An improved feature extraction algorithm for automatic defect identification based on eddy current pulsed thermography. (December 2018)

• Record Type: Journal Article
• Authors: Zhu, Peipei; Yin, Chun; Cheng, Yuhua; Huang, Xuegang; Cao, Jiuwen; Vong, Chi-Man; Wong, Pak Kin
• Is Part Of: Mechanical systems and signal processing. Volume 113(2018)
• Page Start: 5
• Page End: 21
• Publication Date: 2018-12
• Subjects: Eddy current pulsed thermography -- Nondestructive testing and evaluation -- Transient thermal response -- Pearson correlation coefficient; Structural dynamics -- Periodicals; Vibration -- Periodicals; Constructions -- Dynamique -- Périodiques; Vibration -- Périodiques; Structural dynamics; Vibration; Periodicals; 621
• DOI: 10.1016/j.ymssp.2017.02.045
• Languages: English
• ISSNs: 0888-3270

Abstract

Highlights: A feature extraction algorithm is used to realize automatic defect identification. It divides the TTRs from in image sequence into several parts by the thresholds. The algorithm finds the low-correlation TTRs by variable interval search. The normalized covariance matrix is calculated to classify the acquired TTRs. The typical TTRs compose one matrix to transform the initial image sequence. Abstract: In this paper, an improved feature extraction algorithm in Eddy Current Pulsed Thermography (ECPT) is developed to realize automatic defect identification. The proposed feature extraction algorithm includes a data block segmentation, a variable interval search, a correlation value classification and a between-class distance decision function. The data block segmentation and variable interval search are firstly combined to reduce the repetitive calculation in automatic defect identification. The classification and between-class distance are used to select the typical features of thermographic sequence. The method is not only able to extract the main image information, but also can reduce the time of thermographic sequence processing to improve the detection efficiency. Experiments and comparisons are provided to demonstrate the capabilities and benefits (i.e. reducing the processing time) of the proposed algorithm in automatic defect identification.