Title :
Intelligent prediction of surface roughness of milling aluminium alloy based on least square support vector machine
Author_Institution :
Key Lab. of Numerical Control of Jiangxi Province, Jiujiang Univ., Jiujiang, China
Abstract :
An intelligent model is developed to predict the surface roughness of aluminium alloy in the milling operation based on least square support vector machine (LS-SVM). The Taguchi´s design of experiment was adopted to provide enough training information with minimal experiment times. The present prediction model is to analyze the effects of condition factors, such as spindle speed, feed rate, etc. on the surface roughness (Ra). The tests have been conducted to verify the LS-SVM model, and the average prediction error is about 8%. It means the model is capable to predict the surface roughness well.
Keywords :
Taguchi methods; aluminium alloys; design of experiments; least squares approximations; milling; support vector machines; surface roughness; Taguchi design of experiment; aluminium alloy milling; intelligent prediction; least square support vector machine; prediction error; surface roughness; Aluminum alloys; Feeds; Least squares methods; Machine intelligence; Milling; Predictive models; Rough surfaces; Support vector machines; Surface roughness; Testing; Aluminium alloy; Least square SVM (LS-SVM); Prediction model; Support vector machine(SVM); Surface roughness;
Conference_Titel :
Control and Decision Conference (CCDC), 2010 Chinese
Conference_Location :
Xuzhou
Print_ISBN :
978-1-4244-5181-4
Electronic_ISBN :
978-1-4244-5182-1
DOI :
10.1109/CCDC.2010.5498687
