共查询到19条相似文献,搜索用时 62 毫秒
1.
2.
3.
基于改进BP神经网络的船舶操纵性能预报 总被引:2,自引:0,他引:2
以某单桨大型船舶在海上的回转性能为例,探讨了应用改进的BP神经网络(Back-pmpagation Neural Network)建立船舶操纵性预报数学模型的方法,并利用matlab语言对其进行了仿真。研究结果表明,改进的BP算法有更快的收敛速度和更好的计算精度。 相似文献
4.
本文利用别尔舍茨所统计的船体操纵水动力的诺谟图进行了多元回归分析,给出了估算船体操纵水动力的简单、可靠而实用的方法。并且利用该回归公式预报了船舶在在无限水域中的操纵运动。计算结果良好,说明该方法很实用,适用于工程设计。 相似文献
5.
6.
船舶在弱机动情况下的变速运动是一种基本的运动,本文对该状态下的船舶运动情况进行分析,运用船舶操纵性理论和数学知识推导出在该状况下预报船舶运动规律的方法——运用船舶操纵响应线性方程预报船舶运动规律。 相似文献
7.
船舶运动极短期预报研究 总被引:4,自引:1,他引:3
本文通过对两艘有航速情况下的船舶运动实测数据的分析,试图寻求一种准确程度较高的极短期预报模型。该文共分两部分,第一部分利用AR模型导出多级AR模型,预报精度明显提高。在对运动瞬时值预报中,利用包络对结果进行修正,精度有所改进;第二部分利用人工神经网络导出了包络的预报模式,预报精度明显高于AR模型。 相似文献
8.
为了利用船舶操纵模拟器进行航海教育培训,以及在船舶设计阶段预报船舶操纵性,建立四自由度船舶操纵运动数学模型以及作用于船体的作用力(矩)计算公式,运用unity开发工具,结合某型船舶数据方便快捷的编制船舶操纵运动三维数值仿真程序。通过船舶变速性能、旋回性能和Z形实验等较为完整的船舶操纵性能数值仿真试验,得到了试验数据,并和该船的实船试验数据以及相关文献的数据进行比对,吻合较好。仿真结果表明:本文的方法是可行的,计算结果是可信的。 相似文献
9.
介绍船舶操纵运动仿真的发展概况、现有成果及人工神经网络的基本理论,探讨将神经网络应用于船舶操纵运动仿真领域,构造一种网络结构和训练方法完成船舶操纵指令与船舶运动态势参数映射的可行性,并构建基于典型BP神经网络模型的操纵运动仿真系统。 相似文献
10.
神经网络在船舶操纵中的应用研究 总被引:2,自引:0,他引:2
该文对人工神经网络用于船舶操纵动态特性的在线学习进行了研究,并提出了基于神经网络预报的操舵控制算法。仿真试验的结果表明了该控制算法的有效性。 相似文献
11.
Takuya Ohmori Masataka Fujino Hideaki Miyata 《Journal of Marine Science and Technology》1998,3(1):22-29
To estimate the maneuvering ability of a ship, an accurate estimation of the hydrodynamic forces and moment acting on the ship's hull is indispensable. For the purpose of developing a numerical method of computing the viscous flow field around a hull and evaluating its validity, the hydrodynamic pressure on the hull and the velocity field were measured. Two full ship models with different hull forms in the aft part were used for the experiment. From the results of pressure measurements, the distribution of hydrodynamic lateral forces was obtained. The simulation method is a numerical solution of the Navier-Stokes equation based on a finitevolume method and applied to the maneuvering motion. The measured and computed results agree qualitatively well, and the method is a valuable tool for estimating the maneuvering ability of a ship. The typical characteristics of the flow field in the steady turning condition are revealed by the numerical simulation, and the mechanism of the relations between hull form, flow field, and hydrodynamic forces are clarified.Translation and combination of articles that appeared in the Journal of the Society of Naval Architects of Japan, vols. 176, 177, 179 (1994–1996): The original article won the SNAJ prize, which is awarded annually to the best papers selected from the SNAJ Journal, JMST, or other quality journals in the field of naval architecture and ocean engineering.This work was conducted as part of the joint SR221 project supported by JSRA (Shipbuilding Research Association of Japan). The authors express their sincere gratitude to the persons concerned, and especially to M. Kanai, S. Eguchi, S. Usami, K. Tatsumi, and T. Kawamura. 相似文献
12.
13.
14.
由于船舶自动化程度的快速提升,越来越多的智能化设备会产生海量的数据,这些数据之间存在着许多联系,如何有效利用这些数据成为了现代船舶管理中所面临的难题。而对于船舶电站来说,可以通过数据挖掘技术,对不同工作状态的船舶电站数据进行采集和分析,从而可以实现对电站设备缺陷的准确预测。本文从电站的具体需求出发,建立了数据挖掘目标函数,通过对电站特征参数的采集,有效提高了其状态预测能力,降低了设备的维护成本。 相似文献
15.
16.
17.
18.
19.
In this paper, Neural Networks (NNs) are used in the modeling of ship maneuvering motion. A nonlinear response model and a linear hydrodynamic model of ship maneuvering motion are also investigated. The maneuverability indices and linear non-dimensional hydrodynamic derivatives in the models are identified by using two-layer feed forward NNs. The stability of parametric estimation is confirmed. Then, the ship maneuvering motion is predicted based on the obtained models. A comparison between the predicted results and the model test results demonstrates the validity of the proposed modeling method. 相似文献