Feasibility of differentiating defect signals of ultrasonic testing for laser weld based on independent component analysis theory

作     者：GUO Liwei,GANG Tie,and LI Jinquan State Key Laboratory of Advanced Welding Production Technology,Harbin Institute of Technology,Harbin 150001,China GUO Liwei,GANG Tie,and LI Jinquan State Key Laboratory of Advanced Welding Production Technology,Harbin Institute of Technology,Harbin 150001,China

作者机构：Harbin Inst Technol State Key Lab Adv Welding Prod Technol Harbin 150001 Peoples R China 

出 版 物：《Rare Metals》 (稀有金属（英文版）)

年 卷 期：2007年第26卷第S1期

页      面：56-60页

核心收录：

学科分类：080503[工学-材料加工工程] 08[工学] 0805[工学-材料科学与工程（可授工学、理学学位）] 0802[工学-机械工程] 080201[工学-机械制造及其自动化] 

主　　题：independent component analysis automatic ultrasonic testing signal processing 

摘      要：Separating noise from observed signals was *** the small defect in the T-shape laser welding joint was inspected by ultrasonic testing system adopting independent component analysis(ICA) theory to process the *** principle of automatic ultrasonic testing signals processing and negentropy law of ICA were *** experimental data were processed using relative analysis tools and results showed that the ICA could separate defects signals from noise effectively in laboratory.