CoChat

Cloud-Edge Collaborative Defect Detection Based on Efficient Yolo Networks and Incremental Learning

Open access

The DOI matches its Crossref record; 25 of the 25 references it cites were found in a registry or an index; 4 of the 7 sources its claims cite were checked for support.

Abstract

Defect detection constitutes one of the most crucial processes in industrial production. With a continuous increase in the number of defect categories and samples, the defect detection model underpinned by deep learning finds it challenging to expand to new categories, and the accuracy and real-time performance of product defect detection are also confronted with severe challenges. This paper addresses the problem of insufficient detection accuracy of existing lightweight models on resource-constrained edge devices by presenting a new lightweight YoloV5 model, which integrates four modules, SCDown, GhostConv, RepNCSPELAN4, and ScalSeq. Here, this paper abbreviates it as SGRS-YoloV5n. Through the incorporation of these modules, the model notably enhances feature extraction and computational efficiency while reducing the model size and computational load, making it more conducive for deployment on edge devices. Furthermore, a cloud-edge collaborative defect detection system is constructed to improve detection accuracy and efficiency through initial detection by edge devices, followed by additional inspection by cloud servers. An incremental learning mechanism is also introduced, enabling the model to adapt promptly to new defect categories and update its parameters accordingly. Experimental results reveal that the SGRS-YoloV5n model exhibits superior detection accuracy and real-time performance, validating its value and stability for deployment in resource-constrained environments. This system presents a novel solution for achieving efficient and accurate real-time defect detection.

Overview

CoChat Summary

## TL;DR

This paper proposes SGRS-YoloV5n, a lightweight YOLOv5n-based defect detector with GhostConv, SCDown, RepNCSPELAN4, and ScalSeq, plus a cloud-edge collaborative workflow for low-latency inspection. It also adds an incremental learning scheme to incorporate new defect categories without full retraining.

## Key findings

  • On the PCB defect dataset, the paper reports the model with all optimization modules achieves 2.7 GFLOPS, mAP 0.935, precision 0.971, and recall 0.900.
  • An ablation result reported mAP up to 0.923 with 3.1 GFLOPS for the backbone using SCDown + GhostConv; adding RepNCSPELAN4 gave mAP 0.924 and 2.4 GFLOPS.
  • Adding ScalSeq + attention-model raised performance to mAP 0.938 and recall 0.902, though with higher GFLOPS.
  • For model size/computation comparison, the paper reports SGRS-YoloV5n is 2.2 MB versus Faster R-CNN’s 76.1 MB, with 2.7 GFLOPs versus 16.87 GFLOPs.
  • In the incremental learning experiment, after adding a seventh defect class (Pad-damage) to a six-class PCB dataset, mAP@0.5 reached 0.338 after simple training.

## Methods

  • The paper designs a lightweight YOLOv5n variant (SGRS-YoloV5n) by integrating GhostConv, C3Ghost, SCDown, RepNCSPELAN4, and ScalSeq to improve feature extraction while reducing computation.
  • It evaluates the method on a public synthetic PCB dataset from Peking University’s Open Laboratory for Intelligent Robotics: 1386 images, expanded to 6237 images by brightness/contrast adjustment, rotation, and flipping; the split is 8:1:1 for training/test/validation.
  • Main analysis includes ablation experiments, comparison with Faster R-CNN and YOLO variants, and a cloud-edge collaborative detection deployment using Raspberry Pi 4 edge devices and a cloud server; incremental learning uses EfficientNet-B0 features, cosine similarity, and fine-tuning with frozen layers.

## Limitations

  • The paper states that in the incremental learning experiment, further optimization is needed to balance detection capabilities of new and old categories.
  • Evident from the text: the reported incremental learning result for the new class is low (mAP@0.5 = 0.338 after simple training), suggesting the method is not yet strong for new-category adaptation.
  • Evident from the text: the method is evaluated on a single PCB defect dataset, so broader generalization beyond this dataset is not demonstrated in the provided text.

Model-written summary. Check it against the paper before relying on it.

Integrity signals

Registry

Crossref · 10.3390/s24185921

Cites

25 of 25 references verified0 citation errors · 0 not checkable

Statistics

Nothing to recompute.

Figures

Figure 1 Cloud-edge collaborative defect inspection system.
Figure 1 Cloud-edge collaborative defect inspection system.CC BY · PubMed Central
Figure 2 Structure of SGRS-YoloV5n (The model proposed in the article is abbreviated as SGRS-YoloV5n because it is based on the YoloV5n model and combines SCDown, GhostConv, RepNCSPELAN4, and ScalSeq in the backbone and neck parts.).
Figure 2 Structure of SGRS-YoloV5n (The model proposed in the article is abbreviated as SGRS-YoloV5n because it is based on the YoloV5n model and combines SCDown, GhostConv, RepNCSPELAN4, and ScalSeq in the backbone and neck parts.).CC BY · PubMed Central
Figure 3 Structure of GhostConv.
Figure 3 Structure of GhostConv.CC BY · PubMed Central
Figure 4 Structure of C3Ghost.
Figure 4 Structure of C3Ghost.CC BY · PubMed Central
Figure 5 Structure of SCDown.
Figure 5 Structure of SCDown.CC BY · PubMed Central
Figure 6 Structure of RepNCSPELAN4.
Figure 6 Structure of RepNCSPELAN4.CC BY · PubMed Central
Figure 7 Structure of ScalSeq.
Figure 7 Structure of ScalSeq.CC BY · PubMed Central
Figure 8 Cloud-edge collaborative defect detection platform.
Figure 8 Cloud-edge collaborative defect detection platform.CC BY · PubMed Central
Figure 9 Examples of PCB defect types: (a) A defect where a necessary hole is missing. (b) Small indentations or nibbles on the PCB edge. (c) A break in the circuit where continuity is lost. (d) A defect caused by unintended connections between conductive parts. (e) An extraneous copper connection leading to an undesired short. (f) Unwanted copper residues left on the PCB.
Figure 9 Examples of PCB defect types: (a) A defect where a necessary hole is missing. (b) Small indentations or nibbles on the PCB edge. (c) A break in the circuit where continuity is lost. (d) A defect caused by unintended connections between conductive parts. (e) An extraneous copper connection leading to an undesired short. (f) Unwanted copper residues left on the PCB.CC BY · PubMed Central
Figure 10 SGRS-YoloV5n and YoloV5n training comparison.
Figure 10 SGRS-YoloV5n and YoloV5n training comparison.CC BY · PubMed Central
Figure 11 Confusion matrixb comparison. (a) Training confusion matrix of Yolov5n; (b) training confusion matrix of SGRS-Yolov5n.
Figure 11 Confusion matrixb comparison. (a) Training confusion matrix of Yolov5n; (b) training confusion matrix of SGRS-Yolov5n.CC BY · PubMed Central
Figure 12 Detection of defect results. (a) Detected missing holes with confidence scores of 0.77 and 0.86. (b) Detected mouse bites with confidence scores of 0.77 and 0.72. (c) Detected open circuits with confidence scores of 0.81 and 0.78. (d) Detected shorts with confidence scores of 0.85 and 0.89. (e) Detected spurs with confidence scores of 0.82 and 0.60. (f) Detected spurious copper with confidence scores of 0.74 and 0.80.
Figure 12 Detection of defect results. (a) Detected missing holes with confidence scores of 0.77 and 0.86. (b) Detected mouse bites with confidence scores of 0.77 and 0.72. (c) Detected open circuits with confidence scores of 0.81 and 0.78. (d) Detected shorts with confidence scores of 0.85 and 0.89. (e) Detected spurs with confidence scores of 0.82 and 0.60. (f) Detected spurious copper with confidence scores of 0.74 and 0.80.CC BY · PubMed Central
Figure 13 Real-time detection results for edge devices.
Figure 13 Real-time detection results for edge devices.CC BY · PubMed Central
Figure 14 Before and after cloud detecting. (a) Original image taken by edge device before cloud processing. (b) Detection results after cloud-based processing. The system accurately detects missing holes with confidence scores of 0.71 and 0.69, and a spur with a confidence score of 0.84.
Figure 14 Before and after cloud detecting. (a) Original image taken by edge device before cloud processing. (b) Detection results after cloud-based processing. The system accurately detects missing holes with confidence scores of 0.71 and 0.69, and a spur with a confidence score of 0.84.CC BY · PubMed Central
Figure 15 Before and after cloud detecting. (a) Original defect characteristics; (b) new defective features.
Figure 15 Before and after cloud detecting. (a) Original defect characteristics; (b) new defective features.CC BY · PubMed Central

Verification

Claims the paper makes

4 Valid · 0 Not valid · 2 Not checked · 25 Own results and interpretations

5 more claims

Create a free account to see all 31 claims and to verify the 1 reference still open.

See all claims — free account
  • It may state two separate claims as one. 19
  • The quote only partly states this claim. 1
  • Probably not a substantial claim. 5

Create a free account to see these claims.

Citations

Cites

Show all 25 references

Cited by

See all 16

Metadata

Authors
Lei, Z., Zhang, Y., Wang, J., & Zhou, M.
Affiliations
North China University of Technology (CN)
Corresponding author
Wang, Jing
Venue
Sensors
Publisher
MDPI AG
Published
2024-09-12
Volume
24
Issue
18
Pages
5921
ISSN
1424-8220 (ISSN-L)
OpenAlex
W4402483118
Cited by
16
References
19
Citations by year
2026: 7 · 2025: 8 · 2024: 1
FWCI
3.26
Type
journal article
Language
en
Open access
Locations
  • Sensors (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Funders
National Natural Science Foundation of China (62373005, 62273007)
Topics
  • Physical Sciences › Engineering › Industrial and Manufacturing Engineering › Industrial Vision Systems and Defect Detection
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
  • Physical Sciences › Engineering › Civil and Structural Engineering › Infrastructure Maintenance and Monitoring
Keywords
product defect detection, cloud-edge collaboration, YOLOv5, incremental learning, edge devices, resource-constrained deployment, real-time object detection, industrial inspection, GhostConv

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

The claim verdicts this report counts are experimental: their accuracy is not yet measured.

A language model drew the claims from the paper on 2026-10-10, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).

A second model labelled each claim on 2026-10-10 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).

Cited sources are checked with a language model’s help (qwen3.8-omni-flash and gpt-6-sol).

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Cloud-Edge Collaborative Defect Detection Based on Efficient Yolo Networks and Incremental Learning. https://app.cochat.ai/papers/10.3390/s24185921
The paper
Lei, Z., Zhang, Y., Wang, J., & Zhou, M. (2024). Cloud-Edge Collaborative Defect Detection Based on Efficient Yolo Networks and Incremental Learning. Sensors. https://doi.org/10.3390/s24185921

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.