|
|
|
| Battery Fault Diagnosis and Anomaly Detection Based on Data Mining and Big Data Analysis |
| Shen Jiangwei1, Yan Chuan1, Liu Yonggang2, Shen Shiquan1, Chen Zheng1 |
1. College of Transportation Engineering Kunming University of Science and Technology Kunming 650000 China;
2. College of Mechanical Engineering Chongqing University Chongqing 400030 China |
|
|
|
Abstract Due to various environmental and operating conditions, traditional battery fault diagnosis is challenging with the development of electrification, intelligence, connectivity, and digitization in the automotive industry. This paper proposes a battery fault diagnosis and anomaly detection method based on data mining and extensive data analysis. The approach involves operational data collection from the power battery through an electric vehicle cloud monitoring platform and a comprehensive analysis of anomaly detection, localization, and diagnosis for individual battery cells.
Firstly, t-SNE is used to visualize the dimension reduction of battery cell data, compressing high- dimensional cell voltage data into low-dimensional data. Then, the K-means algorithm is applied for clustering analysis. Combined with the principles of Gaussian distribution and Z-score, diagnostic coefficients are designed to locate abnormal batteries. Subsequently, the entropy-weighted coefficient of the variation method is used to assess the degree of abnormality for each battery cell. Finally, a diagnostic standard is established using the 3σ-MSS filtering strategy. Compared to the COF and LOF algorithms based on statistical processing of the fault matrix, the proposed method compresses the voltage data of 30 series of individual batteries into two dimensions and effectively detects abnormal battery cells. For a specific period, the voltage curve of the 7th series of individual batteries exhibits significant fluctuations, with a rapid voltage drop at the 28th and 207th seconds, reaching a maximum voltage difference of 236 mV. The Z-value in the diagnostic coefficient designed based on the Z-score for the 7th series of individual batteries is significantly higher than other cells, indicating an anomaly. The overall score for the 7th series in the battery comprehensive evaluation shows a score difference of 0.727. Using the 3σ-MSS filtering strategy for fault probability statistics, a small percentage of vehicles show a battery fault probability exceeding 15% with variable positions likely resulting from unexpected accidents. Most vehicles have a fault frequency below 2%, and the positions of such faults are fixed, possibly due to vehicle design defects or inherent issues. According to the diagnostic results, the 3σ-MSS filtering strategy is suitable for fault probability statistics in batteries. In the time dimension of fault probability statistics, the fault probabilities in spring, summer, autumn, and winter are 1.99%, 4.95%, 3.67%, and 9.52%, respectively, with average fault probabilities of 1.54%, 4.31%, 3.07%, and 4.59%.
In conclusion, (1) using t-SNE and K-means for dimension reduction and clustering analysis can effectively detect whether individual battery cells experience anomalies. Additionally, the diagnostic coefficient designed based on the Z-score accurately diagnoses voltage anomalies and locates faulty cells. (2) Compared to LOF and COF algorithms, the 3σ-MSS filtering strategy has more apparent advantages and can further identify and diagnose battery fault types for fault probability statistics. (3) Accordingl to the three-year historical operational data of different vehicles, the frequency of faults does not differ significantly between spring and autumn. However, in summer and winter, the frequency of battery faults is relatively high, which provides maintenance recommendations for the stable operation of vehicles.
|
|
Received: 27 December 2023
|
|
|
|
|
|
[1] 王震坡, 李晓宇, 袁昌贵, 等. 大数据下电动汽车动力电池故障诊断技术挑战与发展趋势[J]. 机械工程学报, 2021, 57(14): 52-63.
Wang Zhenpo, Li Xiaoyu, Yuan Changgui, et al.Challenge and prospects for fault diagnosis of power battery system for electrical vehicles based on big-data[J]. Journal of Mechanical Engineering, 2021, 57(14): 52-63.
[2] 王义军, 左雪. 锂离子电池荷电状态估算方法及其应用场景综述[J]. 电力系统自动化, 2022, 46(14): 193-207.
Wang Yijun, Zuo Xue.Review on estimation methods for state of charge of lithium-ion battery and their application scenarios[J]. Automation of Electric Power Systems, 2022, 46(14): 193-207.
[3] 尹杰, 刘博, 孙国兵, 等. 基于迁移学习和降噪自编码器-长短时间记忆的锂离子电池剩余寿命预测[J]. 电工技术学报, 2024, 39(1): 289-302.
Yin Jie, Liu Bo, Sun Guobing, et al.Transfer learning denoising autoencoder-long short term memory for remaining useful life prediction of Li-ion batteries[J]. Transactions of China Electrotechnical Society, 2024, 39(1): 289-302.
[4] 顾菊平, 蒋凌, 张新松, 等. 基于特征提取的锂离子电池健康状态评估及影响因素分析[J]. 电工技术学报, 2023, 38(19): 5330-5342.
Gu Juping, Jiang Ling, Zhang Xinsong, et al.Estimation and influencing factor analysis of lithium-ion batteries state of health based on features extraction[J]. Transactions of China Electrotechnical Society, 2023, 38(19): 5330-5342.
[5] Sun Zhenyu, Wang Zhenpo, Liu Peng, et al.An online data-driven fault diagnosis and thermal runaway early warning for electric vehicle batteries[J]. IEEE Transactions on Power Electronics, 2022, 37(10): 12636-12646.
[6] Tran M K, Fowler M.A review of lithium-ion battery fault diagnostic algorithms: current progress and future challenges[J]. Algorithms, 2020, 13(3): 62-80.
[7] Chen Kui, Liao Qiang, Liu Kai, et al.Capacity degradation prediction of lithium-ion battery based on artificial bee colony and multi-kernel support vector regression[J]. Journal of Energy Storage, 2023, 72: 108160.
[8] 杨梦洁, 杨爱军, 叶奕君, 等. 基于气体分析的锂离子电池热失控早期预警研究进展[J]. 电工技术学报, 2023, 38(17): 4507-4538.
Yang Mengjie, Yang Aijun, Ye Yijun, et al.Research progress on early warning of thermal runaway of Li-ion batteries based on gas analysis[J]. Transactions of China Electrotechnical Society, 2023, 38(17): 4507-4538.
[9] Jiang Jiuchun, Li Taiyu, Chang Chun, et al.Fault diagnosis method for lithium-ion batteries in electric vehicles based on isolated forest algorithm[J]. Journal of Energy Storage, 2022, 50: 104177.
[10] Jiang Jiuchun, Cong Xinwei, Li Shuowei, et al.A hybrid signal-based fault diagnosis method for lithium-ion batteries in electric vehicles[J]. IEEE Access, 2021, 9: 19175-19186.
[11] XiongRui, Pan Yue, Shen Weixiang, et al. Lithium-ion battery aging mechanisms and diagnosis method for automotive applications: recent advances and perspectives[J]. Renewable and Sustainable Energy Reviews, 2020, 131: 110048.
[12] 徐佳宁, 梁栋滨, 魏国, 等. 串联电池组接触电阻故障诊断分析[J]. 电工技术学报, 2017, 32(18): 106-112.
Xu Jianing, Liang Dongbin, Wei Guo, et al.Series battery pack’s contact resistance fault diagnosis analysis[J]. Transactions of China Electrotechnical Society, 2017, 32(18): 106-112.
[13] Ma Mina, Duan Qiangling, Li Xiaoyu, et al.Fault diagnosis of external soft-short circuit for series connected lithium-ion battery pack based on modified dual extended Kalman filter[J]. Journal of Energy Storage, 2021, 41: 102902.
[14] Yu Quanqing, Dai Lei, Xiong Rui, et al.Current sensor fault diagnosis method based on an improved equivalent circuit battery model[J]. Applied Energy, 2022, 310: 118588.
[15] Wang Yujie, Tian Jiaqiang, Chen Zonghai, et al.Model based insulation fault diagnosis for lithium-ion battery pack in electric vehicles[J]. Measurement, 2019, 131: 443-451.
[16] Feng Xuning, Pan Yue, He Xiangming, et al.Detecting the internal short circuit in large-format lithium-ion battery using model-based fault-diagnosis algorithm[J]. Journal of Energy Storage, 2018, 18(4): 26-39.
[17] Schmid M, Gebauer E, Hanzl C, et al.Active model-based fault diagnosis in reconfigurable battery systems[J]. IEEE Transactions on Power Electronics, 2021, 36(3): 2584-2597.
[18] Chatterjee S, Kumar Gatla R, Sinha P, et al.Fault detection of a Li-ion battery using SVM based machine learning and unscented Kalman filter[J]. Materials Today: Proceedings, 2023, 74: 703-707.
[19] 刘嘉蔚, 李奇, 陈维荣, 等. 基于在线序列超限学习机和主成分分析的蒸汽冷却型燃料电池系统快速故障诊断方法[J]. 电工技术学报, 2019, 34(18): 3949-3960.
Liu Jiawei, Li Qi, Chen Weirong, et al.Fast fault diagnosis method of evaporatively cooled fuel cell system based on online sequential extreme learning machine and principal component analysis[J]. Transactions of China Electrotechnical Society, 2019, 34(18): 3949-3960.
[20] Shang Yunlong, Lu Gaopeng, Kang Yongzhe, et al.A multi-fault diagnosis method based on modified sample entropy for lithium-ion battery strings[J]. Journal of Power Sources, 2020, 446: 227275.
[21] Samanta A, Chowdhuri S, Williamson S S.Machine learning-based data-driven fault detection/diagnosis of lithium-ion battery: a critical review[J]. Electronics, 2021, 10(11): 1309-1326.
[22] 黄凯, 丁恒, 郭永芳, 等. 基于数据预处理和长短期记忆神经网络的锂离子电池寿命预测[J]. 电工技术学报, 2022, 37(15): 3753-3766.
Huang Kai, Ding Heng, Guo Yongfang, et al.Prediction of remaining useful life of lithium-ion battery based on adaptive data preprocessing and long short-term memory network[J]. Transactions of China Electrotechnical Society, 2022, 37(15): 3753-3766.
[23] Zhou Shiyao, Chen Ziqiang, Lin Tiantian.Lithium-ion battery cell open circuit fault diagnostics: methods, analysis, and comparison[J]. IEEE Transactions on Power Electronics, 2023, 38(2): 2493-2505.
[24] Yao Lei, Fang Zhanpeng, Xiao Yanqiu, et al.An intelligent fault diagnosis method for lithium battery systems based on grid search support vector machine[J]. Energy, 2021, 214: 118866.
[25] Yao Lei, Xiao Yanqiu, Gong Xiaoyun, et al.A novel intelligent method for fault diagnosis of electric vehicle battery system based on wavelet neural network[J]. Journal of Power Sources, 2020, 453: 227870.
[26] Li Xiaoyu, Wang Zhenpo.A novel fault diagnosis method for lithium-ion battery packs of electric vehicles[J]. Measurement, 2018, 116: 402-411.
[27] Zhao Yang, Liu Peng, Wang Zhenpo, et al.Fault and defect diagnosis of battery for electric vehicles based on big data analysis methods[J]. Applied Energy, 2017, 207: 354-362.
[28] Yao Lei, Xu Shiming, Xiao Yanqiu, et al. Fault identification of lithium-ion battery pack for electric vehicle based on GA optimized ELM neural network[J]. IEEE Access, 1809, 10: 15007-15022.
[29] Kobak D, Berens P.The art of using t-SNE for single-cell transcriptomics[J]. Nature Communications, 2019, 10: 5416.
[30] Kuraria A, Jharbade N, Soni M.Centroid selection process using WCSS and elbow method for K-mean clustering algorithm in data mining[J]. International Journal of Scientific Research in Science, Engineering and Technology, 2018, 4(11): 190-195.
[31] Xiong Rui, Sun Wanzhou, Yu Quanqing, et al.Research progress, challenges and prospects of fault diagnosis on battery system of electric vehicles[J]. Applied Energy, 2020, 279: 115855.
[32] Qiu Yishu, Cao Wenjiong, Peng Peng, et al.A novel entropy-based fault diagnosis and inconsistency evaluation approach for lithium-ion battery energy storage systems[J]. Journal of Energy Storage, 2021, 41: 102852.
[33] Lan Jiamei, Wei Ruichao, Huang Shenshi, et al.In-depth bibliometric analysis on research trends in fault diagnosis of lithium-ion batteries[J]. Journal of Energy Storage, 2022, 54: 105275.
[34] 刘座辰, 林磊, 殷天翔, 等. 一种模块化多电平换流器子模块开路故障的快速检测与诊断方法[J]. 电工技术学报, 2022, 37(19): 4883-4894.
Liu Zuochen, Lin Lei, Yin Tianxiang, et al.A fast open-circuit fault detection and diagnosis method for sub-modules of modular multilevel converters[J]. Transactions of China Electrotechnical Society, 2022, 37(19): 4883-4894.
[35] Nowak-Brzezińska A, Horyń C.Exploration of outliers in if-then rule-based knowledge bases[J]. Entropy, 2020, 22(10): 1096.
[36] Wang Hongzhi, Bah M J, Hammad M.Progress in outlier detection techniques: a survey[J]. IEEE Access, 2019, 7: 107964-108000. |
|
|
|
2024, Vol. 39 
