基于BS_Bagging-cLightGBM模型的电动汽车故障预测方法

doi:10.16088/j.issn.1001-6600.2022062401

摘要/Abstract

摘要： 针对因电动汽车故障数据样本类别不平衡引起的机器模型分类性能欠佳、故障查全率低的问题,本文提出一种以LightGBM为基学习器改进的Bagging集成电动汽车故障预测模型:在Bagging集成学习中使用Borderline_SMOTE方法对训练集重新采样,改善训练子集的数据不平衡程度,避免小类样本信息缺失;将权重系数和正则化项嵌入LightGBM基学习器的损失函数中,提高训练中小类样本的错分类代价。实验结果表明,该模型可有效提高故障查全率、宏平均和AUC值,其中AUC值达到0.898 4,故障样本的查全率为0.808 3,在电动汽车不平衡数据集上的故障分类性能显著优于传统单一模型和其他对比算法。

关键词: 故障诊断, LightGBM模型, Bagging集成学习, 不平衡数据, Borderline_SMOTE

Abstract: In view of the defects of inefficient classification and low recall rate caused by the class imbalance of fault data of electric vehicle, an improved Bagging ensemble fault diagnosis method based on LightGBM in the fault classification process for electric vehicle is proposed in this paper. In the Bagging integrated learning model, the training set sampled by Borderline_SMOTE to improve the data imbalance in the training subset and avoid missing information on the faulty class. By embedding weight coefficients and regularization terms into the loss function of LightGBM, the misclassification cost of faulty classes in model training is increased. Through comparative experiments, the results show that the proposed model can effectively improve the recall rate, macro average F₁ measure and AUC on fault diagnosis, in which AUC reaches 0.898 4, and the recall rate is 0.808 3. The fault classification performance of this model on the unbalanced data set of electric vehicles is significantly more effective in classifying faults of electric vehicle than the single model and other comparative algorithms.

Key words: fault diagnosis, LightGBM, Bagging ensemble learning, unbalanced data, Borderline_SMOTE

中图分类号: U472;TP181

田晟, 张津铭, 李成伟, 李嘉. 基于BS_Bagging-cLightGBM模型的电动汽车故障预测方法[J]. 广西师范大学学报（自然科学版）, 2023, 41(3): 9-19.

TIAN Sheng, ZHANG Jinming, LI Chengwei, LI Jia. Fault Prediction of Electric Vehicle Based on BS_Bagging-cLightGBM Model[J]. Journal of Guangxi Normal University(Natural Science Edition), 2023, 41(3): 9-19.

参考文献

[1] HONG J C, WANG Z P, YAO Y T. Fault prognosis of battery system based on accurate voltage abnormity prognosis using long short-term memory neural networks[J]. Applied Energy, 2019, 251: 113381. DOI:10.1016/j.apenergy.2019.113381.
[2] 贾爱芹,陈建军,蒋志强,等.基于灰色支持向量机的汽车制动系统故障诊断与预测[J].机械设计与研究,2015,31(1):149-152. DOI:10.13952/j.cnki.jofmdr.2015.0039.
[3] GALAGEDARAGE DON M, KHAN F. Process fault prognosis using hidden Markov model-Bayesian networks hybrid model[J]. Industrial & Engineering Chemistry Research, 2019, 58(27): 12041-12053. DOI:10.1021/acs.iecr.9b00524.
[4] 许水清,刘锋,何怡刚,等.基于自适应滑模观测器的新能源汽车驱动系统电流传感器微小故障诊断[J/OL].中国电机工程学报:1-13[2022-11-06].http://kns.cnki.net/kcms/detail/11.2107.TM.20221012.1643.016.html.
[5] WANG X, HAN T. Transformer fault diagnosis based on stacking ensemble learning[J]. IEEJ Transactions on Electrical and Electronic Engineering, 2020, 15(12): 1734-1739. DOI:10.1002/tee.23247.
[6] 马新娜,赵猛,祁琳.基于卷积脉冲神经网络的故障诊断方法研究[J].广西师范大学学报(自然科学版),2022,40(3):112-120. DOI:10.16088/j.issn.1001-6600.2021070808.
[7] WEN P G, ZHI M, ZHANG G Y, et al. Fault prediction of elevator door system based on PSO-BP neural network[J]. Engineering, 2016, 8(11): 761-766. DOI:10.4236/eng.2016.811068.
[8] GANGSAR P, TIWARI R. Multiclass fault taxonomy in rolling bearings at interpolated and extrapolated speeds based on time domain vibration data by SVM algorithms[J]. Journal of Failure Analysis and Prevention, 2014, 14(6): 826-837. DOI:10.1007/s11668-014-9893-4.
[9] 戴银娟,付石磊.基于改进C4.5算法的新型车辆故障预测方法研究[J].常熟理工学院学报,2019,33(5):72-77. DOI:10.16101/j.cnki.cn32-1749/z.2019.05.018.
[10] 陈维刚, 张会林. 基于RF-LightGBM算法在风机叶片开裂故障预测中的应用[J]. 电子测量技术, 2020, 43(1): 162-168. DOI:10.19651/j.cnki.emt.1903316.
[11] 刘金硕,刘必为,张密,等. 基于GBDT的电力计量设备故障预测[J]. 计算机科学, 2019, 46(S1): 392-396.
[12] 杨正森.基于FTRL和XGBoost算法的产品故障预测模型[J].计算机系统应用,2019,28(3):179-184. DOI:10.15888/j.cnki.csa.006808.
[13] JOHNSON J M, KHOSHGOFTAAR T M. Survey on deep learning with class imbalance[J]. Journal of Big Data, 2019, 6(1): 27. DOI:10.1186/s40537-019-0192-5
[14] BAUDER R A, KHOSHGOFTAAR T M, HASANIN T. Data sampling approaches with severely imbalanced big data for Medicare fraud detection[C]//2018 IEEE 30th International Conference on Tools with Artificial Intelligence (ICTAI). Piscataway, NJ: IEEE, 2018: 137-142. DOI:10.1109/ICTAI.2018.00030.
[15] GUO J, WAN X, LIN H, et al. An active learning method based on mistake sampling for large scale imbalanced classification[C]//2017 International Conference on Service Systems and Service Management. Piscataway, NJ: IEEE, 2017: 1-6. DOI:10.1109/ICSSSM.2017.7996301.
[16] SEIFFERT C, KHOSHGOFTAAR T M, VAN HULSE J, et al. A hybrid approach to alleviating class imbalance[J]. IEEE Transactions On Systems, Man, and Cybernetics-Part A: Systems And Humans, 2010,40(1):185-197. DOI:10.1109/TSMCA.2009.2029559.
[17] BITEUS J, LINDGREN T. Planning flexible maintenance for heavy trucks using machine learning models, constraint programming, and route optimization[J]. SAE International Journal of Materials and Manufacturing, 2017, 10(3): 306-315. DOI:10.4271/2017-01-0237.
[18] 颜诗旋,朱平,刘钊.基于改进LightGBM模型的汽车故障预测方法研究[J].汽车工程,2020,42(6):815-819,825. DOI:10.19562/j.chinasae.qcgc.2020.06.016.
[19] 肖梁,韩璐,魏鹏飞,等.基于Bagging集成学习的多集类不平衡学习[J].计算机技术与发展,2021,31(10):1-6. DOI:10.3969/j.issn.1673-629X.2021.10.001.
[20] COSTA C F, NASCIMENTO M A. IDA 2016 industrial challenge: using machine learning for predicting failures[C]//Advances in Intelligent Data Analysis XV. Cham: Springer, 2016: 381-386. DOI:10.1007/978-3-319-46349-0_33.
[21] KE G L, MENG Q, FINLEY T, et al. LightGBM: a highly efficient gradient boosting decision tree[C]//Proceedings of the 31st International Conference on NeuralInformation Processing Systems. Red Hook: Curran Associates Inc., 2017:3149-3157.
[22] 颜诗旋. 面向汽车大数据类别不平衡特点的机器学习方法及其应用研究[D].上海:上海交通大学,2020. DOI:10.27307/d.cnki.gsjtu.2020.001714.
[23] 张弛,李浩,胡海涛,等.基于自动特征工程的飞行器轴承故障诊断[J].化工学报,2021,72(S1):430-436,569. DOI:10.11949/0438-1157.20201539.
[24] CERQUEIRA V, MONIZ N, SOARES C. VEST: automatic feature engineering for forecasting[J/OL]. Machine Learning: 1-23[2022-11-06].http://doi.org/10.1007/s10994-021-05959-y. DOI: 10.1007/s10994-021-05959-y.
[25] XIA S X, ZHOU X F, SHI H B, et al. A fault diagnosis method based on attention mechanism with application in Qianlong-2 autonomous underwater vehicle[J]. Ocean Engineering, 2021, 233: 109049. DOI:10.1016/j.oceaneng.2021.109049.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed