硕士学位论文二级倒立摆的神经网络模糊控制方法的应用研究论文作者： 指导教师：申请学位类别：工学硕士学科、领域：控制理论与控制工程所在单位：电气信息学院答辩日期： 授予学位单位：1摘 要摘 要倒立摆是一个强耦合、绝对不稳定、多变量、高阶次的非线性系统，它将计算机控制、机器人技术、智能控制等有机的结合在一起，倒立摆系统作为一种典型的实验装置，它可以很好的验证控制理论的实际应用性能，在各行业中，对复杂被控对象的控制具有广泛的实践指导意义本文主要是通过对模糊控制理论和神经网络控制理论进行研究，提出了一种结合了二者优点的控制方法：神经网络的模糊控制方法，并对该方法的进行了深入的理论研究和仿真实验本文以固高二级倒立摆为控制对象，分别采用牛顿力学方法和拉格朗日方程方法分别对一级和二级倒立摆系统进行数学建模在二级倒立摆系统数学模型的基础上，采用极点配置方法、LQR控制方法、模糊控制方法对二级倒立摆系统进行控制然后通过对模糊控制理论和神经网络控制理论进行研究，提出了一种神经网络模糊控制方法这种控制方法通过最优控制方法得到反馈矩阵，通过计算机融合技术，减少倒立摆输入变量的个数；采用BP算法与梯度下降法结合的混合算法，利用已经获得的客观输入输出数据组，对模糊控制器的隶属函数形状和控制规则进行不断修正，得到希望的输出数据。
仿真实验表明，神经网络模糊控制方法能够对二级倒立摆系统进行很好的控制，而且系统的鲁棒性良好，且它的控制效果优于一般的LQR控制器关键词 倒立摆； 模糊控制； 神经网络控制；自适应神经网络模糊；3AbstractInverted pendulum is an absolutely not stability, high order time, multivariable and strong coupling nonlinear system, it unifies the robot technology intelligent control and computer control organically. As a kind of typical experimental device, Inverted pendulum system can verify control theory effectively. It has a wide range of practical guiding significance to complex controlled object control in various industries.This paper is based on fuzzy control theory and neural network control theory, and it proposes a combination of the advantages of both adaptive neural network control method of fuzzy control. It carried out in-depth theoretical study and simulation experiment . This paper treat high solid double inverted pendulum as control object, adopt the Newtons mechanics method and Lagrange equation method, and conduct mathematical modeling about primary and secondary inverted pendulum system. It on the basis of the mathematical model of the double inverted pendulum system, adopted LQR theory controller, fuzzy controller to control the double inverted pendulum system. Then based on fuzzy control theory and neural network control theory, this paper proposes a fuzzy control method based on adaptive neural network. This kind of control method through the optimal control method to reduce the number of input variables of the inverted; Using hybrid algorithm combined with BP algorithm and the gradient descent method. It uses obtained input and obtained output data sets, constantly revised the shape of membership function of fuzzy controller and the control rules, get desirable output data. Simulation experiments show that the method can control the double inverted pendulum system effectively, and robustness in the system is good. and its control effect is better than that of general LQR controller. Key words Inverted pendulum; Fuzzy control; neural network control; Fuzzy neural network adaptive; 目 录摘 要..............................................................................................................................IAbstract......................................................................................................................II第1章 绪论................................................................................................................1 1.1 倒立摆系统简介...................................................................................... 1.2 课题研究目的和意义............................................................................................. 1.3 倒立摆研究发展现状............................................................................................. 1.4 论文主要内容及结构安排............................................................................... 1.4.1主要内容.................................................................................................. 1.4.2 文章结构安排......................................................................................... 1.5 本章小结..............................................................................................................第2章 直线一级倒立摆和二级倒立摆的数学建模及定性分析............................ 2.1 平面一级倒立摆系统的建模与分析............................................................ 2.1.1 用牛顿-欧拉方法对一级倒立摆建模................................................................ 2.1.2 用拉格朗日方法对一级倒立摆建模........................................................ 2.1.3 一级倒立摆系统性能分析..................................................................... 2.2 平面二级倒立摆系统的建模与分析........................................................ 2.2.1 用拉格朗日方法对二级倒立摆建模........................................... 2.2.2 二级倒立摆的系统性能分析............................................................... 2.3 本章小结.............................................................................................................第3章 倒立摆系统的两种常用控制方法研究.......................................................... 3.1二级倒立摆的极点配置控制方法研究................................................. 3.1.1 二级倒立摆的极点配置方法控制基本原理.................................................. 3.1. 2 二级倒立摆的极点配置方法仿真实验.................................................... 3.2 二级倒立摆线性二次型最优控制LQR控制方法研究.....................。