Abstract
Highly accurate state of charge (SOC) estimation of lithium-ion batteries is one of the key technologies of battery management systems in electric vehicles. The performance of SOC estimation directly influences the driving range and safety of these vehicles. Due to external disturbances, temperature variation and electromagnetic interference, accurate SOC estimation becomes difficult. To accurately estimate the SOC of lithium-ion batteries, this article presents a novel machine-learning method to address the risk of gradient explosion and gradient decent using the dynamic nonlinear auto-regressive models with exogenous input neural network (NARX) with long short-term memories (LSTM).The proposed hybrid NARX model embeds LSTM memory, which provides jump-ahead connections in the time-unfolded model. These jump-ahead connections provide a shorter path for the propagation of gradient information, therefore reducing long-term dependence on the recurrent neural network. Experimental results show that the estimation performance root mean square error (RMSE) of the proposed model is less than 1%, and this model has better multitime prediction performance. Finally, the hybrid NARX and LSTM model is compared with the standard back propagation neural network based on particle swarm optimization (BPNN-PSO), the least-squares support vector machine (LS-SVM) and LSTM existing models under urban dynamometer driving schedule (UDDS) and dynamic stress test (DST) conditions. The proposed hybrid NARX-LSTM model yield relative to other methods and can estimate the battery SOC with high accuracy. The RMSE of proposed model is improved by approximately 60% compared with the standard LSTM.
Highlights
Environmental protection and energy consumption reduction have gained widespread attention in the twenty-first century, and electric vehicles (EVs) have developed rapidly [1]
The standard long and short time series (LSTM) and hybrid NARX and LSTM models can accurately estimate the state of charge (SOC) of the battery when compared with back propagation neural networks (BPNNs)-PSO and leastsquares support vector machine (LS-support vector machine (SVM))
The proposed model combines the advantages of the NARX model and the LSTM model
Summary
Environmental protection and energy consumption reduction have gained widespread attention in the twenty-first century, and electric vehicles (EVs) have developed rapidly [1]. To overcome the issues of exploding gradients or vanishing gradients, long and short time series (LSTM) is used in the NARX model for SOC prediction of lithium-ion batteries [32]–[34]. A method combining LSTM and NARX neural networks for SOC estimation of lithium-ion batteries. The phenomenon of the exploding gradient and vanishing gradient has become an important factor restricting the NARX neural network, and the NARX dynamic neural network combined with LSTM is proposed to estimate the SOC of the battery. The most important feature of the hybrid NARX dynamic neural network is the embedding of LSTM memories, which provide jump ahead connections in the time-unfolding network These jump ahead connections provide a shorter path for the propagation of gradient information, reducing the long-term dependence on the recurrent neural network. To explain the proposed method clearly, the algorithm of hybrid NARX and LSTM model is presented, as shown in table 1
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
