摘要
随着海上养殖走向深远海,海洋养殖装备将面临更加恶劣的海况,为了保证装备的安全,必须对其锚泊系统的安全进行评估。采用传统水动力计算分析的方法,能够获得准确的锚泊系统张力,但是计算时间要求很长。为了快速的获取恶劣海况下养殖平台锚泊系统的张力分布,本研究基于机器学习的方法构建了养殖平台锚泊系缆力预报评估的计算模型(SSA-BP模型),该模型引入了麻雀搜索算法对BP神经网络的权值和阈值进行优化,改善了模型的预报性能。该模型将规则波波高、周期、流速作为模型输入指标,将系泊缆力作为模型输出指标,进行BP预报模型的训练。用麻雀搜索算法对BP模型进行优化并训练(SSA-BP模型),并针对改进后的SSA-BP模型预报结果与传统的BP模型预报结果进行对比。经过对比分析发现,SSA-BP模型整体的各项指标均低于BP模型,且SSA-BP模型各工况系缆力的预报误差也均低于BP模型并更贴近真实值。研究表明,该SSA-BP模型能够给出更加准确的预报结果。
With the development of mariculture moving to the deep sea,mariculture equipment will face worse sea conditions.To ensure the safety of the equipment,it is necessary to evaluate the safety of its anchoring system.Using the traditional hydrodynamic calculation and analysis method,the accurate mooring system tension can be obtained,but the calculation time is very long.To quickly obtain the tension distribution of the mooring system of the aquaculture platform under bad sea conditions,a calculation model for the prediction and evaluation of the mooring force of the aquaculture platform(ssa-bp model)is constructed based on the machine learning method.The sparrow search algorithm is introduced into the model to optimize the weight and threshold of the BP neural network,which improves the prediction performance of the model.The model takes the regular wave height,period,and velocity as the model input index and the mooring line force as the model output index to train the BP prediction model.The sparrow search algorithm is used to optimize and train the BP model(ssa-bp model),and the prediction results of the improved ssa-bp model are compared with those of the traditional BP model.Through comparative analysis,it is found that the overall indicators of ssa-bp model are lower than the BP model,and the prediction error of the mooring force of ssa-bp model under various working conditions is also lower than the BP model and closer to the real value.Finally,it is concluded that the new ssa-bp model can give more accurate prediction results.
作者
许条建
金延儒
蒋梅荣
麻常雷
XU Tiaojian;JIN Yanru;JIANG Meirong;MA Changlei(State Key Laboratory of Coastal and Offshore Engineering,Dalian University of Technology,Dalian,116024,Liaoning,China;CNOOC Research Institute Co.,Ltd.,Beijing,100028,China;National Ocean Technology Center,Tianjin,300112,China;CCCC Fourth Harbor Engineering Institute Co.,Ltd.,Guangzhou,510230,Guangdong,China)
出处
《渔业现代化》
CSCD
2022年第6期17-26,共10页
Fishery Modernization
基金
国家自然科学基金面上项目(51979037)
中央高校基本科研业务费(DUT21LK30)。
关键词
深远海养殖平台
系缆力
BP神经网络
麻雀搜索算法
快速预报
deep sea aquaculture platform
mooring force
BP neural network
sparrow search algorithm
fast forecast
