Cost Prediction of Equipment System Using LS-SVM with PSO

Considering the shortcomings of conventional cost prediction methods, least squares support vector machine (LS-SVM) was adopted to establish the cost prediction model of equipment system, which could efficiently solve the problems on the determination of network structure and the phenomena of over-fitting in neural network methods. And due to the importance of parameters optimization in LS-SVM model, particle swarm optimization (PSO) was used to optimize the model parameters. The experiment results show that PSO can quickly obtain the optimal parameters satisfying the precision requirement with a simple calculation, which solves the problem of complex calculation and empiricism in conventional methods. The evaluation on the testing cases shows the LS-SVM model with PSO has a good generalization performance and can be popularized in cost prediction. At last, the experiment on an independent testing case shows the model optimized by PSO has a better prediction performance than by grid search.