神经网络故障诊断技术及在导航系统中的应用

发布时间：2018-02-13 17:23

本文关键词： 神经网络故障诊断 PSO 组合导航　出处：《沈阳航空航天大学》2017年硕士论文　论文类型：学位论文

【摘要】：随着科学技术的飞速发展,单一的导航系统的精度已经无法满足如今的需求。因此,随着计算机技术和现代控制理论的进步,组合导航系统广泛的应用于各类载体上。但是复杂的系统使得故障更易发生,因此故障诊断技术成为了提高组合导航系统精度和可靠性的重要手段。本文首先论述了神经网络的发展概况和基本原理,简单介绍了神经网络的分类和学习方式。介绍了粒子群优化(PSO)算法的基本原理,在标准粒子群优化算法的基础上,针对粒子群算法后期收敛慢、易陷入局部最优解的缺点,提出了一种可调节学习因子和惯性权重的改进粒子群算法,并将改进的粒子群算法引入到神经网络中,提出了一种基于改进PSO-BP网络的故障诊断方法。简要的介绍了组合导航系统的组成原理,INS和GPS各自的工作原理和误差指标。建立INS/GPS组合导航系统状态方程和观测方程。以陀螺仪故障诊断为例,对改进PSO-BP网络故障诊断方法进行仿真验证,证明该算法相对于标准粒子群算法的优越性。将改进PSO-BP网络应用于组合导航故障诊断中,并验证了其可行性与准确性。
[Abstract]:With the rapid development of science and technology, the accuracy of a single navigation system has been unable to meet the needs of today, so with the progress of computer technology and modern control theory, Integrated navigation systems are widely used in all kinds of carriers. But complex systems make failures more likely. Therefore, fault diagnosis technology has become an important means to improve the accuracy and reliability of integrated navigation system. This paper introduces the classification and learning method of neural network, introduces the basic principle of particle swarm optimization (PSO) algorithm. Based on the standard PSO algorithm, the PSO algorithm has the disadvantages of slow convergence and easy to fall into the local optimal solution. An improved particle swarm optimization algorithm with adjustable learning factor and inertia weight is proposed, and the improved particle swarm optimization algorithm is introduced into the neural network. A fault diagnosis method based on improved PSO-BP network is presented. The composition principle of integrated navigation system and the working principle and error index of ins and GPS are introduced briefly. The state equation of INS/GPS integrated navigation system and its observation are established. Taking gyroscope fault diagnosis as an example, The improved PSO-BP network fault diagnosis method is verified by simulation, which proves its superiority over the standard particle swarm optimization algorithm. The improved PSO-BP network is applied to the integrated navigation fault diagnosis, and its feasibility and accuracy are verified.
【学位授予单位】：沈阳航空航天大学
【学位级别】：硕士
【学位授予年份】：2017
【分类号】：TN967.2;TP183

【参考文献】