以遺傳規劃技術應用於核能電廠之爐心燃料設計研究

The Load Pattern Design of Nuclear Power Plant Reactor Core By Genetic Programming

蕭德勇(Der-Yeong Shiau)

指導教授 ： 葉佳炫

元智大學/資訊學院/資訊管理學系/碩士(2004年)

摘要

核能電廠爐心佈局設計是一項非常重要的任務。模擬退火演算、基因演算禁忌搜尋法及專家系統類型的解決方案應用，降低大量爐心動態計算。
遺傳規劃是一個新的資訊技術。透過爐心追隨演化驗證，確認遺傳規劃是可以完全勝任。不僅優異的表現，無可限量的潛能將可協助於高科技研究中。本研究的結果為遺傳規劃應用於爐心佈局之先驅。

關鍵字

人工智慧 ； 遺傳規劃

並列摘要

The Core pattern design is the most important mission of nuclear power plant. Simulated Annealing, genetic algorithm, Tabu search and expert system type solutions apply on this task, decreasing mass neutronics dynamics computation.
Genetic programming is a new information technology. Through the verifying of core follow evolution, validates GP can handle it all. Not only excellent presentation, the limitless potential can help more efficient in hi-tech researching. This achievement is a pioneer on the fuel layout application.

並列關鍵字

Artificial Intelligence ； Genetic Programming

參考文獻

[1]J. G. Stevens et. al, ”Optimization of Pressurized Water Shuffling by Simulated Annealing with Heuristics” , Nucl. Sci. Eng., v. 121 , p. 67 (1995)。

[2]D. J. KROPACZEK and P. J. TURINSKY, ”In-Core Nuclear Fuel Management Optimization for Pressurized Water Reactor UtilizingSimulated Annealing” , Nucl. Technol., 9 5, p. 9 (1991)。

[3]M. D. DeChaine, M. A. Feltus, “Nuclear Fuel Management Optimization Using Genetic Algorithm” , Nuclear Tech., v. 111 , p. 109-114 (1995)。

[4]Akio Yamamoto and etc. “ISIGHT: An Integrated Scooping Analysis Tool for In-core Fuel Management of PWR”, Journal of Nuclear Science and Technology, v. 3 4 , n. 8, p. 847-855 (1997)。

[5]Glover F., 1990, “Tabu search-Part I”, ORSA Journal on Computing。