Intelligent Prediction of Aeroengine Wear Based on the SVR Optimized by GMPSO

In order to predict aeroengine wear accurately and automatically, as a predictor, support vector regression (SVR) was optimized by means of particle swarm optimization (PSO). The guided mutation strategy of PSO (GMPSO) is presented herein to determine the proper structure parameters of an SVR, as we...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Bo Zheng, Feng Gao, Xin Ma, Xiaoqiang Zhang
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	support vector regression particle swarm optimization guided mutation spectral analysis wear prediction 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/6a006ee0727f410a8cfcbd58d4f62209
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:6a006ee0727f410a8cfcbd58d4f62209
record_format	dspace
spelling	oai:doaj.org-article:6a006ee0727f410a8cfcbd58d4f622092021-11-25T16:32:26ZIntelligent Prediction of Aeroengine Wear Based on the SVR Optimized by GMPSO10.3390/app1122105922076-3417https://doaj.org/article/6a006ee0727f410a8cfcbd58d4f622092021-11-01T00:00:00Zhttps://www.mdpi.com/2076-3417/11/22/10592https://doaj.org/toc/2076-3417In order to predict aeroengine wear accurately and automatically, as a predictor, support vector regression (SVR) was optimized by means of particle swarm optimization (PSO). The guided mutation strategy of PSO (GMPSO) is presented herein to determine the proper structure parameters of an SVR, as well as the embedding dimensions of the training samples. The guided mutation strategy was able to increase the diversity of particles and improve the probability of finding the global extremum. Furthermore, single-step and multi-step prediction methods were designed to meet different accuracy requirements. A prediction comparison study on spectral analysis data was carried out, and the contrast experiments show that compared with SVR optimized by means of a traditional PSO, a neural network and an auto regressive moving average (ARMA) prediction model, the SVR optimized by means of the GMPSO approach produced prediction results not only with higher accuracy, but also with better consistency.Bo ZhengFeng GaoXin MaXiaoqiang ZhangMDPI AGarticlesupport vector regressionparticle swarm optimizationguided mutationspectral analysiswear predictionTechnologyTEngineering (General). Civil engineering (General)TA1-2040Biology (General)QH301-705.5PhysicsQC1-999ChemistryQD1-999ENApplied Sciences, Vol 11, Iss 10592, p 10592 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	support vector regression particle swarm optimization guided mutation spectral analysis wear prediction Technology T Engineering (General). Civil engineering (General) TA1-2040 Biology (General) QH301-705.5 Physics QC1-999 Chemistry QD1-999
spellingShingle	support vector regression particle swarm optimization guided mutation spectral analysis wear prediction Technology T Engineering (General). Civil engineering (General) TA1-2040 Biology (General) QH301-705.5 Physics QC1-999 Chemistry QD1-999 Bo Zheng Feng Gao Xin Ma Xiaoqiang Zhang Intelligent Prediction of Aeroengine Wear Based on the SVR Optimized by GMPSO
description	In order to predict aeroengine wear accurately and automatically, as a predictor, support vector regression (SVR) was optimized by means of particle swarm optimization (PSO). The guided mutation strategy of PSO (GMPSO) is presented herein to determine the proper structure parameters of an SVR, as well as the embedding dimensions of the training samples. The guided mutation strategy was able to increase the diversity of particles and improve the probability of finding the global extremum. Furthermore, single-step and multi-step prediction methods were designed to meet different accuracy requirements. A prediction comparison study on spectral analysis data was carried out, and the contrast experiments show that compared with SVR optimized by means of a traditional PSO, a neural network and an auto regressive moving average (ARMA) prediction model, the SVR optimized by means of the GMPSO approach produced prediction results not only with higher accuracy, but also with better consistency.
format	article
author	Bo Zheng Feng Gao Xin Ma Xiaoqiang Zhang
author_facet	Bo Zheng Feng Gao Xin Ma Xiaoqiang Zhang
author_sort	Bo Zheng
title	Intelligent Prediction of Aeroengine Wear Based on the SVR Optimized by GMPSO
title_short	Intelligent Prediction of Aeroengine Wear Based on the SVR Optimized by GMPSO
title_full	Intelligent Prediction of Aeroengine Wear Based on the SVR Optimized by GMPSO
title_fullStr	Intelligent Prediction of Aeroengine Wear Based on the SVR Optimized by GMPSO
title_full_unstemmed	Intelligent Prediction of Aeroengine Wear Based on the SVR Optimized by GMPSO
title_sort	intelligent prediction of aeroengine wear based on the svr optimized by gmpso
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/6a006ee0727f410a8cfcbd58d4f62209
work_keys_str_mv	AT bozheng intelligentpredictionofaeroenginewearbasedonthesvroptimizedbygmpso AT fenggao intelligentpredictionofaeroenginewearbasedonthesvroptimizedbygmpso AT xinma intelligentpredictionofaeroenginewearbasedonthesvroptimizedbygmpso AT xiaoqiangzhang intelligentpredictionofaeroenginewearbasedonthesvroptimizedbygmpso
_version_	1718413141933555712

Intelligent Prediction of Aeroengine Wear Based on the SVR Optimized by GMPSO

Ejemplares similares