Data‐Driven Hybrid Internal Temperature Estimation Approach for Battery Thermal Management

Abstract

Temperature is a crucial state to guarantee the reliability and safety of a battery during operation. The ability to estimate battery temperature, especially the internal temperature, is of paramount importance to the battery management system for monitoring and thermal control purposes. In this paper, a data-driven approach combining the RBF neural network (NN) and the extended Kalman filter (EKF) is proposed to estimate the internal temperature for lithium-ion battery thermal management. To be specific, the suitable input terms and the number of hidden nodes for the RBF NN are first optimized by a two-stage stepwise identification algorithm (TSIA). Then, the teaching-learning-based optimization (TLBO) algorithm is developed to optimize the centres and widths in every neuron of basis function. After optimizing the RBF NN model, a battery lumped thermal model is adopted as the state function with the EKF to filter out the outliers of the RBF model and reduce the estimation error. This data-driven approach is validated under four different conditions in comparison with the linear NN models. The experimental results demonstrate that the proposed RBF data-driven approach outperforms the other approaches and can be extended to other types of batteries for thermal monitoring and management.

Gaussian Process Regression With Automatic Relevance Determination Kernel for Calendar Aging Prediction of Lithium-Ion Batteries

“…After training, the dataset from 'Group 2' (yellow cases) is used to verify the effectiveness of the proposed model. Moreover, to evaluate the prediction performance of the data-driven model, several key quantitative metrics are adopted in this study [31]. Here N is the total number of predicted points, y j andỹ j stand for each actual capacity data and each predicted value, respectively.…”

“…1) Maximum absolute error (MAE): By defining as (1), MAE is used to illustrate the maximum difference between the predicted and real test values. The larger the MAE values, the poorer the predicted accuracy is [31].…”

“…2) Root mean square error (RMSE): RMSE is another widely used metric to measure the overall difference between the predicted values and real test values. By defining as (2), the closer RMSE reaches to 0, the better the prediction accuracy is achieved [31].…”

Simplification strategy research on hard‐cased Li‐ion battery for thermal modeling

“…According to the number of states, the former can be categorized into one state, two state, and multi‐state lumped thermal models. The model parameters are obtained with least square algorithm, or machine learning methods, such as linear neural network and RBF neural network . Due to its simple structure and ease of implementation, the lumped thermal models are usually embedded in the battery management system (BMS) for real‐time temperature estimation or coupled to other physical fields for more precise studies .…”

“…The model parameters are obtained with least square algorithm, 31,33,38 or machine learning methods, such as linear neural network 39 and RBF neural network. 40 Due to its simple structure and ease of implementation, the lumped thermal models are usually embedded in the battery management system (BMS) for real-time temperature estimation 33,38 or coupled to other physical fields for more precise studies. 34,41 For example, the electro-thermal-agingcoupled model is established to capture the nonlinear electrical, thermal, and aging dynamics of a Lion-ion battery.…”