Applying SDR with CNN to Identify Weld Defect: A New Processing Method
Authors:
- 1 May 2023
- journal article
- research article
- Published by American Society of Civil Engineers (ASCE) in Journal of Pipeline Systems Engineering and Practice
- Vol. 14 (2) , 06023001
Abstract
X-ray weld images are investigated to achieve nondestructive identification of defects in oil and gas pipeline welds. The content mainly includes image filtering and enhancement, weld defect suspected defect region (SDR) segmentation, and defect identification. (1) The x-ray image quality is poor, as shown by a lot of noise and low contrast. Therefore, the mean filtering method is used to filter out the noise, and a nonlinear enhancement using sin function is proposed to improve the contrast between the weld and the background. (2) In the image segmentation, a segmentation method of SDR is proposed. Region of interest (ROI) is first extracted, and then SDRs are segmented using clustering. (3) In defect identification, deep learning networks are used for SDRs. A 6-stage, 10-layer convolutional neural network (CNN) network structure is designed, and the convolutional kernels are set to be and . In the experiments, the proposed method is able to automate the processing of x-ray weld images and improve the processing efficiency. The identification accuracy rate is 98.9%.
Keywords
This publication has 22 references indexed in Scilit:
- A pairwise graph regularized constraint based on deep belief network for fault diagnosisDigital Signal Processing, 2021
- Unsupervised weld defect classification in radiographic images using multivariate generalized Gaussian mixture model with exact computation of mean and shape parametersComputers in Industry, 2019
- Automatic segmentation of dermoscopy images using saliency combined with adaptive thresholding based on wavelet transformMultimedia Tools and Applications, 2019
- AN ADAPTIVE-NETWORK-BASED FUZZY INFERENCE SYSTEM FOR PREDICTING SPRINGBACK OF U-BENDINGTransactions of the Canadian Society for Mechanical Engineering, 2013
- Multiclass defect detection and classification in weld radiographic images using geometric and texture featuresExpert Systems with Applications, 2010
- Automatic detection of welding defects using texture featuresInsight - Non-Destructive Testing and Condition Monitoring, 2003
- Uncertainty modelling using Dempster–Shafer theory for improving detection of weld defectsPattern Recognition Letters, 2003
- Defect detection in X-ray images using fuzzy reasoningImage and Vision Computing, 2001
- An automated radiographic NDT system for weld inspection: Part II—Flaw detectionNDT & E International, 1998
- Automatic recognition of welding defects in real-time radiographyNDT International, 1990