神经模糊控制在船舶自动舵中的应用  

Application of neuro-fuzzy control to marine autopilot

作　　者：汪明慧[1] 余永权[1] 曾碧[1] 

机构地区：[1]广东工业大学计算机学院,广州510006

出　　处：《计算机应用》2010年第8期2261-2264,共4页journal of Computer Applications

基　　金：广东省自然科学基金资助项目(05001801)

摘　　要：针对常规模糊自动舵由于受船舶控制过程的非线性、时变性以及风浪干扰等因素影响,模糊控制规则和隶属函数需要校正,利用神经网络的自学习能力,用神经网络去实现模糊控制,设计自动舵神经模糊控制器,采用BP算法和最小二乘算法的混合学习算法实现对模糊规则和隶属函数的参数训练,提高控制器的自适应能力。仿真实验表明所设计的控制器有效可行,适应船舶在风浪干扰环境下的控制性能要求。Neuro-fuzzy control technology was applied to marine autopilot.The nero-fuzzy controller for autopilot was designed in this paper.Learning ability of neural network was utilized to optimize the fuzzy controller.Hybrid learning rule a combination of Back Propagation algorithm BP and Least Square Estimator LSE was utilized to realize parameter adjustment of fuzzy control rule and membership function in order to improve the adaptive capacity of the controller.The simulation result shows that the controller designed is effective and feasible to satisfy the control performance requirements when marine is under wave interference.

关 键 词：神经模糊控制 自动舵 混合学习算法 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]