In this study, the grinding force of the creep feed grinding are modeled and forecasted by using the improved back propagation neural (BPN) network. The results show that the grinding energy can be accurately predicted by the application of the grinding force model. Due to the previous paper, the workpiece burning occurs as the grinding energy is greater than the critical grinding. Thus, a judgment for the occurrence of the workpiece burning can be achieved. Comparing with the experimental results, the applied algorithm of the improved BPN network is proved to be effective in forecasting the working conditions of the workpiece burning. Thus, a selection scheme of working conditions in view of the avoidance of the workpiece burning is further developed. Considering the working efficiency, the working conditions are selected to maximum metal removed rate, MRRmax. The results show that a larger size of wheel is available to have a better working efficiency.
Read full abstract