Structural Optimization of Large Part of Machine Tools Based on BP Neural Network

A design method of structural optimization of large part of machine tools was proposed based on neural network and finite element method. With the pillar of XK713B numerically-controlled boring and milling machine as an example, the BP neural network model corresponding to structure parameters and dynamic characteristics of the pillar was built, and rapid sampling of the neural network model was carried out with the help of APDL language. Then, optimization of the design variables was done and satisfied results were obtained. Calculation results show that, by using the neural network model, error between calculation results and expectations is less than 5%.