Thermal runaway accidents in lithium batteries necessitate effective thermal management. This study proposes a liquid cooling plate with internal spiral-array fins and investigates its performance under electrochemically coupled temperature-dependent heat generation conditions. A pseudo-two-dimensional (P2D) electrochemical model simulates battery discharge at 0.5C–2C rates to obtain heat generation characteristics, which serve as inputs for a fluid–solid coupled heat transfer model. The effects of spiral fin parameters—pitch (S) and height (h)—are systematically analyzed. Three main contributions are presented: spiral fins induce secondary flow that disrupts thermal boundary layer development and enhances fluid mixing, with smaller pitch extending the flow path and increasing radial velocity; a performance evaluation criterion (PEC)-based analysis identifies the optimal parameter range that balances heat transfer enhancement and pressure drop penalty; and increasing the fin height raises the finned area proportion and swirl intensity, suppressing bypass flow and strengthening heat transfer, with effects more pronounced at higher discharge rates. Key quantitative findings show that at 2C discharge, the optimized configuration (S = 3 mm, h = 0.5 mm) achieves a comprehensive performance index of 2.19 and reduces the maximum temperature by 25.32% compared to smooth channels. This work integrates electrochemical and thermal models to provide a new approach for optimizing spiral fin microchannels tailored to lithium battery operation.

The continuously improving power density of Li-ion batteries and the widespread application of fast charging and discharging have rendered thermal management an increasingly critical task. Cold plates are among the most important means for such a task, and their channel structure significantly affects battery performance. Aiming to further improve the thermohydraulic performance of cold plate, this study proposes a cold plate with sinusoidal wave-shaped channel. Using channel quantity, amplitude, wavelength, diameter, and coolant mass flow rate as variables, the orthogonal experimental scheme is employed to design combinations of different variables for numerical simulation. The numerical simulation results are used to train a deep neural network for cold plate performance prediction. The trained neural network can accurately predict the maximum temperature, comprehensive performance indicators, and entropy generation rate with errors below 5.0%, 5.0%, and 10.0%, respectively. Multi-objective optimization design (MOOD) is implemented by combining a deep neural network with the NSGA-II genetic optimization, yielding two sets of Pareto fronts as follows: one for maximizing comprehensive performance indicator and minimizing entropy generation rate, and the other for minimizing maximum temperature and entropy generation rate, and TOPSIS decision points are provided. This study provides a new method and valuable MOOD results for the thermal management of Li-ion batteries and cold plate engineering while offering theoretical guidance for practical applications.