| Abstract |
Efficient electric machinery often need to be accurately thermally conditioned. Heat sinks and heatingsurfaces frequently used to allow for precise temperature control of critical equipment. To tacklethe thermal challenges in the art, different methodologies, such as the parametric or the topology optimization are introduced. Compared to parametric optimization, topology optimization allows for more tailored cooling solutions on intrigue geomteries related to propulsion. Being based on gradient descent algorithm from the machine learning toolbox, topology optimization may suffer from the susceptibility to be trapped in local minimums. In this approach the set up is designed to alleviate the risk for local minimums and instead aim for a more global optimization. For this purpose an artificial intelligence pipeline is scripted to run several gradient descent based topology optimization assessments under a genetic algorithm optimization loop. The resulting geometry shown to substantially improve the cooling ability in the given packaging volume in a light duty ground vehicle. |
