Sub-region Alopex optimization method with RSM for design of permanent magnet machines

Based on an Alopex optimization algorithm and a response surface model (RSM), a hybrid sub-region methodology is presented to solve the optimal design problems of permanent magnet (PM) machines. The Alopex optimization method is processed both in subspace and in global solution space. In order to decrease the computing time, a multi quadric radial basis function (MQRBF) is embedded in the optimization. The proposed method speeds up the convergence rate while keeps the accuracy of the solution. A numerical experiment is given to validate the efficiency and effectiveness of the method.