基于LS-SVM的船舶航向模型预测控制

针对船舶动态性能具有较强的非线性、大惯性及时变性的特点,采用具有RBF核函数的最小二乘支持向量机(LS-SVM),利用其可以任意逼近非线性模型的良好特性实现对船舶模型有效辨识,得到船舶航向控制系统的非线性逼近模型,并将其与模型预测控制方法相结合,将最小二乘支持向量机辨识得到的系统模型作为预测模型,并将系统模型进行线性化并用线性预测控制方法求得解析的控制律,实现对船舶航向的预测控制,达到良好航向保持目的。仿真结果表明,最小二乘支持向量机降低了计算复杂度,且有较快计算速度,在小样本情况下具有良好的泛化能力;基于最小二乘支持向量机的船舶航向预测控制系统对外界干扰及模型参数摄动均具有较好的适应能力以及良好的控制性能。

Model Predictive Control of Ship Course with LS-SVM

To the characteristic of the ship dynamic performance such as non-linearity,large inertia and time variation,the least square support vector machine (LS-SVM)with kernel RBF is used to identify the ship model efficiently.And it is combined with model predictive control to keep the ship course with analytical control law derived from linear predictive control method.Simulation results show that LS-SVM reduces calculating complexity with high calculating speed.And it also has good generalization ability with s...