An Automatic Deep Segmentation Network for Pixel-Level Welding Defect Detection

Yang, Lei; Song, Shouan; Fan, Junfeng; Huo, Benyan; Li, En; Liu, Yanhong

doi:10.1109/tim.2021.3127645

Cited by 27 publications

(7 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, the combination of ASPP and the Convolutional Block Attention Module (CBAM) [18] or Coordinate Attention (CA) [19] is frequently adopted to solve respective tasks [20][21][22][23][24][25][26]. Similar approaches can be found in other architectures like the U-Net [27][28][29][30][31]. These studies have achieved state-of-the-art experimental results in their respective tasks.…”

Section: Introductionmentioning

confidence: 93%

A Real-Time Dual-Task Defect Segmentation Network for Grinding Wheels with Coordinate Attentioned-ASP and Masked Autoencoder

Li,

Zhang

et al. 2024

Machines

View full text Add to dashboard Cite

The current network for the dual-task grinding wheel defect semantic segmentation lacks high-precision lightweight designs, making it challenging to balance lightweighting and segmentation accuracy, thus severely limiting its practical application in grinding wheel production lines. Additionally, recent approaches for addressing the natural class imbalance in defect segmentation fail to leverage the inexhaustible unannotated raw data on the production line, posing huge data wastage. Targeting these two issues, firstly, by discovering the similarity between Coordinate Attention (CA) and ASPP, this study has introduced a novel lightweight CA-ASP module to the DeeplabV3+, which is 45.3% smaller in parameter size and 53.2% lower in FLOPs compared to the ASPP, while achieving better segmentation precision. Secondly, we have innovatively leveraged the Masked Autoencoder (MAE) to address imbalance. By developing a new Hybrid MAE and applying it to self-supervised pretraining on tremendous unannotated data, we have significantly uplifted the network’s semantic understanding on the minority classes, which leads to further rises in both the overall accuracy and accuracy of the minorities without additional computational growth. Lastly, transfer learning has been deployed to fully utilize the highly related dual tasks. Experimental results demonstrate that the proposed methods with a real-time latency of 9.512 ms obtain a superior segmentation accuracy on the mIoU score over the compared real-time state-of-the-art methods, excelling in managing the imbalance and ensuring stability on the complicated scenes across the dual tasks.

show abstract

Section: Introductionmentioning

confidence: 93%

A Real-Time Dual-Task Defect Segmentation Network for Grinding Wheels with Coordinate Attentioned-ASP and Masked Autoencoder

Li,

Zhang

et al. 2024

Machines

View full text Add to dashboard Cite

show abstract

“…A wide range of datasets and classified faults can be observed, from significantly reduced (e.g., [40]) to more extensive datasets (e.g., [41]). Works [39] and [48] stand out, where up to 14 faults can be classified, and, in [48], the defect regions are also segmented. Defects such as cracks, lack of fusion, and lack of penetration are the most evaluated.…”

Section: Related Workmentioning

confidence: 99%

LoHi-WELD: A Novel Industrial Dataset for Weld Defect Detection and Classification, a Deep Learning Study, and Future Perspectives

Biasuz Block,

Dutra da Silva,

Eugnio Lazzaretti

et al. 2024

IEEE Access

View full text Add to dashboard Cite

The automated inspection of weld beads is of great importance for many industrial processes. Failures may cause a loss of mechanical resistance of the weld bead and compromise the manufactured part. Several methods have been proposed in the literature to address this problem, and recently, methods based on deep learning have gained prominence in terms of performance and applicability. However, such methods require vast and reliable datasets for different real defects, which have yet to be available in recent literature. Hence, this paper presents LoHi-WELD, an original and public database to address the problem of weld defect detection and classification of four common types of defects -pores, deposits, discontinuities, and stains -with 3,022 real weld bead images manually annotated for visual inspection, composed by low and high-resolution images, acquired from a Metal Active Gas robotic welding industrial process. We also explore variations of a baseline deep architecture for the proposed dataset based on a YOLOv7 network and discuss several case analyses. We show that a lightweight architecture, ideal for industrial edge devices, can achieve up to 0.69 of mean average precision (mAP) considering a fine-grained defect classification and 0.77 mAP for a coarse classification. Open challenges are also presented, promoting future research and enabling robust solutions for industrial scenarios. The proposed dataset, architecture, and trained models are publicly available on GitHub a .

show abstract

“…The LSTM network is used to fuse the extracted 19 dimensional features and learn time series information from the fused features. Yang et al [85] introduced an innovative method for locating welding defects using an encoder-decoder network architecture and an attention-guided segmentation network. In order to minimize the loss of important information in the deep encoder module caused by multiple convolution and pooling operations, they incorporated an enhanced attention block and a bidirectional convolutional long short-term memory (BiConvLSTM) block into the skip connections between the encoder path and the decoder path.…”

Section: Deep Learning In Weldingmentioning

confidence: 99%

Review on the Application of the Attention Mechanism in Sensing Information Processing for Dynamic Welding Processes

Xu,

Liu,

et al. 2024

JMMP

View full text Add to dashboard Cite

Arc welding is the common method used in traditional welding, which constitutes the majority of total welding production. The traditional manual and manual teaching welding method has problems with high labor costs and limited efficiency when faced with mass production. With the advancement in technology, intelligent welding technology is expected to become a solution to this problem in the future. To achieve the intelligent welding process, modern sensing technology can be employed to effectively simulate the welder’s sensory perception and cognitive abilities. Recent studies have advanced the application of sensing technologies, leading to the advancement in intelligent welding process. The review is divided into two aspects. First, the theory and applications of various sensing technologies (visual, sound, arc, spectral signal, etc.) are summarized. Then, combined with the generalization of neural networks and attention mechanisms, the development trends in welding sensing information processing and modeling technology are discussed. Based on the existing research results, the feasibility, advantages, and development direction of attention mechanisms in the welding field are analyzed. In the end, a brief conclusion and remarks are presented.

show abstract

An Automatic Deep Segmentation Network for Pixel-Level Welding Defect Detection

Cited by 27 publications

References 48 publications

A Real-Time Dual-Task Defect Segmentation Network for Grinding Wheels with Coordinate Attentioned-ASP and Masked Autoencoder

A Real-Time Dual-Task Defect Segmentation Network for Grinding Wheels with Coordinate Attentioned-ASP and Masked Autoencoder

LoHi-WELD: A Novel Industrial Dataset for Weld Defect Detection and Classification, a Deep Learning Study, and Future Perspectives

Review on the Application of the Attention Mechanism in Sensing Information Processing for Dynamic Welding Processes

Contact Info

Product

Resources

About