State of Charge Prediction Algorithm of Lithium-Ion Battery Based on PSO-SVR Cross Validation

• Published in: IEEE access Vol. 8; pp. 10234 - 10242
• Main Authors: Li, Ran, Xu, Shihui, Li, Sibo, Zhou, Yongqin, Zhou, Kai, Liu, Xianzhong, Yao, Jie
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 2020; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Lithium; Lithium-ion batteries; Lithium-ion power battery; Mathematical model; Mathematical models; Model accuracy; nonlinear data diagnosis; Nonlinear systems; Parameters; Particle swarm optimization; Prediction models; Predictive models; Real time; Rechargeable batteries; State of charge; State prediction; support vector machine; Support vector machines
• ISSN: 2169-3536; 2169-3536
• DOI: 10.1109/ACCESS.2020.2964852

Lithium-ion battery refers to a complex nonlinear system. Real-time diagnosis and accurate prediction of battery state of charge(SOC) parameters are hotspots and critical issues in battery research. To reduce the dependence of state of charge prediction on battery model accuracy and speed, and achieve real-time online estimation, a SOC prediction model of lithium-ion battery system is developed based on the model of support vector machine (SVM). SVM parameter is optimized using an algorithm of particle swarm optimization, and the performance of prediction model is assessed using cross-validation. The obtained experimental data is simulated, involving the comparison with the support vector machine model, and the prediction simulation of the battery in the state of fault. The results reveal that this model with a better performance than that of the support vector machine exhibits high accuracy and generalization ability.