基于模糊神经网络的多电机功率平衡控制研究

发布时间：2018-04-23 02:11

本文选题：多机驱动 + 功率平衡　；参考：《中国矿业大学》2014年硕士论文

【摘要】：带式输送机是一种高效的散装物料输送设备，因其具有诸多优点被广泛地应用于煤炭行业及其他众多工业领域。随着带式输送机的大型化，其驱动方式常采用多电机驱动，在多机驱动系统中需要解决的一个重要问题就是驱动电机的功率平衡。将模糊神经网络用于解决多电机功率平衡问题，具有响应速度快，控制精度高等优点。本文详细分析了多机驱动系统中出现功率不平衡现象的原因，结合可控起动传输(Controlled Start Transmission, CST)装置的工作过程详细阐述了其调节多电机功率平衡的原理，并针对带式输送机的实际启动特点为其设计了理想的起动速度曲线。本文对传统的多电机功率平衡控制策略进行对比分析，并对主从控制方式的多电机功率平衡控制系统进行仿真。仿真结果显示，采用传统的功率平衡控制方法时，控制系统滞后现象明显，，控制精度有待提高。针对传统控制方法的不足，本文提出一种基于模糊神经网络的多电机功率平衡补偿控制策略。模糊神经网络兼具模糊逻辑系统和人工神经网络的优势，本文详细介绍了模糊逻辑系统的组成和神经网络的结构分类及学习方式，重点研究了BP学习算法。针对传统学习算法中学习速率难以设定的问题，采用学习速率自动调整的方法对其进行改进。本文还系统地给出了基于模糊神经网络的多电机功率平衡控制器的设计方法，针对隐含层节点数目难以确定的问题，采用试凑法来解决。设计了模糊神经网络控制器，实现了CST压力PI控制器给定值的在线自适应调整，有效地消除了控制系统的滞后现象，提高了控制精度。本文采用MATLAB软件对文中所述的控制方法进行仿真验证，仿真结果表明，该方法具有响应速度快，鲁棒性强，功率平衡精度高等优点，完全满足带式输送机对多电机输出功率平衡的要求。
[Abstract]:Belt conveyor is an efficient equipment for conveying bulk materials. It is widely used in coal industry and many other industrial fields because of its many advantages. With the development of belt conveyor, the drive mode is usually driven by multi-motor. The power balance of driving motor is an important problem to be solved in the multi-motor drive system. The fuzzy neural network is used to solve the power balance problem of multi-motor, which has the advantages of fast response speed and high control precision. In this paper, the causes of power imbalance in multi-machine drive system are analyzed in detail, and the principle of regulating the power balance of multi-motor is described in detail in combination with the working process of controllable start transmission controlled Start transmission (CSTs) device. According to the actual starting characteristics of belt conveyor, the ideal starting speed curve is designed. In this paper, the traditional multi-motor power balance control strategy is compared and analyzed, and the multi-motor power balance control system with master-slave control is simulated. The simulation results show that the hysteresis of the control system is obvious and the control precision needs to be improved when the traditional power balance control method is adopted. In view of the shortcomings of traditional control methods, this paper presents a power balance compensation control strategy for multi-motor based on fuzzy neural network. Fuzzy neural network has the advantages of both fuzzy logic system and artificial neural network. In this paper, the composition of fuzzy logic system and the structure classification and learning method of neural network are introduced in detail, and the BP learning algorithm is emphatically studied. In order to solve the problem that the learning rate is difficult to set in the traditional learning algorithm, the method of automatically adjusting the learning rate is adopted to improve it. The design method of multi-motor power balance controller based on fuzzy neural network is also given in this paper. Aiming at the problem that the number of hidden layer nodes is difficult to determine, the trial and error method is used to solve the problem. The fuzzy neural network controller is designed, and the on-line adaptive adjustment of the given value of the CST pressure Pi controller is realized, which effectively eliminates the lag phenomenon of the control system and improves the control precision. In this paper, MATLAB software is used to verify the proposed control method. The simulation results show that the method has the advantages of fast response speed, strong robustness and high precision of power balance. Fully meet the belt conveyor to the multi-motor output power balance requirements.
【学位授予单位】：中国矿业大学
【学位级别】：硕士
【学位授予年份】：2014
【分类号】：TM301.2

【参考文献】