Automatic Detection of Weld Defects in Pressure Vessel X-Ray Image Based on CNN
نویسندگان
چکیده
The visual automatic detection method based on artificial intelligence has attracted more and attention. In order to improve the performance of weld nondestructive defect detection, we propose DRepDet (Dilated RepPoints Detector). First, analyze dataset in detail summarize distribution characteristics data, that is, scale is very different aspect ratio range large. Second, according design DResBlock module, introduce dilated convolution with rates process feature extraction expand receptive field large-scale defects. Based anchor-free framework RepPoints, DRepDet. Extensive experiments show our proposed detector can detect 7 types When using combined rate network AP50 Recall50 big defects are improved by 3.1% 3.3% respectively, while small not affected, almost same or slightly improved. final whole a large margin, 6% 4.2% compared Cascade R-CNN 1.4% 2.9% RepPoints.
منابع مشابه
Automatic Detection of Weld Defects in Pressure Vessels using Fuzzy Neural Network
The interpretation of possible weld discontinuities in industrial radiography is ensured by human interpreters. The types of defects are porosity, lack of penetration, shrinkage, and fracture. It is thus desirable to develop computer-aided techniques to assist the interpreter in evaluating the quality of the welded joints. Using back propagation algorithm the images of weld defects are trained....
متن کاملAutomatic Detection of Weld Defects in Pressure Vessels using Fuzzy Neural Network
The interpretation of possible weld discontinuities in industrial radiography is ensured by human interpreters. The types of defects are porosity, lack of penetration, shrinkage, and fracture. It is thus desirable to develop computer-aided techniques to assist the interpreter in evaluating the quality of the welded joints. Using back propagation algorithm the images of weld defects are trained....
متن کاملfuzzy-based medical x-ray image classification
in this paper a novel fuzzy scheme for medical x-ray image classification is presented. in this method, any image is partitioned in to 25 overlapping subimages and then shape-texture features are extracted from shape and directional information extracted from any subimage. in the classification stage, we apply a fuzzy membership to any subimage with respect to euclidean distance between feature...
متن کاملA Weld Defects Detection System Based on a Spectrometer
Improved product quality and production methods, and decreased production costs are important objectives of industries. Welding processes are part of this goal. There are many studies about monitoring and controlling welding process. This work presents a non-intrusive on-line monitoriment system and some algorithms capable of detecting GTAW weld defects. Some experiments were made to simulate w...
متن کاملFeature Extraction and Optimisation for X-ray Weld Image Classification
Computer aided image analysis systems for radiographic inspection (X-ray or gamma ray) are among the most commonly used Non-destructive Evaluation (NDE) methods. The accuracy of these systems is very much depending on the selected features which are extracted from weld defect images. In this paper, we firstly introduce a computer aided image analysis system for X-ray image inspection and evalua...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Wuhan University Journal of Natural Sciences
سال: 2022
ISSN: ['1007-1202', '1993-4998']
DOI: https://doi.org/10.1051/wujns/2022276489