Research On Energy Consumption Prediction Model Of CNC Milling Machine Considering Tool Wear

Environmental problems brought about by energy consumption have attracted widespread attention.The manufacturing industry consumes a lot of energy,and the continuous discharge of pollutants such as waste water and exhaust gas has caused a huge impact on the environment.CNC machine tool processing is one of the important ways to complete parts processing.An accurate and effective machine tool energy consumption prediction model can meet the needs of machine tool energy efficiency evaluation and energy consumption optimization.However,in the machining process,tool wear will not only affect the energy consumption of CNC machine tools,but also affect the machining quality and machining accuracy of parts.Therefore,it is of great significance to consider tool wear into the energy consumption prediction model of CNC milling machine.This paper first analyzes the energy consumption of CNC milling machine,and divides the energy consumption of CNC milling machine into idling energy consumption,air feed energy consumption,basic energy consumption,auxiliary system energy consumption and material removal energy consumption.The above energy consumption characteristics are analyzed,and power models of the above energy consumption are established respectively.Then,the energy consumption time of each energy-consuming component is established according to the CNC code,so as to construct the energy consumption model of the CNC milling machine without considering the tool wear.Then,the mechanism of tool wear is analyzed,and the extraction process of the maximum wear amount of the tool flank based on artificial intelligence machine vision technology is proposed.This method is easy to operate and can achieve results close to the extraction method based on metallographic microscope.The effects of tool wear,rotational speed,feed rate and depth of cut on the material removal power of CNC milling machines were analyzed by response surface methodology.It can be seen from the variance analysis and response surface method that tool wear has a significant impact on the material removal power of CNC milling machines.Therefore,the tool wear amount,rotational speed,feed rate and cutting depth are used as the input of the material removal power prediction model.A material removal power prediction model of CNC milling machine considering tool wear is established based on Long-Short Term Memory(LSTM)neural network.Finally,the energy consumption prediction model of CNC milling machine considering tool wear is established.Finally,relevant data are obtained through experimental research.Regression analysis was carried out according to the experimental data to obtain the correlation coefficient of idle power and idle feed power.The material removal power prediction model based on LSTM neural network is trained using the experimental data,and finally the material removal power prediction model based on LSTM considering tool wear is obtained.The prediction accuracy of the material removal power prediction model of CNC milling machine based on LSTM neural network is 94.55%.The proposed prediction model is compared with BP neural network,time series neural network and traditional models,and the validity and superiority of the proposed model are verified.