Early Remaining Useful Life Prediction for Lithium-Ion Batteries Using a Gaussian Process Regression Model Based on Degradation Pattern Recognition
Lithium-ion batteries experience nonlinear degradation characteristics during long-term operation. Accurate estimation of their remaining useful life (RUL) is of significant importance for early fault diagnosis and residual value evaluation. However, existing RUL prediction approaches often suffer f...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-06-01
|
| Series: | Batteries |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2313-0105/11/6/221 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850156173122076672 |
|---|---|
| author | Linlin Fu Bo Jiang Jiangong Zhu Xuezhe Wei Haifeng Dai |
| author_facet | Linlin Fu Bo Jiang Jiangong Zhu Xuezhe Wei Haifeng Dai |
| author_sort | Linlin Fu |
| collection | DOAJ |
| description | Lithium-ion batteries experience nonlinear degradation characteristics during long-term operation. Accurate estimation of their remaining useful life (RUL) is of significant importance for early fault diagnosis and residual value evaluation. However, existing RUL prediction approaches often suffer from limited accuracy and insufficient specificity. To address these limitations, this study proposes an RUL prediction methodology based on Gaussian process regression, which incorporates degradation pattern recognition and auxiliary features derived from knee points. First, 9 health-related features are extracted from the first 100 charge/discharge cycles of the battery. Based on these extracted features, clustering and classification techniques are employed to categorize the batteries into three distinct degradation patterns. Moreover, feature importance is assessed to identify and eliminate redundant indicators, thereby enhancing the relevance of the feature set for prediction. Subsequently, for each degradation pattern, GPR-based models with composite kernel functions are constructed by integrating knee point positions and their corresponding slopes. The model hyperparameters are further optimized through the particle swarm optimization (PSO) algorithm to improve the adaptability and generalization capability of the predictive models. Experimental results demonstrate that the proposed method achieves a high level of predictive accuracy, with an overall mean absolute percentage error (MAPE) of approximately 8.70%. Furthermore, compared with conventional prediction methods, the proposed approach exhibits superior performance and can serve as an effective evaluation tool for diverse application scenarios, including lithium-ion battery health monitoring, early prognostics, and echelon utilization. |
| format | Article |
| id | doaj-art-d1c59f910d4c4c6696ba25bbfb89d935 |
| institution | OA Journals |
| issn | 2313-0105 |
| language | English |
| publishDate | 2025-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Batteries |
| spelling | doaj-art-d1c59f910d4c4c6696ba25bbfb89d9352025-08-20T02:24:39ZengMDPI AGBatteries2313-01052025-06-0111622110.3390/batteries11060221Early Remaining Useful Life Prediction for Lithium-Ion Batteries Using a Gaussian Process Regression Model Based on Degradation Pattern RecognitionLinlin Fu0Bo Jiang1Jiangong Zhu2Xuezhe Wei3Haifeng Dai4School of Automotive Studies, Tongji University, Shanghai 201804, ChinaSchool of Automotive Studies, Tongji University, Shanghai 201804, ChinaSchool of Automotive Studies, Tongji University, Shanghai 201804, ChinaSchool of Automotive Studies, Tongji University, Shanghai 201804, ChinaSchool of Automotive Studies, Tongji University, Shanghai 201804, ChinaLithium-ion batteries experience nonlinear degradation characteristics during long-term operation. Accurate estimation of their remaining useful life (RUL) is of significant importance for early fault diagnosis and residual value evaluation. However, existing RUL prediction approaches often suffer from limited accuracy and insufficient specificity. To address these limitations, this study proposes an RUL prediction methodology based on Gaussian process regression, which incorporates degradation pattern recognition and auxiliary features derived from knee points. First, 9 health-related features are extracted from the first 100 charge/discharge cycles of the battery. Based on these extracted features, clustering and classification techniques are employed to categorize the batteries into three distinct degradation patterns. Moreover, feature importance is assessed to identify and eliminate redundant indicators, thereby enhancing the relevance of the feature set for prediction. Subsequently, for each degradation pattern, GPR-based models with composite kernel functions are constructed by integrating knee point positions and their corresponding slopes. The model hyperparameters are further optimized through the particle swarm optimization (PSO) algorithm to improve the adaptability and generalization capability of the predictive models. Experimental results demonstrate that the proposed method achieves a high level of predictive accuracy, with an overall mean absolute percentage error (MAPE) of approximately 8.70%. Furthermore, compared with conventional prediction methods, the proposed approach exhibits superior performance and can serve as an effective evaluation tool for diverse application scenarios, including lithium-ion battery health monitoring, early prognostics, and echelon utilization.https://www.mdpi.com/2313-0105/11/6/221lithium-ion batteryearly life predictionhealth features extractiondegradation pattern recognitionGaussian process regressionhyperparameter optimization |
| spellingShingle | Linlin Fu Bo Jiang Jiangong Zhu Xuezhe Wei Haifeng Dai Early Remaining Useful Life Prediction for Lithium-Ion Batteries Using a Gaussian Process Regression Model Based on Degradation Pattern Recognition Batteries lithium-ion battery early life prediction health features extraction degradation pattern recognition Gaussian process regression hyperparameter optimization |
| title | Early Remaining Useful Life Prediction for Lithium-Ion Batteries Using a Gaussian Process Regression Model Based on Degradation Pattern Recognition |
| title_full | Early Remaining Useful Life Prediction for Lithium-Ion Batteries Using a Gaussian Process Regression Model Based on Degradation Pattern Recognition |
| title_fullStr | Early Remaining Useful Life Prediction for Lithium-Ion Batteries Using a Gaussian Process Regression Model Based on Degradation Pattern Recognition |
| title_full_unstemmed | Early Remaining Useful Life Prediction for Lithium-Ion Batteries Using a Gaussian Process Regression Model Based on Degradation Pattern Recognition |
| title_short | Early Remaining Useful Life Prediction for Lithium-Ion Batteries Using a Gaussian Process Regression Model Based on Degradation Pattern Recognition |
| title_sort | early remaining useful life prediction for lithium ion batteries using a gaussian process regression model based on degradation pattern recognition |
| topic | lithium-ion battery early life prediction health features extraction degradation pattern recognition Gaussian process regression hyperparameter optimization |
| url | https://www.mdpi.com/2313-0105/11/6/221 |
| work_keys_str_mv | AT linlinfu earlyremainingusefullifepredictionforlithiumionbatteriesusingagaussianprocessregressionmodelbasedondegradationpatternrecognition AT bojiang earlyremainingusefullifepredictionforlithiumionbatteriesusingagaussianprocessregressionmodelbasedondegradationpatternrecognition AT jiangongzhu earlyremainingusefullifepredictionforlithiumionbatteriesusingagaussianprocessregressionmodelbasedondegradationpatternrecognition AT xuezhewei earlyremainingusefullifepredictionforlithiumionbatteriesusingagaussianprocessregressionmodelbasedondegradationpatternrecognition AT haifengdai earlyremainingusefullifepredictionforlithiumionbatteriesusingagaussianprocessregressionmodelbasedondegradationpatternrecognition |