LS-SVM-based surface roughness prediction model for a reflective fiber optic sensor  

作　　者：Li Fu Jun Luo Weimin Chen Xueming Liu Dong Zhou zhongling Zhang Sheng Li 付丽;罗钧;陈伟民;刘学明;周东;张中玲;李胜(Key Lab of Optoelectronic Technology ＆ Systems of Ministry of Education, Chongqing University, Chongqing 400044, China 5011 District Measurement Station of Weapon Industry, Chongqing 400050, China)

机构地区：[1]Key Lab of Optoelectronic Technology&Systems of Ministry of Education,Chongqing University,Chongqing 400044,China [2]5011 District Measurement Station of Weapon Industry,Chongqing 400050,China

出　　处：《Chinese Optics Letters》2017年第9期61-65,共5页中国光学快报（英文版）

摘　　要：Reflective fiber optic sensors have advantages for surface roughness measurements of some special workpieces,but their measuring precision and efficiency need to be improved further. A least-squares support vector machine（LS-SVM）-based surface roughness prediction model is proposed to estimate the surface roughness, Ra, and the coupled simulated annealing（CSA） and standard simplex（SS） methods are combined for the parameter optimization of the mode. Experiments are conducted to test the performance of the proposed model, and the results show that the range of average relative errors is-4.232%–2.5709%. In comparison with the existing models, the LS-SVM-based model has the best performance in prediction precision, stability, and timesaving.Reflective fiber optic sensors have advantages for surface roughness measurements of some special workpieces,but their measuring precision and efficiency need to be improved further. A least-squares support vector machine（LS-SVM）-based surface roughness prediction model is proposed to estimate the surface roughness, Ra, and the coupled simulated annealing（CSA） and standard simplex（SS） methods are combined for the parameter optimization of the mode. Experiments are conducted to test the performance of the proposed model, and the results show that the range of average relative errors is-4.232%–2.5709%. In comparison with the existing models, the LS-SVM-based model has the best performance in prediction precision, stability, and timesaving.

关 键 词：SVM LS-SVM-based surface roughness prediction model for a reflective fiber optic sensor 

分 类 号：TP212[自动化与计算机技术—检测技术与自动化装置]