SOC Prediction of Power Battery Based on SVM
Qiyan Yan
Abstract
In order to predict the state of charge(SOC) accurately in power battery management system, genetic algorithm(GA) is used to optimize support vector machine (SVM), and the SOC of battery is predicted. The current, voltage and temperature of the battery are taken as the input of the training model, and the SOC is used as the output of establish the model. The prediction experiment of SOC is carried out. The experimental results show that the prediction model has high prediction accuracy, the maximum relative error is less than 3% and the average relative error is less than 2.5%. Compared with the prediction result of neural network, it is more practical.
Topics & Concepts
Battery (electricity)Support vector machineState of chargeComputer scienceArtificial neural networkGenetic algorithmApproximation errorVoltagePower (physics)Mean squared prediction errorArtificial intelligenceMachine learningAlgorithmEngineeringElectrical engineeringQuantum mechanicsPhysicsAdvanced Algorithms and ApplicationsAdvanced Battery Technologies ResearchAdvanced Sensor and Control Systems