Prediction of Surface Roughness Based on Least Square Support Vector Machine in Low-Frequency Vibration Cutting Process

Wei Wen Du; Li Zhi Gu; Jiao Tao Wang

doi:10.4028/www.scientific.net/KEM.620.592

Paper Titles

FRACAS Based Failure Information Management for High-Speed Train
p.569

Hardware Development of CNC System Based on OMAPL138 and FPGA
p.575

Intelligent Testing System for AC Load Based on PLC
p.581

Precision Measurement and Error Evaluation of Connecting Rod Standard Gauge Block Based on CMM
p.587

Prediction of Surface Roughness Based on Least Square Support Vector Machine in Low-Frequency Vibration Cutting Process
p.592

Fuzzy Self-Tuning PID Controller for Pressure Control in VCM
p.598

A Probability Distribution Model for Optimal Selecting Cooperators in Supply Chains
p.607

A Resilient Novel Compressed-Domain Audio Recognition Method for Anti-Linear Speed Change
p.613

A Sequential Numbering Power Flow Calculation Method for Distribution Network
p.619

HomeKey Engineering MaterialsKey Engineering Materials Vol. 620Prediction of Surface Roughness Based on Least...

Prediction of Surface Roughness Based on Least Square Support Vector Machine in Low-Frequency Vibration Cutting Process

Abstract:

A prediction method based on least square support vector machine is introduced into the surface roughness prediction model in low-frequency vibration cutting. The model is created with low-frequency vibration cutting experiment for the corresponding relationship between vibration parameters and cutting parameters and the workpiece surface roughness. The training sample set is constructed to train regression models of least square support vector machine through experimental data. Identification of training sample set is done to gain the regression parameters a and b. The amplitude of A, vibration frequency f, feed f₁ and spindle speed n are used as the input variable in X_i. Predicted values of surface roughness are forecasted with the model. Evaluation is made with the difference between the predicted value and experiment. Comparison with BP neural network and support vector machine method has shown that the least square support vector machine prediction model works faster than SVM method, the prediction error is about 29% of that by support vector machine, and the prediction accuracy is higher than the BP model.