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.

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.

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.

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.

Hybrid Bacterial Foraging Optimization with Sparse Autoencoder for Energy Systems

The Internet of Things(IoT)technologies has gained significant interest in the design of smart grids(SGs).The increasing amount of distributed generations,maturity of existing grid infrastructures,and demand network transformation have received maximum attention.An essential energy storing model mostly the electrical energy stored methods are developing as the diagnoses for its procedure was becoming further compelling.The dynamic electrical energy stored model using Electric Vehicles(EVs)is comparatively standard because of its excellent electrical property and flexibility however the chance of damage to its battery was there in event of overcharging or deep discharging and its mass penetration deeply influences the grids.This paper offers a new Hybridization of Bacterial foraging optimization with Sparse Autoencoder(HBFOA-SAE)model for IoT Enabled energy systems.The proposed HBFOA-SAE model majorly intends to effectually estimate the state of charge(SOC)values in the IoT based energy system.To accomplish this,the SAE technique was executed to proper determination of the SOC values in the energy systems.Next,for improving the performance of the SOC estimation process,the HBFOA is employed.In addition,the HBFOA technique is derived by the integration of the hill climbing(HC)concepts with the BFOA to improve the overall efficiency.For ensuring better outcomes for the HBFOA-SAE model,a comprehensive set of simulations were performed and the outcomes are inspected under several aspects.The experimental results reported the supremacy of the HBFOA-SAE model over the recent state of art approaches.

Modeling and SOC estimation of lithium iron phosphate battery considering capacity loss

Modeling and state of charge(SOC)estimation of Lithium cells are crucial techniques of the lithium battery management system.The modeling is extremely complicated as the operating status of lithium battery is affected by temperature,current,cycle number,discharge depth and other factors.This paper studies the modeling of lithium iron phosphate battery based on the Thevenin’s equivalent circuit and a method to identify the open circuit voltage,resistance and capacitance in the model is proposed.To improve the accuracy of the lithium battery model,a capacity estimation algorithm considering the capacity loss during the battery’s life cycle.In addition,this paper solves the SOC estimation issue of the lithium battery caused by the uncertain noise using the extended Kalman filtering(EKF)algorithm.A simulation model of actual lithium batteries is designed in Matlab/Simulink and the simulation results verify the accuracy of the model under different operating modes.

Active Cell Balancing Control Strategy for Parallelly Connected LiFePO_(4) Batteries

While several recent studies have focused on elimi-nating the imbalance of energy stored in series-connected battery cells,very little attention has been given to balancing the energy stored in parallel-connected battery cells.As such,this paper aims at presenting a new balancing approach for parallel LiFePO_(4) battery cells.In this regard,a Backpropagation Neural Network(BPNN)based technique is employed to develop a Battery Management System(BMS)that can assess the charging status of all cells and control its operations through a DC/DC Buck-Boost converter.Simulation results demonstrate the effectiveness of the proposed approach in balancing the energy stored in parallel-connected battery cells in which the state of charge(SoC)estimation error is found to be only 1.15%.