State of health estimation for Li-Ion battery using incremental capacity analysis and Gaussian process regression

• Published in: Energy (Oxford) Vol. 190; p. 116467
• Main Authors: Li, Xiaoyu, Yuan, Changgui, Li, Xiaohui, Wang, Zhenpo
• Format: Journal Article
• Language: English
• Published: Oxford Elsevier Ltd 01.01.2020; Elsevier BV
• Subjects: Aging; Batteries; Covariance; Degradation; Energy storage; Feature extraction; Gaussian process; Gaussian regression process; Health; Incremental capacity analysis; Lithium; Lithium batteries; Lithium-ion batteries; Maintenance costs; Predictions; Product safety; Regression analysis; Regression models; Reliability; State of health; Lithium-ion batteries; Incremental capacity analysis; Gaussian regression process; State of health
• ISSN: 0360-5442; 1873-6785
• DOI: 10.1016/j.energy.2019.116467

The state of health for lithium battery is necessary to ensure the reliability and safety for battery energy storage system. Accurate prediction battery state of health plays an extremely important role in guaranteeing safety and minimizing maintenance costs. However, the complex physicochemical characteristics of battery degradation cannot be obtained directly. Here a novel Gaussian process regression model based on the partial incremental capacity curve is proposed. First, an advanced Gaussian filter method is applied to obtain the smoothing incremental capacity curves. The health indexes are then extracted from the partial incremental capacity curves as the input features of the proposed model. Additionally, the mean and the covariance function of the proposed method are applied to predict battery state of health and the model uncertainty, respectively. Four aging datasets from NASA data repository are employed for demonstrating the predictive capability and efficacy of the degradation model using the proposed method. Besides, different initial health conditions of the tested batteries are used to verify the robustness and reliability of the proposed method. Results show that the proposed method can provide accurate and robust state of health estimation. •Gaussian filter method is proposed to smooth the incremental capacity curves.•A novel battery health prognostic method based on partial incremental capacity curve is proposed. .•The health indexes are extracted from partial incremental capacity curves as model input features.•Gaussian progress regression is applied to establish the battery degradation model based on battery health indexes.•Four batteries from NASA database are used to verify the robustness of the proposed method.