Machine failure prediction technique using recurrent neural network long short-term memory-particle swarm optimization algorithm

This paper proposes a hybrid prediction technique based on Recurrent Neural Network Long-Short-Term Memory (RNN-LSTM) with the integration of Particle Swarm Optimization (PSO) algorithm to estimate the Remaining Useful Life (RUL) of machines. LSTM is an improvement of RNN as RNN faces issues with pr...

Full description

Main Authors: Rashid, N.A., Abdul Aziz, I., Hasan, M.H.B.
Format: Article
Institution: Universiti Teknologi Petronas
Record Id / ISBN-0: utp-eprints.23513 /
Published: Springer Verlag 2019
Online Access: https://www.scopus.com/inward/record.uri?eid=2-s2.0-85065925843&doi=10.1007%2f978-3-030-19810-7_24&partnerID=40&md5=f32eb9404f711e8e244ade6d877db179
http://eprints.utp.edu.my/23513/
Tags: Add Tag
No Tags, Be the first to tag this record!
id utp-eprints.23513
recordtype eprints
spelling utp-eprints.235132021-08-19T07:58:02Z Machine failure prediction technique using recurrent neural network long short-term memory-particle swarm optimization algorithm Rashid, N.A. Abdul Aziz, I. Hasan, M.H.B. This paper proposes a hybrid prediction technique based on Recurrent Neural Network Long-Short-Term Memory (RNN-LSTM) with the integration of Particle Swarm Optimization (PSO) algorithm to estimate the Remaining Useful Life (RUL) of machines. LSTM is an improvement of RNN as RNN faces issues with predicting long-term dependencies. Issues such as vanishing and exploding gradients are the results of backpropagating errors, taking place when the network is learning to store and relate information over extended time intervals. RNN-LSTM is a feasible technique for this research due to its effectiveness in resolving sequential long-term dependencies problems. However, the accuracy can still be enhanced to a satisfactory value considering the optimal network topology has not been discovered yet. Accuracy improvement can be achieved by resorting to hyperparameter tuning. A result of proof of concept validates that by increasing the number of epochs, the accuracy of prediction has improved but increases the execution time. To optimize between the accuracy and execution time, a population-inspired Particle Swarm Optimization (PSO) algorithm is employed. PSO will be utilized to select the optimal RNN-LSTM topology specifically the learning rate instead of using manual search. This optimized hybrid prediction technique is useful to be implemented in predictive maintenance to predict machine failure. © Springer Nature Switzerland AG 2019. Springer Verlag 2019 Article NonPeerReviewed https://www.scopus.com/inward/record.uri?eid=2-s2.0-85065925843&doi=10.1007%2f978-3-030-19810-7_24&partnerID=40&md5=f32eb9404f711e8e244ade6d877db179 Rashid, N.A. and Abdul Aziz, I. and Hasan, M.H.B. (2019) Machine failure prediction technique using recurrent neural network long short-term memory-particle swarm optimization algorithm. Advances in Intelligent Systems and Computing, 985 . pp. 243-252. http://eprints.utp.edu.my/23513/
institution Universiti Teknologi Petronas
collection UTP Institutional Repository
description This paper proposes a hybrid prediction technique based on Recurrent Neural Network Long-Short-Term Memory (RNN-LSTM) with the integration of Particle Swarm Optimization (PSO) algorithm to estimate the Remaining Useful Life (RUL) of machines. LSTM is an improvement of RNN as RNN faces issues with predicting long-term dependencies. Issues such as vanishing and exploding gradients are the results of backpropagating errors, taking place when the network is learning to store and relate information over extended time intervals. RNN-LSTM is a feasible technique for this research due to its effectiveness in resolving sequential long-term dependencies problems. However, the accuracy can still be enhanced to a satisfactory value considering the optimal network topology has not been discovered yet. Accuracy improvement can be achieved by resorting to hyperparameter tuning. A result of proof of concept validates that by increasing the number of epochs, the accuracy of prediction has improved but increases the execution time. To optimize between the accuracy and execution time, a population-inspired Particle Swarm Optimization (PSO) algorithm is employed. PSO will be utilized to select the optimal RNN-LSTM topology specifically the learning rate instead of using manual search. This optimized hybrid prediction technique is useful to be implemented in predictive maintenance to predict machine failure. © Springer Nature Switzerland AG 2019.
format Article
author Rashid, N.A.
Abdul Aziz, I.
Hasan, M.H.B.
spellingShingle Rashid, N.A.
Abdul Aziz, I.
Hasan, M.H.B.
Machine failure prediction technique using recurrent neural network long short-term memory-particle swarm optimization algorithm
author_sort Rashid, N.A.
title Machine failure prediction technique using recurrent neural network long short-term memory-particle swarm optimization algorithm
title_short Machine failure prediction technique using recurrent neural network long short-term memory-particle swarm optimization algorithm
title_full Machine failure prediction technique using recurrent neural network long short-term memory-particle swarm optimization algorithm
title_fullStr Machine failure prediction technique using recurrent neural network long short-term memory-particle swarm optimization algorithm
title_full_unstemmed Machine failure prediction technique using recurrent neural network long short-term memory-particle swarm optimization algorithm
title_sort machine failure prediction technique using recurrent neural network long short-term memory-particle swarm optimization algorithm
publisher Springer Verlag
publishDate 2019
url https://www.scopus.com/inward/record.uri?eid=2-s2.0-85065925843&doi=10.1007%2f978-3-030-19810-7_24&partnerID=40&md5=f32eb9404f711e8e244ade6d877db179
http://eprints.utp.edu.my/23513/
_version_ 1741196687429337088
score 11.62408

Similar Items