State-of-Charge Prediction of Battery Management System Based on Principal Component Analysis and Improved Support Vector Machine for Regression

Abstract

State-of-charge (SOC) prediction is an important part of the battery management system (BMS) in electric vehicles. Since external factors (voltage, current, temperature, arrangement of the battery, etc.) impact SOC prediction differently, the SOC is difficult to model. In this paper, we apply principal component analysis (PCA) to analyze the contribution of various external factors and propose a new SOC prediction method based on an improved support vector machine for regression (SVR) with data classification and training set size optimization. Three groups of simulation experiments with different inputs based on the original SVR algorithm are conducted in the software ADVISOR, and the simulation results show that the input of three features of the battery (current, voltage and temperature) can satisfy the SOC prediction accuracy. The improved SVR algorithm is then applied to the simulation experiment of the three input features. The proposed method is demonstrated to be faster and more accurate than the original SVR algorithm through a comparison of the simulation results. INDEX TERMS State-of-charge (SOC) , principal component analysis (PCA) , support vector machine for regression (SVR) , battery management system (BMS), electric vehicles.

Decision Support System for Economic Management of Large Enterprises Based on Artificial Intelligence

“…So, this is maintained and managed by the system administrator. When each position and department are established, it is necessary to select the operation authority of the system it has [23,24]. When an employee is promoted or demoted, as long as the position is a position in the system, and the position and department information is modified in its basic information, there is no need to change its operation authority again.…”

Predicting road traffic density using a machine learning-driven approach

“…In addition, SVR could provide satisfactory modeling performance in the presence of limited samples [17]. They showed to be useful in several applications as renewable energies modeling, and prediction [19], [20], State-of-charge prediction of battery [21], swarm motion prediction [22]. Importantly, to model input-output data, the SVR model adjusts the error inside a certain threshold instead of minimizing it like in classical regression models.…”

Double Extended Kalman Filter Algorithm Based on Weighted Multi-Innovation and Weighted Maximum Correlation Entropy Criterion for Co-Estimation of Battery SOC and Capacity

“… 34 A support vector machine algorithm with data classification and dataset size optimization was proposed for SOC prediction. 35 A stacked bidirectional long short-term memory (SBLSTM) neural network was proposed for SOC estimation of lithium-ion batteries. 36 Ren et al proposed to use a particle swarm optimization algorithm to optimize the parameters of long and short memory network for battery SOC estimation.…”

“…Chemali et al proposed a deep feedforward neural network (DFNN), which used data under different temperatures and scenes for training so that the measured battery-related data could be directly mapped to SOC through the network in the paper . A support vector machine algorithm with data classification and dataset size optimization was proposed for SOC prediction . A stacked bidirectional long short-term memory (SBLSTM) neural network was proposed for SOC estimation of lithium-ion batteries .…”