A Smart Monitoring System for Automatic Welding Defect Detection

Sassi, Paolo; Tripicchio, Paolo; Avizzano, Carlo Alberto

doi:10.1109/tie.2019.2896165

Cited by 113 publications

(38 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Their excellent performance in feature learning from image urged people to use them in automatic defect detection [54][55][56]. For automatic detection of welding defects, the application of two methods begin to rise, especially the application of convolutional neural network (CNN) which is a typical deep learning model [57][58][59].…”

Section: New Methodsmentioning

confidence: 99%

Review on Computer Aided Weld Defect Detection from Radiography Images

Hou

Zhang

et al. 2020

Applied Sciences

View full text Add to dashboard Cite

The weld defects inspection from radiography films is critical for assuring the serviceability and safety of weld joints. The various limitations of human interpretation made the development of innovative computer-aided techniques for automatic detection from radiography images an interest point of recent studies. The studies of automatic defect inspection are synthetically concluded from three aspects: pre-processing, defect segmentation and defect classification. The achievement and limitations of traditional defect classification method based on the feature extraction, selection and classifier are summarized. Then the applications of novel models based on learning(especially deep learning) were introduced. Finally, the achievement of automation methods were discussed and the challenges of current technology are presented for future research for both weld quality management and computer science researchers.

show abstract

Section: New Methodsmentioning

confidence: 99%

Review on Computer Aided Weld Defect Detection from Radiography Images

Hou

Zhang

et al. 2020

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…On the other hand, for the problem of insufficient data, transfer learning technology can be introduced in the CNN diagnostic framework. Transfer learning can map the knowledge in the B domain to the A domain [36][37][38]. With the transfer learning method, a small amount of data can still achieve a high diagnostic accuracy [39,40].…”

Section: Introductionmentioning

confidence: 99%

A Deep Parallel Diagnostic Method for Transformer Dissolved Gas Analysis

Duan

2020

Applied Sciences

View full text Add to dashboard Cite

With the development of Industry 4.0, as a pivotal part of the power system, large-capacity power transformers are requiring fault diagnostic methods with higher intelligence, accuracy and anti-interference ability. Considering the powerful capability for extracting non-linear features and the sensitivity differences to features of deep learning methods, this paper proposes a deep parallel diagnostic method for transformer dissolved gas analysis (DGA). In view of the insufficient and imbalanced dataset of transformers, adaptive synthetic oversampling (ADASYN) was implemented to augment the fault dataset. Then, the newly constructed dataset was normalized and input into the LSTM-based diagnostic framework. Then, the dataset was converted into images as the input of the CNN-based diagnostic framework. At the same time, the problem of still insufficient data was compensated by the introduction of transfer learning technology. Finally, the diagnostic models were trained and tested respectively, and the Dempster-Shafer (DS) evidence theory was introduced to fuse the diagnostic confidence matrices of the two models to achieve deep parallel diagnosis. The results of the proposed deep parallel diagnostic method show that without complex feature extraction, the diagnostic accuracy rate could reach 96.9%. Even when the dataset was superimposed with 3% random noises, the rate only decreased by 0.62%.Appl. Sci. 2020, 10, 1329 2 of 18 their shortcomings in learning ability, processing efficiency, and feature extraction ability. For example, the learning ability of the fuzzy methods are not satisfying [7,8]. Neural networks (NN) tend to fall into local optimal solutions [9,10]. The K-nearest neighbor (KNN) method is inefficient in high-dimensional space [11]. The support vector machine (SVM) is essentially a two-classifier, which makes it more troublesome to deal with multi-classification problems [12,13]. There are also some relevant diagnosis studies on combining traditional ratio methods and intelligent methods, which are combinations of previous researches, and have achieved certain effects [14][15][16]. However, the features extracted by the ratio methods are still limited. And the anti-interference ability of the combined models need further testing. In recent years, due to the strong ability of deep learning to extract complex non-linear features, some papers have tried to introduce it into the field of transformer fault diagnosis. And the fault diagnostic accuracy of deep learning methods has been significantly improved compared to traditional machine learning diagnostic models'. The authors in [17] proposed a DBN-based fault diagnostic method that used the uncoded ratio of DGA data as the model input. Compared with the traditional methods', the accuracy was significantly improved. The authors in [18] introduced a method for identifying and locating winding faults based on CNN and transformer impulse tests. And the results showed that the method was effective. The authors in [19] studied the internal fault diagnosis of...

show abstract

“…There are three main methods of current non-destructive testing of welding quality: 1) online monitoring of the quality of the welding process; 2) non-destructive testing of internal defects of welding (radiation [5][6][7][8][9], ultrasonic, [10][11][12][13][14], etc. ); 3) detection of surface defects of welding (visual [15,16], structured light [17][18][19][20][21], etc.). The latter two inspection methods belong to post-weld inspection, and it is difficult to take advantage of the high speed and high efficiency of laser welding.…”

Section: Introductionmentioning

confidence: 99%

“…In the subsequent artificial neural network classification, good results were obtained in the multi-defect type data set. Starting from state-of-the-art deep architectures, Sassi et al have been practically used in the inspection of welding defects on an assembly line of fuel injectors, successfully completing quality inspection tasks that usually require manual completion, and the model can further improve performance with new data collected during operation [16]. Obtaining the plasma radiation through the fiber probe, Yuanhang and his team used the plasma spectral data and the neural network designed to classify the defects of the fiber laser welding [40], indicating the corresponding relationship between the output of the classifier and the welding defects.…”

Section: Introductionmentioning

confidence: 99%

A New Method to Assess Fiber Laser Welding Quality of Stainless Steel 304 Based on Machine Vision and Hidden Markov Models

et al. 2020

View full text Add to dashboard Cite

High-power fiber laser welding has a broad range of applications in industrial processing and modern intelligent manufacturing, but how to assess the quality of laser welding has always been a concern. In the welding process, the geometric feature of the keyhole generated by the high temperature of laser can directly reflect quality of the laser welding. By using machine vision to acquire images in real time and analyze related features, the quality of laser welding can be evaluated, which reduce the cost and time in later inspection. Nevertheless, due to the dynamic complexity of the keyhole as well as the blurring of the keyhole and full penetration hole boundary caused by metal vapor and spatter, identification of multiple type defects through machine vision is still a problem that requires a solution. This paper presents a novel laser welding defect classification method using keyhole boundary-based feature based on machine vision and Hidden Markov process. After effective segmenting the collected welding image, the shapes of the keyhole as well as the full penetration hole were automatically extracted using the characteristics of gray projection distribution and the Poisson extinction method. Subsequently, a pre-trained Hidden Markov Model was employed to establish the connection between the keyhole's geometry and the welding quality defects. Experiments indicate that our theory can efficiently and accurately extract the key geometric shapes. Welding experimental data involving stainless steel 304 verifies the feasibility of the classification theory, which can monitor welding quality and reveal potential porosity and penetration defects.

show abstract

A Smart Monitoring System for Automatic Welding Defect Detection

Cited by 113 publications

References 20 publications

Review on Computer Aided Weld Defect Detection from Radiography Images

Review on Computer Aided Weld Defect Detection from Radiography Images

A Deep Parallel Diagnostic Method for Transformer Dissolved Gas Analysis

A New Method to Assess Fiber Laser Welding Quality of Stainless Steel 304 Based on Machine Vision and Hidden Markov Models

Contact Info

Product

Resources

About