Auto-NAHL: A Neural Network Approach for Condition-Based Maintenance of Complex Industrial Systems

<p dir="ltr">Nowadays, machine learning has emerged as a promising alternative for condition monitoring of industrial processes, making it indispensable for maintenance planning. Such a learning model is able to assess health states in real time provided that both training and testin...

وصف كامل

محفوظ في:
التفاصيل البيبلوغرافية
المؤلف الرئيسي: Tarek Berghout (16905132) (author)
مؤلفون آخرون: Mohamed Benbouzid (13183968) (author), S. M. Muyeen (14778337) (author), Toufik Bentrcia (16905135) (author), Leila-Hayet Mouss (16905138) (author)
منشور في: 2021
الموضوعات:
الوسوم: إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
_version_ 1864513561751977984
author Tarek Berghout (16905132)
author2 Mohamed Benbouzid (13183968)
S. M. Muyeen (14778337)
Toufik Bentrcia (16905135)
Leila-Hayet Mouss (16905138)
author2_role author
author
author
author
author_facet Tarek Berghout (16905132)
Mohamed Benbouzid (13183968)
S. M. Muyeen (14778337)
Toufik Bentrcia (16905135)
Leila-Hayet Mouss (16905138)
author_role author
dc.creator.none.fl_str_mv Tarek Berghout (16905132)
Mohamed Benbouzid (13183968)
S. M. Muyeen (14778337)
Toufik Bentrcia (16905135)
Leila-Hayet Mouss (16905138)
dc.date.none.fl_str_mv 2021-11-09T00:00:00Z
dc.identifier.none.fl_str_mv 10.1109/access.2021.3127084
dc.relation.none.fl_str_mv https://figshare.com/articles/journal_contribution/Auto-NAHL_A_Neural_Network_Approach_for_Condition-Based_Maintenance_of_Complex_Industrial_Systems/24056562
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Engineering
Electrical engineering
Information and computing sciences
Artificial intelligence
Machine learning
Feature extraction
Classification algorithms
Tuning
Training
Mathematical models
Correlation
Tools
Compressed sensing
Condition monitoring
Fault detection
Hydraulic systems
Industrial system
Machine learning
Particle swarm optimization
Predictive maintenance
dc.title.none.fl_str_mv Auto-NAHL: A Neural Network Approach for Condition-Based Maintenance of Complex Industrial Systems
dc.type.none.fl_str_mv Text
Journal contribution
info:eu-repo/semantics/publishedVersion
text
contribution to journal
description <p dir="ltr">Nowadays, machine learning has emerged as a promising alternative for condition monitoring of industrial processes, making it indispensable for maintenance planning. Such a learning model is able to assess health states in real time provided that both training and testing samples are complete and have the same probability distribution. However, it is rare and difficult in practical applications to meet these requirements due to the continuous change in working conditions. Besides, conventional hyperparameters tuning via grid search or manual tuning requires a lot of human intervention and becomes inflexible for users. Two objectives are targeted in this work. In an attempt to remedy the data distribution mismatch issue, we firstly introduce a feature extraction and selection approach built upon correlation analysis and dimensionality reduction. Secondly, to diminish human intervention burdens, we propose an Automatic artificial Neural network with an Augmented Hidden Layer (Auto-NAHL) for the classification of health states. Within the designed network, it is worthy to mention that the novelty of the implemented neural architecture is attributed to the new multiple feature mappings of the inputs, where such configuration allows the hidden layer to learn multiple representations from several random linear mappings and produce a single final efficient representation. Hyperparameters tuning including the network architecture, is fully automated by incorporating Particle Swarm Optimization (PSO) technique. The designed learning process is evaluated on a complex industrial plant as well as various classification problems. Based on the obtained results, it can be claimed that our proposal yields better response to new hidden representations by obtaining a higher approximation compared to some previous works.</p><h2>Other Information</h2><p dir="ltr">Published in: IEEE Access<br>License: <a href="https://creativecommons.org/licenses/by/4.0/legalcode" target="_blank">https://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1109/access.2021.3127084" target="_blank">https://dx.doi.org/10.1109/access.2021.3127084</a></p>
eu_rights_str_mv openAccess
id Manara2_53d300a7ae1997c4d03c89f7e6b2c034
identifier_str_mv 10.1109/access.2021.3127084
network_acronym_str Manara2
network_name_str Manara2
oai_identifier_str oai:figshare.com:article/24056562
publishDate 2021
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling Auto-NAHL: A Neural Network Approach for Condition-Based Maintenance of Complex Industrial SystemsTarek Berghout (16905132)Mohamed Benbouzid (13183968)S. M. Muyeen (14778337)Toufik Bentrcia (16905135)Leila-Hayet Mouss (16905138)EngineeringElectrical engineeringInformation and computing sciencesArtificial intelligenceMachine learningFeature extractionClassification algorithmsTuningTrainingMathematical modelsCorrelationToolsCompressed sensingCondition monitoringFault detectionHydraulic systemsIndustrial systemMachine learningParticle swarm optimizationPredictive maintenance<p dir="ltr">Nowadays, machine learning has emerged as a promising alternative for condition monitoring of industrial processes, making it indispensable for maintenance planning. Such a learning model is able to assess health states in real time provided that both training and testing samples are complete and have the same probability distribution. However, it is rare and difficult in practical applications to meet these requirements due to the continuous change in working conditions. Besides, conventional hyperparameters tuning via grid search or manual tuning requires a lot of human intervention and becomes inflexible for users. Two objectives are targeted in this work. In an attempt to remedy the data distribution mismatch issue, we firstly introduce a feature extraction and selection approach built upon correlation analysis and dimensionality reduction. Secondly, to diminish human intervention burdens, we propose an Automatic artificial Neural network with an Augmented Hidden Layer (Auto-NAHL) for the classification of health states. Within the designed network, it is worthy to mention that the novelty of the implemented neural architecture is attributed to the new multiple feature mappings of the inputs, where such configuration allows the hidden layer to learn multiple representations from several random linear mappings and produce a single final efficient representation. Hyperparameters tuning including the network architecture, is fully automated by incorporating Particle Swarm Optimization (PSO) technique. The designed learning process is evaluated on a complex industrial plant as well as various classification problems. Based on the obtained results, it can be claimed that our proposal yields better response to new hidden representations by obtaining a higher approximation compared to some previous works.</p><h2>Other Information</h2><p dir="ltr">Published in: IEEE Access<br>License: <a href="https://creativecommons.org/licenses/by/4.0/legalcode" target="_blank">https://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1109/access.2021.3127084" target="_blank">https://dx.doi.org/10.1109/access.2021.3127084</a></p>2021-11-09T00:00:00ZTextJournal contributioninfo:eu-repo/semantics/publishedVersiontextcontribution to journal10.1109/access.2021.3127084https://figshare.com/articles/journal_contribution/Auto-NAHL_A_Neural_Network_Approach_for_Condition-Based_Maintenance_of_Complex_Industrial_Systems/24056562CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/240565622021-11-09T00:00:00Z
spellingShingle Auto-NAHL: A Neural Network Approach for Condition-Based Maintenance of Complex Industrial Systems
Tarek Berghout (16905132)
Engineering
Electrical engineering
Information and computing sciences
Artificial intelligence
Machine learning
Feature extraction
Classification algorithms
Tuning
Training
Mathematical models
Correlation
Tools
Compressed sensing
Condition monitoring
Fault detection
Hydraulic systems
Industrial system
Machine learning
Particle swarm optimization
Predictive maintenance
status_str publishedVersion
title Auto-NAHL: A Neural Network Approach for Condition-Based Maintenance of Complex Industrial Systems
title_full Auto-NAHL: A Neural Network Approach for Condition-Based Maintenance of Complex Industrial Systems
title_fullStr Auto-NAHL: A Neural Network Approach for Condition-Based Maintenance of Complex Industrial Systems
title_full_unstemmed Auto-NAHL: A Neural Network Approach for Condition-Based Maintenance of Complex Industrial Systems
title_short Auto-NAHL: A Neural Network Approach for Condition-Based Maintenance of Complex Industrial Systems
title_sort Auto-NAHL: A Neural Network Approach for Condition-Based Maintenance of Complex Industrial Systems
topic Engineering
Electrical engineering
Information and computing sciences
Artificial intelligence
Machine learning
Feature extraction
Classification algorithms
Tuning
Training
Mathematical models
Correlation
Tools
Compressed sensing
Condition monitoring
Fault detection
Hydraulic systems
Industrial system
Machine learning
Particle swarm optimization
Predictive maintenance