Research on the prediction of reduction ratio for pore closure in heavy forging stock based on particle swarm optimization and support vector machine

At present, the prediction of reduction ratio for pore closure in heavy forgings stock is limited to the finite element numerical simulation and complex mathematical formula. To make it fit in forgings application, it is proposed that a new forecasting method by using the SVM model to predict the critical reduction ratio of pore closure. Firstly, it is selected that several major factors which affecting pore closure as the input features of SVM. Then, it is optimized that SVM´s nuclear parameters with Particle Swarm Optimization in order to enhance its accuracy. Finally, a SVM model is trained by combining with LIB-SVM toolbox. The model can predict the critical reduction ratio of pore closure in heavy forging quickly in compared with computer simulation results, the correlation coefficient reached almost 85%, and it had a good prediction performance.