Open Access
ARTICLE
A Fault Detection Method for Electric Vehicle Battery System Based on Bayesian Optimization SVDD Considering a Few Faulty Samples
School of Electronics and Electrical Engineering, Anhui Polytechnic University, Wuhu, 241000, China
* Corresponding Author: Fanyong Cheng. Email:
(This article belongs to the Special Issue: Advanced Modelling, Operation, Management and Diagnosis of Lithium Batteries)
Energy Engineering 2024, 121(9), 2543-2568. https://doi.org/10.32604/ee.2024.051231
Received 01 March 2024; Accepted 26 April 2024; Issue published 19 August 2024
Abstract
Accurate and reliable fault detection is essential for the safe operation of electric vehicles. Support vector data description (SVDD) has been widely used in the field of fault detection. However, constructing the hypersphere boundary only describes the distribution of unlabeled samples, while the distribution of faulty samples cannot be effectively described and easily misses detecting faulty data due to the imbalance of sample distribution. Meanwhile, selecting parameters is critical to the detection performance, and empirical parameterization is generally time-consuming and laborious and may not result in finding the optimal parameters. Therefore, this paper proposes a semi-supervised data-driven method based on which the SVDD algorithm is improved and achieves excellent fault detection performance. By incorporating faulty samples into the underlying SVDD model, training deals better with the problem of missing detection of faulty samples caused by the imbalance in the distribution of abnormal samples, and the hypersphere boundary is modified to classify the samples more accurately. The Bayesian Optimization NSVDD (BO-NSVDD) model was constructed to quickly and accurately optimize hyperparameter combinations. In the experiments, electric vehicle operation data with four common fault types are used to evaluate the performance with other five models, and the results show that the BO-NSVDD model presents superior detection performance for each type of fault data, especially in the imperceptible early and minor faults, which has seen very obvious advantages. Finally, the strong robustness of the proposed method is verified by adding different intensities of noise in the dataset.Keywords
Cite This Article
![cc](https://www.techscience.com/static/images/cc.jpg?t=20230215)
This work is licensed under a Creative Commons Attribution 4.0 International License , which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.