Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
762414 | Energy Conversion and Management | 2006 | 7 Pages |
Abstract
The support vector machine (SVM) is a novel type of learning machine based on statistical learning theory that can map a nonlinear function successfully. As a battery is a nonlinear system, it is difficult to establish the relationship between the load voltage and the current under different temperatures and state of charge (SOC). The SVM is used to model the battery nonlinear dynamics in this paper. Tests are performed on an 80Ah Ni/MH battery pack with the Federal Urban Driving Schedule (FUDS) cycle to set up the SVM model. Compared with the Nernst and Shepherd combined model, the SVM model can simulate the battery dynamics better with small amounts of experimental data. The maximum relative error is 3.61%.
Related Topics
Physical Sciences and Engineering
Energy
Energy (General)
Authors
Wang Junping, Chen Quanshi, Cao Binggang,