论文部分内容阅读
In this paper,a model which is based on SVM is established for forecasting the surface properties of steels after laser phase-transformation hardened.A new approach of selecting learning parameters is proposed on analysis of model structure,and an algorithm of sequential minimal optimization (SMO) is used for optimizing the model parameters.The optimized model is applied for forecasting and verifying surface properties of steels after laser phase-transformation hardening with 15 different kinds of processing parameters.Comprise to the actual experimental values,the forecasting relative error is only 2.5749%.The result shows that SVM forecasting model has high accuracy and good generalized performance and it could be used for drawing up the process parameters of laser phase-transformation hardening.