Using Deep Learning to Detect Defects in Manufacturing: A Comprehensive Survey and Current Challenges
Использование глубокого обучения для обнаружения дефектов в производстве: всесторонний обзор и современные проблемы
2020-12-16
SCID: 54.1/mb3euqby
Discuss with AI
deep learningmachine visionmanufacturing defect detectionsmall object detectionultrasonic testing
Figures from the paper
Abstract (AI)
The detection of product defects is essential in quality control in manufacturing. This study surveys stateoftheart deep-learning methods in defect detection. First, we classify the defects of products, such as electronic components, pipes, welded parts, and textile materials, into categories. Second, recent mainstream techniques and deep-learning methods for defects are reviewed with their characteristics, strengths, and shortcomings described. Third, we summarize and analyze the application of ultrasonic testing, filtering, deep learning, machine vision, and other technologies used for defect detection, by focusing on three aspects, namely method and experimental results. To further understand the difficulties in the field of defect detection, we investigate the functions and characteristics of existing equipment used for defect detection. The core ideas and codes of studies related to high precision, high positioning, rapid detection, small object, complex background, occluded object detection and object association, are summarized. Lastly, we outline the current achievements and limitations of the existing methods, along with the current research challenges, to assist the research community on defect detection in setting a further agenda for future studies.
Key Findings
1
It reviews mainstream deep-learning defect-detection methods, comparing their characteristics, strengths, shortcomings, and reported experimental results.
2
It summarizes methods and codes targeting high precision, accurate localization, rapid detection, small objects, complex backgrounds, occlusions, and object association.
3
The study analyzes ultrasonic testing, filtering, deep learning, machine vision, and related technologies for manufacturing defect detection.
4
The survey categorizes manufacturing defects across products including electronic components, pipes, welded parts, and textile materials.
5
The survey identifies current achievements, limitations, equipment-related considerations, and unresolved challenges to guide future defect-detection research.
Research Object
Defect detection in manufactured products (electronic components, pipes, welded parts, textile materials) using deep-learning and related sensing technologies
Research Subject
Deep-learning-based defect detection methods, their performance, limitations, and challenges in manufacturing quality control
Publication Details
Publication Date
2020-12-16
Journal
Publisher
ISSN
Cited by
514
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest
References available in scid.ai9
Deep Residual Learning for Image Recognition2016
ImageNet classification with deep convolutional neural networks2017
Very Deep Convolutional Networks for Large-Scale Image Recognition2014
Gradient-based learning applied to document recognition1998
Generative Adversarial Networks: An Overview2018
A Review of Recent Advances in Surface Defect Detection using Texture analysis Techniques2008
Automatic Defect Detection of Fasteners on the Catenary Support Device Using Deep Convolutional Neural Network2017
Visual-Based Defect Detection and Classification Approaches for Industrial Applications—A SURVEY2020
Applications of Ultrasonic Techniques in Oil and Gas Pipeline Industries: A Review2015
Cited by5
YOLO-v1 to YOLO-v8, the Rise of YOLO and Its Complementary Nature toward Digital Manufacturing and Industrial Defect Detection2023
Artificial Intelligence-Based Smart Quality Inspection for Manufacturing2023
Deep Learning and Computer Vision Techniques for Enhanced Quality Control in Manufacturing Processes2024
Application of artificial intelligence in the materials science, with a special focus on fuel cells and electrolyzers2024
A Comprehensive Survey on Machine Learning Driven Material Defect Detection2025