Filters








469 Hits in 6.2 sec

Vision based Identification and Classification of Weld Defects in Welding Environments: A Review

Mohd Shah Hairol Nizam, Ab Rashid Mohd Zamzuri, Sulaiman Marizan, Shukor Ahmad Zaki
2016 Indian Journal of Science and Technology  
, neural networks, interference fit line profiles diffuse system and according to the average gray level.  ...  This paper is a review for the identification and classification of weld defects in welding environments based on vision.  ...  Another approach is to compare a state of the art methods of multi-class classification (Support Vector Machines and Neural Networks) 9 for detection and classification using seven different classes  ... 
doi:10.17485/ijst/2016/v9i20/82779 fatcat:txxbypasordgfoycoc5mi6vggi

Multiclass defect detection and classification in weld radiographic images using geometric and texture features

Ioannis Valavanis, Dimitrios Kosmopoulos
2010 Expert systems with applications  
Three fold cross validation was utilized and experimental results are reported for three different classifiers (Support Vector Machine, Neural Network, k-NN).  ...  In this paper, a method for the detection and classification of defects in weld radiographs is presented.  ...  We also compare the state of the art Support Vector Machine and Neural Network multi-class classifiers.  ... 
doi:10.1016/j.eswa.2010.04.082 fatcat:b2mtl3paqvg67psd7mayyal3wu

Welding Defect Detection and Classification Using Geometric Features

J. Hassan, A. Majid Awan, A. Jalil
2012 2012 10th International Conference on Frontiers of Information Technology  
We present a novel technique for the detection and classification of weld defects by means of geometric features.  ...  Using these shape descriptors (geometric features) we classify the defects by Artificial Neural Network.  ...  Features extraction was followed by SVM (support vector machine) to classify defects. Some suitable features were used in their technique to estimate accuracy of classification of weld defects.  ... 
doi:10.1109/fit.2012.33 dblp:conf/fit/HassanAJ12 fatcat:bj5nqkc6crfbrkta4zodxqe6ne

A Multi-Sensor Data Fusion System for Laser Welding Process Monitoring

Fuqin Deng, Yongshen Huang, Song Lu, Yingying Chen, Jia Chen, Hua Feng, Jianmin Zhang, Yong Yang, Junjie Hu, Tin Lun Lam, Fengbin Xia
2020 IEEE Access  
Experimental results have demonstrated that IDDNet can achieve better multi-classification results than the support vector machine, with an overall accuracy of 97.57%.  ...  INDEX TERMS Laser welding process monitoring, in-process defect detection, multi-sensor data fusion, convolution neural network.  ...  Conventional ML methods include decision tree (random forest) [23] , support vector machine (SVM) [24] , Naive Bayes [25] .  ... 
doi:10.1109/access.2020.3015529 fatcat:isarzlvql5bc3h3ziri67vfuze

Quality Evaluation and Automatic Classification in Resistance Spot Welding by Analyzing the Weld Image on Metal Bands by Computer Vision

Yang Ou, Yueping Li
2015 International Journal of Signal Processing, Image Processing and Pattern Recognition  
Further we extract features describing the shape of localized objects in segmented images .Using these shape descriptors (geometric feature) we classify the defects by Artificial Neural Network.  ...  The input of the system is the image of a weld imprint on a metal band which covers the electrodes against wear and soiling.  ...  ACKNOWLEDGEMENTS This work is supported by youth foundation of shenzhen Polytechnic (2213K3190016), foundation of shenzhen Polytechnic (2213K3190028) and open foundation of key laboratory of optoelectronic  ... 
doi:10.14257/ijsip.2015.8.5.31 fatcat:q4cy4nkp6nddddx6s65iiliuhy

Automatic Detection and Characterization of Weld Defects Using CNN Algorithm in Machine Learning

S. Ramesh Krishnan
2021 Asian Review of Mechanical Engineering  
Convolutional Neural Network (CNN) algorithm in machine learning can be used for the automation of defect detection in radiography thereby reducing human intervention and associated delays.  ...  By the use of robotics the welding parameters can be adjusted and the issue of welding defects can be resolved.  ...  An approach to the detection of the main types of defects of welded joints using a combination of convolutional neural networks and support vector machine methods was made by Sizyakin et al., They used  ... 
doi:10.51983/arme-2021.10.1.2937 fatcat:guxkbwqjezdedogev5bsvj4n7y

Learning Defect Classifiers for Textured Surfaces Using Neural Networks and Statistical Feature Representations

D. Weimer, H. Thamer, B. Scholz-Reiter
2013 Procedia CIRP  
In this paper we present a machine vision system which uses basic patch statistics from raw image data combined with a two layer neural network to detect surface defects on arbitrary textured and weakly  ...  Detecting surface defects is a challenging visual recognition problem arising in many processing steps during manufacturing. These defects occur with arbitrary size, shape and orientation.  ...  Acknowledgements The authors gratefully acknowledge the financial support by Deutsche Forschungsgemeinschaft (DFG, German Research Foundation) for Subproject B5 he CRC 747 (Collaborative Mikrokaltumformen  ... 
doi:10.1016/j.procir.2013.05.059 fatcat:daznd6e73zdadcyw4u6dk7rbgy

Ultrasonic sensor based defect detection and characterisation of ceramics

Manasa Kesharaju, Romesh Nagarajah, Tonzhua Zhang, Ian Crouch
2014 Ultrasonics  
An alternative inspection system was developed to detect defects in 16 ceramic components using an Artificial Neural Network (ANN) based signal processing technique. 17 The inspection methodology proposed  ...  Defects such as free 14 silicon, un-sintered silicon carbide material and conventional porosity are often difficult to detect using 15 conventional x-radiography.  ...  Recently, classifiers such as neural 64 networks (NN), neuro-fuzzy classifiers, tree classifiers and support vector machines (SVM) 65 have found wide applications[8].  ... 
doi:10.1016/j.ultras.2013.07.018 pmid:23973193 fatcat:5nyrouuvjrcxjbya3zns3k34de

A new image recognition and classification method combining Transfer Learning Algorithm and MobileNet model for welding defects

Haihong Pan, Zaijun Pang, Yaowei Wang, Yijue Wang, Lin Chen
2020 IEEE Access  
By using the ImageNet dataset (non-welding defect data) to pre-train a MobileNet model, migrate the MobileNet model to the welding defects classification field.  ...  They can effectively accelerate the convergence rate and improve the classification network generalization.  ...  Machine learning methods such as artificial neural network (ANN), support vector machine (SVM) and fuzzy system are the most widely used in the field of X-ray image defects recognition.  ... 
doi:10.1109/access.2020.3005450 fatcat:ya6vnsfixffizfjypeurupsrmm

Embedded vision system for monitoring arc welding with thermal imaging and deep learning

Andrea Fernandez, A´Lvaro Souto, Roi Me´Ndez-Rial
2020 Zenodo  
We propose a deep learning processing pipeline with a CNNLSTM architecture for the detection and classification of defects based on video sequences.  ...  The experimental results show that the CNN-LSTM architecture is able to model the complex dynamics of the welding process and detect and classify defects with high accuracy.  ...  , principal component analysis or artificial neural networks.  ... 
doi:10.5281/zenodo.4300341 fatcat:awf5iesorvdxlbmafs72y6cfxu

Weld defect classification in radiographic images using unified deep neural network with multi-level features

Lu Yang, Hongquan Jiang
2020 Journal of Intelligent Manufacturing  
Wang and Guo 2014) , potential defects were detected, then support vector machine (SVM) was used to distinguish real defects from the potential ones.  ...  Computer vision and machine learning methods are always used to detect and classify weld defects in an automated RT system.  ... 
doi:10.1007/s10845-020-01581-2 fatcat:xo6odylv6fgjbnfzfbjqexlq6a

AN INDUSTRIAL INSPECTION APPROACH FOR WELD DEFECTS USING MACHINE LEARNING ALGORITHM

Kalai Selvi V, John Aravindar D
2019 International journal of advances in signal and image sciences  
Initially, the features that distinguish weld defects and no defects in the weld image are extracted by SURF.  ...  In this study, an effective method for weld defect classification using machine learning algorithm is presented.  ...  Then the classification is made by linear and non-linear Support Vector Machine (SVM).  ... 
doi:10.29284/ijasis.5.1.2019.15-21 fatcat:w6z44tf2g5h6lnqjc67b4hqe2y

Melt-Pool Defects Classification for Additive Manufactured Components in Aerospace Use-Case

Siva Krishna Dasari, Abbas Cheddad, Jonatan Palmquist
2020 2020 7th International Conference on Soft Computing & Machine Intelligence (ISCMI)  
ACKNOWLEDGMENT This work is partly supported by the research project "Model Driven Development and Decision Support" funded by the Knowledge Foundation (grant: 20120278) in Sweden.  ...  vector and Artificial Neural Networks (ANN) [4] .  ...  ., have used traditional ML techniques which are k-Nearest Neighbors (kNN), Bayesian networks, Support Vector Machines (SVM) and decision trees for defects classification of surface of iron casting images  ... 
doi:10.1109/iscmi51676.2020.9311555 fatcat:jh6ynd6aajg57necgnpof2ivzi

Transfer Learning with CNN for Classification of Weld Defect

Samuel Kumaresan, K. S. Jai Aultrin, S. S. Kumar, M. Dev Anand
2021 IEEE Access  
[4] proposed a method for weld defect classification using Artificial Neural Network (ANN), while extracting the textural features in different direction for several spatial pixel distances.  ...  By treating these values as feature vectors, machine learning models such as Support Vector Machine (SVM), Logistic Regression, Decision Trees, or Random Forests can be trained.  ...  His research interest includes medical image analysis, satellite image processing, multi resolution techniques and deep learning.  ... 
doi:10.1109/access.2021.3093487 fatcat:i3uxx6daznachkl2jdo3wjow2a

Review on the Recent Welding Research with Application of CNN-Based Deep Learning Part I: Models and Applications

Kidong Lee, Sung Yi, Soongkeun Hyun, Cheolhee Kim
2021 Journal of Welding and Joining  
During machine learning algorithms, deep learning refers to a neural network containing multiple hidden layers.  ...  Among the deep learning algorithms, the convolutional neural network (CNN) has recently received the spotlight for performing classification or regression based on image input.  ...  deep learning in arc welding 12) , and quality classification through SVM (Supported Vector Machine), a machine learning algorithim 13, 14) .  ... 
doi:10.5781/jwj.2021.39.1.1 fatcat:3xxzvi627fb3vo2ux4hhmgsf3m
« Previous Showing results 1 — 15 out of 469 results