Assembly Quality Detection Based on Class-Imbalanced Semi-Supervised Learning

Due to the imperfect assembly process, the unqualified assembly of a missing gasket or lead seal will affect the product’s performance and possibly cause safety accidents. Machine vision method based on deep learning has been widely used in quality inspection. Semi-supervised learning (SSL) has been...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Zichen Lu, Jiabin Jiang, Pin Cao, Yongying Yang
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	intelligent quality inspection semi-supervised learning imbalanced data mean teacher Technology T Engineering (General). Civil engineering (General) TA1-2040 Biology (General) QH301-705.5 Physics QC1-999 Chemistry QD1-999
Acceso en línea:	https://doaj.org/article/9ea34548f1ad43199b740fa5f895b7ae
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:9ea34548f1ad43199b740fa5f895b7ae
record_format	dspace
spelling	oai:doaj.org-article:9ea34548f1ad43199b740fa5f895b7ae2021-11-11T15:23:51ZAssembly Quality Detection Based on Class-Imbalanced Semi-Supervised Learning10.3390/app1121103732076-3417https://doaj.org/article/9ea34548f1ad43199b740fa5f895b7ae2021-11-01T00:00:00Zhttps://www.mdpi.com/2076-3417/11/21/10373https://doaj.org/toc/2076-3417Due to the imperfect assembly process, the unqualified assembly of a missing gasket or lead seal will affect the product’s performance and possibly cause safety accidents. Machine vision method based on deep learning has been widely used in quality inspection. Semi-supervised learning (SSL) has been applied in training deep learning models to reduce the burden of data annotation. The dataset obtained from the production line tends to be class-imbalanced because the assemblies are qualified in most cases. However, most SSL methods suffer from lower performance in class-imbalanced datasets. Therefore, we propose a new semi-supervised algorithm that achieves high classification accuracy on the class-imbalanced assembly dataset with limited labeled data. Based on the mean teacher algorithm, the proposed algorithm uses certainty to select reliable teacher predictions for student learning dynamically, and loss functions are modified to improve the model’s robustness against class imbalance. Results show that when only 10% of the total data are labeled, and the imbalance rate is 5.3, the proposed method can improve the accuracy from 85.34% to 93.67% compared to supervised learning. When the amount of annotated data accounts for 20%, the accuracy can reach 98.83%.Zichen LuJiabin JiangPin CaoYongying YangMDPI AGarticleintelligent quality inspectionsemi-supervised learningimbalanced datamean teacherTechnologyTEngineering (General). Civil engineering (General)TA1-2040Biology (General)QH301-705.5PhysicsQC1-999ChemistryQD1-999ENApplied Sciences, Vol 11, Iss 10373, p 10373 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	intelligent quality inspection semi-supervised learning imbalanced data mean teacher Technology T Engineering (General). Civil engineering (General) TA1-2040 Biology (General) QH301-705.5 Physics QC1-999 Chemistry QD1-999
spellingShingle	intelligent quality inspection semi-supervised learning imbalanced data mean teacher Technology T Engineering (General). Civil engineering (General) TA1-2040 Biology (General) QH301-705.5 Physics QC1-999 Chemistry QD1-999 Zichen Lu Jiabin Jiang Pin Cao Yongying Yang Assembly Quality Detection Based on Class-Imbalanced Semi-Supervised Learning
description	Due to the imperfect assembly process, the unqualified assembly of a missing gasket or lead seal will affect the product’s performance and possibly cause safety accidents. Machine vision method based on deep learning has been widely used in quality inspection. Semi-supervised learning (SSL) has been applied in training deep learning models to reduce the burden of data annotation. The dataset obtained from the production line tends to be class-imbalanced because the assemblies are qualified in most cases. However, most SSL methods suffer from lower performance in class-imbalanced datasets. Therefore, we propose a new semi-supervised algorithm that achieves high classification accuracy on the class-imbalanced assembly dataset with limited labeled data. Based on the mean teacher algorithm, the proposed algorithm uses certainty to select reliable teacher predictions for student learning dynamically, and loss functions are modified to improve the model’s robustness against class imbalance. Results show that when only 10% of the total data are labeled, and the imbalance rate is 5.3, the proposed method can improve the accuracy from 85.34% to 93.67% compared to supervised learning. When the amount of annotated data accounts for 20%, the accuracy can reach 98.83%.
format	article
author	Zichen Lu Jiabin Jiang Pin Cao Yongying Yang
author_facet	Zichen Lu Jiabin Jiang Pin Cao Yongying Yang
author_sort	Zichen Lu
title	Assembly Quality Detection Based on Class-Imbalanced Semi-Supervised Learning
title_short	Assembly Quality Detection Based on Class-Imbalanced Semi-Supervised Learning
title_full	Assembly Quality Detection Based on Class-Imbalanced Semi-Supervised Learning
title_fullStr	Assembly Quality Detection Based on Class-Imbalanced Semi-Supervised Learning
title_full_unstemmed	Assembly Quality Detection Based on Class-Imbalanced Semi-Supervised Learning
title_sort	assembly quality detection based on class-imbalanced semi-supervised learning
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/9ea34548f1ad43199b740fa5f895b7ae
work_keys_str_mv	AT zichenlu assemblyqualitydetectionbasedonclassimbalancedsemisupervisedlearning AT jiabinjiang assemblyqualitydetectionbasedonclassimbalancedsemisupervisedlearning AT pincao assemblyqualitydetectionbasedonclassimbalancedsemisupervisedlearning AT yongyingyang assemblyqualitydetectionbasedonclassimbalancedsemisupervisedlearning
_version_	1718435381556281344

Assembly Quality Detection Based on Class-Imbalanced Semi-Supervised Learning

Ejemplares similares