遗传算法在船舶电缆布局优化设计中的应用研究

船舶电缆布局优化是实现船舶布线自动化的一项技术难题,这一问题的解决可节省大量电缆布局设计的时间和费用。建立优化模型,并对传统遗传算法中初始种群的产生方法、选择算子及变异算子进行改进,增加检测操作,从而构造求解该模型的改进遗传算法。仿真结果表明,该算法是一种具有全局寻优能力的布局优化方法,具有高效性、实用性,并可扩展于解决船舶设计中的其它优化问题。     

基于遗传算法的企业间协同制造战略伙伴选择的方法

协同制造是一种能够实现快速响应市场的生产模式,该生产模式已经成为21世纪制造业发展的必然趋势．为了实现当前制造环境下制造资源共享与优化配置,描述了企业间协同制造的基本概念,提出了协同制造任务的分配和资源发现,分析了协同制造的策略与运行模式及战略伙伴的选择,比较了几种算法的优缺点,给出了应用实例,用遗传算法对事例进行了论证并对事例进行了优化,得出了可行性的结论．     

基于切片技术的点云数据预处理研究

针对扫描点云杂乱无序的特点,讨论了点云数据预处理的问题,提出了一种新的基于点云切片的数据预处理迭代算法．通过对点云最小包围盒进行均匀分割及分割后点云的密度分析,对密度过大的分割块进行迭代分割,建立了3个方向的点云切片和截面线．结果不仅大大减少了点云数据量,并且在点云密度过大的区域很好地保持了模型的原始特征,同时将原始的无序数据点集转化为具有层列结构的有序组织形式,确定了各点之间的相互关系,为后续曲线曲面拟合做了很好的准备．     

On the numerical accuracy of the prediction of resistance coefficients in ship stern flow calculations

This article presents a study on the accuracy of the numerical determination of the friction and pressure resistance coefficients of ship hulls. The investigation was carried out for the KVLCC2 tanker at model- and full-scale Reynolds numbers. Gravity waves were neglected, i.e., we adopted the so-called double-model flow. Single-block grids with H–O topology were adopted for all the calculations. Three eddy viscosity models were employed: the one-equation eddy viscosity and the two-equation models proposed by Menter and the TNT version of the two-equation k-ω model. Verification exercises were performed in sets of nearly geometrically similar grids with different densities in the streamwise, normal, and girthwise directions. The friction and pressure resistance coefficients were calculated for different levels of the iterative error and for computational domains of different size. The results show that on the level of grid refinement used, it is possible to calculate the viscous resistance coefficients in H–O grids that do not match the ship contour with a numerical uncertainty of less than 1%. The differences between the predictions of different turbulence models were larger than the numerical uncertainty; however, these differences tended to decrease with increases in the Reynolds number. The pressure resistance was remarkably sensitive to domain size and far-field boundary conditions. Either a large domain or the application of a viscous–inviscid interaction procedure is needed for reliable results. This work was presented in part at the International Conference on Computational Methods in Marine Engineering—MARINE 2007, Barcelona, June 3–4, 2007.     

Workspace analysis to generate a collision-free torch path for a ship welding robot

We propose a method to determine the optimal initial location and to generate torch paths for a ship welding robot with 6 degrees of freedom (DOF). The optimal initial location is determined using an objective function, which is set up by combining constraints on the torch posture, manipulability, and the range of each joint angle to avoid collisions. A genetic algorithm (GA) is used to optimize the objective function because it does not require additional derivatives. After the initial location is determined, torch paths are generated by interpolating the starting point, endpoints and torch postures using inverse kinematics. Our method can be applied to automate the welding job for each block during ship building, irrespective of the shape of the robots, by changing the objective function.     

一种新型船舶智能载重测量仪的研究与应用

针对船舶货物卸载重量计量难的现状,开发了一种新型的船舶智能载重测量仪,并提出一种结构树编码免疫辨识算法实现船舶重量模型的辨识,该测量仪通过检测船体前后左右四个位置的吃水深度,精确计算船舶重量、船体倾斜度等数据,实现船舶卸货计量的智能化与自动化.在散装水泥运输船上的应用实践表明,该测量仪能实现比较理想的测量精度,误差小于0.5%,完全能满足船舶运输中对中低价货物的计量要求.     

基于LM算法的组合导航系统的故障诊断

LM (Levenberg-Marquardt)算法是梯度下降法与高斯-牛顿法的结合,在训练次数与精度上明显优于标准的BP算法.介绍了BP神经网络,采用LM算法对标准BP算法进行改进,并应用于船舶组合导航系统的故障诊断.仿真结果表明,LM算法可有效地提高学习速度,缩短训练时间,诊断效果好.     

基于遗传算法优化模糊控制器的船舶航向控制

针对模糊控制器中的量化因子、比例因子、积分系数、模糊规则之间互相耦合,人工整定困难的问题,提出了一种基于遗传优化的船舶航向模糊PID自动控制算法。仿真对比试验表明,经遗传优化后的船舶航向模糊PID控制性能得到了极大的提高,系统无超调,上升快,工作稳定,具有较强的鲁棒性。     

船舶柴油机调速器参数整定的多目标优化和多属性决策研究

综合考虑系统在输入阶跃扰动和负荷扰动两个工况时的超调量、稳定时间和ITAE指标,研究了PID控制器参数寻优的问题。采用多目标遗传算法求出Pareto最优解,使用信息熵法和逼近理想解的排序方法（TOPSIS）对Pareto最优解给出了排序。计算了一艘水面船舶柴油机调速器控制的数值算例,结果表明本文方法有效,所设计的PID性能优异,可以工程实际应用。     

AIS与VTS的雷达／ARPA信息融合的研究与实现

分析了信息融合的必要性,并在信息融合基本原理的基础上,提出了信息融合的步骤,采用模糊数学中正态型隶属度函数算法实现AIS与VTS的雷达/ARPA信息融合,解决了不同设备处理同一信息的差异问题。