AI-based Control and Optimization Algorithm for Synthesis of Electrified Drives

Drive electrification is one major development area to decrease greenhouse emissions. Especially computer aided synthesis and optimization tools are necessary for early drive concept development as well as the concept definition. Depending on the investigation and boundary parameters, the number of possible variants is in the millions. Hence the result quality as well as the investigation time depend significantly on the used optimization and control algorithm of the synthesis. In this paper we introduce an algorithm, comprising of a fuzzy logic in combination with a search space algorithm for controlling a drive system synthesis as well as optimizations. In a first application of the algorithm for a D-segment parallel hybrid topology optimization, the global optimum was found within 1.33 % of all possible simulations. Furthermore, the algorithm was able to find additional solutions close to the global optimum.