다중 섬 유전자 알고리즘 기반 A60 급 격벽 관통 관의방화설계에 대한 이산변수 근사최적화 (Approximate Optimization with Discrete Variables of Fire Resistance Design of A60 Class Bulkhead Penetration Piece Based on Multi-island Genetic Algorithm)

서지정보

· 발행기관 : 한국기계가공학회
· 수록지 정보 : 한국기계가공학회지 / 20권 / 6호 / 33 ~ 43페이지
· 저자명 : 박우창, 송창용

초록

A60 class bulkhead penetration piece is a fire resistance system installed on a bulkhead compartment to protectlives and to prevent flame diffusion in a fire accident on a ship and offshore plant. This study focuses on theapproximate optimization of the fire resistance design of the A60 class bulkhead penetration piece using amulti-island genetic algorithm. Transient heat transfer analysis was performed to evaluate the fire resistance design ofthe A60 class bulkhead penetration piece. For approximate optimization, the bulkhead penetration piece length,diameter, material type, and insulation density were considered discrete design variables; moreover, temperature, cost,and productivity were considered constraint functions. The approximate optimum design problem based on themeta-model was formulated by determining the discrete design variables by minimizing the weight of the A60 classbulkhead penetration piece subject to the constraint functions. The meta-models used for the approximate optimizationwere the Kriging model, response surface method, and radial basis function-based neural network. The results fromthe approximate optimization were compared to the actual results of the analysis to determine approximate accuracy.
We conclude that the radial basis function-based neural network among the meta-models used in the approximateoptimization generates the most accurate optimum design results for the fire resistance design of the A60 classbulkhead penetration piece.

영어초록

A60 class bulkhead penetration piece is a fire resistance system installed on a bulkhead compartment to protectlives and to prevent flame diffusion in a fire accident on a ship and offshore plant. This study focuses on theapproximate optimization of the fire resistance design of the A60 class bulkhead penetration piece using amulti-island genetic algorithm. Transient heat transfer analysis was performed to evaluate the fire resistance design ofthe A60 class bulkhead penetration piece. For approximate optimization, the bulkhead penetration piece length,diameter, material type, and insulation density were considered discrete design variables; moreover, temperature, cost,and productivity were considered constraint functions. The approximate optimum design problem based on themeta-model was formulated by determining the discrete design variables by minimizing the weight of the A60 classbulkhead penetration piece subject to the constraint functions. The meta-models used for the approximate optimizationwere the Kriging model, response surface method, and radial basis function-based neural network. The results fromthe approximate optimization were compared to the actual results of the analysis to determine approximate accuracy.
We conclude that the radial basis function-based neural network among the meta-models used in the approximateoptimization generates the most accurate optimum design results for the fire resistance design of the A60 classbulkhead penetration piece.

참고자료

· 없음