Optimization of Generator Stator End Winding Structure Based on Improved PSO and SVM

The selection of parameters in the support vector machine (SVM) approximation model plays an important role in the performance of the model. Therefore, the support vector machine parameters need to be optimized. Because the particle swarm algorithm is easy to be premature and easy to fall into the local optimal solution, the improved particle swarm optimization algorithm is used to optimize the parameters, and the support vector machine approximation model with optimal parameters is established. Finally, the support vector machine approximation model of optimal parameters and particle swarm optimization algorithm are combined and used in the optimization of stator end winding structure of large steam turbine generator. The validity of the method is verified by the analysis of the results, and good optimization results are obtained.