Multi Objective Optimization of Cutting Process Based on Improved Particle Swarm Optimization Algorithm

Abstract

With the rapid development of machinery industry, the processing parameters which affect on the quality of the products in machining and measuring index also appeared diversified, which makes the study of multi-objective optimization problem is very important. Among the many factors, cutting consumption plays a key role in many indicators, in effect, cutting force and cutting temperature on the quality and performance of products is the most prominent, so this paper takes PCBN tool cutting Cr12MoV steel as the experimental basis, the cutting parameters to optimize the parameters;the cutting force and cutting temperature as the index;with the aid of the BP neural network modeling of cutting force and cutting temperature, at the same time, this paper improved particle swarm optimization algorithm to achieve multiple objectives, provides multi objective optimization parameters more reliable for die steel production process.