Cutting Force Prediction of High-Speed Milling Hardened Steel Based on BP Neural Networks

摘要

It is absolutely necessary to machine the complex mould cavity with micro-ball end mill in high speed machining. Because of the priceless and frangi-bility of the tool, it is significant to predict the cutting force in order to lessen the tool's disrepair, to ensure the quality and to improve efficiency. This paper established the cutting force prediction model based on BP neural network when machining arc surface of hardened steel in high speed. According to the sample set of experimental results used to train and test the neural network, we realize the cutting force prediction and simulation through introducing the elastic grads' decrease method to improve the speed of convergence and precision in the process of cutting. The practice showed that most of the error values are about 5% except some special individual. Obviously, to predict the cutting force is feasible in the process of non-stability and non-linear extremely of cutting through the non-linear neural network.