基于变结构模糊神经网络的开关磁阻电动机非线性模型

开关磁阻电动机驱动系统是一个时变、非线性系统 ,若采用通常的建模方法 ,无法获得精确的数学模型。给出了开关磁阻电机变结构模糊神经网络非线性模型 ,基于Takagi Sugeno模糊神经网络 ,提出可变结构的变步长学习算法。仿真结果表明此法比BP神经网络具有更高的精度和更快的收敛速度。     

神经网络在开关磁阻电机控制中的应用研究

本文分析开关磁阻电机驱动系统特性,提出了一种运用神经网络对其进行控制的方法,并与传统ＰＩＤ控制方式进行了比较,给出了仿真控制结果,表明了这种基于神经网络控制方法应用于开关磁阻电机驱动系统的优越性和可行性。     

神经网络在开关磁阻电机控制中的应用研究

本文分析开关磁阻电机驱动系统特性,提出了一种运用神经网络对其进行控制的方法,并与传统PID控制方式进行了比较,给出了仿真控制结果,表明了这种基于神经网络控制方法应用于开关磁阻电机驱动系统的优越性和可行性。     

开关磁阻电机转矩控制策略研究

给出了一种开关磁阻电机驱动系统转矩控制方案,通过对SRM电动机转矩的实时观测,利用模糊神经网络设计了一种SRM转矩闭环控制器.理论分析和仿真结果表明,该SRM电动机转矩闭环控制策略能够有效地控制SRM电动机相转矩按期望相转矩变化,从而实现了开关磁阻电机驱动系统高性能、低脉动转矩控制.     

基于BP神经网络的开关磁阻电机建模及仿真

为了改善开关磁阻电机的性能分析和控制效果,建立精确的开关磁阻电机模型是极其重要的。在获得准确的电机电磁特性基础上,利用神经网络所具有的非线性映射能力,建立开关磁阻电机非线性模型。本文采用基于附加动量法的BP神经网络建立开关磁阻电机磁链模型和转矩模型,同时在Matlab/Simulink平台上搭建电机控制系统模型。实验表明,该建模方法能满足开关磁阻电机驱动系统的高性能要求。     

开关磁阻电机模糊神经网络PID转速控制

针对开关磁阻电机调速系统难以控制的问题,提出了基于模糊FCMAC神经网络的PID控制方法,该方法的主要思想是将马丹尼直接推理法与CMAC神经网络相结合,构成模糊FCMAC神经网络,实时调整PID控制参数.仿真结果表明,与传统的PID控制方法相比较,该方法大大改善了开关磁阻电机调速系统的动、静态性能,且无需精确的数学模型...     

开关磁阻电机神经网络非线性映射建模方法研究

针对开关磁阻电机磁场的强非线性和高饱和性,通过有限元法得到了磁化以及转矩特性曲线簇。在此基础之上,利用神经网络的非线性映射能力,分别采取反向传播神经网络以及径向基函数神经网络对曲线簇进行了学习,进而在Matlab中建立了开关磁阻电机驱动系统的非线性动态仿真模型。对神经网络的结构及训练参数进行了敏感性分析,优化了取值,提高了逼近及泛化能力。在不同控制方法下,通过与有限元分析所得相电流以及合成转矩曲线的比较,验证了所建立开关磁阻电机驱动系统神经网络动态仿真模型的有效性。     

基于转矩逆模型的开关磁阻电机滑模变结构控制

开关磁阻电机的转矩脉动是其应用的一个问题.该文应用小波神经网络建立对应开关磁阻电机位置信号的非线性映射,估计转子位置角度,提出利用自适应模糊神经网络学习训练开关磁阻电机转矩逆模型优化期望转矩所需的相电流,采用滑模电流控制器实现电机转矩的低脉动控制,仿真结果表明方法的有效性,能够有效地控制开关磁阻电机转矩按期望变化.     

开关磁阻系统鲁棒性控制方法研究

在航空起动/发电系统中,开关磁阻电机(switched reluctance motor,SRM)的双凸极结构和高转矩脉动使航空起动/发电系统模型表现出高度的非线性和不确定性。为了解决SRM的非线性问题,提高系统的响应速度,降低转矩转速脉动,同时提高系统的抗干扰能力,本文基于协同控制和自适应模糊逻辑的基本原理,提出了一种自适应模糊终端协同控制方法(adaptive fuzzy terminal synergetic control,AFTSC)。针对开关磁阻系统模型的高度非线性和不确定性,协同控制确保了系统的鲁棒性,模糊逻辑估计了控制律的非线性方程,提高了控制器的有效性,同时降低了系统的计算体量。仿真和实验结果表明,在自适应模糊终端协同控制方法下,开关磁阻电机系统表现出更好的响应特性,该控制器对于开关磁阻电机转速和转矩的变化表现出更强的鲁棒性,相比于常规基于遗传算法的PID控制器具有更好的性能。     

对开关磁阻电机驱动系统的探讨

介绍开关磁阻电机驱动系统的国内外发展概况,开关磁阻电动机转矩的计算方法,驱动电源电路的种类,控制装置的发展方向及与直流电机、鼠笼式异步电动机驱动系统的比较。提出了开关磁阻电机驱动系统需要进一步研究探讨的问题。     

Fuzzy logic control of a switched reluctance motor drive

The paper deals with the fuzzy logic control of a switched reluctance motor (SRM) drive. The fundamentals of the fuzzy logic are first illustrated, pointing out the aspects related to the control under consideration. A fuzzy logic controller (FLC) of the motor speed is then designed and simulated. The results show that the use of an FLC in the speed loop gives the drive superior performances. In particular, the robustness of the drive has been proved     

Power converter control based on neural and fuzzy methods

The new power converter control approaches based on neural network techniques and fuzzy logic theorems are briefly reviewed and discussed in this paper. Current-controlled voltage source inverters offer substantial advantages in improving motor system dynamics for high-performance AC drive systems. The controller switches follow a set of reference current waveforms. Fixed-band and sinusoidal-band hysteresis current controllers have been studied. The first part of this paper develops neural network and fuzzy logic based current-controlled voltage source inverters. The models and learning techniques have been investigated by simulation. The implementation of neural networks is described and simulation results are presented. In the second part of this paper, the new UPS (uninterruptible power supply) with fuzzy logic compensator is proposed. The proposed fuzzy logic compensator is used to prevent voltage drop from nonlinear loads. The total harmonic distortion (THD) of the proposed scheme is better than that of conventional deadbeat control methods for linear and nonlinear loads. The applications of fuzzy and neural network control to DC-DC converters operating at finite switching frequency are studied in the third part of this paper. The fuzzy logic and neural network controller for unity power factor rectifiers, half-bridge DC-DC ZVZCS converters, DC motor drives, induction motor drives and permanent-magnet motor drives are also discussed. Some simulations are presented in this paper.     

开关磁阻电机的Pi-sigma模糊神经网络建模

开关磁阻电机的磁路高度饱和及双凸极结构导致了相绕组的磁链是转子位置和相电流的非线性函数。本文采用兼具Takagi-Sugeno(T-S)模糊逻辑和神经网络优点的Pi-sigma模糊神经网络来建立开关磁阻电机的非线性模型并采用了附加动量项的自适应学习速率训练算法。实现了开关磁阻电机的较高精度建模,减少了学习训练次数,简化了结构,使其可在线快速运算。本文通过对相电流与转子位置角的非均匀间隔采样和对论域的全面覆盖,来达到测量数据的合理分布,以提高建模精度和泛化能力并减少测试数据量。通过对模型输出数据与实测数据进行比较及对泛化样本数据的校验表明,本文所建立的模型具有精度较高、泛化能力较好、结构较简洁、运算速度较快等特点。     

基于模糊补偿的神经网络算法在调速系统中的应用

提出了一种带模糊补偿的神经网络算法并应用在异步电机速度控制系统中，一个动态神经网络用于被控装置的在线辨识，然后根据被控装置的输出和参考模型的响应迭代出控制信号，具有四条简单规则的模糊逻辑块用于提高整个系统的闭环特性。仿真结果显示，对比传统的最优PID控制器，本文提出的控制策略具有更好的瞬变特性及抗干扰特性。     

带补偿的神经网络辩识器在异步电机调速系统中的应用

本文提出了一种带模糊补偿的神经网络算法并应用在异步电机速度控制系统中.一个动态神经网络用于被控装置的在线辨识,然后根据被控装置的输出和参考模型的响应迭代出控制信号,具有四条简单规则的模糊逻辑块用于提高整个系统的闭环特性.仿真结果显示,对比传统的最优PID控制器,本文提出的控制策略具有更好的瞬变特性及抗干扰特性.     

Reference Model with an Adaptive Hermite Fuzzy Neural Network Controller for Tracking a Synchronous Reluctance Motor

This article presents a reference adaptive Hermite fuzzy neural network controller for a synchronous reluctance motor. Although synchronous reluctance motors are mathematically and structurally simple, they perform poorly under dynamic modes of operation because certain parameters, such as the external load and non-linear friction, are difficult to control. The proposed adaptive Hermite fuzzy neural network controller overcomes this problem, as using the Hermite function instead of the conventional Gaussian function shortens the training time. Furthermore, the proposed adaptive Hermite fuzzy neural network controller uses an online self-tuning fuzzy neural network to estimate the system's lumped uncertainty. The estimation method involves a fuzzy controller with expert knowledge of the initial weight of the neural network. Finally, the Lyapunov stability theory and adaptive update law were applied to guarantee system convergence. In this article, the responsiveness of the adaptive Hermite fuzzy neural network controller and an adaptive reference sliding-mode controller is compared. The experimental results show that the adaptive Hermite fuzzy neural network controller markedly improved the system's lumped uncertainty and external load response.     

开关磁阻电机模糊PID控制系统研究

介绍了模糊PID控制的开关磁阻电机调速方法,其兼有模糊控制和PID控制的优点,适用于非线性对象,并且具有较高的稳态精度.给出了1.1 kW开关磁阻电机控制器的设计实例,解决了因电机负载及运行状态不同所需PID参数不同的问题.理论与实践表明,采用模糊控制调节PID参数的方式对优化电机控制和提高系统性价比具有重要意义.     

比例因子自调整模糊神经网络SRM控制研究

基于开关磁阻电机原理,对智能控制算法在开关磁阻电机中的应用进行研究,将模糊逻辑和神经网络控制相结合,对量化因子、比例因子在线调整以提高系统性能.对改进算法控制效果进行仿真,与常规算法进行仿真比较分析;最后以TMS320LF2407 DSP为核心控制芯片、三相不对称半桥电路为SR电机功率变换器主电路控制SR电机,给出实...     

ANALYSIS OF POWER CONVERTER CONTROL USING NEURAL NETWORK AND RULE-BASED METHODS

ABSTRACT

Current-controlled voltage source inverters offer substantial advantages in improving motor system dynamics for high-performance ac drive systems. The controller switches follow a set of reference current waveforms. Fixed-band hysteresis and sinusoidal-band hysteresis controllers have been studied. The first part of this paper develops neural network and fuzzy logic based current-controlled voltage source inverters. The models and learning techniques have been investigated by simulation. The implementation of neural networks is described and simulation results are presented. In the second part of this paper, the new UPS (uninterruptible power supply) with fuzzy logic compensator is proposed. Proposed fuzzy logic compensator is used to prevent voltage drop from nonlinear load. The total harmonic distortion (THD) of proposed scheme is better than that of conventional deadbeat control method for linear and nonlinear load. In the third part of this paper, the application of fuzzy control to DC-DC converters operating at finite switching frequency is studied. Several control methods currently used for buck, boost and buck/boost converters are compared to the fuzzy converter control. Simulation results for several control methods are presented. The simulations show that the fuzzy control method has better dynamic performance and less steady state error.     

基于模糊神经网络的感应电机直接转矩控制

传统的直接转矩控制存在较大的转矩脉动。为了减小转矩脉动,提高控制性能,将模糊神经网络算法引入到直接转矩控制当中,设计了基于模糊神经网络的直接转矩控制系统。所采用的Takagi--Sugeno型模糊神经网络充分融合了模糊逻辑和神经网络两者的优点。在模糊神经网络的训练过程中,采用了一种最小二乘算法和BP算法相结合的混合算法进行学习,提高了学习速度。为了验证该算法有效性和可行性,在MATLAB／Simulink环境下建立了基于模糊神经网络的直接转矩控制系统仿真模型,进行了仿真研究。仿真结果表明采用Takagi—Sugeno型的模糊神经网络算法使直接转矩控制系统的转矩脉动明显变小,控制性能明显改善。