响应型船舶运动模型的建模与遗传算法辨识

为了建立更准确的响应型船舶运动模型,在充分考虑横摇对舵响应的非最小相位性、阻尼震荡性和惯性横倾的基础上,提出一种横摇响应型模型,其参数具有物理意义明显和估值简单的特点。在此基础上,以某多功能运输船的非线性运动模型的对舵响应输出为试验数据,应用自适应遗传算法对船舶运动响应模型的各参数进行辨识,得到该船的艏摇与横摇的响应模型。仿真试验结果显示,遗传算法辨识后的船舶响应型模型能以较高的精度逼近试验数据,进而验证了响应型船舶运动模型及其参数辨识的有效性和可靠性。

基于遗传算法的时栅误差参数辨识与补偿方法研究

针对现有磁场式时栅角位移传感器原始测量精度低且误差成分复杂等特点,提出一种基于遗传算法的误差参数辨识与补偿方法,该方法根据时栅误差数学模型抽象出适应于生物遗传法则的遗传算法模型。首先将磁场式时栅误差辨识参数的样本数据进行针对性训练,并设置约束条件,然后利用遗传算法的“部分可观测黑箱性”特点进行数据样本迭代,并与时栅误差参数建立的目标函数寻求最佳逼近,以此完成误差参数的最优估计和误差曲线的最佳补偿。实验研究表明,采用遗传算法建立的时栅误差参数辨识模型辨识准确,对时栅误差成分中最主要的二次、四次误差有明显减少作用,其中二次误差减小66.67%、四次误差减小54.05%;与此同时,对一次误差及高频误差成分也有不同程度的抑制。

Parallel Processing Based on Ship Maneuvering in Identification of Interaction Force Coefficients

The parallel processing based on the free running model test was adopted to predict the interaction force coefficients （flow straightening coefficient and wake fraction） of ship maneuvering. And the multipopulation genetic algorithm （MPGA） based on real coding that can contemporarily process the data of free running model and simulation of ship maneuvering was applied to solve the problem. Accordingly the optimal individual was obtained using the method of genetic algorithm. The parallel processing of multiopulation solved the prematurity in the identification for single population, meanwhile, the parallel processing of the data of ship maneuvering （turning motion and zigzag motion） is an attempt to solve the coefficient drift problem. In order to validate the method, the interaction force coefficients were verified by the procedure and these coefficients measured were compared with those ones identified. The maximum error is less than 5%, and the identification is an effective method.