Regular Neural Network Based Machining Parameters Optimization Model Of NC Machine Tool

Abstract

Energy consumption process is the basis for energy efficiency improvement of machine tools. Most of the existing researches focus on the static modelling of energy consumption of a machine tool; however, there are a few studies that paid attention to that how process parameters influence the energy consumption of machine tools during processing. It is noted that the process parameters can be selected to reduce energy consumption during machining processes without additional investment. In this paper, a characteristic energy consumption model for NC machine tool was proposed. Then, the mapping rule between process parameters and energy consumption of machine tool was studied, and the model was solved with the regular neural network (RNN). Finally, the result was verified with an experiment of milling the surface of aluminium block, which can effectively improve the energy efficiency of machine tool. The experiment results are shown that regular neural network is used to optimize the process parameters and process the same machining characteristics; we analyze the in machining process of machine tool based on the three cutting parameters, and then, a model of energy consumption. We employ to learn, and use this trained model to select optimal parameters.