Cooling Performance Enhancement and Gaussian Process Regression-Based Multi-Objective Optimisation of a Weapon Turret Control Computer

This study optimised the thermal performance of an air-cooled weapon turret control computer used in military missions by integrating experimental, numerical, and machine learning methods. To address thermal localisation and heat accumulation in high-power-density electronic components, two heat pipes with high effective thermal conductivity were embedded in the heat sink block. Based on numerical predictions, this configuration yielded an 8% thermal enhancement; however, its experimental verification remains a subject for future work. The accuracy of the three-dimensional Computational Fluid Dynamics model was validated within an acceptable error tolerance using experimental data from a physical prototype. To reduce the high computational cost of the parametric design space, Gaussian Process Regression, notable for its probabilistic nature, was employed as a surrogate model instead of traditional artificial neural networks, which tend to overfit small-scale deterministic data. The GPR model successfully mapped the system variance, demonstrating an extremely high coefficient of determination and a minimal margin of error in predicting the maximum chip temperature and system pressure drop. Cross-validation analyses conclusively demonstrated that the model has high generalisation capability without overfitting the dataset. Multi-objective Pareto optimisation was conducted by scanning a dense design grid generated over the trained continuous surrogate model. The optimal balanced design configuration identified along the Pareto front maintained the chip temperature within the safe zone, below the critical operating limit, while significantly reducing aerodynamic resistance on the fan, energy consumption, and noise issues, without compromising the system’s thermal performance. The developed GPR-based methodology offers a stable and reliable optimisation framework that minimises trial-and-error costs in the design of military thermal management systems.