoring system based on a LSTM network is proposed to estimate the remaining fatigue life of automotive suspension. Specifically, first durability tests under various driving cycles are implemented to obtain sequential sensory data provided by common sensors on a test car. Then, a LSTM-based load identification method is designed to predict dynamic stress histories based on the available sensory data. Finally, the damages and remaining fatigue life of the suspensions are estimated by each time step. The experimental results prove that our model can achieve a better performance compared with other representative models.
format Article
id doaj-art-d225ab103b1c464e906abbf53d58d093
institution DOAJ
issn 1070-9622
1875-9203
language English
publishDate 2021-01-01
publisher Wiley
record_format Article
series Shock and Vibration
spelling doaj-art-d225ab103b1c464e906abbf53d58d0932025-08-20T03:24:02ZengWileyShock and Vibration1070-96221875-92032021-01-01202110.1155/2021/66260246626024Health Monitoring of Automotive Suspensions: A LSTM Network ApproachHaoju Hu0Huan Luo1Xiaoqiang Deng2GAC Automotive Research & Development Center, Guangzhou 511434, ChinaGAC Automotive Research & Development Center, Guangzhou 511434, ChinaGAC Automotive Research & Development Center, Guangzhou 511434, ChinaIn the automotive industry, one of the critical issues is to develop a health monitoring system for condition assessment and remaining fatigue life estimation of key load-bearing components including automotive suspension. However, considering the difficulty to obtain expert knowledge and nonlinear dynamics in large-scale sensory data, health monitoring of automotive suspension is a challenging work. With the development of deep learning based sequence models in recent years, a long short-term memory (LSTM) network has been proved to capture long-term dependencies in time-series prediction without additional expert knowledge. In this paper, a novel health monitoring system based on a LSTM network is proposed to estimate the remaining fatigue life of automotive suspension. Specifically, first durability tests under various driving cycles are implemented to obtain sequential sensory data provided by common sensors on a test car. Then, a LSTM-based load identification method is designed to predict dynamic stress histories based on the available sensory data. Finally, the damages and remaining fatigue life of the suspensions are estimated by each time step. The experimental results prove that our model can achieve a better performance compared with other representative models.http://dx.doi.org/10.1155/2021/6626024
spellingShingle Haoju Hu
Huan Luo
Xiaoqiang Deng
Health Monitoring of Automotive Suspensions: A LSTM Network Approach
Shock and Vibration
title Health Monitoring of Automotive Suspensions: A LSTM Network Approach
title_full Health Monitoring of Automotive Suspensions: A LSTM Network Approach
title_fullStr Health Monitoring of Automotive Suspensions: A LSTM Network Approach
title_full_unstemmed Health Monitoring of Automotive Suspensions: A LSTM Network Approach
title_short Health Monitoring of Automotive Suspensions: A LSTM Network Approach
title_sort health monitoring of automotive suspensions a lstm network approach
url http://dx.doi.org/10.1155/2021/6626024
work_keys_str_mv AT haojuhu healthmonitoringofautomotivesuspensionsalstmnetworkapproach
AT huanluo healthmonitoringofautomotivesuspensionsalstmnetworkapproach
AT xiaoqiangdeng healthmonitoringofautomotivesuspensionsalstmnetworkapproach