Prediction on extrusion force in copper-chromium alloy extrusion processing based on projection pursuit regression

The paper proposes a new model to predict the backward extrusion force of Cu-0.75Cr copper alloy based on Projection Pursuit Regression (PPR). Three major technological parameters of the fault plane contraction rate, convex model awl angle and extrusion temperature are regarded as the influencing factors and the extrusion force in the backward extrusion process is regarded as the influencing object. A complex non-linear relationship is established through the PPR model between the influencing factors and the influencing object. The orthogonal test data are used to train the model. The trained model is used to predict the extrusion force of Cu-0.75Cr copper alloy in a certain backward extrusion condition. The result demonstrates that the prediction accuracy and processing speed of the model have greatly been improved and the mean error of the prediction is 0.5%.