No Cover Image

E-Thesis 199 views 47 downloads

Computational issues in process optimisation using historical data. / Nazri Mohd Nawi

Swansea University Author: Nazri Mohd Nawi

Abstract

This thesis presents a new generic approach to improve the computational efficiency of neural-network-training algorithms and investigates the applicability of its 'learning from examples'' featured in improving the performance of a current intelligent diagnostic system. The contribut...

Full description

Published: 2007
Institution: Swansea University
Degree level: Doctoral
Degree name: Ph.D
URI: https://cronfa.swan.ac.uk/Record/cronfa42799
Tags: Add Tag
No Tags, Be the first to tag this record!
first_indexed 2018-08-02T18:55:34Z
last_indexed 2018-08-03T10:11:07Z
id cronfa42799
recordtype RisThesis
fullrecord <?xml version="1.0"?><rfc1807><datestamp>2018-08-02T16:24:30.5077956</datestamp><bib-version>v2</bib-version><id>42799</id><entry>2018-08-02</entry><title>Computational issues in process optimisation using historical data.</title><swanseaauthors><author><sid>01fa9bb7aa608f32204690b2a946de7b</sid><ORCID>NULL</ORCID><firstname>Nazri Mohd</firstname><surname>Nawi</surname><name>Nazri Mohd Nawi</name><active>true</active><ethesisStudent>true</ethesisStudent></author></swanseaauthors><date>2018-08-02</date><abstract>This thesis presents a new generic approach to improve the computational efficiency of neural-network-training algorithms and investigates the applicability of its 'learning from examples'' featured in improving the performance of a current intelligent diagnostic system. The contribution of this thesis is summarised in the following two points: For the first time in the literature, it has been shown that significant improvements in the computational efficiency of neural-network algorithms can be achieved using the proposed methodology based on using adaptive-gain variation. The capabilities of the current Knowledge Hyper-surface method (Meghana R. Ransing, 2002) are enhanced to overcome its existing limitations in modelling an exponential increase in the shape of the hyper-surface. Neural-network techniques, particularly back-propagation algorithms, have been widely used as a tool for discovering a mapping function between a known set of input and output examples. Neural networks learn from the known example set by adjusting its internal parameters, referred to as weights, using an optimisation procedure based on the 'least square fit principle'. The optimisation procedure normally involves thousands of iterations to converge to an acceptable solution. Hence, improving the computational efficiency of a neural-network algorithm is an active area of research. Various options for improving the computational efficiency of neural networks have been reviewed in this thesis. It has been shown in the existing literature that the variation of the gain parameter improves the learning efficiency of the gradient-descent method. However, it can be concluded from previous researchers' claims that the adaptive-gain variation improved the learning rate and hence the efficiency. It was discovered in this thesis that the gain variation has no influence on the learning rate; however, it actually influences the search direction. This made it possible to develop a novel approach that modifies the gradient-search direction by introducing the adaptive-gain variation. The proposed method is robust and has been shown that it can easily be implemented in all commonly used gradient- based optimisation algorithms. It has also been shown that it significantly improves the computational efficiency as compared to existing neural-network training algorithms. Computer simulations on a number of benchmark problems are used throughout to illustrate the improvement proposed in this thesis. In a foundry a large amount of data is generated within the foundry every time a casting is poured. Furthermore, with the increased number of computing tools and power there is a need to develop an efficient, intelligent diagnostic tool that can learn from the historical data to gain further insight into cause and effect relationships. In this study the performance of the current Knowledge Hyper-surface method was reviewed and the mathematical formulation of the current Knowledge Hyper-surface method was analysed to identify its limitations. An enhancement is proposed by introducing mid-points in the existing shape formulation. It is shown that the midpoints' shape function can successfully constrain the shape of decision hyper-surface to become more realistic with an acceptable result in a multi-dimensional case. This is a novel and original approach and is of direct relevance to the foundry industry.</abstract><type>E-Thesis</type><journal/><journalNumber></journalNumber><paginationStart/><paginationEnd/><publisher/><placeOfPublication/><isbnPrint/><issnPrint/><issnElectronic/><keywords>Computer science.;Artificial intelligence.</keywords><publishedDay>31</publishedDay><publishedMonth>12</publishedMonth><publishedYear>2007</publishedYear><publishedDate>2007-12-31</publishedDate><doi/><url/><notes/><college>COLLEGE NANME</college><department>Engineering</department><CollegeCode>COLLEGE CODE</CollegeCode><institution>Swansea University</institution><degreelevel>Doctoral</degreelevel><degreename>Ph.D</degreename><apcterm/><lastEdited>2018-08-02T16:24:30.5077956</lastEdited><Created>2018-08-02T16:24:30.5077956</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>Nazri Mohd</firstname><surname>Nawi</surname><orcid>NULL</orcid><order>1</order></author></authors><documents><document><filename>0042799-02082018162522.pdf</filename><originalFilename>10807575.pdf</originalFilename><uploaded>2018-08-02T16:25:22.8000000</uploaded><type>Output</type><contentLength>12561675</contentLength><contentType>application/pdf</contentType><version>E-Thesis</version><cronfaStatus>true</cronfaStatus><embargoDate>2018-08-02T16:25:22.8000000</embargoDate><copyrightCorrect>false</copyrightCorrect></document></documents><OutputDurs/></rfc1807>
spelling 2018-08-02T16:24:30.5077956 v2 42799 2018-08-02 Computational issues in process optimisation using historical data. 01fa9bb7aa608f32204690b2a946de7b NULL Nazri Mohd Nawi Nazri Mohd Nawi true true 2018-08-02 This thesis presents a new generic approach to improve the computational efficiency of neural-network-training algorithms and investigates the applicability of its 'learning from examples'' featured in improving the performance of a current intelligent diagnostic system. The contribution of this thesis is summarised in the following two points: For the first time in the literature, it has been shown that significant improvements in the computational efficiency of neural-network algorithms can be achieved using the proposed methodology based on using adaptive-gain variation. The capabilities of the current Knowledge Hyper-surface method (Meghana R. Ransing, 2002) are enhanced to overcome its existing limitations in modelling an exponential increase in the shape of the hyper-surface. Neural-network techniques, particularly back-propagation algorithms, have been widely used as a tool for discovering a mapping function between a known set of input and output examples. Neural networks learn from the known example set by adjusting its internal parameters, referred to as weights, using an optimisation procedure based on the 'least square fit principle'. The optimisation procedure normally involves thousands of iterations to converge to an acceptable solution. Hence, improving the computational efficiency of a neural-network algorithm is an active area of research. Various options for improving the computational efficiency of neural networks have been reviewed in this thesis. It has been shown in the existing literature that the variation of the gain parameter improves the learning efficiency of the gradient-descent method. However, it can be concluded from previous researchers' claims that the adaptive-gain variation improved the learning rate and hence the efficiency. It was discovered in this thesis that the gain variation has no influence on the learning rate; however, it actually influences the search direction. This made it possible to develop a novel approach that modifies the gradient-search direction by introducing the adaptive-gain variation. The proposed method is robust and has been shown that it can easily be implemented in all commonly used gradient- based optimisation algorithms. It has also been shown that it significantly improves the computational efficiency as compared to existing neural-network training algorithms. Computer simulations on a number of benchmark problems are used throughout to illustrate the improvement proposed in this thesis. In a foundry a large amount of data is generated within the foundry every time a casting is poured. Furthermore, with the increased number of computing tools and power there is a need to develop an efficient, intelligent diagnostic tool that can learn from the historical data to gain further insight into cause and effect relationships. In this study the performance of the current Knowledge Hyper-surface method was reviewed and the mathematical formulation of the current Knowledge Hyper-surface method was analysed to identify its limitations. An enhancement is proposed by introducing mid-points in the existing shape formulation. It is shown that the midpoints' shape function can successfully constrain the shape of decision hyper-surface to become more realistic with an acceptable result in a multi-dimensional case. This is a novel and original approach and is of direct relevance to the foundry industry. E-Thesis Computer science.;Artificial intelligence. 31 12 2007 2007-12-31 COLLEGE NANME Engineering COLLEGE CODE Swansea University Doctoral Ph.D 2018-08-02T16:24:30.5077956 2018-08-02T16:24:30.5077956 Faculty of Science and Engineering School of Engineering and Applied Sciences - Uncategorised Nazri Mohd Nawi NULL 1 0042799-02082018162522.pdf 10807575.pdf 2018-08-02T16:25:22.8000000 Output 12561675 application/pdf E-Thesis true 2018-08-02T16:25:22.8000000 false
title Computational issues in process optimisation using historical data.
spellingShingle Computational issues in process optimisation using historical data.
Nazri Mohd Nawi
title_short Computational issues in process optimisation using historical data.
title_full Computational issues in process optimisation using historical data.
title_fullStr Computational issues in process optimisation using historical data.
title_full_unstemmed Computational issues in process optimisation using historical data.
title_sort Computational issues in process optimisation using historical data.
author_id_str_mv 01fa9bb7aa608f32204690b2a946de7b
author_id_fullname_str_mv 01fa9bb7aa608f32204690b2a946de7b_***_Nazri Mohd Nawi
author Nazri Mohd Nawi
author2 Nazri Mohd Nawi
format E-Thesis
publishDate 2007
institution Swansea University
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 1
active_str 0
description This thesis presents a new generic approach to improve the computational efficiency of neural-network-training algorithms and investigates the applicability of its 'learning from examples'' featured in improving the performance of a current intelligent diagnostic system. The contribution of this thesis is summarised in the following two points: For the first time in the literature, it has been shown that significant improvements in the computational efficiency of neural-network algorithms can be achieved using the proposed methodology based on using adaptive-gain variation. The capabilities of the current Knowledge Hyper-surface method (Meghana R. Ransing, 2002) are enhanced to overcome its existing limitations in modelling an exponential increase in the shape of the hyper-surface. Neural-network techniques, particularly back-propagation algorithms, have been widely used as a tool for discovering a mapping function between a known set of input and output examples. Neural networks learn from the known example set by adjusting its internal parameters, referred to as weights, using an optimisation procedure based on the 'least square fit principle'. The optimisation procedure normally involves thousands of iterations to converge to an acceptable solution. Hence, improving the computational efficiency of a neural-network algorithm is an active area of research. Various options for improving the computational efficiency of neural networks have been reviewed in this thesis. It has been shown in the existing literature that the variation of the gain parameter improves the learning efficiency of the gradient-descent method. However, it can be concluded from previous researchers' claims that the adaptive-gain variation improved the learning rate and hence the efficiency. It was discovered in this thesis that the gain variation has no influence on the learning rate; however, it actually influences the search direction. This made it possible to develop a novel approach that modifies the gradient-search direction by introducing the adaptive-gain variation. The proposed method is robust and has been shown that it can easily be implemented in all commonly used gradient- based optimisation algorithms. It has also been shown that it significantly improves the computational efficiency as compared to existing neural-network training algorithms. Computer simulations on a number of benchmark problems are used throughout to illustrate the improvement proposed in this thesis. In a foundry a large amount of data is generated within the foundry every time a casting is poured. Furthermore, with the increased number of computing tools and power there is a need to develop an efficient, intelligent diagnostic tool that can learn from the historical data to gain further insight into cause and effect relationships. In this study the performance of the current Knowledge Hyper-surface method was reviewed and the mathematical formulation of the current Knowledge Hyper-surface method was analysed to identify its limitations. An enhancement is proposed by introducing mid-points in the existing shape formulation. It is shown that the midpoints' shape function can successfully constrain the shape of decision hyper-surface to become more realistic with an acceptable result in a multi-dimensional case. This is a novel and original approach and is of direct relevance to the foundry industry.
published_date 2007-12-31T03:53:40Z
_version_ 1763752668705062912
score 11.012678

Similar Items