Modeling the performance of electrochemical machining process using free pattern search

Abstract

Electrochemical machining is increasing in importance. It provides an economical and effective way to machine extremely difficult to cut metals and always have a higher machining rate, better surface roughness and control. In this paper, a new predictive approach called Free Pattern Search (FPS) is used to explicitly modeling the performance of electrochemical machining. FPS is based on the expression tree of gene expression programming (GEP) to encode the individuals and express them to a non-determinative tree using a fixed length individual. FPS is inspired by Pattern Search (PS) and Free Search (FS), and it hybrids a scatter manipulator to keep the diversity of the population. Three machining parameters, the feed rate, voltage and flow rate of electrolyte are used as the independent input variables when prediction the material remove rate, surface roughness and over cut. Experiments are conducted to verify the performance of FPS and FPS obtains good results in prediction. The predictive model found by FPS agrees with the experimental results well. The relationships between variables and performance are also showed clearly in the predictive model, and the results shows that they are fit to the experiments well.