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
Shaobo Li, Jing Yang, Zheng Wang, Hao Dong, Jun Wang, Shihao Tang
2020-12-16

deep learningmachine visionmanufacturing defect detectionsmall object detectionultrasonic testing
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.
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.

Defect detection in manufactured products (electronic components, pipes, welded parts, textile materials) using deep-learning and related sensing technologies

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
Access Type
Author Information
Authors
Shaobo Li
Jing Yang
Zheng Wang
Hao Dong
Jun Wang
Shihao Tang
Explore further
Open the scid.ai AI chat with a ready-made request: it will find papers on a similar topic and help build a literature review.
Find similar papers in the chat →
Make a presentation
100%