A Knowledge-Based Approach to Crack Detection in Thermographic Images

Abstract

This paper describes an innovative visual inspection system for the detection of small cracks in metal parts. Given the extremely low dimension of the defects to be detected, the system is based on a thermographic approach: defects are recognized analyzing the heat flux induced by an excitation. The system is able to analyze parts of very high complexity, like a crankshaft, thanks to the introduction of an articulated robot, used for moving the part. The system also benefits from a deep knowledge of the inspected part and of the imaging system: this is exploited to reduce the high number of artifacts and reflections that appear in thermographic images when heat sources are employed. The core of the inspection mechanism is a computer vision algorithm that is capable of analyzing the thermographic images, extract the thermal information, and exploit a Support Vector Machine (SVM) classifier to provide a final decision on the presence of a crack in the analyzed part.

Autonomous robotic system for thermographic detection of defects in upper layers of carbon fiber reinforced polymers

“…Indeed, images are not bimodal as Viable alternatives are to be evaluated. One of them is the knowledge-based approach [6] by means of the high level of knowledge of the experimental setup and the backward projection [2] of each image point onto the 3D polygon mesh model of the CFRP part. The model, view and projection transformation matrices, whose composition is the mapping from the part space to the image space, are all well-known.…”

“…Their analysis for revealing defective areas is the main focus of this paper. It is addressed by taking advantage of the high level of knowledge of the entire system provided by the calibrations [6] and adapting an image sharpening technique well-known in photography, the UnSharp Masking (USM). Since the bonding cannot be simulated, defects are revealed by comparing each PPT phase image with the respective defect-free reference.…”