State of temperature detection of Li-ion batteries by intelligent gray box model

Abstract

Li-Ion batteries are among the key enablers of more sustainable use of energy. However, they need to be supervised and undergo continuous maintenance to assure safety and longevity. This paper focuses on the sensorless detection of the State of Temperature (SOT) of the Li-ion batteries during the operational life cycle of the battery irrespective of its state of charge. The paper presents the new Intelligent Gray Box Model (IGBM) to detect the SOT of Li-ion cells: that combines the three most powerful diagnostic tools Electrochemical Impedance Spectroscopy (EIS), Equivalent Circuit Model (ECM), and Artificial Neural Network Classifier (NNC). The work introduces the experimental test bench capable of emulating real-world and embedded constraints to conduct EIS onboard, its data preprocessing, and useful information extraction for the entire frequency spectrum. Furthermore, this paper presents a new hybrid parameter identification that combines the Whale Optimization Algorithm (WOA) and Levenberg Marquardt algorithm (LM) to identify the fractional order ECM. Finally, a neural network classifier is designed, optimized, and compared with different feature scaling techniques to evaluate its accuracy and robustness to detect and classify exact battery temperatures in real time from experimental data.