Real-Time High-Performance Laser Welding Defect Detection by Combining ACGAN-Based Data Enhancement and Multi-Model Fusion

Most of the existing laser welding process monitoring technologies focus on the detection of post-engineering defects, but in the mass production of electronic equipment, such as laser welding metal plates, the real-time identification of defect detection has more important practical significance. T...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Kui Fan, Peng Peng, Hongping Zhou, Lulu Wang, Zhongyi Guo
Formato: article
Lenguaje:EN
Publicado: MDPI AG 2021
Materias:
Acceso en línea:https://doaj.org/article/0c43a5587b5f46199abe50bd1244f9d6
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:0c43a5587b5f46199abe50bd1244f9d6
record_format dspace
spelling oai:doaj.org-article:0c43a5587b5f46199abe50bd1244f9d62021-11-11T19:15:21ZReal-Time High-Performance Laser Welding Defect Detection by Combining ACGAN-Based Data Enhancement and Multi-Model Fusion10.3390/s212173041424-8220https://doaj.org/article/0c43a5587b5f46199abe50bd1244f9d62021-11-01T00:00:00Zhttps://www.mdpi.com/1424-8220/21/21/7304https://doaj.org/toc/1424-8220Most of the existing laser welding process monitoring technologies focus on the detection of post-engineering defects, but in the mass production of electronic equipment, such as laser welding metal plates, the real-time identification of defect detection has more important practical significance. The data set of laser welding process is often difficult to build and there is not enough experimental data, which hinder the applications of the data-driven laser welding defect detection method. In this paper, an intelligent welding defect diagnosis method based on auxiliary classifier generative adversarial networks (ACGAN) has been proposed. Firstly, a ten-class dataset consisting of 6467 samples, was constructed, which originate from the optical and thermal sensory parameters in the welding process. A new structured ACGAN network model is proposed to generate fake data similar to the true defect feature distributions. In addition, in order to make the difference between different defects categories more obvious after data expansion, a data filtering and data purification scheme was proposed based on ensemble learning and an SVM (support vector machine), which is used to filter the bad generated data. In the experiments, the classification accuracy can reach 96.83% and 85.13%, for the CNN (convolutional neural network) algorithm model and ACGAN model, respectively. However, the accuracy can further improve to 97.86% and 98.37% for the fusion models of ACGAN-CNN and ACGAN-SVM-CNN models, respectively. The results show that ACGAN can not only be used as an algorithm model for classification, but also be used to achieve superior real-time classification and recognition through data enhancement and multi-model fusion.Kui FanPeng PengHongping ZhouLulu WangZhongyi GuoMDPI AGarticledefect detectionACGANsample generationmulti-algorithm model fusionChemical technologyTP1-1185ENSensors, Vol 21, Iss 7304, p 7304 (2021)
institution DOAJ
collection DOAJ
language EN
topic defect detection
ACGAN
sample generation
multi-algorithm model fusion
Chemical technology
TP1-1185
spellingShingle defect detection
ACGAN
sample generation
multi-algorithm model fusion
Chemical technology
TP1-1185
Kui Fan
Peng Peng
Hongping Zhou
Lulu Wang
Zhongyi Guo
Real-Time High-Performance Laser Welding Defect Detection by Combining ACGAN-Based Data Enhancement and Multi-Model Fusion
description Most of the existing laser welding process monitoring technologies focus on the detection of post-engineering defects, but in the mass production of electronic equipment, such as laser welding metal plates, the real-time identification of defect detection has more important practical significance. The data set of laser welding process is often difficult to build and there is not enough experimental data, which hinder the applications of the data-driven laser welding defect detection method. In this paper, an intelligent welding defect diagnosis method based on auxiliary classifier generative adversarial networks (ACGAN) has been proposed. Firstly, a ten-class dataset consisting of 6467 samples, was constructed, which originate from the optical and thermal sensory parameters in the welding process. A new structured ACGAN network model is proposed to generate fake data similar to the true defect feature distributions. In addition, in order to make the difference between different defects categories more obvious after data expansion, a data filtering and data purification scheme was proposed based on ensemble learning and an SVM (support vector machine), which is used to filter the bad generated data. In the experiments, the classification accuracy can reach 96.83% and 85.13%, for the CNN (convolutional neural network) algorithm model and ACGAN model, respectively. However, the accuracy can further improve to 97.86% and 98.37% for the fusion models of ACGAN-CNN and ACGAN-SVM-CNN models, respectively. The results show that ACGAN can not only be used as an algorithm model for classification, but also be used to achieve superior real-time classification and recognition through data enhancement and multi-model fusion.
format article
author Kui Fan
Peng Peng
Hongping Zhou
Lulu Wang
Zhongyi Guo
author_facet Kui Fan
Peng Peng
Hongping Zhou
Lulu Wang
Zhongyi Guo
author_sort Kui Fan
title Real-Time High-Performance Laser Welding Defect Detection by Combining ACGAN-Based Data Enhancement and Multi-Model Fusion
title_short Real-Time High-Performance Laser Welding Defect Detection by Combining ACGAN-Based Data Enhancement and Multi-Model Fusion
title_full Real-Time High-Performance Laser Welding Defect Detection by Combining ACGAN-Based Data Enhancement and Multi-Model Fusion
title_fullStr Real-Time High-Performance Laser Welding Defect Detection by Combining ACGAN-Based Data Enhancement and Multi-Model Fusion
title_full_unstemmed Real-Time High-Performance Laser Welding Defect Detection by Combining ACGAN-Based Data Enhancement and Multi-Model Fusion
title_sort real-time high-performance laser welding defect detection by combining acgan-based data enhancement and multi-model fusion
publisher MDPI AG
publishDate 2021
url https://doaj.org/article/0c43a5587b5f46199abe50bd1244f9d6
work_keys_str_mv AT kuifan realtimehighperformancelaserweldingdefectdetectionbycombiningacganbaseddataenhancementandmultimodelfusion
AT pengpeng realtimehighperformancelaserweldingdefectdetectionbycombiningacganbaseddataenhancementandmultimodelfusion
AT hongpingzhou realtimehighperformancelaserweldingdefectdetectionbycombiningacganbaseddataenhancementandmultimodelfusion
AT luluwang realtimehighperformancelaserweldingdefectdetectionbycombiningacganbaseddataenhancementandmultimodelfusion
AT zhongyiguo realtimehighperformancelaserweldingdefectdetectionbycombiningacganbaseddataenhancementandmultimodelfusion
_version_ 1718431567759540224