【作者】 戴军；

【导师】 庞永杰；

【作者基本信息】 哈尔滨工程大学 ， 流体力学， 2002， 硕士

【摘要】 模糊逻辑控制器已被成功地应用于许多复杂对象的控制过程中，但是它们都面临着如何获取足够的知识以及过分依赖经验和先验知识的问题。模糊控制器设计需要解决的问题是语言变量的定义、对应各语言变量之隶属函数的确定以及控制规则的选取。目前人们尝试通过机器学习来解决这些问题，将遗传算法用于模糊控制器设计是其中的方法之一。本文以哈尔滨工程大学研制的“智水-Ⅲ”号水下机器人为控制对象，讨论将遗传算法应用于水下机器人模糊控制器设计的可行性。 论文基于水下机器人的运动仿真系统，首先以手工试错方式建立了基本的模糊控制器。然后在此基础上，分两种情况讨论了将遗传算法用于水下机器人模糊控制器设计的可行性。第一种情况是采用由专家经验获取的模糊控制规则，只优化隶属函数；第二种情况是同步优化模糊控制规则和隶属函数。对每种情况均以纵向控制和横向控制为例，进行了控制效果的仿真研究。 仿真结果表明基于遗传算法的模糊控制器设计方法对水下机器人来说是可行的，本文的方法对于水下机器人操纵与自适应控制的研究有一定的指导意义。更多还原

【Abstract】 Although fuzzy logic controllers have been successfully applied in many complex industrial processes, they experience a deficiency in knowledge acquisition and rely to a great extent on empirical and heuristic knowledge which, in many cases, cannot be objectively elicited. Among the problems to be resolved in fuzzy controller design are the determination of the linguistic state space, definition of the membership functions of each linguistic term and the derivation of the control rules. In recent years machine learning methods have been applied to this kind of intelligent control problems. One of the methods is the Genetic Algorithm(GA). The feasibility of designing fuzzy logic controller for Autonomous Underwater Vehicle(AUV) with the help of GA is discussed in this paper, and the testbed used here is an AUV which is developed by Harbin Engineering University.Based on the AUV’s motion simulation system, the basic fuzzy logic controller is established using manual trial-and-error process at first. Then two approaches to discuss the feasibility of applying GA to AUV’s fuzzy logic controller design are presented. One approach is to optimize membership function with GA based on a hand-designed fuzzy rule base. Another approach is to design membership function and fuzzy rule base with GA simultaneously. To check the effectiveness of each method, simulation research is done, which takes longitudinal-control and side-control as examples. The performance of the controller is discussed.The simulation results indicate that the designing method base on GA is feasible to AUV. The approaches discussed in the paper are practicable for the research of AUV’s maneuverability and adaptive control.更多还原