RNN Evaluation of Surface Roughness Prediction for Ultrasonic Vibration Cutting of CNC Machine Tools
Ultrasonic vibration cutting is a hot spot in CNC machine tool manufacturing,and ensuring the surface quality of the workpiece is the key goal.Therefore,a prediction and evaluation method of ultrasonic vibration cutting for CNC machine tools based on regression neural network(RNN)is designed,and the milling test is carried out.The research results show that the correlation between the predicted results and the measured results is as high as 0.99,indicating that a good prediction effect is obtained,and the maximum deviation is only 0.05,indicating that the proposed algorithm can guarantee the ideal processing results.Compared with convolutional neural network(CNN),support vector machine(SVM)and Gaussian process regression(GPR),RNN obtained better prediction results.The wear and roughness values were 3.685 and 2.216,respectively,and the R2 value reached 0.975.This research is helpful to be suitable for high-precision manufacturing field and has good development value.
vibration cuttingsurface roughnessregression neural networkwear and tearquality assessment
NETL
NSTL
万方数据
