Welding Defects Classification Based on Multi-Weights Neural Network

2013 ◽  
Vol 820 ◽  
pp. 130-133
Author(s):  
Liang Hua ◽  
Peng Xue ◽  
Jin Ping Tang ◽  
Hui Jin ◽  
Qi Zhang
Keyword(s):  
Neural Network ◽  
Dimensional Space ◽  
Incomplete Fusion ◽  
Geometrical Shape ◽  
X Ray ◽  
Welding Technology ◽  
X Ray Imaging ◽  
Welding Defects ◽  
Defects Classification

Incomplete fusion and incomplete penetration are two types of damage serious welding defects. These two kinds of defects have the similarity in the features in X-ray imaging. Identifying the two kinds of defects automatically and accurately can improve the welding technology and improve the quality of welding effectively. The causes of defects and features of X-ray images are described in the paper. The welding defects calssification method based on multi-weights neural network is put forward in the paper. The multi-weights neural network based on graphic geometry theory is introduced, which uses the geometrical shape in high dimensional space to cover the same class defect samples via constructing multi-weights neural network. The experimental results proved the effectiveness of the algorithm.

scholarly journals Truncated Inception Net: COVID-19 Outbreak Screening using Chest X-rays

2020 ◽  
Author(s):  
Dipayan Das ◽  
KC Santosh ◽  
Umapada Pal
Keyword(s):  
Neural Network ◽  
World Wide ◽  
Imaging Techniques ◽  
Imaging Systems ◽  
Ct Scans ◽  
X Rays ◽  
X Ray ◽  
X Ray Imaging ◽  
Proposed Model ◽  
Different Types

Abstract Since December 2019, the Coronavirus Disease (COVID-19) pandemic has caused world-wide turmoil in less than a couple of months, and the infection, caused by SARS-CoV-2, is spreading at an unprecedented rate. AI-driven tools are used to identify Coronavirus outbreaks as well as forecast their nature of spread, where imaging techniques are widely used, such as CT scans and chest X-rays (CXRs). In this paper, motivated by the fact that X-ray imaging systems are more prevalent and cheaper than CT scan systems, a deep learning-based Convolutional Neural Network (CNN) model, which we call Truncated Inception Net, is proposed to screen COVID-19 positive CXRs from other non-COVID and/or healthy cases. To validate our proposal, six different types of datasets were employed by taking the following CXRs: COVID-19 positive, Pneumonia positive, Tuberculosis positive, and healthy cases into account. The proposed model achieved an accuracy of 99.96% (AUC of 1.0) in classifying COVID- 19 positive cases from combined Pneumonia and healthy cases. Similarly, it achieved an accuracy of 99.92% (AUC of 0.99) in classifying COVID-19 positive cases from combined Pneumonia, Tuberculosis and healthy CXRs. To the best of our knowledge, as of now, the achieved results outperform the existing AI-driven tools for screening COVID-19 using CXRs.

Study of Explosion Welding of Mg Alloy with Aluminium

2010 ◽  
Vol 297-301 ◽  
pp. 1177-1182 ◽  
Author(s):  
Michal Benák ◽  
Milan Turňa ◽  
Peter Palček ◽  
Peter Nesvadba
Keyword(s):  
High Speed ◽  
Explosion Welding ◽  
Mg Alloy ◽  
Basic Requirement ◽  
X Ray ◽  
Welding Technology ◽  
Alloy Type ◽  
Parallel Arrangement ◽  
Joint Quality

The aim of the present work was to solve the technology for welding Mg alloy type AZ 63 with aluminium and to assess the quality of the fabricated joints (bimetals-composites). In solving the welding technology, the high affinity of Mg to oxygen has to be considered and therefore as suitable technology either metallurgical joining in vacuum (electron beam etc.) or high-speed solid state welding seem to be feasible. Explosion welding with Semtex S 30 explosive was approved experimentally. Parallel arrangement of welded materials was applied. The more plastic Al material was accelerated. Quality of bonds (bimetals) was assessed by defectoscopy (ultrasound), optical microscopy, microhardness measurement and X-ray microanalysis. It can be generally stated that the basic requirement on joint quality (namely the undulated boundary) was met. The structural composition and absence of inhomogeneities in fabricated bimetals suggest that the desired quality was achieved.

Detection and Application of Hull Weld Quality Based on MATLAB Image Processing

2014 ◽  
Vol 912-914 ◽  
pp. 1509-1512
Author(s):  
Kai Jun Chen
Keyword(s):  
Image Processing ◽  
Ultrasonic Testing ◽  
Texture Features ◽  
X Ray ◽  
Welding Defects ◽  
Testing Technology ◽  
The Cost ◽  
Detecting Method ◽  
Analysis Quality

Proposed on the basis of nondestructive testing technology, such as ultrasonic testing and X-ray detecting, image processing of hull welding based on MATLAB is a simple detecting method to detect the quality of welding. By image processing, physical dimensions, such as circumferences and shapes, as well as the intensity and texture features of welds can be concluded. Then, through numerical analysis, quality problems, including porosities, slags, undercuts, overlaps, welding defects and others, if exist, can be determined. This method decreases the cost and reduces the harm to people’s health. Experimental results showed that the detecting system can calculate and determine the major features of the welds effectively and accurately, and possesses good practical value.

The Weldability of Primer-Coated Steel for Shipbuilding by CO2 Laser

2006 ◽  
Vol 321-323 ◽  
pp. 1745-1749 ◽  
Author(s):  
Jong Do Kim ◽  
Jin Seok Oh ◽  
Hyun Joon Park
Keyword(s):  
Welding Parameters ◽  
Coated Steel ◽  
Zinc Vapor ◽  
Welding Technology ◽  
Weld Material ◽  
Welding Defects ◽  
Lap Welding ◽  
Welding Defect ◽  
Alternative Idea

The application of laser welding technology has been considered to shipbuilding structure. However, when this technology is applied to primer-coated steel, good quality weld beads are not easily obtained. Because the primer-coated layer caused the spatter, humping bead and porosity which are main part of the welding defect attributed to the powerful vaporizing pressure of zinc. So we performed experiment with objectives of understanding spatter and porosity formation mechanism and producing sound weld beads in 6 t primer coated steels by a CO2 CW laser. The effects of welding parameters; defocused distance, welding speed, coated thickness and coated position; were investigated in the bead shape and penetration depth on bead and lap welding. Alternative idea was suggested to suspend the welding defect by giving a reasonable gap clearance for primer coated thickness. The zinc of primer has a boiling point that is lower than melting point of steel. Zinc vapor builds up at the interface between the two sheets and this tends to deteriorate the quality of the weld by ejecting weld material from lap position or leaving porosity. Significant effects of primer coated position were lap side rather than surface. Therefore introducing a small gap clearance in the lap position, the zinc vapor could escape through it and sound weld beads can be acquired. In conclusion, formation and suspension mechanism of the welding defects was suggested by controlling the factors.

Validation of radiographic quality of simulation software - ImaSim

2021 ◽  
pp. 1-10
Author(s):  
Zhonghang Wu ◽  
Jieying Yu ◽  
Qianqing Wu ◽  
Pengfei Hou ◽  
Jiuai Sun
Keyword(s):  
Spatial Resolution ◽  
Simulation Software ◽  
Virtual Simulation ◽  
Radiographic Imaging ◽  
Proof Of Concept ◽  
X Ray ◽  
X Ray Imaging ◽  
Radiographic Contrast ◽  
Exposure Setting

BACKGROUND: Virtual radiographic simulation has been found educationally effective for students to practice their clinical examinations remotely or online. A free available virtual simulator-ImaSim has received particular attention for radiographic science education because of its portability, free of charge and no constrain of location and physical facility. However, it lacks evidence to validate this virtual simulation software to faithfully reproduce radiographs comparable to that taken from a real X-ray machines to date. OBJECTIVE: To evaluate imaging quality of the virtual radiographs produced by the ImaSim. Thus, the deployment of this radiographic simulation software for teaching and experimental studying of radiography can be justified. METHODS: A real medical X-ray examination machine is employed to scan three standard QC phantoms to produce radiographs for comparing to the corresponding virtual radiographs generated by ImaSim software. The high and low range of radiographic contrast and comprehensive contrast-detail performance are considered to characterize the radiographic quality of the virtual simulation software. RESULTS: ImaSim software can generate radiographs with a contrast ranging from 30% to 0.8% and a spatial resolution as low as 0.6mm under the selected exposure setting condition. The characteristics of contrast and spatial resolution of virtual simulation generally agree with that of real medical X-ray examination machine. CONCLUSION: ImaSim software can be used to simulate a radiographic imaging process to generate radiographs with contrast and detail detectability comparable to those produced by a real X-ray imaging machine. Therefore, it can be adopted as a flexible educational tool for proof of concept and experimental design in radiography.

In vitro comparison of subjective image quality of the pana digital intraoral x-ray imaging system and conventional intraoral radiography in caries detection

1998 ◽  
Vol 14 (2) ◽  
pp. 75-83 ◽  
Author(s):  
Yoshiko Ariji ◽  
Jin-ichi Takahashi ◽  
Osamu Matsui ◽  
Tsuneichi Okano ◽  
Munetaka Naitoh ◽  
...  
Keyword(s):  
Image Quality ◽  
Imaging System ◽  
Caries Detection ◽  
Intraoral Radiography ◽  
Subjective Image Quality ◽  
X Ray ◽  
X Ray Imaging ◽  
In Vitro Comparison

scholarly journals Advanced Object Detection in Bio-Medical X-Ray Images for Anomaly Detection and Recognition

2021 ◽  
Vol 12 (2) ◽  
pp. 93-110
Author(s):  
Garv Modwel ◽  
Anu Mehra ◽  
Nitin Rakesh ◽  
K. K. Mishra
Keyword(s):  
Neural Network ◽  
Computer Vision ◽  
Vision System ◽  
Human Vision ◽  
Biomedical Image Processing ◽  
X Ray ◽  
Biomedical Image ◽  
X Ray Imaging ◽  
Magnetic Resonance Imaging Mri ◽  
Result Analysis

The human vision system is mimicked in the format of videos and images in the area of computer vision. As humans can process their memories, likewise video and images can be processed and perceptive with the help of computer vision technology. There is a broad range of fields that have great speculation and concepts building in the area of application of computer vision, which includes automobile, biomedical, space research, etc. The case study in this manuscript enlightens one about the innovation and future scope possibilities that can start a new era in the biomedical image-processing sector. A pre-surgical investigation can be perused with the help of the proposed technology that will enable the doctors to analyses the situations with deeper insight. There are different types of biomedical imaging such as magnetic resonance imaging (MRI), computerized tomographic (CT) scan, x-ray imaging. The focused arena of the proposed research is x-ray imaging in this subset. As it is always error-prone to do an eyeball check for a human when it comes to the detailing. The same applied to doctors. Subsequently, they need different equipment for related technologies. The methodology proposed in this manuscript analyses the details that may be missed by an expert doctor. The input to the algorithm is the image in the format of x-ray imaging; eventually, the output of the process is a label on the corresponding objects in the test image. The tool used in the process also mimics the human brain neuron system. The proposed method uses a convolutional neural network to decide on the labels on the objects for which it interprets the image. After some pre-processing the x-ray images, the neural network receives the input to achieve an efficient performance. The result analysis is done that gives a considerable performance in terms of confusion factor that is represented in terms of percentage. At the end of the narration of the manuscript, future possibilities are being traces out to the limelight to conduct further research.

scholarly journals Deep Learning Based Hybrid Models for Prediction of COVID-19 using Chest X-Ray

2020 ◽  
Author(s):  
Shree Charran R ◽  
Rahul Kumar Dubey
Keyword(s):  
Data Augmentation ◽  
False Negative ◽  
X Ray ◽  
Infected Case ◽  
X Ray Imaging ◽  
Normal Chest ◽  
Chest X Ray ◽  
To Come ◽  
Spread Of Infection

COVID-19 has ended up being the greatest pandemic to come to pass for on humanity in the last century. It has influenced all parts of present day life. The best way to confine its spread is the early and exact finding of infected patients. Clinical imaging strategies like Chest X-ray imaging helps specialists to assess the degree of spread of infection. In any case, the way that COVID-19 side effects imitate those of conventional Pneumonia brings few issues utilizing of Chest Xrays for its prediction accurately. In this investigation, we attempt to assemble 4 ways to deal with characterize between COVID-19 Pneumonia, NON-COVID-19 Pneumonia, and an Healthy- Normal Chest X-Ray images. Considering the low accessibility of genuine named Chest X-Ray images, we incorporated combinations of pre-trained models and data augmentation methods to improve the quality of predictions. Our best model has achieved an accuracy of 99.5216%. More importantly, the hybrid did not predict a False Negative Normal (i.e. infected case predicted as normal) making it the most attractive feature of the study.

Sign in / Sign up

Export Citation Format

Share Document