In this paper, an analogous study of the velocity and temperature profiles inside microchannel cooling plates (with hydraulic diameter of 6 mm), placed on a large pouch-type LiFePO₄ battery, is presented using both the laboratory and simulation techniques. For this, we used reverse engineering (RE), computed tomography (CT) scanning, Detroit Engineering Products (DEP) MeshWorks 8.0 for surface meshing of the cold plate, and STAR CCM+ for steady-state simulation. The numerical study was conducted for 20 A (1C) and 40 A (2C) and different operating temperatures. For experimental work, three heat flux sensors were used and were intentionally pasted at distributed locations, out of which one was situated near the negative tab (anode) and the other was near the positive tab (cathode), because the heat production is high near electrodes and the one near the mid body. Moreover, the realizable k-ε turbulence model in STAR CCM+ is used for simulation of the stream in a microchannel cooling plate, and the computational fluid dynamics (CFD) simulations under constant current (CC) discharge load cases are studied. Later, the validation is conducted with the lab data to ensure sufficient cooling occurs for the required range of temperature. The outcome of this research work shows that as C-rates and ambient temperature increase, the temperature contours of the cooling plates also increase.

This paper investigates the application of hybrid reinforcement learning (RL) models to optimize lithium-ion batteries’ charging and discharging processes in electric vehicles (EVs). By integrating two advanced RL algorithms—deep Q-learning (DQL) and active-critic learning—within the framework of battery management systems (BMSs), this study aims to harness the combined strengths of these techniques to improve battery efficiency, performance, and lifespan. The hybrid models are put through their paces via simulation and experimental validation, demonstrating their capability to devise optimal battery management strategies. These strategies effectively adapt to variations in battery state of health (SOH) and state of charge (SOC) relative error, combat battery voltage aging, and adhere to complex operational constraints, including charging/discharging schedules. The results underscore the potential of RL-based hybrid models to enhance BMSs in EVs, offering tangible contributions towards more sustainable and reliable electric transportation systems.