Study on Basic Experiment and Optimization Prediction Model of Orthogonal Electrolytic Machining of Film Cooling Hole in High Temperature Nickel-Based Alloy Blades

Abstract

The orthogonal test was designed based on high temperature nickel-based alloy Inconel718. The variance analysis was carried out on the test results. The significant factor was determined by the significance test. The model structure was trained by the electrolytic processing test data, and finally the prediction model of the momentum-adaptive learning BP Neural Network is established. The model is used to predict the pore size of stainless steel micropores processed under different processing parameters. The results show that the model has a prediction error of less than 5% and has a strong predictive power.