Title: Effective de-noising and characterisation of defects in eddy current-NDE images
Authors: Balakrishnan Sasi; M.S. Ahamed Ali; C. Babu Rao; T. Jayakumar
Addresses: Non Destructive Evaluation Division, Indira Gandhi Centre for Atomic Research, Kalpakkam, Tamil Nadu, India ' PSG College of Technology, Coimbatore, Tamil Nadu, India ' Non Destructive Evaluation Division, Indira Gandhi Centre for Atomic Research, Kalpakkam, Tamil Nadu, India ' Non Destructive Evaluation Division, Indira Gandhi Centre for Atomic Research, Kalpakkam, Tamil Nadu, India
Abstract: Non Destructive Evaluation (NDE) plays an important role in assessment of structural integrity of engineering components. Among various NDE techniques, eddy current NDE is widely used for detection of defects in installed components because of its ease of operation, non-contact and versatility. However, in the case of welded components, the presence of microstructural variations affects the material parameters such as conductivity and permeability. This in-turn produces large amplitude disturbing signals (weld noise) that mask small amplitude signals from defects. This demands the development of de-noising methodology, which enhances the characterisation of defects using Artificial Neural Network (ANN). This paper discusses the discrete wavelet transform-based de-noising method for elimination of weld noise and enhancement of defect information. The paper also briefs the characterisation of defects from the enhanced defect region using Multilayer Perceptron (MLP) based back propagation ANN.
Keywords: eddy current testing; DWT; discrete wavelet transform; de-noising methods; MLP; multilayer perceptron; back propagation ANNs; artificial neural networks; image processing; nondestructive evaluation; NDE; weld noise; welded components; microstructure; defect characterisation; welding defects.
International Journal of Signal and Imaging Systems Engineering, 2015 Vol.8 No.4, pp.235 - 249
Accepted: 30 May 2013
Published online: 10 Jul 2015 *