Force modeling and forecasting in creep feed grinding using improved BP neural network

摘要

The object of this study is to model and forecast the grinding force for the creep feed grinding process, using back propagation (BP) neural network. The BP neural network is improved by integrating an error distribution function (EDF), a process that proves to be useful in overcoming local minimum problems effectively, so as to find the global minimum solution, and greatly accelerate the convergence speed. Compared with the theoretical force model, the force model implemented by the improved BP neural network is found to be accurate and to predict the grinding force satisfactorily.