Research on Performance Degradation Prediction Method of Electric Vehicle Reducers Based on MDS-GA-SVR

He Yinda; Li Weilin; Chen Feng; He Qingchuan; Pan Jun; Ma Xingjian

doi:10.16578/j.issn.1004.2539.2024.01.020

您当前的位置：

首页 >

文章列表页 >

Research on Performance Degradation Prediction Method of Electric Vehicle Reducers Based on MDS-GA-SVR

Development·Application | 更新时间：2024-12-13

- Research on Performance Degradation Prediction Method of Electric Vehicle Reducers Based on MDS-GA-SVR
- Journal of Mechanical Transmission Vol. 48, Issue 1, Pages: 135-142(2024)
- 作者机构：
  
  1.浙江理工大学浙江省机电产品可靠性技术研究重点实验室，浙江杭州 310018
  2.浙江方圆检测集团股份有限公司浙江省市场监管新能源汽车驱动系统重点实验室，浙江杭州 310018
- 作者简介：
- 基金信息：
- DOI：10.16578/j.issn.1004.2539.2024.01.020
  CLC：
- Published：15 January 2024，
  
  Received：25 October 2022，
  
  Revised：07 January 2023，
- 稿件说明：
移动端阅览
何胤达,李威霖,陈锋等.基于MDS-GA-SVR的电动汽车减速器性能退化预测方法研究[J].机械传动,2024,48(01):135-142.

He Yinda,Li Weilin,Chen Feng,et al.Research on Performance Degradation Prediction Method of Electric Vehicle Reducers Based on MDS-GA-SVR[J].Journal of Mechanical Transmission,2024,48(01):135-142.
何胤达,李威霖,陈锋等.基于MDS-GA-SVR的电动汽车减速器性能退化预测方法研究[J].机械传动,2024,48(01):135-142. DOI： 10.16578/j.issn.1004.2539.2024.01.020.

He Yinda,Li Weilin,Chen Feng,et al.Research on Performance Degradation Prediction Method of Electric Vehicle Reducers Based on MDS-GA-SVR[J].Journal of Mechanical Transmission,2024,48(01):135-142. DOI： 10.16578/j.issn.1004.2539.2024.01.020.

摘要

针对电动汽车减速器性能退化预测方法难以充分挖掘退化信息，导致预测精度低的问题，提出了一种联合多维尺度（Multiple Dimensional Scale，MDS）变换和遗传算法优化支持向量回归（Genetic Algorithm opitimized Support Vector Regression，GA-SVR）进行性能退化预测建模方法。通过时域、频域、时频域特征提取方法对减速器的振动信号进行处理，利用MDS算法建立了综合退化特征指标；以信号特征指标与综合性能退化指标作为训练与预测数据集，利用遗传算法确定最优惩罚参数

和核参数

并构建SVR模型；

通过试验获得了减速器的寿命数据，并利用所提方法建立了高精度的性能退化模型。结果表明，本文所提模型的预测精度均高于PSO-SVR、GS-SVR以及反向传播（Back Propagation，BP）神经网络预测模型，均方根误差值分别降低了50.63%、75.35%、84.73%，确定系数

分别提高了3.93%、6.51%、9.51%，证明了所提方法的优越性。

Abstract

A method for modeling performance degradation with multiple dimensional scale (MDS) transformation and genetic algorithm optimized support vector regression (GA-SVR) is proposed to improve the prediction accuracy of electric vehicle reducers by fully exploiting the performance degradation information. The features of vibration signals are extracted by using time domain

frequency domain

and time-frequency domain signal analyzing methods

and then the comprehensive degradation feature indicators are established by using the MDS algorithm. All the above-mentioned indicators are used as the data set for training and prediction. The optimal penalty parameter

and kernel parameter

are determined by using the genetic algorithm. A performance degradation model with high-precision is established based on the GA-SVR model by analyzing the testing data. The experiment results show that the prediction accuracy by using the proposed method is much higher than the results using PSO-SVR

GS-SVR and back propagation (BP) neural network. The RMSE values are reduced by 50.63%

75.16% and 84.73%

and the

values are increased respectively by 3.93%

6.51% and 9.51%

which proves the superiority of the proposed method.

关键词

电动汽车减速器多维尺度变换遗传算法支持向量回归退化趋势预测

Keywords

Electric vehicle reducerMultiple dimensional scalingGenetic algorithmSupport vector regressionDegradation trend prediction

references

王永超.中国新能源汽车发展现状评析［J］.新能源科技，2022（11）：34-36.

WANG Yongchao.Analysis on the development status of new energy vehicles in China［J］.New Energy Technology，2022（11）：34-36.

LIU X T，ZHENG S L，CHEN T，et al.Durability life prediction of a reducer system based on low-amplitude load strengthening and damage［J］.Journal of the Chinese Society of Mechanical Engineers，2017，38（1）：81-91.

CHEN F，LI W L，WENG W X，et al.An adaptive trend index-driven remaining useful life prediction method for renewable energy vehicle reducers［J］.Shock and Vibration，2021（19）：1-10.

张秀华，刘怀举，朱才朝，等.基于数据驱动的零部件疲劳寿命预测研究现状与发展趋势［J］.机械传动，2021，45（10）：1-14.

ZHANG Xiuhua，LIU Huaiju，ZHU Caichao，et al.Current situation and developing trend of fatigue life prediction of components based on data-driven［J］.Journal of Mechanical Transmission，2021，45（10）：1-14.

夏鋆.电动汽车减速器疲劳寿命分析与预测方法研究［D］.重庆：重庆理工大学，2020：86-89.

XIA Jun.Research on fatigue life analysis and prediction method of electric vehicle gear reducer［D］.Chongqing：Chongqing University of Technology，2020：86-89.

赵方洲，卢剑伟，栾振，等.变速器齿轮传动刚柔耦合建模与疲劳寿命预测［J］.合肥工业大学学报（自然科学版），2019，42（4）：467-472.

ZHAO Fangzhou，LU Jianwei，LUAN Zhen，et al.Rigid-flexible coupled modeling and fatigue life prediction of transmission gears system［J］.Journal of Hefei University of Technology （Natural Science），2019，42（4）：467-472.

王国锋，曹增欢，冯海生，等.基于多阶段退化建模的谐波减速器实时可靠性评估与寿命预测［J］.天津大学学报（自然科学与工程技术版），2022，55（2）：122-132.

WANG Guofeng，CAO Zenghuan，FENG Haisheng，et al.Real-time reliability evaluation and life prediction of harmonic reducer based on multistage degradation modeling［J］.Journal of Tianjin University （Science and Technology），2022，55（2）：122-132.

宋仁旺，张岩，石慧.基于Copula函数的齿轮箱剩余寿命预测方法［J］.系统工程理论与实践，2020，40（9）：2466-2474.

SONG Renwang，ZHANG Yan，SHI Hui.Prediction method of the remaining useful life of gearbox based on Copula function［J］.Systems Engineering-Theory & Practice，2020，40（9）：2466-2474.

PAN Y B，HONG R J，CHEN J，et al.Performance degradation assessment of a wind turbine gearbox based on multi-sensor data fusion［J］.Mechanism and Machine Theory，2019，137：509-526.

CHEN X Y，WANG Y，SUN H R，et al.A generalized degradation tendency tracking strategy for gearbox remaining useful life prediction［J］.Measurement，2023，206：212.

SU X W，TOMOVIC M M，ZHU D M.Diagnosis of gradual faults in high-speed gear pairs using machine learning［J］.Journal of the Brazilian Society of Mechanical Sciences and Engineering，2019，41（4）：1-11.

HUANG H Z，WANG H K，LI Y F，et al.Support vector machine based estimation of remaining useful life：current research status and future trends［J］.Journal of Mechanical Science and Technology，2015，29（1）：151-163.

李天梅，司小胜，刘翔，等.大数据下数模联动的随机退化设备剩余寿命预测技术［J］.自动化学报，2022，48（9）：2119-2141.

LI Tianmei，SI Xiaosheng，LIU Xiang，et al.Data-model interactive remaining useful life prediction technologies for stochastic degrading devices with big data［J］.Acta Automatica Sinica，2022，48（9）：2119-2141.

莫仁鹏，司小胜，李天梅，等.基于多尺度特征与注意力机制的轴承寿命预测［J］.浙江大学学报（工学版），2022，56（7）：1447-1456.

MO Renpeng，SI Xiaosheng，LI Tianmei，et al.Bearing life prediction based on multi-scale features and attention mechanism［J］.Journal of Zhejiang University （Engineering Science），2022，56（7）：1447-1456.

ROSSO O A，BLANCO S，YORDANOVA J，et al.Wavelet entropy：a new tool for analysis of short duration brain electrical signals［J］.Journal of Neuroscience Methods，2001，105（1）：65-75.

谢国民，蔺晓雨.基于改进SSA优化MDS-SVM的变压器故障诊断方法［J］.控制与决策，2023，38（2）：459-467.

XIE Guomin，LIN Xiaoyu.Transformer fault diagnosis method based on improved SSA optimized MDS-SVM［J］.Control and Decision，2023，38（2）：459-467.

CHENG G，TONG X.Fuzzy clustering multiple kernel support vector machine［C］//2018 International Conference on Wavelet Analysis and Pattern Recognition （ICWAPR）.IEEE，2018：7-12.

CHAUHAN V K，DAHYIA K，SHARMA A.Problem formulations and solvers in linear SVM：a review［J］.Artificial Intelligence Review，2019，52（2）：803-855.

乔守旭，钟文义，谭思超，等.基于PCA-GA-SVM的竖直下降两相流流型预测［J］.核动力工程，2022，43（3）：85-93.

QIAO Shouxu，ZHONG Wenyi，TAN Sichao，et al.Prediction of vertical-downward two-phase flow pattern based on PCA-GA-SVM［J］.Nuclear Power Engineering，2022，43（3）：85-93.

全国汽车标准化技术委员会.纯电动乘用车用减速器总成技术条件：QC/T 1022—2015［S］.北京：科学技术文献出版社，2016：1-11.

National Technical Committee of Auto Standardization.Technical specification for reduction gearbox of battery electric passenger cars：QC/T 1022—2015［S］.Beijing：Scientific and Technical Documentation Press，2016：1-11.

王柱.海上风力发电机组齿轮箱故障信号提取与剩余寿命预测方法研究［D］.长春：吉林大学，2020：17-41.

WANG Zhu.Research on method for extraction of fault signal and remaining life prediction of gearbox in offshore wind turbine［D］.Changchun：Jilin University，2020：17-41.

邱晓梅，隋文涛，王峰，等.基于相关系数和BP神经网络的轴承剩余寿命预测［J］.组合机床与自动化加工技术，2019（4）：63-65.

QIU Xiaomei，SUI Wentao，WANG Feng，et al.Remaining life prediction of bearing based on correlation coefficient and BP neural network［J］.Modular Machine Tool & Automatic Manufacturing Technique，2019（4）：63-65.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Research on Background Noise Separation of Reducers Based on VMD and FastICA

Leg Configuration and Foot Motion Space Estimation of a Quadruped Robot Considering Waist Characteristics

NVH Analysis and Optimization of Light Truck Electric Drive Axles Based on Romax

Kinematic Analysis and Trajectory Planning of Redundant Mobile Manipulators

Optimization of NVH Performance of Electric Vehicle Reducers Based on Gear Transmission Error

Related Author

Li Weilin

Jiang Yangming

Zhang Zhongjie

Liu Ting

Lin Ting

Cheng Xu

Chen Feng

Wang Keyu

Related Institution

College of Mechanical Engineering, Zhejiang University of Technology

Zhejiang Fangyuan Test Group Co., Ltd.

College of Energy and Mechanical Engineering, Shanghai University of Electric Power

College of Automobile and Traffic Engineering, Liaoning University of Technology

College of Mechanical Engineering, University of South China

⁰