Surface Roughness Modeling Based On Improved MEP Algorithm And Multi- Objective Optimization Of Processing Parameters

The selection of machining parameters is not only directly related to the quality of processing, but also has a significant impact on processing efficiency, the performance of machine tools and cutter tools and energy consumption. In traditional NC machining process, it is often difficult to get the ideal result through the processing handbook and the experience of the workers. Although there were some research on optimization of machining parameters, but commonly through the empirical formula and lacking physical modeling of the actual process, the optimization results often differ from the actual value with a considerable degree of discrepancy. Therefore, this paper makes a deep research on physical modeling and optimization of machining parameters in NC turning process.Proposed an adaptive multi-population MEP algorithm named IMEP and built a surface roughness model based on IMEP algorithm. Firstly, describes the basic principle of MEP algorithm is studied introduces the MEP algorithm, analyzes the advantages and disadvantages of the MEP algorithm, the MEP algorithm is improved in terms of fitness function, crossover and mutation probability, crossover strategy, multi-population and parallel computation. The IMEP algorithm is tested. Results show that the IMEP algorithm is superior to MEP algorithm in terms of convergence speed, accuracy, and evolutionary efficiency. According to the NC turning process, the surface roughness model based on IMEP algorithm is established. The surface roughness model is verified. The results show that the IMEP algorithm can establish an explicit model of surface roughness with high efficiency and high precision.Put forward the improvement with the nondominated sorting genetic algorithm Ⅱ (NSGA-Ⅱ) and realized the multi-objective optimization model of high speed and high accuracy. For multi-objective optimization problems in machining process, using the basic principle of NSGA-Ⅱ algorithm, improving the crossover operator, mutation operator and adding parallel computing to NSGA-Ⅱ to improve NSGA-Ⅱ algorithm, (the improved algorithm is defined as NSGA-Ⅱ-Improve). The NSGA-Ⅱ-Improve algorithm is tested, results show that NSGA-Ⅱ-Improve algorithm outperforms NSGA-Ⅱ algorithm in operating efficiency, the convergence metric and diversity metric, and can obtain a greater range of Pareto solutions.Do research on the application of IMEP algorithm and NSGA-Ⅱ-Improve algorithm in the actual machining process. Design orthogonal experiments to obtain the surface roughness, building surface roughness physical model by IMEP algorithm, and use ANOVA to find the influence of machining parameters on surface roughness. Using NSGA-Ⅱ-Improve algorithm do multi-objective optimization with two objectives:one is the surface roughness model built by IMEP and the other is energy consumption model, the optimized machining parameters are verified by experiments. The results show that the proposed algorithm can efficiently solve the machining parameter optimization problem.