论文部分内容阅读
为减轻船舶在大风浪中剧烈的横摇,减摇鳍是目前应用最广泛的减摇装置。针对船舶减摇鳍系统的非线性和不确定性,在系统不确定性函数结构未知的情况下,提出一种RBF神经网络自适应滑模控制方法。采用RBF神经网络逼近系统不确定动态,并设计权值的自适应律,结合滑模控制增强系统的鲁棒性。在不同有义波高和不同浪向角下,建立随机海浪的干扰模型,应用simulink对系统进行仿真。仿真结果表明,该控制策略在各种海况下,均具有良好的减摇效果和较强的鲁棒性。
In order to reduce the ship’s violent rolling in large waves, fin stabilizer is the most widely used anti-roll device. Aiming at the nonlinearity and uncertainty of fin stabilizer system, a RBF neural network adaptive sliding mode control method is proposed under the condition that the structure of system uncertainty function is unknown. The RBF neural network is used to approximate the uncertain system dynamics and to design the adaptive law of weights. The sliding mode control is used to enhance the robustness of the system. In different sense of wave height and different wave angle, the interference model of random sea waves is established, simulink is used to simulate the system. Simulation results show that this control strategy has good anti-rolling effect and strong robustness under various sea conditions.