.png){kind=icon}
.png){kind=icon}
Return
Thermography pattern analysis and separation
.png){kind=icon}
PRE
AI
DOI：10.1063/1.4884644.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Analysis of thermography spatial-transient patterns has considerable potential to enable automatic identification and quantification of defects in non-destructive testing and evaluation. This Letter proposes a non-negative pattern separation model for eddy current pulsed thermography to automatically extract important spatial and time patterns according to the transient thermal sequences without any pre-training or prior knowledge. In particular, the method is scale-invariant, such that large differences in surface emissivity, hot spots, and cool areas with dynamic range of thermal contrast can be extracted. Finally, an artificial slot in a steel sample with shining, black strip on the surface is tested to validate the proposed method. (C) 2014 AIP Publishing LLC.
Keywords:
IDENTIFICATION
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
3.6
Papers:
10.4W
Citations:
17.8W