No Cover Image

E-Thesis 613 views

Predictive Maintenance of an External Gear Pump using Machine Learning Algorithms / KAYALVIZHI LAKSHMANAN

Swansea University Author: KAYALVIZHI LAKSHMANAN

Full text not available from this repository: check for access using links below.

DOI (Published version): 10.23889/SUthesis.58703

Abstract

The importance of Predictive Maintenance is critical for engineering industries, such as manufacturing, aerospace and energy. Unexpected failures cause unpredictable downtime, which can be disruptive and high costs due to reduced productivity. This forces industries to ensure the reliability of thei...

Full description

Published: Swansea 2021
Institution: Swansea University
Degree level: Doctoral
Degree name: Ph.D
Supervisor: Auricchio, Ferdinando ; Gil, Antonio J.
URI: https://cronfa.swan.ac.uk/Record/cronfa58703
Tags: Add Tag
No Tags, Be the first to tag this record!
first_indexed 2021-11-18T12:44:44Z
last_indexed 2022-05-13T03:31:11Z
id cronfa58703
recordtype RisThesis
fullrecord <?xml version="1.0"?><rfc1807><datestamp>2022-05-12T14:55:04.3723657</datestamp><bib-version>v2</bib-version><id>58703</id><entry>2021-11-18</entry><title>Predictive Maintenance of an External Gear Pump using Machine Learning Algorithms</title><swanseaauthors><author><sid>83529ed200f9c5d1b9283ca9ffc1e0ba</sid><firstname>KAYALVIZHI</firstname><surname>LAKSHMANAN</surname><name>KAYALVIZHI LAKSHMANAN</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2021-11-18</date><abstract>The importance of Predictive Maintenance is critical for engineering industries, such as manufacturing, aerospace and energy. Unexpected failures cause unpredictable downtime, which can be disruptive and high costs due to reduced productivity. This forces industries to ensure the reliability of their equip-ment. In order to increase the reliability of equipment, maintenance actions, such as repairs, replacements, equipment updates, and corrective actions are employed. These actions a&#xFB00;ect the &#xFB02;exibility, quality of operation and manu-facturing time. It is therefore essential to plan maintenance before failure occurs.Traditional maintenance techniques rely on checks conducted routinely based on running hours of the machine. The drawback of this approach is that maintenance is sometimes performed before it is required. Therefore, conducting maintenance based on the actual condition of the equipment is the optimal solu-tion. This requires collecting real-time data on the condition of the equipment, using sensors (to detect events and send information to computer processor).Predictive Maintenance uses these types of techniques or analytics to inform about the current, and future state of the equipment. In the last decade, with the introduction of the Internet of Things (IoT), Machine Learning (ML), cloud computing and Big Data Analytics, manufacturing industry has moved forward towards implementing Predictive Maintenance, resulting in increased uptime and quality control, optimisation of maintenance routes, improved worker safety and greater productivity.The present thesis describes a novel computational strategy of Predictive Maintenance (fault diagnosis and fault prognosis) with ML and Deep Learning applications for an FG304 series external gear pump, also known as a domino pump. In the absence of a comprehensive set of experimental data, synthetic data generation techniques are implemented for Predictive Maintenance by perturbing the frequency content of time series generated using High-Fidelity computational techniques. In addition, various types of feature extraction methods considered to extract most discriminatory informations from the data. For fault diagnosis, three types of ML classi&#xFB01;cation algorithms are employed, namely Multilayer Perceptron (MLP), Support Vector Machine (SVM) and Naive Bayes (NB) algorithms. For prognosis, ML regression algorithms, such as MLP and SVM, are utilised. Although signi&#xFB01;cant work has been reported by previous authors, it remains di&#xFB03;cult to optimise the choice of hyper-parameters (important parameters whose value is used to control the learning process) for each speci&#xFB01;c ML algorithm. For instance, the type of SVM kernel function or the selection of the MLP activation function and the optimum number of hidden layers (and neurons).It is widely understood that the reliability of ML algorithms is strongly depen-dent upon the existence of a su&#xFB03;ciently large quantity of high-quality training data. In the present thesis, due to the unavailability of experimental data, a novel high-&#xFB01;delity in-silico dataset is generated via a Computational Fluid Dynamic (CFD) model, which has been used for the training of the underlying ML metamodel. In addition, a large number of scenarios are recreated, ranging from healthy to faulty ones (e.g. clogging, radial gap variations, axial gap variations, viscosity variations, speed variations). Furthermore, the high-&#xFB01;delity dataset is re-enacted by using degradation functions to predict the remaining useful life (fault prognosis) of an external gear pump.The thesis explores and compares the performance of MLP, SVM and NB algo-rithms for fault diagnosis and MLP and SVM for fault prognosis. In order to enable fast training and reliable testing of the MLP algorithm, some prede&#xFB01;ned network architectures, like 2n neurons per hidden layer, are used to speed up the identi&#xFB01;cation of the precise number of neurons (shown to be useful when the sample data set is su&#xFB03;ciently large). Finally, a series of benchmark tests are presented, enabling to conclude that for fault diagnosis, the use of wavelet features and a MLP algorithm can provide the best accuracy, and the MLP al-gorithm provides the best prediction results for fault prognosis. In addition, benchmark examples are simulated to demonstrate the mesh convergence for the CFD model whereas, quanti&#xFB01;cation analysis and noise in&#xFB02;uence on training data are performed for ML algorithms.</abstract><type>E-Thesis</type><journal/><volume/><journalNumber/><paginationStart/><paginationEnd/><publisher/><placeOfPublication>Swansea</placeOfPublication><isbnPrint/><isbnElectronic/><issnPrint/><issnElectronic/><keywords>Fault diagnosis, Fault prognosis, Wavelet transform, Noise perturbation, Support Vector Machine, MultiLayer Perceptron, Naive Bayes</keywords><publishedDay>18</publishedDay><publishedMonth>11</publishedMonth><publishedYear>2021</publishedYear><publishedDate>2021-11-18</publishedDate><doi>10.23889/SUthesis.58703</doi><url/><notes/><college>COLLEGE NANME</college><CollegeCode>COLLEGE CODE</CollegeCode><institution>Swansea University</institution><supervisor>Auricchio, Ferdinando ; Gil, Antonio J.</supervisor><degreelevel>Doctoral</degreelevel><degreename>Ph.D</degreename><degreesponsorsfunders>Erasmus Mundus Joint Doctorate in Simulation in Engineering and Entrepreneurship Development</degreesponsorsfunders><apcterm/><lastEdited>2022-05-12T14:55:04.3723657</lastEdited><Created>2021-11-18T12:41:59.2316387</Created><path><level id="1">Faculty of Science and Engineering</level><level id="2">School of Engineering and Applied Sciences - Uncategorised</level></path><authors><author><firstname>KAYALVIZHI</firstname><surname>LAKSHMANAN</surname><order>1</order></author></authors><documents><document><filename>Under embargo</filename><originalFilename>Under embargo</originalFilename><uploaded>2022-05-12T14:51:41.0721739</uploaded><type>Output</type><contentLength>10738655</contentLength><contentType>application/pdf</contentType><version>Redacted version - open access</version><cronfaStatus>true</cronfaStatus><embargoDate>2024-07-16T00:00:00.0000000</embargoDate><documentNotes>Copyright: The author, Kayalvizhi Lakshmanan, 2021.</documentNotes><copyrightCorrect>true</copyrightCorrect><language>eng</language></document></documents><OutputDurs/></rfc1807>
spelling 2022-05-12T14:55:04.3723657 v2 58703 2021-11-18 Predictive Maintenance of an External Gear Pump using Machine Learning Algorithms 83529ed200f9c5d1b9283ca9ffc1e0ba KAYALVIZHI LAKSHMANAN KAYALVIZHI LAKSHMANAN true false 2021-11-18 The importance of Predictive Maintenance is critical for engineering industries, such as manufacturing, aerospace and energy. Unexpected failures cause unpredictable downtime, which can be disruptive and high costs due to reduced productivity. This forces industries to ensure the reliability of their equip-ment. In order to increase the reliability of equipment, maintenance actions, such as repairs, replacements, equipment updates, and corrective actions are employed. These actions affect the flexibility, quality of operation and manu-facturing time. It is therefore essential to plan maintenance before failure occurs.Traditional maintenance techniques rely on checks conducted routinely based on running hours of the machine. The drawback of this approach is that maintenance is sometimes performed before it is required. Therefore, conducting maintenance based on the actual condition of the equipment is the optimal solu-tion. This requires collecting real-time data on the condition of the equipment, using sensors (to detect events and send information to computer processor).Predictive Maintenance uses these types of techniques or analytics to inform about the current, and future state of the equipment. In the last decade, with the introduction of the Internet of Things (IoT), Machine Learning (ML), cloud computing and Big Data Analytics, manufacturing industry has moved forward towards implementing Predictive Maintenance, resulting in increased uptime and quality control, optimisation of maintenance routes, improved worker safety and greater productivity.The present thesis describes a novel computational strategy of Predictive Maintenance (fault diagnosis and fault prognosis) with ML and Deep Learning applications for an FG304 series external gear pump, also known as a domino pump. In the absence of a comprehensive set of experimental data, synthetic data generation techniques are implemented for Predictive Maintenance by perturbing the frequency content of time series generated using High-Fidelity computational techniques. In addition, various types of feature extraction methods considered to extract most discriminatory informations from the data. For fault diagnosis, three types of ML classification algorithms are employed, namely Multilayer Perceptron (MLP), Support Vector Machine (SVM) and Naive Bayes (NB) algorithms. For prognosis, ML regression algorithms, such as MLP and SVM, are utilised. Although significant work has been reported by previous authors, it remains difficult to optimise the choice of hyper-parameters (important parameters whose value is used to control the learning process) for each specific ML algorithm. For instance, the type of SVM kernel function or the selection of the MLP activation function and the optimum number of hidden layers (and neurons).It is widely understood that the reliability of ML algorithms is strongly depen-dent upon the existence of a sufficiently large quantity of high-quality training data. In the present thesis, due to the unavailability of experimental data, a novel high-fidelity in-silico dataset is generated via a Computational Fluid Dynamic (CFD) model, which has been used for the training of the underlying ML metamodel. In addition, a large number of scenarios are recreated, ranging from healthy to faulty ones (e.g. clogging, radial gap variations, axial gap variations, viscosity variations, speed variations). Furthermore, the high-fidelity dataset is re-enacted by using degradation functions to predict the remaining useful life (fault prognosis) of an external gear pump.The thesis explores and compares the performance of MLP, SVM and NB algo-rithms for fault diagnosis and MLP and SVM for fault prognosis. In order to enable fast training and reliable testing of the MLP algorithm, some predefined network architectures, like 2n neurons per hidden layer, are used to speed up the identification of the precise number of neurons (shown to be useful when the sample data set is sufficiently large). Finally, a series of benchmark tests are presented, enabling to conclude that for fault diagnosis, the use of wavelet features and a MLP algorithm can provide the best accuracy, and the MLP al-gorithm provides the best prediction results for fault prognosis. In addition, benchmark examples are simulated to demonstrate the mesh convergence for the CFD model whereas, quantification analysis and noise influence on training data are performed for ML algorithms. E-Thesis Swansea Fault diagnosis, Fault prognosis, Wavelet transform, Noise perturbation, Support Vector Machine, MultiLayer Perceptron, Naive Bayes 18 11 2021 2021-11-18 10.23889/SUthesis.58703 COLLEGE NANME COLLEGE CODE Swansea University Auricchio, Ferdinando ; Gil, Antonio J. Doctoral Ph.D Erasmus Mundus Joint Doctorate in Simulation in Engineering and Entrepreneurship Development 2022-05-12T14:55:04.3723657 2021-11-18T12:41:59.2316387 Faculty of Science and Engineering School of Engineering and Applied Sciences - Uncategorised KAYALVIZHI LAKSHMANAN 1 Under embargo Under embargo 2022-05-12T14:51:41.0721739 Output 10738655 application/pdf Redacted version - open access true 2024-07-16T00:00:00.0000000 Copyright: The author, Kayalvizhi Lakshmanan, 2021. true eng
title Predictive Maintenance of an External Gear Pump using Machine Learning Algorithms
spellingShingle Predictive Maintenance of an External Gear Pump using Machine Learning Algorithms
KAYALVIZHI LAKSHMANAN
title_short Predictive Maintenance of an External Gear Pump using Machine Learning Algorithms
title_full Predictive Maintenance of an External Gear Pump using Machine Learning Algorithms
title_fullStr Predictive Maintenance of an External Gear Pump using Machine Learning Algorithms
title_full_unstemmed Predictive Maintenance of an External Gear Pump using Machine Learning Algorithms
title_sort Predictive Maintenance of an External Gear Pump using Machine Learning Algorithms
author_id_str_mv 83529ed200f9c5d1b9283ca9ffc1e0ba
author_id_fullname_str_mv 83529ed200f9c5d1b9283ca9ffc1e0ba_***_KAYALVIZHI LAKSHMANAN
author KAYALVIZHI LAKSHMANAN
author2 KAYALVIZHI LAKSHMANAN
format E-Thesis
publishDate 2021
institution Swansea University
doi_str_mv 10.23889/SUthesis.58703
college_str Faculty of Science and Engineering
hierarchytype
hierarchy_top_id facultyofscienceandengineering
hierarchy_top_title Faculty of Science and Engineering
hierarchy_parent_id facultyofscienceandengineering
hierarchy_parent_title Faculty of Science and Engineering
department_str School of Engineering and Applied Sciences - Uncategorised{{{_:::_}}}Faculty of Science and Engineering{{{_:::_}}}School of Engineering and Applied Sciences - Uncategorised
document_store_str 0
active_str 0
description The importance of Predictive Maintenance is critical for engineering industries, such as manufacturing, aerospace and energy. Unexpected failures cause unpredictable downtime, which can be disruptive and high costs due to reduced productivity. This forces industries to ensure the reliability of their equip-ment. In order to increase the reliability of equipment, maintenance actions, such as repairs, replacements, equipment updates, and corrective actions are employed. These actions affect the flexibility, quality of operation and manu-facturing time. It is therefore essential to plan maintenance before failure occurs.Traditional maintenance techniques rely on checks conducted routinely based on running hours of the machine. The drawback of this approach is that maintenance is sometimes performed before it is required. Therefore, conducting maintenance based on the actual condition of the equipment is the optimal solu-tion. This requires collecting real-time data on the condition of the equipment, using sensors (to detect events and send information to computer processor).Predictive Maintenance uses these types of techniques or analytics to inform about the current, and future state of the equipment. In the last decade, with the introduction of the Internet of Things (IoT), Machine Learning (ML), cloud computing and Big Data Analytics, manufacturing industry has moved forward towards implementing Predictive Maintenance, resulting in increased uptime and quality control, optimisation of maintenance routes, improved worker safety and greater productivity.The present thesis describes a novel computational strategy of Predictive Maintenance (fault diagnosis and fault prognosis) with ML and Deep Learning applications for an FG304 series external gear pump, also known as a domino pump. In the absence of a comprehensive set of experimental data, synthetic data generation techniques are implemented for Predictive Maintenance by perturbing the frequency content of time series generated using High-Fidelity computational techniques. In addition, various types of feature extraction methods considered to extract most discriminatory informations from the data. For fault diagnosis, three types of ML classification algorithms are employed, namely Multilayer Perceptron (MLP), Support Vector Machine (SVM) and Naive Bayes (NB) algorithms. For prognosis, ML regression algorithms, such as MLP and SVM, are utilised. Although significant work has been reported by previous authors, it remains difficult to optimise the choice of hyper-parameters (important parameters whose value is used to control the learning process) for each specific ML algorithm. For instance, the type of SVM kernel function or the selection of the MLP activation function and the optimum number of hidden layers (and neurons).It is widely understood that the reliability of ML algorithms is strongly depen-dent upon the existence of a sufficiently large quantity of high-quality training data. In the present thesis, due to the unavailability of experimental data, a novel high-fidelity in-silico dataset is generated via a Computational Fluid Dynamic (CFD) model, which has been used for the training of the underlying ML metamodel. In addition, a large number of scenarios are recreated, ranging from healthy to faulty ones (e.g. clogging, radial gap variations, axial gap variations, viscosity variations, speed variations). Furthermore, the high-fidelity dataset is re-enacted by using degradation functions to predict the remaining useful life (fault prognosis) of an external gear pump.The thesis explores and compares the performance of MLP, SVM and NB algo-rithms for fault diagnosis and MLP and SVM for fault prognosis. In order to enable fast training and reliable testing of the MLP algorithm, some predefined network architectures, like 2n neurons per hidden layer, are used to speed up the identification of the precise number of neurons (shown to be useful when the sample data set is sufficiently large). Finally, a series of benchmark tests are presented, enabling to conclude that for fault diagnosis, the use of wavelet features and a MLP algorithm can provide the best accuracy, and the MLP al-gorithm provides the best prediction results for fault prognosis. In addition, benchmark examples are simulated to demonstrate the mesh convergence for the CFD model whereas, quantification analysis and noise influence on training data are performed for ML algorithms.
published_date 2021-11-18T04:15:26Z
_version_ 1763754038221864960
score 11.016235

Similar Items