Research on Working Characteristics Prediction of Passenger Vehicle Shock Absorber Based on Deep Learning:: Science Publishing Group

Research on Working Characteristics Prediction of Passenger Vehicle Shock Absorber Based on Deep Learning

Jinyun Chang^1,2, Xuewu Zhu^1,2, Chao Han^1,2, Xingming Zhao^1,2, Jiaxing Sun^1,2, Feng Hu^1,2

¹Research and Development Institute of China First Automobile Group Co., Ltd, Changchun, China

²State Key Laboratory of Comprehensive Technology for Automobile Vibration Noise and Safety Control, Changchun, China

American Journal of Electrical and Computer Engineering, Volume 6, Issue 2, December 2022

Pages: 91-98

Received: Nov. 25, 2022

Accepted: Dec. 16, 2022

Published: Dec. 29, 2022

DOI: 10.11648/j.ajece.20220602.15

Downloads:

Views:

Download PDF: Download PDF

Export Citation: Export citation to RIS Export citation to BibTeX

Abstract

The shock absorber is an important component of the automobile suspension system, which mainly plays the role of attenuating vibration during the driving of the car. The shock absorber is subjected to complex alternating loads during the recovery and compression process, and its dynamic damping characteristics show strong nonlinearity. The dynamic performance of the shock absorber has an important impact on the vehicle ride comfort and handling stability, so it is of great significance to carry out the prediction research on the working characteristics of the shock absorber. This paper introduces the structure and working principle of an automobile hydraulic shock absorber, and analyzes the reasons for the high nonlinearity of the working characteristics of the shock absorber. A prediction method and implementation framework of shock absorber working characteristics based on long short memory neural network (LSTM) algorithm are proposed, and abundant sample data are obtained through passenger vehicle durability test and shock absorber bench test. The effectiveness of feature selection is verified by data preprocessing and distribution law statistics. Finally, the LSTM intelligent algorithm is used to train, verify and test the sample data, and a prediction model of the working characteristics of the shock absorber is established. By comparing with the actual working characteristics data of the shock absorber, the accuracy and applicability of the prediction model are verified.

Keywords

Working Characteristics of Shock Absorber, Deep Learning Algorithm, LSTM, Dynamic Response Prediction

To cite this article

Jinyun Chang, Xuewu Zhu, Chao Han, Xingming Zhao, Jiaxing Sun, et al. (2022). Research on Working Characteristics Prediction of Passenger Vehicle Shock Absorber Based on Deep Learning. American Journal of Electrical and Computer Engineering, 6(2), 91-98. https://doi.org/10.11648/j.ajece.20220602.15

Copyright © 2022 Authors retain the copyright of this article.
This article is an open access article distributed under the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0/) which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

References

1.	Ma, T., Cui, Z., & Zhang, M. (2013). Modeling and Simulating of the Gas-precharged Dual-sleeve Shock Absorber with Multiple Valve Plates Using AMESim. Journal of Mechanical Engineering, 49 (12), 123-130. doi: 10.3901/JME.2013.12.123.
2.	Duym, S. W. R. (2000). Simulation Tools, Modelling and Identification, for an Automotive Shock Absorber in the Context of Vehicle Dynamics. Vehicle System Dynamics, 33 (4), 261-285, doi: 10.1076/0042-3114(200004)33:4;1-U;FT261.
3.	Songschon, S., Okuma, M., Amornsawaddirak, T., & Lapapong, S. (2014). Physical Characteristics of Twin-Tube Shock Absorber. SAE Int. J. Passeng. Cars-Mech. Syst. 7 (1), 375-381. doi: 10.4271/2014-01-2001.
4.	Zhao, X., Peng, L., Cao, Z., Sun, J., Yu, C., Zhang, Y. (2020). Research on the Simulation Method of Working Characteristics Identification of Passenger Car Suspension Shock Absorber, China Society of Automotive Engineers (3), 2020, 335-339. doi: 10.26914/c.cnkihy.2020.023499.
5.	Drupp, M., & Hänsel, M. (2021). Relative Prices and Climate Policy: How the Scarcity of Nonmarket Goods Drives Policy Evaluation. American Economic Journal: Economic Policy, 13 (1), 168-201. doi: 10.1257/pol.2018076.
6.	Lu, Z., & Li, S. (2002). Development of Simulation and Analysis Technology for Dynamic Characteristics of Cylindrical Hydraulic Damper. Journal of Tsinghua University (Natural Science Edition), 42 (11), 5. doi: 10.3321/j.issn:1000-0054.2002.11.031.
7.	Hornik, K. (1991). Approximation Capabilities of Multilayer Feedforward Networks. Neural Networks, 4 (2), 251-257. doi: 10.1016/0893-6080(91)90009-T.
8.	Hang, S. (2007). Simulation of Damping Characteristics of Automobile Double tube Shock Absorber. Huazhong University of Science and Technology.
9.	Liu, D., Zhao, T., Liu, Y., & Wang, H. (2019). Research on the Simulation Method of a Vehicle Shock Absorber Based on AMESim. Automotive Practical Technology. 289 (10), 127-130. doi: CNKI:SUN:SXQC.0.2019-10-045.
10.	Hochreiter, S., Jü, & Schmidhuber, R. A. (1997). Long Short-term Memory. Neural Computation, 9 (8), 1735-1780. doi: 10.1162/neco.1997.9.8.1735.
11.	Miao, Y., Gowayyed, M., & Metze, F. (2016). EESEN: End-to-End Speech Recognition using Deep RNN Models and WFST-based Decoding. 2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU). IEEE.
12.	Wang, C., & Fu, Y. (2020). Ship Trajectory Prediction Based on Attention in Bidirectional Recurrent Neural Networks. 2020 5th International Conference on Information Science, Computer Technology and Transportation (ISCTT). doi: 10.1109/ISCTT51595.2020.00100.
13.	Suo, Y., Chen, W., Claramunt, C., & Yang, S. (2020). A Ship Trajectory Prediction Framework Based on a Recurrent Neural Network. Sensors, 20 (18). Doi: 10.3390/s20185133.
14.	Islam, M. U., Hossain, M. M., & Kashem, M. A. (2021). Covfake: a Word Embedding Coupled with LSTM Approach for Covid Related Fake News Detection. International Journal of Computer Applications (10). doi: 10.5120/IJCA2021920977.
15.	Shahid, F., Zameer, A., & Muneeb, M. (2021). A Vovel Genetic LSTM Model for Wind Power Forecast. Energy (1). doi: 10.1016/j.energy.2021.120069.
16.	Zhou, D., Wu, Y., & Zhou, H. (2021). A Nonintrusive Load Monitoring Method for Microgrid Ems Using Bi-lstm Algorithm. Complexity, 2021. doi: 10.1155/2021/6688889.