基于双层递归神经网络模型求解最优组播路由

基于覆盖网络的组播作为一种新的IP网络组播解决方案已得到广泛关注。提出了一种利用改进的双层递归神经网络模型求解VPON网络环境下的QoS（服务质量）最优组播路由的方案。该方案在选择路由时综合考虑链路的可用带宽及节点的剩余处理能力，并运用一种基于改进的双层递归神经网络模型——MTLRNN进行求解，与其它启发式组播路由算法相比，该方案在满足应用的QoS要求的前提下，使全网的负载分配更加均衡，同时在解的有效性及接纳的组播应用会话数方面都有比较大的改善。     

自适应RBF神经网络在CDMA移动通信上行链路功率控制中的应用研究

提出了一种自适应RBF神经网络功率控制方案。详细研究了该网络在DS-CDMA通信中，进行上行链路闭环功率控制(基于信扰比(SIR))的应用理论，给出了该网络参数的计算方法。最后用计算机仿真法模拟出该控制器的运行性能。结果表明基于SIR的自适应RBF神经网络功率控制器能自适应地调整移动台的发射功率，使基站接收信号的信扰比始终非常接近于一个常数，且有比定步长功率控制更小的SIR跟踪误差，从而可以降低接收信号的中断概率、提高信道容量。     

一种基于BP神经网络群的自适应分类方法及其应用

本文针对基于BP神经网络的分类系统,提出了神经网络群的概念,在此基础上给出了一种系统自适应增长算法,使得在新的目标类型加入时系统结构能够自适应调整.验证结果表明,该算法可以在增加新的目标类型时简化系统结构的调整过程,缩短重新训练网络所需要的时间,从而有效地提高网络的训练效率.     

单隐含层模糊递归小波神经网络的观测器设计

根据模糊神经网络在非线性函数逼近方面的特性和小波变换具有良好的时频两维信号的分析能力,建立了结合两者优点的单隐含层模糊递归小波神经网络(Single hidden Layer Fuzzy Recurrent Wavelet Neural Network,SLFRWNN),并分析了SLFRWNN的结构、激活函数形式及激活函数对网络性能的影响.在此基础上,提出了一种基于SLFRWNN的自适应观测器设计方法,并通过引入Lyapunov函数,证明了这种观测器设计方法的稳定性,进而给出该网络观测器的初始化和最佳训练算法;仿真结果表明SLFRWNN观测器能很好地观测系统的状态.     

基于RFNN的复杂机动事件检测方法

针对态势评估中复杂机动事件检测的精度及实时性问题,提出了基于粗糙集-模糊神经网络(RFNN)的事件检测方法,通过粗糙集理论获取数据样本中的最简规则集,然后根据这些规则构造模糊神经网络各层的神经元个数及相关参数初始值,最后用BP算法迭代求出网络的各种参数.仿真结果证明RFNN用于复杂机动事件检测的有效性,同时可以发现其在...     

基于自适应模糊神经网络的感应电机矢量控制

感应电机在传统PI控制中,参数固定且容易超调。针对该问题,文中研究了一种基于自适应模糊神经网络PI控制与全阶自适应观测器的感应电机矢量控制方案。根据感应电机数学模型建立了全阶自适应观测器的模型,采用Lyapunov稳定性理论对其进行了稳定性分析设计,并推导了转速自适应律。电机速度外环PI由自适应模糊神经网络推理系统在线整定优化,与传统控制方案相比,该方法易于实现,能够有效提高控制精准性,抑制外部扰动,节省了传感器成本。MATLAB/Simulink仿真实验表明,所提方案不仅改善了无速度传感器感应电机矢量控制系统的动态性能,还减小了外部负载扰动等情况的影响,提高了系统的自适应性和鲁棒性。     

延时-回归神经网络及在超声马达控制中的应用

提出了一个结构简单的延时—回归神经网络(Time-delay recurrent neural network,TDRNN)模型.通过在网络中同时引入延时结构和反馈结构来保证网络具有高的记忆"深度"和的记忆"分辨率".建立了TDRNN型的控制器对超声马达进行控制,推导了TDRNN的动态递归反传算法.在离散型Lyapunov稳定性的意义下,导出了权值自适应学习速率的取值范围,保证控制系统的快速收敛.对超声马达速度控制的数值实验表明,本文提出的延时—回归神经网络在动态系统的辨识和控制方面具有很好的性能.     

基于DBFNN的推设及其在电力系统励磁控制中的应用

本文采用后推设计算法为一类严格反馈系统设计了基于方向基函数神经网络(DBFNN)的自适应控制器.在后推算法中的每步都引入一积分型的Lyapunov函数来设计一个虚拟控制器,并在最后一步为闭环系统综合设计了神经网络控制器.网络权值的调整基于所选择的Lyapunov函数,于是设计方案能保证整个闭环系统是最终一致有界的.把所设计控制方案用于带有未知参数和外部干扰的电力系统励磁控制中.仿真结果表明了所设计控制器的有效性.     

储备池计算概述

针对传统递归神经网络存在训练困难的问题,一种新的递归神经网络的训练方法——储备池计算被提出,这种方法的核心思想是只训练网络部分连接权,其余连接权一经产生就不再改变,网络的训练一般只需要通过求解线性回归问题.广义地说,储备池可以作为一种时序相关的核函数使用,从而完全拓展了其应用领域,使之不再仅仅是递归神经网络训练算法的一...     

基于Elman神经网络的多目标跟踪技术的研究

首先叙述了Elman神经网络的结构、原理和学习方法.针对Elman网络的学习率对网络收敛速度及稳定性影响很大,提出了一种可以自适应调整学习速率的改进的Elman网络学习算法;并基于Elman神经网络,采用模糊推理进行数据关联的方法,结合扩展卡尔曼滤波,提出一种新的多目标跟踪方法.最后应用此方法采用两个传感器对两个运动目标进行跟踪实验,并与BP神经网络对比得出仿真结果,实验结果表明,所提出的方法是一种可行的多目标跟踪方法.     

Recurrent-Fuzzy-Neural-Network-Controlled Linear Induction Motor Servo Drive Using Genetic Algorithms

A recurrent fuzzy neural network (RFNN) controller based on real-time genetic algorithms (GAs) is developed for a linear induction motor (LIM) servo drive in this paper. First, the dynamic model of an indirect field-oriented LIM servo drive is derived. Then, an online training RFNN with a backpropagation algorithm is introduced as the tracking controller. Moreover, to guarantee the global convergence of tracking error, a real-time GA is developed to search the optimal learning rates of the RFNN online. The GA-based RFNN control system is proposed to control the mover of the LIM for periodic motion. The theoretical analyses for the proposed GA-based RFNN controller are described in detail. Finally, simulated and experimental results show that the proposed controller provides high-performance dynamic characteristics and is robust with regard to plant parameter variations and external load disturbance     

Robust friction state observer and recurrent fuzzy neural network design for dynamic friction compensation with backstepping control

In this article, we investigate a robust friction compensation scheme for the purpose of accomplishing high-precision positioning performance in a servo mechanical system with nonlinear dynamic friction. To estimate the friction state and tackle the robustness problem for uncertainty, a recurrent fuzzy neural network (RFNN) and reconstructed error compensator as well as a robust friction state observer are developed. The asymptotic stability of the series of friction compensation methodologies are verified from the Lyapunov’s stability theory. Some simulations and experiments on a frictional servo mechanical system were carried out to evaluate the effectiveness of the proposed control scheme.     

Adaptive neuro-fuzzy control of a flexible manipulator

This paper describes an adaptive neuro-fuzzy control system for controlling a flexible manipulator with variable payload. The controller proposed in this paper is comprised of a fuzzy logic controller (FLC) in the feedback configuration and two dynamic recurrent neural networks in the forward path. A dynamic recurrent identification network (RIN) is used to identify the output of the manipulator system, and a dynamic recurrent learning network (RLN) is employed to learn the weighting factor of the fuzzy logic. It is envisaged that the integration of fuzzy logic and neural network based-controller will encompass the merits of both technologies, and thus provide a robust controller for the flexible manipulator system. The fuzzy logic controller, based on fuzzy set theory, provides a means for converting a linguistic control strategy into control action and offering a high level of computation. On the other hand, the ability of a dynamic recurrent network structure to model an arbitrary dynamic nonlinear system is incorporated to approximate the unknown nonlinear input–output relationship using a dynamic back propagation learning algorithm. Simulations for determining the number of modes to describe the dynamics of the system and investigating the robustness of the control system are carried out. Results demonstrate the good performance of the proposed control system.     

Precise friction control for the nonlinear friction system using the friction state observer and sliding mode control with recurrent fuzzy neural networks

This paper deals with a tracking control problem of a mechanical servo system with nonlinear dynamic friction which contains a directly immeasurable friction state variable and an uncertainty caused by incomplete parameter modeling and its variations. In order to provide an efficient solution to these control problems, we propose a composite control scheme, which consists of a friction state observer, a RFNN approximator and an approximation error compensator with sliding mode control. In first, a sliding mode controller and friction state observer are designed to estimate the unknown internal state of the LuGre friction model. Next, a RFNN is developed to approximate an unknown lumped friction uncertainty. Finally, an adaptive error compensator is designed to compensate an approximation error of RFNN. Some simulations and experiments on the mechanical servo system composed of ball-screw and DC servo motor are executed. Their results give a satisfactory performance of the proposed control scheme.     

Robust Fuzzy Neural Network Sliding-Mode Control for Two-Axis Motion Control System

A robust fuzzy neural network (RFNN) sliding-mode control based on computed torque control design for a two-axis motion control system is proposed in this paper. The two-axis motion control system is an$x-y$table composed of two permanent-magnet linear synchronous motors. First, a single-axis motion dynamics with the introduction of a lumped uncertainty including cross-coupled interference between the two-axis mechanism is derived. Then, to improve the control performance in reference contours tracking, the RFNN sliding-mode control system is proposed to effectively approximate the equivalent control of the sliding-mode control method. Moreover, the motions at$x$-axis and$y$-axis are controlled separately. Using the proposed control, the motion tracking performance is significantly improved, and robustness to parameter variations, external disturbances, cross-coupled interference, and friction force can be obtained as well. Furthermore, the proposed control algorithms are implemented in a TMS320C32 DSP-based control computer. From the simulated and experimental results due to circle and four leaves reference contours, the dynamic behaviors of the proposed control systems are robust with regard to uncertainties.     

A recurrent fuzzy cellular neural network system with automatic structure and template learning

It is widely accepted that using a set of cellular neural networks (CNNs) in parallel can achieve higher level information processing and reasoning functions either from application or biologics points of views. Such an integrated CNN system can solve more complex intelligent problems. In this paper, we propose a novel framework for automatically constructing a multiple-CNN integrated neural system in the form of a recurrent fuzzy neural network. This system, called recurrent fuzzy CNN (RFCNN), can automatically learn its proper network structure and parameters simultaneously. The structure learning includes the fuzzy division of the problem domain and the creation of fuzzy rules and CNNs. The parameter learning includes the tuning of fuzzy membership functions and CNN templates. In the RFCNN, each learned fuzzy rule corresponds to a CNN. Hence, each CNN takes care of a fuzzily separated problem region, and the functions of all CNNs are integrated through the fuzzy inference mechanism. A new online adaptive independent component analysis mixture-model technique is proposed for the structure learning of RFCNN, and the ordered-derivative calculus is applied to derive the recurrent learning rules of CNN templates in the parameter-learning phase. The proposed RFCNN provides a solution to the current dilemma on the decision of templates and/or fuzzy rules in the existing integrated (fuzzy) CNN systems. The capability of the proposed RFCNN is demonstrated on the real-world defect inspection problems. Experimental results show that the proposed scheme is effective and promising.     

Decoupled stator-flux-oriented induction motor drive with fuzzyneural network uncertainty observer

A stator-flux-oriented induction motor drive using online rotor time-constant estimation with a robust speed controller is introduced in this paper. The estimation of the rotor time constant is made on the basis of the model reference adaptive system using an energy function. The estimated rotor time-constant is used in the current-decoupled controller, which is designed to decouple the torque and flux in the stator-flux-field-oriented control. Moreover, a robust speed controller, which is comprised of an integral-proportional speed controller and a fuzzy neural network uncertainty observer, is designed to increase the robustness of the speed control loop. The effectiveness of the proposed control scheme is demonstrated by simulation and experimental results     

Temperature control by chip-implemented adaptive recurrent fuzzy controller designed by evolutionary algorithm

Online adaptive temperature control by field-programmable gate array (FPGA) - implemented adaptive recurrent fuzzy controller (ARFC) chip is proposed in this paper. The RFC is realized according to the structure of Takagi-Sugeno-Kang (TSK)-type recurrent fuzzy network. Direct inverse control configuration is used. To design RFC offline, evolutionary fuzzy controller using the hybrid of the Simplex method and particle swarm optimization (SPSO) is proposed. In SPSO, each RFC corresponds to a particle, and all the free parameters in RFC are optimally searched. We use the PSO to find a good solution globally, and the incorporation of the Simplex method helps find a better solution around the local region of the best solution found by PSO so far. Then, online adaptive temperature control with ARFC chip implemented by FPGA is proposed. In the ARFC chip, the consequent parameters of all rules are all tuned online using gradient descent. To verify the performance of the ARFC chip, experiments on a water bath temperature system are performed.     

自动巡航汽车自适应逆控制的建模与仿真

研究神经网络非线性系统的自适应建模和逆建模策略用于非线性的自动巡航系统的控制及可行性。通过对自适应逆控制方法与现行的反馈控制、模糊控制、PID控制进行对比,并在有干扰的情况下系统需要一定的收敛时间,通过运用Matlab软件进行仿真。根据仿真结果分析,当对象输出没有受到干扰时,其在线辨识对象模型和逆模型有十分好的效果;当对象输出存在一些干扰时,由于干扰的存在,需要一段时间来将两个辨识模型收敛。因此,基于动态神经网络的非线性自适应逆控制系统是十分可行的。