Calculation Method of Probability Integration Method Parameters Based on MIV-GP-BP Model

In order to guarantee the precision of the parameters of the probability integral method (PIM), starting from optimizing input and improving algorithm an algorithm integrating the genetic algorithm (GA) and particle swarm optimization (PSO) was put forward to optimize the prediction model of BP neur...

Description complète

Détails bibliographiques
Auteurs principaux: Shenshen Chi, Xuexiang Yu*, Lei Wang
Format: Article
Langue:English
Publié: Faculty of Mechanical Engineering in Slavonski Brod, Faculty of Electrical Engineering in Osijek, Faculty of Civil Engineering in Osijek 2021-01-01
Collection:Tehnički Vjesnik
Sujets:
Accès en ligne:https://hrcak.srce.hr/file/365675
_version_ 1827282305258881024
author Shenshen Chi
Xuexiang Yu*
Lei Wang
author_facet Shenshen Chi
Xuexiang Yu*
Lei Wang
author_sort Shenshen Chi
collection DOAJ
description In order to guarantee the precision of the parameters of the probability integral method (PIM), starting from optimizing input and improving algorithm an algorithm integrating the genetic algorithm (GA) and particle swarm optimization (PSO) was put forward to optimize the prediction model of BP neural network and the mean impact value algorithm (MIV) was applied to optimize the input of BP neural network. The mean impact value algorithm (MIV) was applied to optimize the input of BP neural network. The measured data of 50 working faces were chosen as the training and testing sets to build the MIV-GP-BP model. The results showed that among the five parameters, the RMSE was between 0.0058 and 1.1575, the MaxRE of q, tanβ, b and θ was less than 5.42%, and the MeaRE was less than 2.81%. The RMSE of s/H did not exceed 0.0058, the MaxRE was less than 9.66% and the MeaRE was less than 4.31% (the parameters themselves were small). The optimized neural network model had higher prediction accuracy and stability.
first_indexed 2024-04-24T09:15:57Z
format Article
id doaj.art-5cf9555912214ab8acbd11d67b51c99b
institution Directory Open Access Journal
issn 1330-3651
1848-6339
language English
last_indexed 2024-04-24T09:15:57Z
publishDate 2021-01-01
publisher Faculty of Mechanical Engineering in Slavonski Brod, Faculty of Electrical Engineering in Osijek, Faculty of Civil Engineering in Osijek
record_format Article
series Tehnički Vjesnik
spelling doaj.art-5cf9555912214ab8acbd11d67b51c99b2024-04-15T16:48:07ZengFaculty of Mechanical Engineering in Slavonski Brod, Faculty of Electrical Engineering in Osijek, Faculty of Civil Engineering in OsijekTehnički Vjesnik1330-36511848-63392021-01-0128116016810.17559/TV-20200429151307Calculation Method of Probability Integration Method Parameters Based on MIV-GP-BP ModelShenshen Chi0Xuexiang Yu*1Lei Wang21) School of Earth and Environment, Anhui University of Science and Technology 2) School of Geomatics, Anhui University of Science and Technology 3) Key Laboratory of Aviation-aerospace-ground Cooperative Monitoring and Early Warning of Coal Mining-induced Disasters of Anhui Higher Education Institutes, Anhui University of Science and Technology 4) Coal Industry Engineering Research Center of Mining Area Environmental and Disaster Cooperative Monitoring, Anhui University of Science and TechnologySchool of Geomatics, Anhui University of Science and Technology, Huainan, 232001, ChinaSchool of Geomatics, Anhui University of Science and Technology, Huainan, 232001, ChinaIn order to guarantee the precision of the parameters of the probability integral method (PIM), starting from optimizing input and improving algorithm an algorithm integrating the genetic algorithm (GA) and particle swarm optimization (PSO) was put forward to optimize the prediction model of BP neural network and the mean impact value algorithm (MIV) was applied to optimize the input of BP neural network. The mean impact value algorithm (MIV) was applied to optimize the input of BP neural network. The measured data of 50 working faces were chosen as the training and testing sets to build the MIV-GP-BP model. The results showed that among the five parameters, the RMSE was between 0.0058 and 1.1575, the MaxRE of q, tanβ, b and θ was less than 5.42%, and the MeaRE was less than 2.81%. The RMSE of s/H did not exceed 0.0058, the MaxRE was less than 9.66% and the MeaRE was less than 4.31% (the parameters themselves were small). The optimized neural network model had higher prediction accuracy and stability.https://hrcak.srce.hr/file/365675BP neural networkMIV algorithmmining subsidenceoptimization algorithmPIMunderground mining
spellingShingle Shenshen Chi
Xuexiang Yu*
Lei Wang
Calculation Method of Probability Integration Method Parameters Based on MIV-GP-BP Model
Tehnički Vjesnik
BP neural network
MIV algorithm
mining subsidence
optimization algorithm
PIM
underground mining
title Calculation Method of Probability Integration Method Parameters Based on MIV-GP-BP Model
title_full Calculation Method of Probability Integration Method Parameters Based on MIV-GP-BP Model
title_fullStr Calculation Method of Probability Integration Method Parameters Based on MIV-GP-BP Model
title_full_unstemmed Calculation Method of Probability Integration Method Parameters Based on MIV-GP-BP Model
title_short Calculation Method of Probability Integration Method Parameters Based on MIV-GP-BP Model
title_sort calculation method of probability integration method parameters based on miv gp bp model
topic BP neural network
MIV algorithm
mining subsidence
optimization algorithm
PIM
underground mining
url https://hrcak.srce.hr/file/365675
work_keys_str_mv AT shenshenchi calculationmethodofprobabilityintegrationmethodparametersbasedonmivgpbpmodel
AT xuexiangyu calculationmethodofprobabilityintegrationmethodparametersbasedonmivgpbpmodel
AT leiwang calculationmethodofprobabilityintegrationmethodparametersbasedonmivgpbpmodel