Application of Neural Network and Genetic Algorithm in Subdivision Optimization

2018 International Conference on Civil and Hydraulic Engineering

土木建筑工程;水利工程

Lv, Zhenwang^1

Dalian Scientific Test and Control Technology Institute, Dalian

116001, China^1

关键词: Anti winds;    Damaged ships;    Functional dependency;    Watertight bulkheads;   

Others  :  https://iopscience.iop.org/article/10.1088/1755-1315/189/6/062010/pdf
DOI  :  10.1088/1755-1315/189/6/062010

学科分类：土木及结构工程学

来源: IOP

【 摘 要 】

It is complicated and time consuming to evaluate the anti-wind capability of a damaged ship. This paper tries to find a way to estimate the ship's anti-wind capability after damage comprehensively with some simplified conditions. The index representing anti-wind capability of damaged ship comprehensively is named "Average Anti-wind Capability". When the change of watertight bulkheads' position is not big, with a series of data calculated by NAPA and programs developed by author, Artificial Neural Network improved by genetic algorithm is applied to study the nature of functional dependency between the"Average Anti-wind Capability" and the positions of transverse watertight bulkheads. Then, genetic algorithm is also employed to find the best combination of watertight bulkhead, making the ship have the best anti-wind capability after damage. This method is verified to be feasible and effective by example calculation.