Welding defect detection: coping with artifacts in the production line

Tripicchio, Paolo; Camacho-Gonzalez, Gerardo; D’Avella, Salvatore

doi:10.1007/s00170-020-06146-4

Cited by 25 publications

(11 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this context, Mower [47] proposes a balanced accuracy statistic that mediates the recall and specificity metrics. A more general approach is to directly scale the confusion matrix terms based on the relative support of each class as proposed by Tripicchio et al [48]. Other studies modify the loss function to account for class imbalance.…”

Section: Common Challenges and Possible Countermeasuresmentioning

confidence: 99%

“…In this context, continuing on the problem of detecting welding defects on injectors heads, the work presented by Tripicchio et al [48] proposes possible solutions to this issue without requiring an architectural change in the learning architecture. The new case had to handle some modifications concerning the parameters associated with the welding process, producing input samples with specific artifacts that the previously designed and trained network did never encounter.…”

Section: Managing Production Variabilitymentioning

confidence: 99%

See 1 more Smart Citation

Welding Defect Detection with Deep Learning Architectures

Tripicchio¹,

D’Avella²

2022

Engineering Principles - Welding and Residual Stresses

Self Cite

View full text Add to dashboard Cite

Welding automation is a fundamental process in manufacturing industries. Production lines integrate welding quality controls to reduce wastes and optimize the production chain. Early detection is fundamental as defects at any stage could determine the rejection of the entire product. In the last years, following the industry 4.0 paradigm, industrial automation lines have seen the introduction of modern technologies. Although the majority of the inspection systems still rely on traditional sensing and data processing, especially in the computer vision domain, some initiatives have been taken toward the employment of machine learning architectures. This chapter introduces deep neural networks in the context of welding defect detection, starting by analyzing common problems in the industrial applications of such technologies and discussing possible solutions in the specific case of quality checks in fuel injectors welding during the production stage.

show abstract

Section: Common Challenges and Possible Countermeasuresmentioning

confidence: 99%

Section: Managing Production Variabilitymentioning

confidence: 99%

Welding Defect Detection with Deep Learning Architectures

Tripicchio¹,

D’Avella²

2022

Engineering Principles - Welding and Residual Stresses

Self Cite

View full text Add to dashboard Cite

show abstract

“…Ding et al [12] proposed the wavelet soft and hard threshold compromise denoising method, Patil et al [13] proposed the techniques of local binary pattern in which local binary code describing region, generating by multiplying threshold with specified weight to conforming pixel and summing up by grey-level co-occurrence matrix to extract statistical texture features, Boaretto et al [14] extracted potential defects based on feedforward multilayer perceptron with back propagation learning algorithm. In addition, there are relevant research on weld feature extraction based on computer vision [15,16]. Although they have made some achievements, there are still problems to be solved [17][18][19].…”

Section: Introductionmentioning

confidence: 99%

Automatic Extraction Method of Weld Weak Defect Features for Ultra-High Voltage Equipment

Zheng¹,

Luo²,

Shen³

et al. 2023

Energy Engineering

View full text Add to dashboard Cite

To solve the problems of low precision of weak feature extraction, heavy reliance on labor and low efficiency of weak feature extraction in X-ray weld detection image of ultra-high voltage (UHV) equipment key parts, an automatic feature extraction algorithm is proposed. Firstly, the original weld image is denoised while retaining the characteristic information of weak defects by the proposed monostable stochastic resonance method. Then, binarization is achieved by combining Laplacian edge detection and Otsu threshold segmentation. Finally, the automatic identification of weld defect area is realized based on the sequential traversal of binary tree. Several characteristic analysis dimensions are established for weld defects of UHV key parts, including defect area, perimeter, slenderness ratio, duty cycle, etc. The experiment using the weld detection image of the actual production site shows that the proposed method can effectively extract the weak feature information of weld defects and further provide reference for decision-making.

show abstract

“…Computer vision and artificial intelligence are becoming essential tools that are integrated into a wide variety of systems. One of the most diffuse application fields of such technology is certainly the quality inspection for the automatic defect detection in the production line [4]. However, even other aspects are increasingly acquiring importance.…”

Section: Introductionmentioning

confidence: 99%

RFID Gazebo-Based Simulator With RSSI and Phase Signals for UHF Tags Localization and Tracking

2022

Self Cite

View full text Add to dashboard Cite

Radio Frequency Identification (RFID) technology is becoming very popular in the new era of Industry 4.0, especially for warehouse management, retails, and logistics. RFID systems can be used for objects identification, localization, and tracking, facilitating everyday operators' efforts. However, the deployment of RFID tags and reader antennas in real-world application scenarios is crucial and takes time. Indeed, deciding where to place tags and/or readers' requires examining many conditions. If some weaknesses appear in the design, the arrangement must be reconsidered. The proposed work presents a novel open-source RFID simulator that allows modeling environments and testing the deployment of RFID tags and antennas apriori. In such a way, validating the performance of the localization or tracking algorithms in simulation, possible weaknesses that could arise may be fixed before facilities are applied on the field. Any number of tags and antennas can be placed in any position in the created scenario, and the simulator provides the phase and the RSSI signals for each tag. Every reader antenna is parametrized so that different antennas of different vendors can be reproduced. The simulator is implemented as a plugin of Gazebo, a widely used robotic framework integrated with the Robot Operating System (ROS), to reach a broad audience. In order to validate the simulator, a warehouse scenario is modeled, and a tag localization algorithm that uses the phase unwrapping technique and hyperbolae intersection method employing a reader antenna mounted on a mobile robot is used to estimate the position of the tags deployed in the scenario. The outcomes of the experiments showed realistic results.

show abstract

Welding defect detection: coping with artifacts in the production line

Cited by 25 publications

References 28 publications

Welding Defect Detection with Deep Learning Architectures

Welding Defect Detection with Deep Learning Architectures

Automatic Extraction Method of Weld Weak Defect Features for Ultra-High Voltage Equipment

RFID Gazebo-Based Simulator With RSSI and Phase Signals for UHF Tags Localization and Tracking

Contact Info

Product

Resources

About