Prediction of aircraft vibration environment based on support vector machines with particle swarm optimization algorithm

Abstract

Aiming at the problem of low generalization capacity in predicting the vibration environment of the aircraft platform, a new predicting model combined particle swarm optimization (PSO) algorithm with support vector machine (SVM) is put forward. In the model, PSO is used to determine parameters of penalty factor, loss function and kernel function of support vector machine. The optimized SVM model can solve the practical problems such as small samples, nonlinear and partial infinitesimal. The engineering analysis results show that the SVM model has better predicting performance than the BP model, which proves that the SVM predicting model is feasible and effective.