Research on internal short-circuit fault diagnosis methods for lithium-ion batteries based on WOA-VMD and PSO-SVM
-
摘要: 為了保證儲能電站和新能源汽車的安全運行，針對鋰離子電池內短路故障引發熱失控現象，提出了鯨魚優化算法優化變分模態分解（WOA-VMD）和粒子群算法優化支持向量機（PSO-SVM）的故障診斷方法. 首先通過WOA尋找VMD分解層數K和懲罰因子α最優參數組合，將鋰離子電池內短路故障信號與正常信號分解出多個模態分量；其次，計算各模態分量（IMF）的樣本熵值作為特征向量；最后將特征向量分別輸入至SVM故障診斷模型與PSO-SVM故障診斷模型中進行故障診斷. 結果表明，SVM故障診斷率66.667%，經PSO優化過的SVM故障診斷率為96.667%，鋰離子電池內短路故障得到了有效識別.Abstract: With the continuous consumption of traditional fossil fuels, people have gradually started to realize the importance of protecting the environment. Therefore, new clean energy sources like wind power have been gradually receiving considerable attention in recent years, along with the rapid development of new energy vehicles as replacements for traditional cars. Lithium-ion batteries have emerged as essential energy storage equipment for clean energy systems and power sources of new energy vehicles. However, these batteries are prone to thermal runaway failure during their usage and pose safety concerns. To ensure the safe operation of energy storage equipment and new energy vehicles, this paper proposes fault diagnosis methods using whale optimization algorithm optimized variational mode decomposition (WOA-VMD) and particle swarm optimization support vector machine (PSO-SVM) for diagnosing internal short-circuit fault voltage signals of lithium batteries, as they cause runaway heating. First, the internal short-circuit fault voltage signal in the lithium battery is decomposed using VMD to obtain a series of natural mode components. Two parameters in the VMD algorithm that significantly impact the decomposition results include the number of decomposition layers K and penalty factor α. To achieve the best decomposition effect, WOA was used to determine the VMD optimal decomposition level K and penalty factor α. Further, the optimal parameter combination is found to be K = 10 and α = 1997. Subsequently, this optimal parameter combination was introduced into VMD decomposition to decompose the internal short-circuit fault signal of the lithium-ion battery to obtain 10 modal components. Thus, the sample entropy of each of the 10 modal components was calculated and used as the eigenvector. Finally, these eigenvectors were inputted into the SVM model, and then the PSO-optimized SVM model was used for fault diagnosis, providing the diagnostic results. The final results showed that the diagnostic accuracy of the direct SVM model remained stable at 66.667%, while the diagnostic accuracy of the PSO-optimized SVM model was stable at 96.667%. Compared with the direct SVM model, the PSO-SVM diagnostic model effectively identified the internal short-circuit fault of the lithium-ion battery in the SVM model after feature selection by the particle swarm optimization algorithm, thereby proving its effectiveness.
-
圖 2 鋰電池內短路故障診斷流程圖
Figure 2. Flow chart of internal short-circuit fault diagnosis of lithium battery
圖 3 鋰電池電壓信號.(a)鋰電池內短路電壓故障信號;(b)鋰電池正常電壓信號
Figure 3. Lithium battery voltage signal: (a) short-circuit voltage fault signal in lithium battery; (b) lithium battery normal voltage signal
圖 5 鋰電池故障信號VMD分解.（a）VMD分解;（b）VMD各分量對應頻譜
Figure 5. VMD decomposition of lithium battery fault signal: (a) VMD decomposition; (b) spectrum corresponding to each component of VMD
圖 6 鋰電池故障信號EMD分解.（a）EMD分解;（b）EMD各分量對應頻譜
Figure 6. EMD decomposition of lithium battery fault signal: (a) EMD decomposition; (b) spectrum corresponding to each component of EMD
圖 7 鋰電池故障信號EEMD分解.（a）EEMD分解;（b）EEMD各分量對應頻譜
Figure 7. EEMD decomposition of lithium battery fault signal: (a) EEMD decomposition; (b) spectrum corresponding to each component of EEMD
圖 8 鋰電池故障與正常電壓的熵值分解對比
Figure 8. Comparison of entropy decomposition between lithium battery fault and normal voltage
表 1 兩種狀態下特征向量及其識別效果
Table 1. Eigenvectors in two states and their recognition effects
Battery status Feature vector True category Forecast category IMF1 IMF2 IMF4 IMF6 IMF7 IMF9 Internal short-circuit fault 0.0050 0.0559 0.1050 0.0151 0.0033 0.0006 1 1 0.0061 0.0518 0.0502 0.0035 0.0001 0.0003 1 1 0.0064 0.0595 0.0396 0.0059 0.0019 0.002 1 1 Normal 0.0037 0.1308 0.0632 0.0018 0.0042 0.0011 2 2 0.0032 0.0272 0.0571 0.0096 0 0.0011 2 2 0.0032 0.0558 0.0241 0.0065 0.0016 0.0003 2 2 
下載: 導出CSV
表 2 經粒子群算法優化前后的診斷結果
Table 2. Diagnosis results before and after PSO
Fault diagnosis method Recognition rate/% SVM 66.667 PSO-SVM 96.667
下載: 導出CSV
啪啪啪视频<noscript id="y4y0w"><source id="y4y0w"></source></noscript> <table id="y4y0w"><option id="y4y0w"></option></table> <li id="y4y0w"></li> <noscript id="y4y0w"></noscript> <noscript id="y4y0w"><kbd id="y4y0w"></kbd></noscript> <noscript id="y4y0w"><source id="y4y0w"></source></noscript> <menu id="y4y0w"></menu> <table id="y4y0w"><rt id="y4y0w"></rt></table> -
參考文獻
[1] Li K X. Research on Thermal Characteristics and Thermal Management System of Electric Vehicle Power Battery [Dissertation]. Tianjin: Tianjin University, 2019李愷翔. 電動汽車動力電池熱特性及熱管理方式研究[學位論文]. 天津:天津大學, 2019 [2] Ma R X, Liu J Z, Wang S F, et al. Progress on thermal runaway propagation characteristics and prevention strategies of lithium-ion batteries. Chin Sci Bull, 2021, 66(23): 2991 doi: 10.1360/TB-2020-1576馬瑞鑫, 劉吉臻, 汪雙鳳, 等. 鋰離子電池熱失控擴展特征及抑制策略研究進展. 科學通報, 2021, 66(23):2991 doi: 10.1360/TB-2020-1576 [3] Long Y, Zhou X Z, Wang Z G, et al. Safety design of power Li-ion battery for rail transit vehicle. Battery Bimon, 2021, 51(6): 614龍源, 周興振, 王占國, 等. 軌道交通車輛用動力鋰離子電池的安全設計. 電池, 2021, 51(6):614 [4] Sun Z Y, Wang Z P, Liu P, et al. Overview of fault diagnosis in new energy vehicle power battery system. J Mech Eng, 2021, 57(14): 87 doi: 10.3901/JME.2021.14.087孫振宇, 王震坡, 劉鵬, 等. 新能源汽車動力電池系統故障診斷研究綜述. 機械工程學報, 2021, 57(14):87 doi: 10.3901/JME.2021.14.087 [5] Qin X W, Du H J, Li M M, et al. Energy storage system design for safety performance improvement. Power Energy, 2021, 42(5): 504秦曉維, 杜海江, 李明明, 等. 提升安全性能的儲能系統設計. 電力與能源, 2021, 42(5):504 [6] Zhang C J, Shi M D, Xu C, et al. Intrinsic safety mechanism and case analysis of energy storage systems based on dynamically reconfigurable battery network. Energy Storage Sci Technol, 2022, 11(8): 2442張從佳, 施敏達, 徐晨, 等. 基于動態可重構電池網絡的儲能系統本質安全機制及實例分析. 儲能科學與技術, 2022, 11(8):2442 [7] Liu H Y, Yang L, Li J L. Battery fault identification based on long-short-term memory networks. Mechatronics, 2020, 26(S1): 17劉宏陽, 楊林, 李濟霖. 基于長短期記憶網絡的電動汽車電池故障診斷. 機電一體化, 2020, 26(S1):17 [8] Shan T X, Wang Z P, Hong J C, et al. Overview of “mechanical abuse-thermal runaway” of electric vehicle power battery and its safety prevention and control technology. J Mech Eng, 2022, 58(14): 252山彤欣, 王震坡, 洪吉超, 等. 新能源汽車動力電池“機械濫用–熱失控”及其安全防控技術綜述. 機械工程學報, 2022, 58(14):252 [9] Yang R X, Xiong R, Sun F C. Experimental platform development and characteristics analysis of external short circuit in lithium-ion batteries. J Electr Eng, 2021, 16(1): 103楊瑞鑫, 熊瑞, 孫逢春. 鋰離子動力電池外部短路測試平臺開發與試驗分析. 電氣工程學報, 2021, 16(1):103 [10] Su W, Zhong G B, Shen J N, et al. The progress in fault diagnosis techniques for lithium-ion batteries. Energy Storage Sci Technol, 2019, 8(2): 225蘇偉, 鐘國彬, 沈佳妮, 等. 鋰離子電池故障診斷技術進展. 儲能科學與技術, 2019, 8(2):225 [11] Yang J, Lin Z K, Tang J, et al. A review of fault characteristics, fault diagnosis and identification for lithium-ion battery systems. CIESC J, 2022, 73(8): 3394楊靜, 林振康, 湯君, 等. 電池系統的故障特征以及多故障的診斷與識別. 化工學報, 2022, 73(8):3394 [12] Zhu X Q, Wang Z P, Hsin W, et al. Review of thermal runaway and safety management for lithium-ion traction batteries in electric vehicles. J Mech Eng, 2020, 56(14): 91 doi: 10.3901/JME.2020.14.091朱曉慶, 王震坡, WANG Hsin, 等. 鋰離子動力電池熱失控與安全管理研究綜述. 機械工程學報, 2020, 56(14):91 doi: 10.3901/JME.2020.14.091 [13] Wang Z F, Luo W, Yan Y, et al. Summary of research on multi-fault diagnosis strategies of lithium-ion power battery sensors. Sci Technol Eng, 2022, 22(27): 11761王志福, 羅崴, 閆愿, 等. 鋰離子動力電池傳感器多故障診斷策略綜述. 科學技術與工程, 2022, 22(27):11761 [14] Chen Z Y, Xiong R, Tian J P, et al. Model-based fault diagnosis approach on external short circuit of lithium-ion battery used in electric vehicles. Appl Energy, 2016, 184: 365 doi: 10.1016/j.apenergy.2016.10.026 [15] Feng X N, Pan Y, He X M, et al. Detecting the internal short circuit in large-format lithium-ion battery using model-based fault-diagnosis algorithm. J Energy Storage, 2018, 18: 26 doi: 10.1016/j.est.2018.04.020 [16] Feng X N, Weng C H, Ouyang M G, et al. Online internal short circuit detection for a large format lithium ion battery. Appl Energy, 2016, 161: 168 doi: 10.1016/j.apenergy.2015.10.019 [17] Zhang M X, Du J Y, Liu L S, et al. Internal short circuit detection method for battery pack based on circuit topology. Sci China Technol Sci, 2018, 61(10): 1502 doi: 10.1007/s11431-017-9299-3 [18] Chen Z Q, Chen X D, Olivira J, et al. Application of deep learning in equipment prognostics and health management. Chin J Sci Instrum, 2019, 40(9): 206陳志強, 陳旭東, José Valente de Olivira, 等. 深度學習在設備故障預測與健康管理中的應用. 儀器儀表學報, 2019, 40(9):206 [19] Wang C, Yuan Z Y, Wang Y W, et al. Overview of key technologies for echelon utilization of decommissioned power batteries. Adv N Renew Energy, 2021, 9(4): 327王存, 袁智勇, 王亦偉, 等. 退役動力電池梯次利用關鍵技術概述. 新能源進展, 2021, 9(4):327 [20] Li T M, Si X S, Liu X, et al. Data-model interactive remaining useful life prediction technologies for stochastic degrading devices with big data. Acta Autom Sin, 2022, 48(9): 2119李天梅, 司小勝, 劉翔, 等. 大數據下數模聯動的隨機退化設備剩余壽命預測技術. 自動化學報, 2022, 48(9):2119 [21] Jiang L L, Deng Z W, Tang X L, et al. Data-driven fault diagnosis and thermal runaway warning for battery packs using real-world vehicle data. Energy, 2021, 234: 121266 doi: 10.1016/j.energy.2021.121266 [22] Xia B, Shang Y L, Nguyen T, et al. A correlation based fault detection method for short circuits in battery packs. J Power Sources, 2017, 337: 1 doi: 10.1016/j.jpowsour.2016.11.007 [23] Naha A, Khandelwal A, Agarwal S, et al. Internal short circuit detection in Li-ion batteries using supervised machine learning. Sci Rep, 2020, 10: 1301 doi: 10.1038/s41598-020-58021-7 [24] Liu Y H. Research on Power Forecasting and Dynamic Environmental Economic Dispatch in Power System with Photovoltaic Power Generation [Dissertation]. Harbin: Northeast Agricultural University, 2021劉彥輝. 含光伏發電的電力系統功率預測和動態環境經濟調度研究[學位論文]. 哈爾濱:東北農業大學, 2021 [25] Wang R, Hou Q L, Shi R Y, et al. Remaining useful life prediction method of lithium battery based on variational mode decomposition and integrated deep model. Chin J Sci Instrum, 2021, 42(4): 111王冉, 后麒麟, 石如玉, 等. 基于變分模態分解與集成深度模型的鋰電池剩余壽命預測方法. 儀器儀表學報, 2021, 42(4):111 [26] Yang B C. Whale Optimization Algorithm-Based Optimum Energy-Management and Battery-Sizing Method for Grid-Connected Microgrids [Dissertation]. Qinhuangdao: Yanshan University, 2020楊柏成. 基于鯨魚優化算法的微網能量管理與電池容量優化[學位論文]. 秦皇島:燕山大學, 2020 [27] Wu Y X, Wang X Z, Cheng Y H, et al. Research on the method of extracting the fault features of walking gearbox of combine harvester. J Agric Mech Res, 2022, 44(2): 23吳又新, 王新忠, 承銀輝, 等. 聯合收割機行走變速箱故障特征提取方法研究. 農機化研究, 2022, 44(2):23 [28] Zhai J Q, Yang X X, Cheng Y Q, et al. Overview of application of fault detection and diagnosis based on machine learning. Comput Meas Contr, 2021, 29(3): 1翟嘉琪, 楊希祥, 程玉強, 等. 機器學習在故障檢測與診斷領域應用綜述. 計算機測量與控制, 2021, 29(3):1 [29] Zhang P, Zhang W H, Zhao X H, et al. Application of WOA-VMD algorithm in bearing fault diagnosis. Noise Vib Contr, 2021, 41(4): 86張萍, 張文海, 趙新賀, 等. WOA-VMD算法在軸承故障診斷中的應用. 噪聲與振動控制, 2021, 41(4):86 -
點擊查看大圖
圖(10) / 表(2)
計量
- 文章訪問數: 5
- HTML全文瀏覽量: 3
- PDF下載量: 0
- 被引次數: 0
