Prognosis Of Lithium-Ion Battery Health with Hybrid EKF-CNN+LSTM Model Using Differential Capacity

2025-04-16

AI Summary

Lithium-ion batteries exhibit unclear degradation mechanisms and low State of Health (SOH) estimation accuracy under multi-rate operating conditions. Method: This paper proposes a differential capacity analysis (DCA)-based degradation modeling and prediction framework. We innovatively design an EKF-CNN-LSTM hybrid model to enable DCA-feature-driven, end-to-end SOH estimation—the first such approach. A Peak Identification Method (PIM) is introduced to quantify multidimensional degradation indicators, and systematic DCA-based analysis reveals accelerated aging mechanisms under fast charging (0.2C–1.5C) and discharging (0.5C–1.6C). Results: Experiments demonstrate that the proposed method achieves MSE and RMSE both below 0.001%, significantly outperforming state-of-the-art approaches. Furthermore, comparative analysis confirms superior degradation robustness of LiFePO₄ over NCA across wide load ranges.

Technology Category

• Cognitive Modeling & Cognitive Systems: Conceptual Inference and Reasoning
• Machine Learning: Life-Long and Continual Learning
• Intelligent Robots: State Estimation

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Systems and Infrastructure for Web, Mobile and WoT: Energy management for devices in mobile Web and WoT environments

Abstract

Battery degradation is a major challenge in electric vehicles (EV) and energy storage systems (ESS). However, most degradation investigations focus mainly on estimating the state of charge (SOC), which fails to accurately interpret the cells' internal degradation mechanisms. Differential capacity analysis (DCA) focuses on the rate of change of cell voltage about the change in cell capacity, under various charge/discharge rates. This paper developed a battery cell degradation testing model that used two types of lithium-ions (Li-ion) battery cells, namely lithium nickel cobalt aluminium oxides (LiNiCoAlO2) and lithium iron phosphate (LiFePO4), to evaluate internal degradation during loading conditions. The proposed battery degradation model contains distinct charge rates (DCR) of 0.2C, 0.5C, 1C, and 1.5C, as well as discharge rates (DDR) of 0.5C, 0.9C, 1.3C, and 1.6C to analyze the internal health and performance of battery cells during slow, moderate, and fast loading conditions. Besides, this research proposed a model that incorporates the Extended Kalman Filter (EKF), Convolutional Neural Network (CNN), and Long Short-Term Memory (LSTM) networks to validate experimental data. The proposed model yields excellent modelling results based on mean squared error (MSE), and root mean squared error (RMSE), with errors of less than 0.001% at DCR and DDR. The peak identification technique (PIM) has been utilized to investigate battery health based on the number of peaks, peak position, peak height, peak area, and peak width. At last, the PIM method has discovered that the cell aged gradually under normal loading rates but deteriorated rapidly under fast loading conditions. Overall, LiFePO4 batteries perform more robustly and consistently than (LiNiCoAlO2) cells under varying loading conditions.

Problem

• Estimating battery health degradation using hybrid EKF-CNN+LSTM model.
• Analyzing internal degradation mechanisms via differential capacity analysis (DCA).
• Comparing performance of LiFePO4 and LiNiCoAlO2 batteries under varying loads.

Innovation

• Hybrid EKF-CNN+LSTM model for battery health
• Differential capacity analysis under varied charge rates
• Peak identification technique for degradation assessment