Research on maintenance spare parts requirement prediction based on LSTM recurrent neural network

The aim of this study was to improve the low accuracy of equipment spare parts requirement predicting, which affects the quality and efficiency of maintenance support, based on the summary and analysis of the existing spare parts requirement predicting research. This article introduces the current l...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Song Weixing, Wu Jingjing, Kang Jianshe, Zhang Jun
Formato:	article
Lenguaje:	EN
Publicado:	De Gruyter 2021
Materias:	lstm spare parts prediction neural network particle swarm Physics QC1-999
Acceso en línea:	https://doaj.org/article/c4d2582737d94ded8493dd190e838151
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:c4d2582737d94ded8493dd190e838151
record_format	dspace
spelling	oai:doaj.org-article:c4d2582737d94ded8493dd190e8381512021-12-05T14:11:02ZResearch on maintenance spare parts requirement prediction based on LSTM recurrent neural network2391-547110.1515/phys-2021-0072https://doaj.org/article/c4d2582737d94ded8493dd190e8381512021-10-01T00:00:00Zhttps://doi.org/10.1515/phys-2021-0072https://doaj.org/toc/2391-5471The aim of this study was to improve the low accuracy of equipment spare parts requirement predicting, which affects the quality and efficiency of maintenance support, based on the summary and analysis of the existing spare parts requirement predicting research. This article introduces the current latest popular long short-term memory (LSTM) algorithm which has the best effect on time series data processing to equipment spare parts requirement predicting, according to the time series characteristics of spare parts consumption data. A method for predicting the requirement for maintenance spare parts based on the LSTM recurrent neural network is proposed, and the network structure is designed in detail, the realization of network training and network prediction is given. The advantages of particle swarm algorithm are introduced to optimize the network parameters, and actual data of three types of equipment spare parts consumption are used for experiments. The performance comparison of predictive models such as BP neural network, generalized regression neural network, wavelet neural network, and squeeze-and-excitation network prove that the new method is effective and provides an effective method for scientifically predicting the requirement for maintenance spare parts and improving the quality of equipment maintenance.Song WeixingWu JingjingKang JiansheZhang JunDe Gruyterarticlelstmspare parts predictionneural networkparticle swarmPhysicsQC1-999ENOpen Physics, Vol 19, Iss 1, Pp 618-627 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	lstm spare parts prediction neural network particle swarm Physics QC1-999
spellingShingle	lstm spare parts prediction neural network particle swarm Physics QC1-999 Song Weixing Wu Jingjing Kang Jianshe Zhang Jun Research on maintenance spare parts requirement prediction based on LSTM recurrent neural network
description	The aim of this study was to improve the low accuracy of equipment spare parts requirement predicting, which affects the quality and efficiency of maintenance support, based on the summary and analysis of the existing spare parts requirement predicting research. This article introduces the current latest popular long short-term memory (LSTM) algorithm which has the best effect on time series data processing to equipment spare parts requirement predicting, according to the time series characteristics of spare parts consumption data. A method for predicting the requirement for maintenance spare parts based on the LSTM recurrent neural network is proposed, and the network structure is designed in detail, the realization of network training and network prediction is given. The advantages of particle swarm algorithm are introduced to optimize the network parameters, and actual data of three types of equipment spare parts consumption are used for experiments. The performance comparison of predictive models such as BP neural network, generalized regression neural network, wavelet neural network, and squeeze-and-excitation network prove that the new method is effective and provides an effective method for scientifically predicting the requirement for maintenance spare parts and improving the quality of equipment maintenance.
format	article
author	Song Weixing Wu Jingjing Kang Jianshe Zhang Jun
author_facet	Song Weixing Wu Jingjing Kang Jianshe Zhang Jun
author_sort	Song Weixing
title	Research on maintenance spare parts requirement prediction based on LSTM recurrent neural network
title_short	Research on maintenance spare parts requirement prediction based on LSTM recurrent neural network
title_full	Research on maintenance spare parts requirement prediction based on LSTM recurrent neural network
title_fullStr	Research on maintenance spare parts requirement prediction based on LSTM recurrent neural network
title_full_unstemmed	Research on maintenance spare parts requirement prediction based on LSTM recurrent neural network
title_sort	research on maintenance spare parts requirement prediction based on lstm recurrent neural network
publisher	De Gruyter
publishDate	2021
url	https://doaj.org/article/c4d2582737d94ded8493dd190e838151
work_keys_str_mv	AT songweixing researchonmaintenancesparepartsrequirementpredictionbasedonlstmrecurrentneuralnetwork AT wujingjing researchonmaintenancesparepartsrequirementpredictionbasedonlstmrecurrentneuralnetwork AT kangjianshe researchonmaintenancesparepartsrequirementpredictionbasedonlstmrecurrentneuralnetwork AT zhangjun researchonmaintenancesparepartsrequirementpredictionbasedonlstmrecurrentneuralnetwork
_version_	1718371500967329792

Research on maintenance spare parts requirement prediction based on LSTM recurrent neural network

Ejemplares similares