Optimization of Aluminum Alloy Rifled Barrel ECM Process Parameters Based on GA-BP Algorithm

Abstract

Electrochemical machining process parameters will affect the surface integrity, surface roughness, service life and other properties of the workpiece. In order to realize high-efficiency and high-quality ECM of aluminum alloy rifled barrel, a method of process parameter optimization based on GA-BP neural network is proposed. The model of BP neural network is established by using MATLAB software. Machining clearance and surface roughness are objective functions. The MSE and linear regression value are analyzed. Genetic algorithm is used to optimize the connection weight and output threshold of BP neural network model. The change of fitness function and the error between predicted value and actual machining value are analyzed. The results show that the GA-BP neural network model can better predict the objective function. The optimal parameters of aluminum alloy rifled barrel ECM are: electrolyte temperature of 29.5±0.2 °C, electrolyte inlet pressure of 1.23±0.02 MPa, power supply voltage of 8.4±0.1 V, and working current of 3600±50 A.