Vehicle Handling and Stability Test Type Recognition Method Based on Convolutional Neural Network

被引：0

作者：

Guan X. ^{[1
]}

Zhong Z. ^{[1
]}

Zhan J. ^{[1
]}

Xi T. ^{[1
]}

Ye H. ^{[1
]}

Gao S. ^{[1
]}

Cheng J. ^{[2
,3
]}

Liao S. ^{[2
,3
]}

Cai J. ^{[2
,3
]}

机构：

[1] Jinlin University, State Key Laboratory of Automotive Simulation and Control, Changchun

[2] Chongqing Key Laboratory of Automobile Intelligent Simulation, Chongqing

[3] Chongqing Changan Automobile Co. ，Ltd., Chongqing

来源：

Qiche Gongcheng/Automotive Engineering | 2023年 / 45卷 / 09期

关键词：

automobile test; convolution neural network; stability; type recognition; vehicle handling;

D O I：

10.19562/j.chinasae.qcgc.2023.09.024

中图分类号：

学科分类号：

摘要：

To meet the need of automatic identification of test types，which is aimed at automatic process⁃ ing of vehicle handling and stability test evaluation indicators，this paper proposes a vehicle handling and stability test type recognition method based on convolutional neural network. On the basis of analyzing the image characteris⁃ tics of the test type data，a vehicle handling and stability test type recognition model based on convolution neural network is established，which consists of 1 input layer，3 convolution layers，3 batch normalization layers，2 Max-pooling layers，5 linear rectification function（ReLU）layers，3 full connection layers，2 Dropout layers，1 Softmax layer and 1 classification layer. The model is trained and verified using 2 250 groups of data collected from the tests. The accuracy of type recognition is 99.33%，and the average recognition time is 0.05 s. The results show that the ve⁃ hicle handling and stability test type recognition method based on convolutional neural network proposed in this pa⁃ per can effectively distinguish different test types，which can be used for automatic processing of vehicle handling and stability test results，and can significantly improve the automatic processing level of vehicle handling and stabil⁃ ity test. © 2023 SAE-China. All rights reserved.

引用

页码：1765 / 1771

页数：6

共 20 条

[1] ZHANG Y C., The study of the function of the car experiments in the research of the car products［D］, (2009)
[2] ZHANG S, XIONG R., Adaptive energy management of a plug-in hybrid electric vehicle based on driving pattern recognition and dynamic programming［J］, Applied Energy, 155, pp. 68-78, (2015)
[3] FRANK R，, Et al., Driver be⁃ havior profiling using smartphones：a low-cost platform for driver monitoring［J］, IEEE Intelligent Transportation Systems Maga⁃ zine, 7, 1, pp. 91-102, (2015)
[4] ZHOU J., Decision fusion of two sensors object classification based on the evidential reasoning rule［J］, Expert Systems with Applications, 210, (2022)
[5] SUBRAMANIAN S C., Learn⁃ ing-based fault diagnosis of air brake system using wheel speed data［J］, Proceedings of the Institution of Mechanical Engineers，Part D： Journal of Automobile Engineering, (2021)
[6] A study of vehicle driving condition rec⁃ ognition using supervised learning methods［J］, IEEE Transac⁃ tions on Transportation Electrification, 8, 2, pp. 1665-1673, (2021)
[7] FRESCHI V., Machine learning techniques to iden⁃ tify unsafe driving behavior by means of in-vehicle sensor data ［J］, Expert Systems with Applications, 176, (2021)
[8] CHAMOLA V，, Et al., Securing the inter⁃ net of vehicles：a deep learning-based classification framework ［J］, IEEE Networking Letters, 3, 2, pp. 94-97, (2021)
[9] NASARUDDIN N, AFDHAL A., A lightweight moving vehicle classification system through attention-based method and deep learning［J］, IEEE Access, 7, pp. 157564-157573, (2019)
[10] pp. 1-6, (2017)

← 1 2 →