PulseExploreJournal ClubDebatesTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
March 19, 2026Journal of Manufacturing and Materials Processing1 citationsOpen Access

Automation of Ultrasonic Monitoring for Resistance Spot Welding Using Deep Learning

View Full Paper
RSRyan ScottDSD. M. StoccoSSSheida Sarafan

Key Points

  • This research aims to automate ultrasonic data analysis for monitoring resistance spot welding processes using deep learning techniques.
  • Developed a two-stage deep learning approach for ultrasonic data analysis.
  • Conducted semantic segmentation to identify molten pool and stack regions in M-scans.
  • Estimated weld nugget diameters using a neural network that incorporates M-scans and segmentation masks.
  • Utilized architectures based on TransUNet, integrating convolutional neural networks and vision transformers.
  • Achieved a mean intersection over union of 0.942 for segmentation of molten pool and stack regions.
  • Estimated weld nugget diameters with a mean absolute error of 0.432 mm.
  • Demonstrated >90% probability of detection at the acceptable diameter threshold with <10% probability of false alarm.
  • Significantly improved inference times: 13.4 ms for segmentation and 4.3 ms for diameter estimation.

Abstract

Reliable process monitoring and quality evaluation for resistance spot welding (RSW) have become more important now than ever. An ultrasonic probe embedded into welding electrodes has enabled the acquisition of data about molten pool formation throughout welding, but automation of high-performance ultrasonic data analyses is still necessary to fully realize a monitoring system. This work proposes a two-stage deep learning (DL) approach for automated ultrasonic data analysis for RSW processing monitoring. The first stage conducts semantic segmentation on ultrasonic M-scan welding process signatures, yielding masks for identified molten pool and stack regions from which weld penetration measurements can be directly extracted, as well as expulsion occurrences throughout welding. From input images and segmentation outputs, the second stage directly estimates resultant weld nugget diameters using an additional neural network. Both stages leveraged architectures based on TransUNet, mixing elements of both convolutional neural networks (CNN) and vision transformers, and the effect of cross-attention for stack-up sheet thickness data fusion was investigated via an ablation study. Additionally, in the diameter estimation stage, the ablation study included alternative feature extraction architectures in the network and investigated the provision of M-scans to the model alongside segmentation masks. In both cases, cross-attention was determined to improve performance, and in the case of diameter estimation, providing M-scans as input was found to be beneficial in general. With cross-attention, the segmentation approach yielded a mean intersection over union (IoU) of 0.942 on molten pool, stack, and expulsion regions in the M-scans with 13.4 ms inference time. With cross-attention, diameter estimates yielded a mean absolute error of 0.432 mm with 4.3 ms inference time, representing a significant improvement over algorithmic approaches based on ultrasonic time of flight. Additionally, the approach attained >90% probability of detection (POD) at 0.830 mm below the acceptable diameter threshold and <10% probability of false alarm (PFA) at 0.828 mm above the threshold. These results demonstrate a novel production-ready application of DL in ultrasonic nondestructive evaluation (NDE) and pave the way for zero-defect RSW manufacturing.

Ask AI
Helpful
Bookmark
Share
View Full Paper

Cite This Study

Scott et al. (2026) studied this question.

synapsesocial.com/papers/69bb92d1496e729e6298068fhttps://doi.org/10.3390/jmmp10030101
Ask AI
Helpful
Bookmark
Share
View Full Paper