State of Health Estimation for Lithium-Ion Batteries Based on TCN-RVM
A State of Health (SOH) estimation of lithium-ion batteries is a core function of battery management systems, directly affecting the safe operation, lifetime prediction, and economic efficiency of batteries. However, existing methods still face challenges in balancing feature robustness and model ge...
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-07-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/15/15/8213 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849239825296654336 |
|---|---|
| author | Yu Zhao Yonghong Xu Yidi Wei Liang Tong Yiyang Li Minghui Gong Hongguang Zhang Baoying Peng Yinlian Yan |
| author_facet | Yu Zhao Yonghong Xu Yidi Wei Liang Tong Yiyang Li Minghui Gong Hongguang Zhang Baoying Peng Yinlian Yan |
| author_sort | Yu Zhao |
| collection | DOAJ |
| description | A State of Health (SOH) estimation of lithium-ion batteries is a core function of battery management systems, directly affecting the safe operation, lifetime prediction, and economic efficiency of batteries. However, existing methods still face challenges in balancing feature robustness and model generalization ability; for instance, some studies rely on features whose physical correlation with SOH lacks strict verification, or the models struggle to simultaneously capture the temporal dynamics of health factors and nonlinear mapping relationships. To address this, this paper proposes an SOH estimation method based on incremental capacity (IC) curves and a Temporal Convolutional Network—Relevance Vector Machine (TCN-RVM) model, with core innovations reflected in two aspects. Firstly, five health factors are extracted from IC curves, and the strong correlation between these features and SOH is verified using both Pearson and Spearman coefficients, ensuring the physical rationality and statistical significance of feature selection. Secondly, the TCN-RVM model is constructed to achieve complementary advantages. The dilated causal convolution of TCN is used to extract temporal local features of health factors, addressing the insufficient capture of long-range dependencies in traditional models; meanwhile, the Bayesian inference framework of RVM is integrated to enhance the nonlinear mapping capability and small-sample generalization, avoiding the overfitting tendency of complex models. Experimental validation is conducted using the lithium-ion battery dataset from the University of Maryland. The results show that the mean absolute error of the SOH estimation using the proposed method does not exceed 0.72%, which is significantly superior to comparative models such as CNN-GRU, KELM, and SVM, demonstrating higher accuracy and reliability compared with other models. |
| format | Article |
| id | doaj-art-6e17e3cabfd9460c8ec5cf5e58f98d56 |
| institution | Kabale University |
| issn | 2076-3417 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj-art-6e17e3cabfd9460c8ec5cf5e58f98d562025-08-20T04:00:50ZengMDPI AGApplied Sciences2076-34172025-07-011515821310.3390/app15158213State of Health Estimation for Lithium-Ion Batteries Based on TCN-RVMYu Zhao0Yonghong Xu1Yidi Wei2Liang Tong3Yiyang Li4Minghui Gong5Hongguang Zhang6Baoying Peng7Yinlian Yan8College of Mechanical and Electrical Engineering, Beijing Information Science and Technology University, Beijing 100192, ChinaCollege of Mechanical and Electrical Engineering, Beijing Information Science and Technology University, Beijing 100192, ChinaSchool of Mechanical Engineering, Beijing Institute of Technology, Beijing 100081, ChinaCollege of Mechanical and Electrical Engineering, Beijing Information Science and Technology University, Beijing 100192, ChinaCollege of Mechanical and Electrical Engineering, Beijing Information Science and Technology University, Beijing 100192, ChinaCollege of Mechanical and Electrical Engineering, Beijing Information Science and Technology University, Beijing 100192, ChinaCollege of Mechanical and Energy Engineering, Beijing University of Technology, Beijing 100124, ChinaCollege of Mechanical and Electrical Engineering, Beijing Information Science and Technology University, Beijing 100192, ChinaCollege of Mechanical and Energy Engineering, Beijing University of Technology, Beijing 100124, ChinaA State of Health (SOH) estimation of lithium-ion batteries is a core function of battery management systems, directly affecting the safe operation, lifetime prediction, and economic efficiency of batteries. However, existing methods still face challenges in balancing feature robustness and model generalization ability; for instance, some studies rely on features whose physical correlation with SOH lacks strict verification, or the models struggle to simultaneously capture the temporal dynamics of health factors and nonlinear mapping relationships. To address this, this paper proposes an SOH estimation method based on incremental capacity (IC) curves and a Temporal Convolutional Network—Relevance Vector Machine (TCN-RVM) model, with core innovations reflected in two aspects. Firstly, five health factors are extracted from IC curves, and the strong correlation between these features and SOH is verified using both Pearson and Spearman coefficients, ensuring the physical rationality and statistical significance of feature selection. Secondly, the TCN-RVM model is constructed to achieve complementary advantages. The dilated causal convolution of TCN is used to extract temporal local features of health factors, addressing the insufficient capture of long-range dependencies in traditional models; meanwhile, the Bayesian inference framework of RVM is integrated to enhance the nonlinear mapping capability and small-sample generalization, avoiding the overfitting tendency of complex models. Experimental validation is conducted using the lithium-ion battery dataset from the University of Maryland. The results show that the mean absolute error of the SOH estimation using the proposed method does not exceed 0.72%, which is significantly superior to comparative models such as CNN-GRU, KELM, and SVM, demonstrating higher accuracy and reliability compared with other models.https://www.mdpi.com/2076-3417/15/15/8213lithium-ion batteryhealth indicatorsTCN-RVM algorithmSOH estimation |
| spellingShingle | Yu Zhao Yonghong Xu Yidi Wei Liang Tong Yiyang Li Minghui Gong Hongguang Zhang Baoying Peng Yinlian Yan State of Health Estimation for Lithium-Ion Batteries Based on TCN-RVM Applied Sciences lithium-ion battery health indicators TCN-RVM algorithm SOH estimation |
| title | State of Health Estimation for Lithium-Ion Batteries Based on TCN-RVM |
| title_full | State of Health Estimation for Lithium-Ion Batteries Based on TCN-RVM |
| title_fullStr | State of Health Estimation for Lithium-Ion Batteries Based on TCN-RVM |
| title_full_unstemmed | State of Health Estimation for Lithium-Ion Batteries Based on TCN-RVM |
| title_short | State of Health Estimation for Lithium-Ion Batteries Based on TCN-RVM |
| title_sort | state of health estimation for lithium ion batteries based on tcn rvm |
| topic | lithium-ion battery health indicators TCN-RVM algorithm SOH estimation |
| url | https://www.mdpi.com/2076-3417/15/15/8213 |
| work_keys_str_mv | AT yuzhao stateofhealthestimationforlithiumionbatteriesbasedontcnrvm AT yonghongxu stateofhealthestimationforlithiumionbatteriesbasedontcnrvm AT yidiwei stateofhealthestimationforlithiumionbatteriesbasedontcnrvm AT liangtong stateofhealthestimationforlithiumionbatteriesbasedontcnrvm AT yiyangli stateofhealthestimationforlithiumionbatteriesbasedontcnrvm AT minghuigong stateofhealthestimationforlithiumionbatteriesbasedontcnrvm AT hongguangzhang stateofhealthestimationforlithiumionbatteriesbasedontcnrvm AT baoyingpeng stateofhealthestimationforlithiumionbatteriesbasedontcnrvm AT yinlianyan stateofhealthestimationforlithiumionbatteriesbasedontcnrvm |