Application of Machine Learning in Ship Unsinkability Design Strategy

doi:10.19423/j.cnki.31-1561/u.2022.04.082

Ship & Boat ›› 2022, Vol. 33 ›› Issue (04): 82-87.DOI: 10.19423/j.cnki.31-1561/u.2022.04.082

Previous Articles Next Articles

Application of Machine Learning in Ship Unsinkability Design Strategy

YANG Chunlei^1,2,3, HUANG Xiaohao^4,5, SHENG Qingwu², WANG Jinbao^1,2,3, PAN Changchun^4,5, FAN Sheming^1,2,3

1. Key Laboratory of Waterjet Propulsion, Shanghai 200011, China;
2. Marine Design & Research Institute of China, Shanghai 200011, China;
3. Shanghai Key Laboratory of Ship Engineering, Shanghai 200011, China;
4. School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai 200240, China;
5. Shanghai Key Laboratory of Navigation and Location Based Services, Shanghai 200240, China

Received:2022-05-26 Revised:2022-06-17 Published:2023-03-17

机器学习在船舶不沉性设计策略中的应用

杨春蕾^1,2,3, 黄晓皓^4,5, 盛庆武², 王金宝^1,2,3, 潘常春^4,5, 范佘明^1,2,3

1. 喷水推进重点实验室上海 200011;
2. 中国船舶及海洋工程设计研究院上海 200011;
3. 上海市船舶工程重点实验室上海 200011;
4. 上海交通大学电子信息与电气工程学院上海 200240;
5. 上海北斗导航与位置服务重点实验室上海 200240

作者简介:杨春蕾（1982-）,男,博士,高级工程师。研究方向：船舶波浪中操纵及水动力优化。黄晓皓（1996-）,男,硕士。研究方向: 机器学习算法开发。盛庆武（1971-）,男,博士,研究员。研究方向：船舶总体与性能研究。王金宝（1969-）,男,博士,研究员。研究方向：船舶流体性能及优化。潘常春（1979-）,男,博士,副教授。研究方向：系统控制与优化。范佘明（1962-）,男,博士,研究员。研究方向：船舶水动力。

Abstract

Abstract: Ship unsinkability is an important performance to evaluate the ship survivability, and it is also a key index for optimizing the subdivision strategy. However, the high cost is still a difficulty restricting the practical application of the unsinkability optimization. More effective methods will be provided with the continuous application of machine learning technology. The optimization of unsinkability subdivision is solved by using the particle swarm optimization (PSO) algorithm based on reinforcement learning. And the optimization system development and interface design is implemented for the integrated machine learning module and unsinkability design module. The effect of different parameter settings in the algorithm on the optimization efficiency is also discussed. The analysis of the optimal solution shows that this method can effectively find out the optimal subdivision scheme. It can provide a basis for formulating scientific subdivision strategies.

Key words: unsinkability, machine learning, particle swarm optimization, reinforcement learning, ship subdivision

摘要： 船舶不沉性是衡量船舶生命力的重要性能,也是优选水密分舱策略的关键指标,但时间成本高仍是制约不沉性寻优实用化的难点。随着机器学习技术应用不断深入,将提供更有效的途径。该研究基于强化学习的粒子群算法求解不沉性分舱优化问题,实现集成机器学习模块和不沉性设计模块的优化系统开发和界面设计,讨论算法中不同参数的设置对寻优能力的影响。通过寻优解的分析,表明该方法能够高效地找到较优的分舱方案,为制定科学的分舱策略等方面提供依据。

关键词: 不沉性, 机器学习, 粒子群, 强化学习, 船舶分舱

CLC Number:

U661.2⁺3

YANG Chunlei, HUANG Xiaohao, SHENG Qingwu, WANG Jinbao, PAN Changchun, FAN Sheming. Application of Machine Learning in Ship Unsinkability Design Strategy[J]. Ship & Boat, 2022, 33(04): 82-87.

杨春蕾, 黄晓皓, 盛庆武, 王金宝, 潘常春, 范佘明. 机器学习在船舶不沉性设计策略中的应用[J]. 船舶, 2022, 33(04): 82-87.

References

[1] 林杰人. 船舶设计原理[M].北京:国防工业出版社,1981:185-190.
[2] 马涅采夫. 船舶不沉性理论[M]. 北京:国防工业出版社,1977:16-141.
[3] 夏齐强,朱韬,朱军. 舰船稳性与破损稳性要求[J]. 船舶工程,2019(6):30-35.
[4] ZHANG S M, PEDERSEN P T, VILLAVICENCIO R.Probability and mechanics of ship collision and grounding[M] . Butterworth-Heinemann,2019:1-59.
[5] PRZEMIENIECHI J S.Mathematical methods in defense analyses[M]. Aiaa,2000:113-142.
[6] TURAN O, CUI H.A reinforcement learning based hybrid evolutionary algorithm for ship stability design[M].Variants of Evolutionary Algorithms for Real-World Applications. Springer Berlin Heidelberg,2012:281-303.
[7] CUI H, TURAN O.Application of a new multi-agent hybrid co-evolution based particle swarm optimisation methodology in ship design[J]. Computer-Aided Design,2010(11): 1013-1027.
[8] ZARAPHONITIS G, BOULOUGOURIS E, PAPANIKOLAOU A.Multi-objective optimization of cruise ships considering the SOLAS 2009 and GOALDS damage stability formulations[C]// Proceedings of the IDFS,2013:89-97.
[9] 姜文英,林焰,陈明, 等. 基于粒子群和蚁群算法的船舶机舱规划方法[J]. 上海交通大学学报,2014(4): 502-507.
[10] 林焰,杨栖,纪卓尚,等. 油船主船体隔舱划分的神经网络专家系统[J]. 中国造船,1994(3):1-10.
[11] 侯岳,浦金云. 求解舰艇抗损性优化的改进变尺度混沌遗传算法[J]. 武汉理工大学学报,2013(5):66-72.
[12] PUISA R, MURPHY A.Practical design optimisation: optimum internal arrangement within a few hours[C]//Compit2014 Redworth. UK,2014:108-122.
[13] KENNEDY J, EBERHART R.Particle swarm optimization[C]// Proceedings of ICNN'95-international conference on neural networks. IEEE,1995:1942-1948.
[14] SHI Y, EBERHART R.Empirical study of particle swarm optimization[C]//Proceedings of the 1999 congress on evolutionary computation-CEC99 . IEEE,1999:1945-1950.
[15] CARLISLE A, DOZIER G.An off-the-shelf PSO[C]// Proceedings of the Workshop on Particle Swarm Optimization. USA,2001.
[16] PIOTROWSKI A P, NAPIORKOWSKI J J, PIOTROWSKA A E .Population size in particle swarm optimization[J]. Swarm and Evolutionary Computation,2020,58:100718.
[17] 程志斌,陈仁铃. 舰船不沉性评价指标初探[J]. 船舶工程,1992(3):17-21.
[18] 曹冬梅,朱忠军,姚熊亮,等. 武器命中概率分布密度对水面舰船沉没概率的影响[J].船舶,2013(2):21-23.
[19] RAVN E S.Probabilistic damage stability of RO-RO ships[M]. Technical University of Denmark,2003.
[20] WATKINS C.Learning from delayed rewards[D]. England:University of Cambridge,1989.
[21] SAMMA H, LIM C P, SALEH J M A new reinforcement learning-based memetic particle swarm optimizer[M]. Elsevier Science Publishers B V, 2016.
[22] RAVN E S, JENSEN J J, BAATRUP J, et al.Robustness of the probabilistic damage stability concept to the degree of details in the subdivision[J]. Ship Technology Research, 2002,49:150-159.

Application of Machine Learning in Ship Unsinkability Design Strategy

机器学习在船舶不沉性设计策略中的应用

PDF

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 2

Recommended Articles

Metrics

[1]	GAO Bing, WANG Lin, ZHANG Shaoming, CHEN Jinhao. On Improvement of Path Planning of Unmanned Ship Using Particle Swarm Optimization Algorithm [J]. Ship & Boat, 2022, 33(06): 47-54.
[2]	ZHANG Pei, LU Mofan, CHEN Cheng, XU Hao, MIAO Chuan. Parameter Adaptive S-Plane Control Algorithm Based on Q-Learning [J]. Ship & Boat, 2022, 33(06): 55-62.