Deep learning-based battery state of charge estimation:Enhancing estimation performance with unlabelled training samples

The estimation of state of charge(SOC)using deep neural networks(DNN)generally requires a considerable number of labelled samples for training,which refer to the current and voltage pieces with knowing their corresponding SOCs.However,the collection of labelled samples is costly and time-consuming.In contrast,the unlabelled training samples,which consist of the current and voltage data with unknown SOCs,are easy to obtain.In view of this,this paper proposes an improved DNN for SOC estimation by effectively using both a pool of unlabelled samples and a limited number of labelled samples.Besides the traditional supervised network,the proposed method uses an input reconstruction network to reformulate the time dependency features of the voltage and current.In this way,the developed network can extract useful information from the unlabelled samples.The proposed method is validated under different drive cycles and temperature conditions.The results reveal that the SOC estimation accuracy of the DNN trained with both labelled and unlabelled samples outperforms that of only using a limited number of labelled samples.In addition,when the dataset with reduced number of labelled samples to some extent is used to test the developed network,it is found that the proposed method performs well and is robust in producing the model outputs with the required accuracy when the unlabelled samples are involved in the model training.Furthermore,the proposed method is evaluated with different recurrent neural networks(RNNs)applied to the input reconstruction module.The results indicate that the proposed method is feasible for various RNN algorithms,and it could be flexibly applied to other conditions as required.

State of charge estimation of Li-ion batteries in an electric vehicle based on a radial-basis-function neural network

The on-line estimation of the state of charge （SOC） of the batteries is important for the reliable running of the pure electric vehicle in practice. Because a nonlinear feature exists in the batteries and the radial-basis-function neural network （RBF NN） has good characteristics to solve the nonlinear problem, a practical method for the SOC estimation of batteries based on the RBF NN with a small number of input variables and a simplified structure is proposed. Firstly, in this paper, the model of on-line SOC estimation with the RBF NN is set. Secondly, four important factors for estimating the SOC are confirmed based on the contribution analysis method, which simplifies the input variables of the RBF NN and enhttnces the real-time performance of estimation. FiItally, the pure electric buses with LiFePO4 Li-ion batteries running during the period of the 2010 Shanghai World Expo are considered as the experimental object. The performance of the SOC estimation is validated and evaluated by the battery data from the electric vehicle.

Fuzzy Model for Estimation of the State-of-Charge of Lithium-Ion Batteries for Electric Vehicles

A fuzzy model was established to estimate the state of charge（SOC） of a lithium-ion battery for electric vehicles.The robust Gustafson-Kessel（GK） clustering algorithm based on clustering validity indices was applied to identify the structure and antecedent parameters of the model.The least squares algorithm was utilized to determine the consequent parameters.Validation results show that this model can provide accurate SOC estimation for the lithium-ion battery and satisfy the requirement for practical electric vehicle applications.

Review of lithium-ion battery state of charge estimation

The technology deployed for lithium-ion battery state of charge(SOC)estimation is an important part of the design of electric vehicle battery management systems.Accurate SOC estimation can forestall excessive charging and discharging of lithium-ion batteries,thereby improving discharge efficiency and extending cycle life.In this study,the key lithium-ion battery SOC estimation technologies are summarized.First,the research status of lithium-ion battery modeling is introduced.Second,the main technologies and difficulties in model parameter identification for lithium-ion batteries are discussed.Third,the development status and advantages and disadvantages of SOC estimation methods are summarized.Finally,the current research problems and prospects for development trends are summarized.

Co-Estimation of State of Charge and Capacity for Lithium-Ion Batteries with Multi-Stage Model Fusion Method

Lithium-ion batteries(LIBs)have emerged as the preferred energy storage systems for various types of electric transports,including electric vehicles,electric boats,electric trains,and electric airplanes.The energy management of LIBs in electric transports for all-climate and long-life operation requires the accurate estimation of state of charge(SOC)and capacity in real-time.This study proposes a multistage model fusion algorithm to co-estimate SOC and capacity.Firstly,based on the assumption of a normal distribution,the mean and variance of the residual error from the model at different ageing levels are used to calculate the weight for the establishment of a fusion model with stable parameters.Secondly,a differential error gain with forward-looking ability is introduced into a proportional–integral observer(PIO)to accelerate convergence speed.Thirdly,a fusion algorithm is developed by combining a multistage model and proportional–integral–differential observer(PIDO)to co-estimate SOC and capacity under a complex application environment.Fourthly,the convergence and anti-noise performance of the fusion algorithm are discussed.Finally,the hardware-in-the-loop platform is set up to verify the performance of the fusion algorithm.The validation results of different aged LIBs over a wide range of temperature show that the presented fusion algorithm can realize a high-accuracy estimation of SOC and capacity with the relative errors within 2%and 3.3%,respectively.

Estimation Method of State-of-Charge For Lithium-ion Battery Used in Hybrid Electric Vehicles Based on Variable Structure Extended Kalman Filter

Since the main power source of hybrid electric vehicle（HEV） is supplied by the power battery,the predicted performance of power battery,especially the state-of-charge（SOC） estimation has attracted great attention in the area of HEV.However,the value of SOC estimation could not be greatly precise so that the running performance of HEV is greatly affected.A variable structure extended kalman filter（VSEKF）-based estimation method,which could be used to analyze the SOC of lithium-ion battery in the fixed driving condition,is presented.First,the general lower-order battery equivalent circuit model（GLM）,which includes column accumulation model,open circuit voltage model and the SOC output model,is established,and the off-line and online model parameters are calculated with hybrid pulse power characteristics（HPPC） test data.Next,a VSEKF estimation method of SOC,which integrates the ampere-hour（Ah） integration method and the extended Kalman filter（EKF） method,is executed with different adaptive weighting coefficients,which are determined according to the different values of open-circuit voltage obtained in the corresponding charging or discharging processes.According to the experimental analysis,the faster convergence speed and more accurate simulating results could be obtained using the VSEKF method in the running performance of HEV.The error rate of SOC estimation with the VSEKF method is focused in the range of 5% to 10% comparing with the range of 20% to 30% using the EKF method and the Ah integration method.In Summary,the accuracy of the SOC estimation in the lithium-ion battery cell and the pack of lithium-ion battery system,which is obtained utilizing the VSEKF method has been significantly improved comparing with the Ah integration method and the EKF method.The VSEKF method utilizing in the SOC estimation in the lithium-ion pack of HEV can be widely used in practical driving conditions.

Adaptive Kalman filter based state of charge estimation algorithm for lithium-ion battery

In order to improve the accuracy of the battery state of charge（SOC） estimation, in this paper we take a lithiumion battery as an example to study the adaptive Kalman filter based SOC estimation algorithm. Firstly, the second-order battery system model is introduced. Meanwhile, the temperature and charge rate are introduced into the model. Then, the temperature and the charge rate are adopted to estimate the battery SOC, with the help of the parameters of an adaptive Kalman filter based estimation algorithm model. Afterwards, it is verified by the numerical simulation that in the ideal case, the accuracy of SOC estimation can be enhanced by adding two elements, namely, the temperature and charge rate.Finally, the actual road conditions are simulated with ADVISOR, and the simulation results show that the proposed method improves the accuracy of battery SOC estimation under actual road conditions. Thus, its application scope in engineering is greatly expanded.

Kalman Filters versus Neural Networks in Battery State-of-Charge Estimation: A Comparative Study

Battery management systems (BMS) must estimate the state-of-charge (SOC) of the battery accurately to prolong its lifetime and ensure a reliable operation. Since batteries have a wide range of applications, the SOC estimation requirements and methods vary from an application to another. This paper compares two SOC estimation methods, namely extended Kalman filters (EKF) and artificial neural networks (ANN). EKF is a nonlinear optimal estimator that is used to estimate the inner state of a nonlinear dynamic system using a state-space model. On the other hand, ANN is a mathematical model that consists of interconnected artificial neurons inspired by biological neural networks and is used to predict the output of a dynamic system based on some historical data of that system. A pulse-discharge test was performed on a commercial lithium-ion (Li-ion) battery cell in order to collect data to evaluate those methods. Results are presented and compared.

SOC estimation of lithium-ion power battery for HEV based on advanced wavelet neural network

In order to improve the estimation accuracy of the battery＇s state of charge（SOC） for the hybrid electric vehicle（HEV）,the SOC estimation algorithm based on advanced wavelet neural network（WNN） is presented.Based on advanced WNN,the SOC estimation model of a lithium-ion power battery for the HEV is first established.Then,the convergence of the advanced WNN algorithm is proved by mathematical deduction.Finally,using an adequate data sample of various charging and discharging of HEV batteries,the neural network is trained.The simulation results indicate that the proposed algorithm can effectively decrease the estimation errors of the lithium-ion power battery SOC from the range of ±8% to ±1.5%,compared with the traditional SOC estimation methods.

考虑应力特征的锂离子电池SOC估算

准确估计荷电状态(SOC)是保证锂离子电池可靠运行的基础。提出基于多维特征特别是结合力信号的数据驱动的SOC估算方法,对锂离子电池应力特征进行Savitzky-Golay(S-G)滤波,形成优化重构后的应力信号。提出基于麻雀搜索算法(SSA)改进的反向传播(BP)神经网络,提高神经网络的全局寻优能力。用恒流(CC)、联邦城市驾驶工况(FUDS)进行评估。在BP神经网络中,相比于单纯使用电信号,考虑应力特征的SOC估算的均方根误差(RMSE)降低89.1%,平均绝对误差(MAE)降低88.8%,考虑应力特征的SSA-BP神经网络的SOC估算误差在0.3%以内,鲁棒性和精确性更高。

温度自适应SMO算法估计锂离子电池的SOC

现有对锂离子电池荷电状态(SOC)的估计,没有考虑温度变化导致的SOC估计准确度降低。提出一种考虑温度的滑模观测(SMO)法进行SOC估计。基于混合脉冲功率测试(HPPC)实验的数据,得到18650型LiFePO4锂离子电池的SOC与温度、参数之间的拟合式,通过台风(Typhoon)系统进行半实物实验分析。温度自适应SMO算法在低温或常温工况下的平均误差较传统SMO算法降低0.3~0.5个百分点,直接通过拟合式所快速估计的SOC较温度自适应SMO算法平均误差在2%左右,常温25℃工况下误差低于1%,能够实现较高的估计精准度,为快速估计SOC提供了较好的算法参考。

引入PID反馈的SHAEKF算法估算电池SOC

电池荷电状态(SOC)的估算精度是电动汽车电池组的重要指标。为提升SOC估算精度,在融合Sage-Husa扩展卡尔曼滤波(SHEKF)算法与自适应扩展卡尔曼滤波(AEKF)算法的基础上,增加比例积分微分(PID)反馈环节,形成改进算法。采用粒子群优化(PSO)算法对二阶RC等效电路模型进行参数辨识;用开源电池数据集对模型和算法进行实验和分析。改进的SHAEKF算法在电池动态应力测试(DST)、北京动态应力测试(BJDST)和美国联邦城市驾驶(FUDS)等工况下的平均估计误差都在1%以内,与单纯的融合算法SHAEKF算法相比,最大误差可减小5%。

基于CSO-AUKF的锂电池SOC估算方法

电池荷电状态(SOC)估算是电池管理系统(BMS)的关键技术之一。针对锂电池提出了一种基于猫群(CSO)算法和自适应无迹卡尔曼滤波(AUKF)算法相结合的电池SOC估算方法;建立了基于二阶RC等效电路模型的锂电池状态方程,采用CSO算法提高电池辨识精度,联合AUKF算法对SOC进行估算;基于混合脉冲功率测试工况(HPPC)和间歇恒流放电工况下的数据对该方法有效性进行了验证。研究结果表明:基于CSO-AUKF估算,SOC最大误差小于1.64%,估算精度及稳定性均好于遗传算法。

适用于宽温度范围的锂离子电池SOC估计方法

精确的荷电状态(SOC)估计是确保动力电池安全稳定运行的关键所在。然而,在实际应用中,环境温度的变化以及噪声干扰等因素使得SOC的精确估计变得困难重重。为了解决这一问题,本文提出一种基于多新息自适应鲁棒无迹卡尔曼滤波(MIARUKF)算法的宽温度范围下锂离子电池SOC多时间尺度联合估计方法,该算法在无迹卡尔曼滤波(UKF)算法的基础上,融合多新息理论、自适应滤波与鲁棒算法。所提算法利用多新息向量对状态估计值进行修正,并对噪声协方差进行及时更新,从而提高SOC的估计精度,通过引入H∞滤波算法来提高该算法的鲁棒性。同时为了降低电池管理系统(BMS)的计算负担,使用UKF算法在宏观时间尺度上在线估计模型参数,采用MIARUKF算法在微观时间尺度上估计电池SOC。最后,在不同SOC初始值、不同温度条件下,对电池SOC的估计结果进行比较和分析,本文所提方法最大绝对误差和平均绝对误差分别为1.05%和0.42%,表明该算法具有较高的精度和较好的鲁棒性。

基于自适应H_(∞)观测器的锂电池SOC与容量联合估计

为了提高锂电池SOC的估计精度,提出了一种基于自适应H_(∞)观测器的锂电池SOC与容量联合估计方法。基于锂电池的二阶RC等效电路模型,并考虑SOC和容量的耦合关系,将容量也作为系统的状态变量进行观测。设计了一种自适应H_(∞)观测器,其参数可随锂电池状态的变化自适应调整。由于在SOC估算时考虑了容量的影响,实现了SOC和容量的同时准确估计。实验结果表明:自适应H_(∞)观测器的估计精度高且鲁棒性强,电池的SOC平均估计误差始终保持在±0.43%以内,相比于EKF和H_(∞)观测器有更高的估计精度与稳定性。

基于多新息扩展卡尔曼滤波的锂离子电池SOC估计

锂电池具有高能量密度、循环寿命长等优点而被广泛应用于电动汽车动力装置,但车辆运行状况复杂多变,且电池内部呈现高度非线性的性质,导致电池荷电状态(state of charge, SOC)难以准确计算。为优化锂电池SOC估计精度,构建结合Warburg元件的分数阶二阶RC模型,采用自适应遗传算法进行参数辨识;融合多新息理论和扩展卡尔曼滤波算法,提出基于多新息扩展卡尔曼滤波(multi innovation extended Kalman filter, MIEKF)的锂离子电池SOC估计算法,并利用试验数据验证该方法的有效性,为提高SOC估计精度和车载锂电池的循环使用寿命提供了新的方法途径和实践支撑。

基于AR-ECM平均差异模型的串联电池组SOC、容量多尺度联合估计方法

考虑电池单体老化差异所致的电池组不一致性,针对串联电池组荷电状态(state of charge,SOC)、容量估计问题,提出一种基于自回归等效电路模型(autoregression equivalent circuit model,AR-ECM)的平均差异模型(mean-difference model,MDM)。基于此模型,提出串联电池组SOC、容量多尺度联合估计算法。该算法由2个部分组成,一是基于AR-ECM的MDM及差异化模型参数辨识策略:条件辨识策略和定频分组辨识策略;二是基于多时间尺度H无穷滤波(multi-timescale H infinity filter,Mts-HIF)的电池组SOC、容量联合估计算法。通过将所提出MDM中的自回归平均模型(autoregression mean model,AR-MM)与传统MDM中的n阶RC平均模型(nRC mean model,nRC-MM)比较,结果表明所提出的AR-MM在复杂运行工况下具有更优的动态跟随性能。依据最小化信息量准则(akaike information criterion,AIC),AR-MM具有更优的复杂度与精度的权衡。通过与基于多时间尺度扩展卡尔曼滤波(multi-timescale extended Kalman filter,Mts-EKF)联合状态估计算法比较,结果表明所提出的Mts-HIF状态估计算法具有更优的鲁棒性、精度和收敛速度。

基于分数阶模型多新息无迹卡尔曼滤波算法的超级电容SOC估计

对超级电容的SOC估计展开了研究。首先,搭建了超级电容测试平台,用于超级电容的参数辨识,并对超级电容进行了常规性能测试;其次,在不同的环境温度和动态工况下采用多种算法进行超级电容SOC估计。结果表明,采用分数阶模型多新息无迹卡尔曼滤波(FOMIUKF)算法对超级电容SOC的估计精度最高,对超级电容的路端电压跟随情况最好,估计结果的均方根误差和平均绝对误差的最大值分别约为1.8%和1.73%。

基于SOC的串联连接锂电池能量均衡控制研究

串联锂电池的SOC均衡控制对提高电池寿命具有重要意义。针对锂电池单体SOC表现出离散性的不同情况,本文研究了一种主动均衡与被动均衡相结合的混合均衡方案,其中主动均衡器拓扑由多绕组反激变换器实现,被动均衡器由电阻与开关组成并联在单体电池两端,详细分析了混合均衡器的工作原理。在控制策略上讨论了锂电池SOC的离散性对均衡速度的影响,引入表征SOC离散度的标准差和表征离散原因的系数以实现SOC不同离散情况下的快速均衡。所提出的混合均衡器拓扑和控制方案能够使耗能与均衡速度获得优化,实验结果验证了文中理论的可行性。

基于注意力机制和CNN-LSTM融合模型的锂电池SOC预测

为提高锂电池荷电状态SOC(state-of-charge)预测精度,提出1种基于注意力机制和卷积神经网络-长短时记忆CNN-LSTM(convolution neural network-long short-term memory)融合模型的锂电池荷电状态预测方法。该模型采用一维CNN和LSTM神经网络学习得到SOC与锂电池放电数据的非线性关系,以及SOC序列存在的长期依赖性。同时,该模型采用“多对一”的结构,将当前时刻的锂电池SOC与多个历史时刻的放电数据建立映射关系,并通过注意力机制关注到对当前时刻SOC影响较大的历史放电数据,进一步提升SOC的预测准确度。动态工况下的锂电池SOC预测实验表明,该方法在不同温度条件下的平均预测误差为0.89%,与SVM、GRU和XGBoost相比,分别降低了81.2%、66.7%和56.5%,且优于未融合注意力机制的LSTM和CNN-LSTM,具有较高的预测精度和应用价值。