Optimal Design of Electrical Machine Utilizing Hybrid Kernel Extreme Learning Machine Method

In the field of electrical engineering, aiming at the optimization design of electrical machine, this paper investigates one novel optimization strategy based on hybrid kernel extreme learning machine. To improve the prediction precision of surrogate model, the improved sparrow search algorithm is applied to solve optimization subproblems in the novel optimization strategy. The parallel infill strategy based on the distance density and the minimum response surface criteria is adopted to seek the optimal solution faster. Finally, test functions and the design of electrical machine are used to test the feasibility, practicability and superiority of the proposed optimization strategy.