Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
September 10, 2026IoTOpen Access

Intelligent Steel Surface Defect Segmentation for Edge-Oriented IIoT Quality Control

View Full Paper
Ask AI
Bookmark
Share

Authors

MCMatheus CamposBPBruno Augusto PereiraMFMoisés Freitas

Discussion

Loading...

Member takes

Overview

Proof-of-concept study demonstrates real-time defect segmentation and optimized edge messaging for steel manufacturing, highlighting trade-offs between model accuracy and latency.

Key Points

  • To evaluate trade-offs between accuracy and computational footprint for steel defect segmentation models and optimize an edge-oriented IIoT messaging architecture.
  • Benchmarked a compact U-Net (0.49 M parameters), an ImageNet-pretrained DeepLabV3+, and an Otsu baseline on a defect-stratified test split of 1,886 Severstal images using Dice, IoU, precision, recall, and F1 metrics.
  • Evaluated a three-layer IIoT communication pipeline on a Raspberry Pi broker across 158,500 MQTT messages using a factorial experimental design.
  • DeepLabV3+ achieved a Dice score of 0.677 at 46.3 ms per image with 37 times more parameters than the compact U-Net, which achieved a Dice score of 0.416 at 38.6 ms per image, while Otsu reached 0.060.
  • Configuring the broker transport layer rather than the publisher achieved a 17-fold reduction in end-to-end latency and sustained 1,920 messages per second without message loss.

Cite This Study

Campos et al. (2026) studied this question.

synapsesocial.com/papers/6aa27b8858559d80afc74d6chttps://doi.org/10.3390/iot7030077
View Full Paper
Ask AI
Bookmark
Share