Affiliations: [a] School of Automation Engineering, University of Electronic, Science and Technology of China, Chengdu, Sichuan, China | [b] China Aerodynamics Research & Development Center, Mianyang, Sichuan, China | [c] Nuclear Power Institute of China, Chengdu, Sichuan, China
Correspondence:
[*]
Corresponding author: Chun Yin, School of Automation Engineering, University of Electronic, Science and Technology of China, Chengdu 611731, Sichuan, China. E-mail:chunyin@uestc.edu.cn;yinchun.86416@163.com
Abstract: Eddy current pulsed thermography (ECPT) has been applied
for a wide range of conductive materials. The enhancement of thermography to
detect the defects is also important. This paper proposes an independent
component analysis (ICA) fusion method based fuzzy algorithm to process the
thermography images. In ICA, three kinds of contrast function are applied to
obtain the different ICs respectively. Then, the corresponding fused ICs are
obtained by the fuzzy fusion algorithm. Meanwhile, the kurtosis of each ICs
before and after fusion are computed to evaluate the performance of the
proposed method. In addition, an experiment is utilized to show the benefits
of the proposed ICA fusion method.
