東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁 到查詢結果 [ null ]

切換: 標籤 | MARC模式 | ISBD

Development of a Supportive Decision...

Turkmen, Gulcin Sarici,

FindBook

Google Book

Amazon

博客來

Development of a Supportive Decision-Making Tool for Multi-Unit Small Modular Reactors /

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Development of a Supportive Decision-Making Tool for Multi-Unit Small Modular Reactors // Gulcin Sarici Turkmen.
作者:	Turkmen, Gulcin Sarici,
面頁冊數:	1 electronic resource (119 pages)
附註:	Source: Dissertations Abstracts International, Volume: 86-06, Section: B.
Contained By:	Dissertations Abstracts International86-06B.
標題:	Nuclear engineering. -
電子資源:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31836959
ISBN:	9798346853060

Development of a Supportive Decision-Making Tool for Multi-Unit Small Modular Reactors /
Turkmen, Gulcin Sarici,

Development of a Supportive Decision-Making Tool for Multi-Unit Small Modular Reactors /Gulcin Sarici Turkmen. - 1 electronic resource (119 pages)

Source: Dissertations Abstracts International, Volume: 86-06, Section: B.

With the growing interest in Small Modular Reactors (SMRs) due to their cost-effectiveness, scalability, and inherent safety features, the deployment of multiple SMR units at a single site is seen as a promising approach to enhancing the flexibility and reliability of nuclear power generation. However, the Fukushima-Daiichi accident underscored the need for rigorous safety assessments of multi-unit nuclear power plants (NPPs), especially considering the complex interdependencies and potential cascading failures that can arise during accidents. The primary goal of this dissertation is to develop a supportive decision-making tool for multi-unit SMRs, integrating a novel Multi-Unit Dynamic Probabilistic Risk Assessment (MUDPRA) methodology with advanced machine learning (ML) techniques to predict accident progression and assist operators in mitigating risks effectively.The research begins by validating a NuScale reactor model through steady-state and transient simulations using RELAP/SCDAPSIM, establishing a reliable foundation for further analysis. Dynamic Event Trees (DETs) are then employed to explore a wide range of potential accident sequences, revealing critical dependencies on the Emergency Core Cooling System (ECCS) valves. The study advances the state-of-the-art by optimizing a Transformer network model using Optuna, resulting in highly accurate predictions of accident progression across multiple scenarios, as evidenced by low cross-validation errors. The model's robustness is confirmed through extensive testing, with 3-fold cross-validation proving particularly effective in maintaining predictive consistency.Key contributions of this research include the development of the supportive decision-making tool tailored specifically for multi-unit SMRs, the proposal and implementation of a comprehensive MUDPRA methodology, and the application of ML techniques to enhance nuclear safety assessments. The findings underscore the importance of integrating probabilistic risk assessments with machine learning to better understand the complexities of multi-unit interactions and improve reactor safety.

English

ISBN: 9798346853060Subjects--Topical Terms:

595435
Nuclear engineering.
Subjects--Index Terms:

Probabilistic risk assessments

Development of a Supportive Decision-Making Tool for Multi-Unit Small Modular Reactors /
LDR:03610nmm a22004333i 4500 001 2438765
005 20260727134419.5
006 m o d
007 cr|nu||||||||
008 261011s2024 miu||||||m |||||||eng d
020 $a 9798346853060
035 $a (MiAaPQD)AAI31836959
035 $a AAI31836959
040 $a MiAaPQD $b eng $c MiAaPQD $e rda
100 1 $a Turkmen, Gulcin Sarici, $e author. $3 3830160
245 1 0 $a Development of a Supportive Decision-Making Tool for Multi-Unit Small Modular Reactors / $c Gulcin Sarici Turkmen.
264 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2024
300 $a 1 electronic resource (119 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Dissertations Abstracts International, Volume: 86-06, Section: B.
500 $a Advisors: Aldemir, Tunc Committee members: Yilmaz, Alper; Smidts, Carol; Vasques, Richard.
502 $b Ph.D. $c The Ohio State University $d 2024.
520 $a With the growing interest in Small Modular Reactors (SMRs) due to their cost-effectiveness, scalability, and inherent safety features, the deployment of multiple SMR units at a single site is seen as a promising approach to enhancing the flexibility and reliability of nuclear power generation. However, the Fukushima-Daiichi accident underscored the need for rigorous safety assessments of multi-unit nuclear power plants (NPPs), especially considering the complex interdependencies and potential cascading failures that can arise during accidents. The primary goal of this dissertation is to develop a supportive decision-making tool for multi-unit SMRs, integrating a novel Multi-Unit Dynamic Probabilistic Risk Assessment (MUDPRA) methodology with advanced machine learning (ML) techniques to predict accident progression and assist operators in mitigating risks effectively.The research begins by validating a NuScale reactor model through steady-state and transient simulations using RELAP/SCDAPSIM, establishing a reliable foundation for further analysis. Dynamic Event Trees (DETs) are then employed to explore a wide range of potential accident sequences, revealing critical dependencies on the Emergency Core Cooling System (ECCS) valves. The study advances the state-of-the-art by optimizing a Transformer network model using Optuna, resulting in highly accurate predictions of accident progression across multiple scenarios, as evidenced by low cross-validation errors. The model's robustness is confirmed through extensive testing, with 3-fold cross-validation proving particularly effective in maintaining predictive consistency.Key contributions of this research include the development of the supportive decision-making tool tailored specifically for multi-unit SMRs, the proposal and implementation of a comprehensive MUDPRA methodology, and the application of ML techniques to enhance nuclear safety assessments. The findings underscore the importance of integrating probabilistic risk assessments with machine learning to better understand the complexities of multi-unit interactions and improve reactor safety.
546 $a English
590 $a School code: 0168
650 4 $a Nuclear engineering. $3 595435
650 4 $a Computer engineering. $3 621879
650 4 $a Electrical engineering. $3 649834
653 $a Probabilistic risk assessments
653 $a Dynamic Event Trees
653 $a Machine learning
653 $a Transformer network
653 $a Machine learning
690 $a 0552
690 $a 0544
690 $a 0464
710 2 $a The Ohio State University. $b Nuclear Engineering. $e degree granting institution. $3 3830161
720 1 $a Aldemir, Tunc $e degree supervisor.
773 0 $t Dissertations Abstracts International $g 86-06B.
790 $a 0168
791 $a Ph.D.
792 $a 2024
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31836959