Graphite Classification Based on Improved Convolution Neural Network

In the development of high-tech industries, graphite has become increasingly more important. The world has gradually entered the graphite era from the silicon era. In order to make good use of high-quality graphite resources, a graphite classification and recognition algorithm based on an improved c...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Guangjun Liu, Xiaoping Xu, Xiangjia Yu, Feng Wang
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	graphite classification transfer learning focal loss convolution neural network Chemical technology TP1-1185 Chemistry QD1-999
Acceso en línea:	https://doaj.org/article/78c21f6121b64894a24c25e58d28c871
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:78c21f6121b64894a24c25e58d28c871
record_format	dspace
spelling	oai:doaj.org-article:78c21f6121b64894a24c25e58d28c8712021-11-25T18:51:20ZGraphite Classification Based on Improved Convolution Neural Network10.3390/pr91119952227-9717https://doaj.org/article/78c21f6121b64894a24c25e58d28c8712021-11-01T00:00:00Zhttps://www.mdpi.com/2227-9717/9/11/1995https://doaj.org/toc/2227-9717In the development of high-tech industries, graphite has become increasingly more important. The world has gradually entered the graphite era from the silicon era. In order to make good use of high-quality graphite resources, a graphite classification and recognition algorithm based on an improved convolution neural network is proposed in this paper. Based on the self-built initial data set, the offline expansion and online enhancement of the data set can effectively expand the data set and reduce the risk of deep convolution neural network overfitting. Based on the visual geometry group 16 (VGG16), residual net 34 (ResNet34), and mobile net Vision 2 (MobileNet V2), a new output module is redesigned and loaded into the full connection layer. The improved migration network enhances the generalization ability and robustness of the model; moreover, combined with the focal loss function, the superparameters of the model are modified and trained on the basis of the graphite data set. The simulation results illustrate that the recognition accuracy of the proposed method is significantly improved, the convergence speed is accelerated, and the model is more stable, which proves the feasibility and effectiveness of the proposed method.Guangjun LiuXiaoping XuXiangjia YuFeng WangMDPI AGarticlegraphiteclassificationtransfer learningfocal lossconvolution neural networkChemical technologyTP1-1185ChemistryQD1-999ENProcesses, Vol 9, Iss 1995, p 1995 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	graphite classification transfer learning focal loss convolution neural network Chemical technology TP1-1185 Chemistry QD1-999
spellingShingle	graphite classification transfer learning focal loss convolution neural network Chemical technology TP1-1185 Chemistry QD1-999 Guangjun Liu Xiaoping Xu Xiangjia Yu Feng Wang Graphite Classification Based on Improved Convolution Neural Network
description	In the development of high-tech industries, graphite has become increasingly more important. The world has gradually entered the graphite era from the silicon era. In order to make good use of high-quality graphite resources, a graphite classification and recognition algorithm based on an improved convolution neural network is proposed in this paper. Based on the self-built initial data set, the offline expansion and online enhancement of the data set can effectively expand the data set and reduce the risk of deep convolution neural network overfitting. Based on the visual geometry group 16 (VGG16), residual net 34 (ResNet34), and mobile net Vision 2 (MobileNet V2), a new output module is redesigned and loaded into the full connection layer. The improved migration network enhances the generalization ability and robustness of the model; moreover, combined with the focal loss function, the superparameters of the model are modified and trained on the basis of the graphite data set. The simulation results illustrate that the recognition accuracy of the proposed method is significantly improved, the convergence speed is accelerated, and the model is more stable, which proves the feasibility and effectiveness of the proposed method.
format	article
author	Guangjun Liu Xiaoping Xu Xiangjia Yu Feng Wang
author_facet	Guangjun Liu Xiaoping Xu Xiangjia Yu Feng Wang
author_sort	Guangjun Liu
title	Graphite Classification Based on Improved Convolution Neural Network
title_short	Graphite Classification Based on Improved Convolution Neural Network
title_full	Graphite Classification Based on Improved Convolution Neural Network
title_fullStr	Graphite Classification Based on Improved Convolution Neural Network
title_full_unstemmed	Graphite Classification Based on Improved Convolution Neural Network
title_sort	graphite classification based on improved convolution neural network
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/78c21f6121b64894a24c25e58d28c871
work_keys_str_mv	AT guangjunliu graphiteclassificationbasedonimprovedconvolutionneuralnetwork AT xiaopingxu graphiteclassificationbasedonimprovedconvolutionneuralnetwork AT xiangjiayu graphiteclassificationbasedonimprovedconvolutionneuralnetwork AT fengwang graphiteclassificationbasedonimprovedconvolutionneuralnetwork
_version_	1718410653313531904

Graphite Classification Based on Improved Convolution Neural Network

Ejemplares similares