Study on Ship Security MonitorUsing Symbiotic-Evolution-Based and Grey-Fuzzy Intelligent Models
博士 === 國立成功大學 === 系統及船舶機電工程學系碩博士班 === 92 === This study presents the hub of an AI-based (artificial intelligence) ship security monitoring system designed to supervise three different maritime monitoring tasks, including propeller-shaft fault detection and diagnosis, human medical diagnosis, and s...
Main Authors: | , |
---|---|
Other Authors: | |
Format: | Others |
Language: | zh-TW |
Published: |
2004
|
Online Access: | http://ndltd.ncl.edu.tw/handle/934xrr |
id |
ndltd-TW-092NCKU5345041 |
---|---|
record_format |
oai_dc |
spelling |
ndltd-TW-092NCKU53450412019-05-15T19:19:28Z http://ndltd.ncl.edu.tw/handle/934xrr Study on Ship Security MonitorUsing Symbiotic-Evolution-Based and Grey-Fuzzy Intelligent Models 應用共生演化與灰色模糊智慧型理論於船舶安全監控之研究 Hui-Kuo Chang 張惠國 博士 國立成功大學 系統及船舶機電工程學系碩博士班 92 This study presents the hub of an AI-based (artificial intelligence) ship security monitoring system designed to supervise three different maritime monitoring tasks, including propeller-shaft fault detection and diagnosis, human medical diagnosis, and smoke- and temperature-based fire alarm. Particular software for the three tasks is developed using a combination of symbiotic evolution, fuzzy clustering, adaptive fuzzy classification, back-propagation neural networking, and grey theory. Essentially, a modularizing scheme for categorizing various monitored/controlled objectives appearing in the ship system is used in this study. Accordingly, two general-purpose software models, the diagnostic software model and the predictive software model, are proposed. These models implementing monitoring tasks properly are established consistent with the behavior characteristics of the monitored objectives. The diagnostic model is a symbiotic evolution-based fuzzy-neural diagnosis model applicable to the interpretation of complex current data. The predictive model is a grey-fuzzy prediction model, which is available to the crucial situation of early-prediction such as fire alarm for small differences in alarm time. When working together, these models can supervise a wide variety of modern maritime data, including electronic compass, hull motion sensors, engine shaft RPM and vibration sensors, GPS, temperature sensors, engine oil condition, and so on. The AI system has self-designing functions that can easily monitor new objects to be input, upon which the system will automatically develop specified monitoring, diagnosis, and response patterns for the new data. In essence, this methodology simplifies the tasks of system design and management, and increases system flexibility. Compared with several traditional methods by applying the same database, the proposed symbiotic evolution-based fuzzy-neural diagnosis model exhibits higher diagnostic rate and lower model construction time. The grey-fuzzy prediction model tested under the circumstances of open-flame and smoldering fires is compared with the commercial detector operating with the same condition. The experimental results reveal that the proposed model gives superior performance. The presented design is useful as a core model for developing more advanced AIs-based monitoring systems. As applied to the monitor maritime, the proposed system provides a good basis for the intelligently remote network-based integration of monitoring system, monitored objects and data. Consequently, the intelligent ship security monitoring system will be essential for optimizing the levels of safety, economy, convenience, and comfort. Hsing-Chia Kuo 郭興家 2004 學位論文 ; thesis 127 zh-TW |
collection |
NDLTD |
language |
zh-TW |
format |
Others
|
sources |
NDLTD |
description |
博士 === 國立成功大學 === 系統及船舶機電工程學系碩博士班 === 92 === This study presents the hub of an AI-based (artificial intelligence) ship security monitoring system designed to supervise three different maritime monitoring tasks, including propeller-shaft fault detection and diagnosis, human medical diagnosis, and smoke- and temperature-based fire alarm. Particular software for the three tasks is developed using a combination of symbiotic evolution, fuzzy clustering, adaptive fuzzy classification, back-propagation neural networking, and grey theory. Essentially, a modularizing scheme for categorizing various monitored/controlled objectives appearing in the ship system is used in this study. Accordingly, two general-purpose software models, the diagnostic software model and the predictive software model, are proposed. These models implementing monitoring tasks properly are established consistent with the behavior characteristics of the monitored objectives.
The diagnostic model is a symbiotic evolution-based fuzzy-neural diagnosis model applicable to the interpretation of complex current data. The predictive model is a grey-fuzzy prediction model, which is available to the crucial situation of early-prediction such as fire alarm for small differences in alarm time. When working together, these models can supervise a wide variety of modern maritime data, including electronic compass, hull motion sensors, engine shaft RPM and vibration sensors, GPS, temperature sensors, engine oil condition, and so on. The AI system has self-designing functions that can easily monitor new objects to be input, upon which the system will automatically develop specified monitoring, diagnosis, and response patterns for the new data. In essence, this methodology simplifies the tasks of system design and management, and increases system flexibility.
Compared with several traditional methods by applying the same database, the proposed symbiotic evolution-based fuzzy-neural diagnosis model exhibits higher diagnostic rate and lower model construction time. The grey-fuzzy prediction model tested under the circumstances of open-flame and smoldering fires is compared with the commercial detector operating with the same condition. The experimental results reveal that the proposed model gives superior performance.
The presented design is useful as a core model for developing more advanced AIs-based monitoring systems. As applied to the monitor maritime, the proposed system provides a good basis for the intelligently remote network-based integration of monitoring system, monitored objects and data. Consequently, the intelligent ship security monitoring system will be essential for optimizing the levels of safety, economy, convenience, and comfort.
|
author2 |
Hsing-Chia Kuo |
author_facet |
Hsing-Chia Kuo Hui-Kuo Chang 張惠國 |
author |
Hui-Kuo Chang 張惠國 |
spellingShingle |
Hui-Kuo Chang 張惠國 Study on Ship Security MonitorUsing Symbiotic-Evolution-Based and Grey-Fuzzy Intelligent Models |
author_sort |
Hui-Kuo Chang |
title |
Study on Ship Security MonitorUsing Symbiotic-Evolution-Based and Grey-Fuzzy Intelligent Models |
title_short |
Study on Ship Security MonitorUsing Symbiotic-Evolution-Based and Grey-Fuzzy Intelligent Models |
title_full |
Study on Ship Security MonitorUsing Symbiotic-Evolution-Based and Grey-Fuzzy Intelligent Models |
title_fullStr |
Study on Ship Security MonitorUsing Symbiotic-Evolution-Based and Grey-Fuzzy Intelligent Models |
title_full_unstemmed |
Study on Ship Security MonitorUsing Symbiotic-Evolution-Based and Grey-Fuzzy Intelligent Models |
title_sort |
study on ship security monitorusing symbiotic-evolution-based and grey-fuzzy intelligent models |
publishDate |
2004 |
url |
http://ndltd.ncl.edu.tw/handle/934xrr |
work_keys_str_mv |
AT huikuochang studyonshipsecuritymonitorusingsymbioticevolutionbasedandgreyfuzzyintelligentmodels AT zhānghuìguó studyonshipsecuritymonitorusingsymbioticevolutionbasedandgreyfuzzyintelligentmodels AT huikuochang yīngyònggòngshēngyǎnhuàyǔhuīsèmóhúzhìhuìxínglǐlùnyúchuánbóānquánjiānkòngzhīyánjiū AT zhānghuìguó yīngyònggòngshēngyǎnhuàyǔhuīsèmóhúzhìhuìxínglǐlùnyúchuánbóānquánjiānkòngzhīyánjiū |
_version_ |
1719088119353966592 |