Control Chart Patterns Recognition Based on Optimized Deep Belief Neural Network and Data Information Enhancement

Control chart patterns (CCPs) are often used for quality control in the manufacturing process, and effective recognition of these patterns is critical to manufacturing. In the dynamic production process, the raw data and features of CCPs are used to recognize or further predict the trends. However,...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Hongyan Chu, Kailin Zhao, Qiang Cheng, Rui Li, Congbin Yang
Formato:	article
Lenguaje:	EN
Publicado:	IEEE 2020
Materias:	Control chart patterns adaptive feature selection and information enhancement artificial fish swarm algorithm deep belief network Electrical engineering. Electronics. Nuclear engineering TK1-9971
Acceso en línea:	https://doaj.org/article/7c7bfb02ab8e48ee87084f21fca551ab
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:7c7bfb02ab8e48ee87084f21fca551ab
record_format	dspace
spelling	oai:doaj.org-article:7c7bfb02ab8e48ee87084f21fca551ab2021-11-19T00:06:26ZControl Chart Patterns Recognition Based on Optimized Deep Belief Neural Network and Data Information Enhancement2169-353610.1109/ACCESS.2020.3036006https://doaj.org/article/7c7bfb02ab8e48ee87084f21fca551ab2020-01-01T00:00:00Zhttps://ieeexplore.ieee.org/document/9248993/https://doaj.org/toc/2169-3536Control chart patterns (CCPs) are often used for quality control in the manufacturing process, and effective recognition of these patterns is critical to manufacturing. In the dynamic production process, the raw data and features of CCPs are used to recognize or further predict the trends. However, the inaccuracy of CCPs information extraction, loss of information, and complex recognizer can lead to the difficulty of recognition. In order to improve the accuracy of information extraction and recognition, a CCPs recognition method based on optimized deep belief network (DBN) and data information enhancement was proposed. Adaptive features selection and information enhancement (AFIE) was used to select the most appropriate features and make these features combine with the raw data to from the dataset in order to reduce the data dimension, and then combine dimensioned data with the selected features to enhance the data information. Further, this study presented a DBN with three restricted Boltzmann machine structures, which was optimized by using the artificial fish swarm algorithm (AFSA). The method of AFIE was discussed to obtain the optimal data set, and parameters of the network structure were analyzed, optimized, and discussed based on experiments and AFSA. At the same time, this method was compared with multi-layer perceptron neural network. The simulation results showed that the method proposed in this study exhibited excellent effect, and the recognition accuracy achieved by this method was 99.78% for 2000 samples of each pattern.Hongyan ChuKailin ZhaoQiang ChengRui LiCongbin YangIEEEarticleControl chart patternsadaptive feature selection and information enhancementartificial fish swarm algorithmdeep belief networkElectrical engineering. Electronics. Nuclear engineeringTK1-9971ENIEEE Access, Vol 8, Pp 203685-203699 (2020)
institution	DOAJ
collection	DOAJ
language	EN
topic	Control chart patterns adaptive feature selection and information enhancement artificial fish swarm algorithm deep belief network Electrical engineering. Electronics. Nuclear engineering TK1-9971
spellingShingle	Control chart patterns adaptive feature selection and information enhancement artificial fish swarm algorithm deep belief network Electrical engineering. Electronics. Nuclear engineering TK1-9971 Hongyan Chu Kailin Zhao Qiang Cheng Rui Li Congbin Yang Control Chart Patterns Recognition Based on Optimized Deep Belief Neural Network and Data Information Enhancement
description	Control chart patterns (CCPs) are often used for quality control in the manufacturing process, and effective recognition of these patterns is critical to manufacturing. In the dynamic production process, the raw data and features of CCPs are used to recognize or further predict the trends. However, the inaccuracy of CCPs information extraction, loss of information, and complex recognizer can lead to the difficulty of recognition. In order to improve the accuracy of information extraction and recognition, a CCPs recognition method based on optimized deep belief network (DBN) and data information enhancement was proposed. Adaptive features selection and information enhancement (AFIE) was used to select the most appropriate features and make these features combine with the raw data to from the dataset in order to reduce the data dimension, and then combine dimensioned data with the selected features to enhance the data information. Further, this study presented a DBN with three restricted Boltzmann machine structures, which was optimized by using the artificial fish swarm algorithm (AFSA). The method of AFIE was discussed to obtain the optimal data set, and parameters of the network structure were analyzed, optimized, and discussed based on experiments and AFSA. At the same time, this method was compared with multi-layer perceptron neural network. The simulation results showed that the method proposed in this study exhibited excellent effect, and the recognition accuracy achieved by this method was 99.78% for 2000 samples of each pattern.
format	article
author	Hongyan Chu Kailin Zhao Qiang Cheng Rui Li Congbin Yang
author_facet	Hongyan Chu Kailin Zhao Qiang Cheng Rui Li Congbin Yang
author_sort	Hongyan Chu
title	Control Chart Patterns Recognition Based on Optimized Deep Belief Neural Network and Data Information Enhancement
title_short	Control Chart Patterns Recognition Based on Optimized Deep Belief Neural Network and Data Information Enhancement
title_full	Control Chart Patterns Recognition Based on Optimized Deep Belief Neural Network and Data Information Enhancement
title_fullStr	Control Chart Patterns Recognition Based on Optimized Deep Belief Neural Network and Data Information Enhancement
title_full_unstemmed	Control Chart Patterns Recognition Based on Optimized Deep Belief Neural Network and Data Information Enhancement
title_sort	control chart patterns recognition based on optimized deep belief neural network and data information enhancement
publisher	IEEE
publishDate	2020
url	https://doaj.org/article/7c7bfb02ab8e48ee87084f21fca551ab
work_keys_str_mv	AT hongyanchu controlchartpatternsrecognitionbasedonoptimizeddeepbeliefneuralnetworkanddatainformationenhancement AT kailinzhao controlchartpatternsrecognitionbasedonoptimizeddeepbeliefneuralnetworkanddatainformationenhancement AT qiangcheng controlchartpatternsrecognitionbasedonoptimizeddeepbeliefneuralnetworkanddatainformationenhancement AT ruili controlchartpatternsrecognitionbasedonoptimizeddeepbeliefneuralnetworkanddatainformationenhancement AT congbinyang controlchartpatternsrecognitionbasedonoptimizeddeepbeliefneuralnetworkanddatainformationenhancement
_version_	1718420618360127488

Control Chart Patterns Recognition Based on Optimized Deep Belief Neural Network and Data Information Enhancement

Ejemplares similares