Abstract No.C181010-266
Author name(s): Mingxing GAO1, Yiwei ZHANG1, Gang LIU1, Yi HUANG1,Yanchang ZHANG2
Company: 1. Dalian University of Technology, China; 2. Marine Design and Research Institute of China, China
FPSO is unavoidably subjected to the impact of collision from standby ship during operation, thus it is necessary to carry out the optimal design for improving the crashworthiness of the FPSO side structure. Due to the complexity of ship collision optimization, traditional optimization methods are difficult to be used effectively. An optimized design of the anti-collision capacity of the FPSO side structure based on orthogonal design, BP network, genetic algorithm and ABAQUS parametric finite element simulation technology is developed. The optimal size of FPSO side structure can be obtained quickly with the above method, and it can improve the crashworthiness and reduce the weight of side structure. To make up for the disadvantages of traditional BP network, the genetic algorithm is applied to optimize its weights and thresholds, which can enhance its prediction precision. A parameterized program is compiled by using Python scripting language to improve the computational efficiency, which can accomplish pre-processing, automatic analysis and post-processing. The results show that the improved BP-GA optimization results have high reliability compared with the simulation results. The optimization method proposed in this paper is versatile and can provide a reference for the optimization of other properties, such as the anti-explosion capacity.
KEY WORDS: FPSO; crashworthiness; BP-GA method; BP neural network; genetic algorithm
All Rights Reserved. If you need the entire text, please contact the author or intl.exchange@ssnaoe.org