An indirect remaining useful life prediction of lithium-ion batteries based on a NARX dynamic neural network
-
摘要: 鋰離子電池的直接健康因子難以實現在線測量，針對此問題，提出一種基于動態神經網絡時間序列的鋰離子電池剩余壽命（Remaining useful life, RUL）間接預測方法。首先根據鋰離子電池的放電數據，提出放電截止時間，恒流放電時間以及放電峰值溫度時間三種間接健康因子并進行灰色關聯分析（Grey relation analysis, GRA）。然后，基于非線性自回歸（Nonlinear autoregressive models with exogenous inputs, NARX）動態神經網絡建立鋰離子電池RUL預測模型。最后將粒子群優化前饋神經網絡（Back propagation neural network based on particle swarm optimization, BPNN-PSO），最小二乘支持向量機（Least square support vector machine, LS-SVM），極限學習機（extreme learning machine, ELM），閉環（Closed-loop）NARX和開環（Open-loop）NARX進行對比分析，驗證了所提方法的優越性。Abstract: With increasingly serious energy shortages and environmental pollution, electric vehicles (EVs) have drawn widespread attention in recent years. The lithium-ion battery is widely used in the field of EVs owing to its superior energy density, life cycle, low self-discharge rate, and maintenance of memory. Prediction of the remaining useful life (RUL) of lithium-ion batteries is a key parameter in battery management systems. The accurate prediction of RUL is a prerequisite to ensuring the safety and reliability of the battery system. The gradual deterioration in the performance of lithium-ion batteries with cycling is normally predicted using capacity and resistance. However, this method is difficult to use in practical applications. To address this problem, a nonlinear autoregressive model with exogenous inputs (NARX) dynamic neural network was proposed to predict RUL. First, according to the discharge data of the lithium-ion battery, three indirect health indicators, namely, cut-off time, constant current time, and peak temperature time in discharge, were proposed, and grey relation analysis (GRA) was used to analyze their relation to capacity. The proposed three indirect health indicators have significant relationships with battery capacity. In addition, due to the influence of temperature vibration, electromagnetic interference, and external disturbance, RUL prediction of the lithium-ion battery is a typical nonlinear problem. In order to cover this weakness, the NARX dynamic neural network was established to predict the RUL of the lithium-ion battery. Finally, a closed-loop and an open-loop NARX were compared with the backpropagation neural network based on particle swarm optimization (BPNN-PSO), least-square support vector machine (LS-SVM), and extreme learning machine (ELM) of existing models under the open data of NASA. The experimental results show that the estimation performance RMSE (NO.5) of the proposed model is improved by about 33% compared with the standard ELM, verifying that the proposed model is superior to other methods in the RUL of lithium-ion batteries.
-
Key words:
- lithium-ion batteries /
- remaining useful life /
- health indicators /
- grey relation analysis /
- NARX
-
圖 5 Closed-loop NARX神經網絡結構圖
Figure 5. Structure of the closed-loop NARX dynamic neural network
圖 6 NARX動態神經網絡的鋰離子電池間接剩余壽命預測
Figure 6. Schematic diagram of the NARX dynamic neural network for RUL prediction
表 1 灰色關聯度分析結果
Table 1. Result of GRA
Indirect health indicators Battery No.5 Battery No.6 Battery No.7 Discharge voltage cut-off interval 0.8955 0.9236 0.9784 Constant current discharge interval 0.9082 0.9172 0.9645 Discharge peak temperature interval 0.8887 0.9248 0.9789 
下載: 導出CSV
中文字幕在线观看表 2 鋰離子電池剩余壽命預測評價指標
Table 2. Predication performance of RUL
Methods Batteries RMSE/% MAPE/% MAE/% BPNN-PSO No.5 2.17 1.21 1.62 No.6 2.31 1.18 1.59 No.7 1.92 0.98 1.45 LS-SVM No.5 1.67 1.11 1.05 No.6 2.07 1.14 1.49 No.7 2.21 1.27 1.70 ELM No.5 2.16 1.13 1.52 No.6 2.07 1.14 1.49 No.7 1.97 1.05 1.56 Closed-loop NARX No.5 1.44 0.41 0.66 No.6 1.38 0.61 0.83 No.7 1.42 0.74 1.11 Open-loop NARX No.5 1.24 0.35 0.51 No.6 1.02 0.35 0.51 No.7 1.19 0.42 0.65
下載: 導出CSV
-
參考文獻
[1] Guo P Y, Cheng Z, Yang L. A data-driven remaining capacity estimation approach for lithium-ion batteries based on charging health feature extraction. J Power Sources, 2019, 412: 442 doi: 10.1016/j.jpowsour.2018.11.072 [2] Tian H X, Qin P L, Li K, et al. A review of the state of health for lithium-ion batteries: Research status and suggestions. J Clean Prod, 2020, 261: 120813 doi: 10.1016/j.jclepro.2020.120813 [3] Xiong R, Zhang Y Z, Wang J, et al. Lithium-ion battery health prognosis based on a real battery management system used in electric vehicles. IEEE Trans Veh Technol, 2019, 68(5): 4110 doi: 10.1109/TVT.2018.2864688 [4] Xue Q, Shen S Q, Li G, et al. Remaining useful life prediction for lithium-ion batteries based on capacity estimation and box-cox transformation. IEEE Trans Veh Technol, 2020, 69(12): 14765 doi: 10.1109/TVT.2020.3039553 [5] Jiao Z Q, Fan X M, Zhang X, et al. State tracking and remaining useful life predictive method of Li-ion battery based on improved particle filter algorithm. Trans China Electrotech Soc, 2020, 35(18): 3979焦自權, 范興明, 張鑫, 等. 基于改進粒子濾波算法的鋰離子電池狀態跟蹤與剩余使用壽命預測方法. 電工技術學報, 2020, 35(18):3979 [6] Zhang J H, Li Q, Chen D P, et al. Real-time states Co-estimation algorithm for Li-ion power batteries based on fast square-root unscented kalman filters. Chin J Eng, 2021, 43(7): 976章軍輝, 李慶, 陳大鵬, 等. 基于快速SR-UKF的鋰離子動力電池SOC聯合估計. 工程科學學報, 2021, 43(7):976 [7] Harper G, Sommerville R, Kendrick E, et al. Recycling lithium-ion batteries from electric vehicles. Nature, 2019, 575(7781): 75 doi: 10.1038/s41586-019-1682-5 [8] ?eruga D, Gosar A, Sweeney C A, et al. Continuous modelling of cyclic ageing for lithium-ion batteries. Energy, 2021, 215: 119079 doi: 10.1016/j.energy.2020.119079 [9] Wu Y T, Xue Q, Shen J W, et al. State of health estimation for lithium-ion batteries based on healthy features and long short-term memory. IEEE Access, 2020, 8: 28533 doi: 10.1109/ACCESS.2020.2972344 [10] Tian J Q, Xu R L, Wang Y J, et al. Capacity attenuation mechanism modeling and health assessment of lithium-ion batteries. Energy, 2021, 221: 119682 doi: 10.1016/j.energy.2020.119682 [11] Jia J F, Liang J Y, Shi Y H, et al. SOH and RUL prediction of lithium-ion batteries based on Gaussian process regression with indirect health indicators. Energies, 2020, 13(2): 375 doi: 10.3390/en13020375 [12] Yang W S, Yao Q F, Ye K J, et al. Empirical mode decomposition and temporal convolutional networks for remaining useful life estimation. Int J Parallel Program, 2020, 48(1): 61 doi: 10.1007/s10766-019-00650-1 [13] Li L B, Ji L, Zhu Y Z, et al. Investigation of RUL prediction of lithium-ion battery equivalent cycle battery pack. Chin J Eng, 2020, 42(6): 796李練兵, 季亮, 祝亞尊, 等. 等效循環電池組剩余使用壽命預測. 工程科學學報, 2020, 42(6):796 [14] Ma Y, Chen Y, Zhang F, et al. Remaining useful life prediction of power battery based on extend h∞ particle filter algorithm. J Mech Eng, 2019, 55(20): 36馬彥, 陳陽, 張帆, 等. 基于擴展H∞粒子濾波算法的動力電池壽命預測方法. 機械工程學報, 2019, 55(20):36 [15] Li Y X, Liu S J, Gao S B, et al. Prediction of lithium-ion battery's remaining useful life based on Wiener process. J Dalian Univ Technol, 2017, 57(2): 126 doi: 10.7511/dllgxb201702003李玥鋅, 劉淑杰, 高斯博, 等. 基于維納過程的鋰離子電池剩余壽命預測. 大連理工大學學報, 2017, 57(2):126 doi: 10.7511/dllgxb201702003 [16] Lyu C, Lai Q Z, Ge T F, et al. A lead-acid battery's remaining useful life prediction by using electrochemical model in the Particle Filtering framework. Energy, 2017, 120: 975 doi: 10.1016/j.energy.2016.12.004 [17] Lin H L, Li S. Remaining useful life prediction of the lithium-ion batteries based on particle filter algorithm. Sci Technol Eng, 2017, 17(29): 296 doi: 10.3969/j.issn.1671-1815.2017.29.043林慧龍, 李賽. 基于粒子濾波的鋰離子電池剩余使用壽命預測. 科學技術與工程, 2017, 17(29):296 doi: 10.3969/j.issn.1671-1815.2017.29.043 [18] Xian W M, Long B, Li M, et al. Prognostics of lithium-ion batteries based on the verhulst model, particle swarm optimization and particle filter. IEEE Trans Instrum Meas, 2014, 63(1): 2 doi: 10.1109/TIM.2013.2276473 [19] Qu J, Zhao X H, Gan W. The remaining life prediction model of lithium battery based on wavelet noise reduction and support vector machine. Mach Des Manuf Eng, 2020, 49(1): 81曲杰, 趙小涵, 甘偉. 基于小波降噪-支持矢量機的鋰離子電池剩余使用壽命預測模型. 機械設計與制造工程, 2020, 49(1):81 [20] Wu J, Zhang C B, Chen Z H. An online method for lithium-ion battery remaining useful life estimation using importance sampling and neural networks. Appl Energy, 2016, 173: 134 doi: 10.1016/j.apenergy.2016.04.057 [21] Wang X C, Zhao J, Li Q Q, et al. A hybrid model for prediction in asphalt pavement performance based on support vector machine and grey relation analysis. J Adv Transp, 2020, 2020: 1 [22] Chen Z W, Li F S, Lin Y, et al. Indirect prediction method of RUL for lithium-ion battery based on GA-ELM. Acta Metrol Sin, 2020, 41(6): 735 doi: 10.3969/j.issn.1000-1158.2020.06.17陳則王, 李福勝, 林婭, 等. 基于GA-ELM的鋰離子電池RUL間接預測方法. 計量學報, 2020, 41(6):735 doi: 10.3969/j.issn.1000-1158.2020.06.17 [23] Zhou Y P, Huang M H. Lithium-ion batteries remaining useful life prediction based on a mixture of empirical mode decomposition and ARIMA model. Microelectron Reliab, 2016, 65: 265 doi: 10.1016/j.microrel.2016.07.151 [24] Liu D T, Luo Y, Liu J, et al. Lithium-ion battery remaining useful life estimation based on fusion nonlinear degradation AR model and RPF algorithm. Neural Comput Appl, 2014, 25(3-4): 557 doi: 10.1007/s00521-013-1520-x [25] Saha B, Goebel K. Battery data set: NASA ames prognostics data repository [DB/OL]. NASA Ames Research Center (2007)[2020-10-22].https://ti.arc.nasa.gov/tech/dash/groups/pcoe/prognostic-data-repository [26] Pang X Q, Wang Z Q, Zeng J C, et al. Prediction for the remaining useful life of lithium-ion battery based on PCA-NARX. Trans Beijing Inst Technol, 2019, 39(4): 406龐曉瓊, 王竹晴, 曾建潮, 等. 基于PCA-NARX的鋰離子電池剩余使用壽命預測. 北京理工大學學報, 2019, 39(4):406 -
點擊查看大圖
圖(17) / 表(2)
計量
- 文章訪問數: 2029
- HTML全文瀏覽量: 718
- PDF下載量: 128
- 被引次數: 0
