Modeling And Machining Optimization Of Energy Consumption For CNC Machine Tools

Environmental issues are gaining increasing attention worldwide,and their environmental impact is also growing due to increasing energy consumption.Concerns about energy conservation and emission reduction have prompted the industry to start a wave of green manufacturing.As the basis of manufacturing,CNC machine tools have a wide range of use and long-life cycle,which makes the optimization of energy consumption during machine tool use an important topic in academic research and industrial applications.Related research shows that the current energy consumption of CNC machine tools is very low,so the research on the energy consumption of CNC machine tools has great potential.In this research,the energy consumption model of the five-axis CNC machine tool is established.Based on the model,the optimization method of the machining process is proposed,and the energy consumption model is applied to the double five-axis mirror milling equipment.On the basis of fully studying and understanding the energy consumption characteristics of machine tools,the energy consumption of CNC machining center is divided into two parts: machine tool un-load power model and milling power model.The key to energy consumption modeling under no-load conditions is the modeling of the various components of the system,including the spindle system,the feed system,the auxiliary system,and the measurement of the basic power.The milling energy consumption modeling is combined with the machine learning method,and the processing parameters are selected as the features.The Gradient Boosting Regression Tree(GBRT)algorithm is used as the fitting model to establish a data-driven milling energy consumption model.Based on the orthogonal experiment,the influence of processing parameters on the energy consumption of the milling was studied.The energy modeling experiment was carried out on a five-axis machining center,and the effectiveness of the model was verified by actually machining a multifeature part.Based on the above energy consumption model,a processing parameter optimization model for machining and a sequence optimization model for multiple features are established.By using an intelligent optimization algorithm,the optimization of milling parameters and feature sequences is realized respectively.Among them,the multi-objective genetic algorithm is used to optimize the processing parameters.The energy consumption per unit volume and the total processing time are the objective functions.Finally,the Pareto solution set that satisfies the constraints is obtained,which can be selected according to the actual processing conditions.The processing sequence optimization is transformed into a classic Traveling Salesman Problem(TSP).The city coordinate is the actual position of the feed axis corresponding to the center of the feature,and the corresponding distance matrix is combined with the energy consumption model to update to the energy consumption matrix.The function is the sum of the energy consumption of the air milling generated when the adjacent machining features are converted,and the optimal processing sequence is obtained by using the genetic algorithm to solve this problem.Further,the modeling method and formula of the five-axis energy consumption model are applied to the double five-axis mirror milling equipment.Since the application field of mirror milling equipment is mainly for milling thin-walled aluminum alloy parts,and the energy consumption of the equipment components is complicated,so the energy consumption of milling in the energy consumption is small and difficult to measure.This reaserch focuses on the establishment of the energy consumption model in the un-load state of the double five-axis mirror milling.The feed rate and corresponding duration are solved from the NC code by the feed velocity decomposition and kinematics inverse solution.Thereby energy consumption prediction is realized based on the established energy consumption model.