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.     

Identification and control of continuous-time nonlinear systems via dynamic neural networks

In this paper, we present an algorithm for the online identification and adaptive control of a class of continuous-time nonlinear systems via dynamic neural networks. The plant considered is an unknown multi-input/multi-output continuous-time higher order nonlinear system. The control scheme includes two parts: a dynamic neural network is employed to perform system identification and a controller based on the proposed dynamic neural network is developed to track a reference trajectory. Stability analysis for the identification and the tracking errors is performed by means of Lyapunov stability criterion. Finally, we illustrate the effectiveness of these methods by computer simulations of the Duffing chaotic system and one-link rigid robot manipulator. The simulation results demonstrate that the model-based dynamic neural network control scheme is appropriate for control of unknown continuous-time nonlinear systems with output disturbance noise.     

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.     

2 m望远镜消旋K镜转台的模型辨识

针对某2 m望远镜消旋K镜转台,提出了一种基于Hankel矩阵奇异值分解的特征系统实现算法对系统的参数和阶次进行辨识。首先,以正弦扫描信号激励转台并同步采集位置反馈信息,利用谱分析法对测试数据进行分析,得到了系统的频率特性曲线;其次,对系统的Hankel矩阵进行奇异值分解,得到了K镜转台的结构模型;最后,采用特征系统实现算法对Hankel矩阵进行辨识,得到了K镜转台的参数模型。实验结果显示:K镜转台相对均衡的最小阶阶次为6阶,在系统的中低频段获得幅度0.31 dB和相位0.87的辨识精度,相对于参数递阶辨识方法,分别提高了50.7%和23%。结果表明:该方法能够确定一个与系统外特性等价的相对均衡的最小阶状态空间模型,在辨识系统阶次和参数估计方面具有较好的可行性和实用性。     

利用改进的BP算法实现神经网络辨识仿真

系统辨识是控制系统设计的基础。基于多层前馈神经网络结构,采用一种改进的BP算法,利用二阶梯度变尺度模型,完成了神经网络非线性系统辨识。与传统的辨识方法比较,神经网络应用于非线性系统辨识具有泛化功能和很好的容错能力,是一种不依赖模型的自适应函数估计器。采用一种改进的BP算法有效地改善了系统收敛速度慢的问题,BP模型已成为神经网络的重要模型之一,从而为控制系统正确设计奠定理论基础。     

Neural predictive controller for insulin delivery using thesubcutaneous route

A neural predictive controller for closed-loop control of glucose using subcutaneous (s.c.) tissue glucose measurement and s.c. infusion of monomeric insulin analogs was developed and evaluated in a simulation study. The proposed control strategy is based on off-line system identification using neural networks (NNs) and nonlinear model predictive controller design. The system identification framework combines the concept of nonlinear autoregressive model with exogenous inputs (NARX) system representation, regularization approach for constructing radial basis function NNs, and validation methods for nonlinear systems. Numerical studies on system identification and closed-loop control of glucose were carried out using a comprehensive model of glucose regulation and a pharmacokinetic model for the absorption of monomeric insulin analogs from the s.c. depot. The system identification procedure enabled construction of a parsimonious network from the simulated data, and consequently, design of a controller using multiple-step-ahead predictions of the previously identified model. According to the simulation results, stable control is achievable in the presence of large noise levels, for unknown or variable time delays as well as for slow time variations of the controlled process. However, the control limitations due to the s.c. insulin administration makes additional action from the patient at meal time necessary     

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。     

一种新的复值递归神经网络训练方法及其应用

一种新的基于数字滤波器理论的全互连复值递归神经网络训练方法被提出.每个递归神经元均具有复数ⅡR滤波器结构.通过优化ⅡR滤波器的系数来更新神经网络的权值,而优化过程则采用逐层优化(LBLO)技术和递归最小平方(RLS)方法.该算法的性能通过将其应用于复信道均衡来加以说明.计算机仿真结果表明,该算法具有较快的收敛速度.这为快速训练复值递归神经网络提供了一条新的途径.     

飞机自动着陆的一种非线性鲁棒控制器设计

将一种直接基于非线性模型的带神经网络补偿信号的逆系统方法用于具有强非线性和受不确定扰动干扰的飞机自动着陆控制,并对神经网络补偿的方式进行了改进。采用神经网络补偿动态逆反馈线性化后伪系统的逆误差,使得非线性系统在参数受到摄动或外部扰动的情况下仍能保持良好的控制效果。可以证明该方法在理论上是收敛的,对于任意的状态初值和给定的期望输出信号,能控制到指定的精度。神经网络的权值是局部收敛的,同时大量仿真表明,经过较少的神经网络离线训练,即能够获得很好的控制效果。最后通过飞机着陆下滑段的仿真验证表明,该方法具有强的鲁棒性和良好的跟踪精度。     

A Generalized Fault Coverage Model for Linear Time-Invariant Systems

This paper proposes a fault coverage model for linear time-invariant (LTI) systems subject to uncertain input. A state-space representation, defined by the state-transition matrix, and the input matrix, is used to represent LTI system dynamic behavior. The uncertain input is considered to be unknown but bounded, where the bound is defined by an ellipsoid. The state-transition matrix, and the input matrix must be such that, for any possible input, the system dynamics meets its intended function, which can be defined by some performance requirements. These performance requirements constrain the system trajectories to some region of the state-space defined by a symmetrical polytope. When a fault occurs, the state-transition matrix, and the input matrix might be altered; and then, it is guaranteed the system survives the fault if all possible post-fault trajectories are fully contained in the region of the state-space defined by the performance requirements. This notion of guaranteed survivability is the basis to model (in the context of LTI systems) the concept of fault coverage, which is a probabilistic measure of the ability of the system to keep delivering its intended function after a fault. Analytical techniques to obtain estimates of the proposed fault coverage model are presented. To illustrate the application of the proposed model, two examples are discussed.     

Intelligent modeling, observation, and control for nonlinearsystems

We present identification methods for nonlinear mechatronic systems. First, we consider a system consisting of a known linear part and an unknown static nonlinearity. With this approach, using an intelligent observer, it is possible to identify the nonlinear characteristic and to estimate all unmeasurable system states. The identification result of the nonlinearity and the estimated system states are used to improve the controller performance. Secondly, the first approach is extended to systems where both the linear parameters and the nonlinear characteristic are unknown. This is achieved by implementing the intelligent observer as a structured recurrent neural network     

基于改进PID神经元网络的多变量系统控制算法

PID神经元网络具有动态特性,在系统控制应用中相比于传统的PID控制方法可取得更优的效果,但其学习算法为梯度学习算法,初始权值随机取得,为了提高其控制量逼近控制目标的速度和系统响应时间,引入粒子群算法对初始权值进行优化,最后应用Matlab软件对改进后的PID神经元网络算法进行仿真。仿真结果表明,该方法具有较好的控制性能。     

交流电机的智能PID控制应用研究

针对交流调速传统控制调速过程中往往会出现转速波动大和超调量等问题,无法满足控制系统的高性能要求,提出了一种自适应神经网络PID控制算法,应用反向传播人工神经网络理论,对于系统模型参数未知的情况下,使用两个人工神经网络分别进行控制系统在线辨识与PID控制器参数在线调整。经与PID控制对比进行了试验验证,表明本控制算法能让系统在很短的时间内调整出优良的控制参数,能够很好的跟踪负载变化,动态响应快,速度跟随准确,具有很强的自适应性和鲁棒性。     

Nonlinear dynamic system modeling using recurrent wavelet network

A recurrent wavelet network for the dynamic system nonparametric modeling is proposed in this paper. It is noted that the suitable recurrent units are introduced so that the dynamics of the wavelet network has been greatly improved. The recurrent backpropagation identification algorithm is also given. The simulation results show that regress system model with large-dimension can be better constructed and the useful guidelines for initialization of the network parameter are also provided with recurrent wavelet network identification.     

基于延时反向传播算法的低复杂度滤波器研究

为了进一步减少管状双线性递归神经网络的计算复杂度,在管状双线性递归神经网络中采用了延时反向传播算法。延时反向传播算法使用了阶次微分,误差函数对权值微分进行后向计算。后向计算顺序降低了初始化要求,减弱了网络对初始化条件敏感性并降低了计算的复杂度。该网络采用了模块化设计,各个模块以并行的方式执行任务,改善了计算效率。基于管状双线性递归神经网络的结构与神经元的数学模型,提出了具体的延时反向传播算法实现方案。同时进行了仿真来评估滤波器在非线性系统辨识方面的性能。实验结果表明基于延时反向传播算法的管状双线性递归神经网络提供了相当好的性能。     

基于LMS算法的自适应控制在稳定回路中的应用

成像器稳定跟踪平台的稳定回路设计是一种高精度、高动态响应的伺服回路设计,为实现较好的控制特性,提出了一种基于LMS算法的Adaline网络参数自适应控制方法,根据被控对象的参数变化,实时调整控制器的参数,由于算法相对简单,满足实际工程应用的要求。为了避免自适应算法运算对系统响应快速性的影响,设计了基于常规控制和自适应控制的双模态控制器结构,根据实际工作条件,进行控制策略的实时切换,既保证了系统响应的快速性,又保证了控制精度。实验结果表明,采用该方法实现的稳定回路具有良好的动态和静态特性。     

Hybrid fuzzy-logic and neural-network controller for MIMO systems

This study developed a hybrid fuzzy-logic and neural-network controller (HFNC) for multiple-input multiple-output (MIMO) systems. The HFNC consists of a fuzzy logic controller (FLC) which was designed to control each degree of freedom (DOF) of a MIMO system individually and an additional coupling neural network which was incorporated into the FLC to compensate for the dynamic coupling effects between each DOF of the MIMO system. Stability and robustness of the HFNC have been demonstrated using a state-space approach. From the simulation results of the 2-link robotic manipulator application and the experimental results of the 6-DOF robot tests, the HFNC demonstrated more superior control performance than the FLC.     

Bio-Interactive Healthcare Service System Using Lifelog Based Context Computing

Intelligent bio-sensor information processing was developed using lifelog based context aware technology to provide a flexible and dynamic range of diagnostic capabilities to satisfy healthcare requirements in ubiquitous and mobile computing environments. To accomplish this, various noise signals were grouped into six categories by context estimation and effectively reconfigured noise reduction filters by neural network and genetic algorithm. The neural network-based control module effectively selected an optimal filter block by noise context-based clustering in running mode, and filtering performance was improved by genetic algorithm in evolution mode. Due to its adaptive criteria, genetic algorithm was used to explore the action configuration for each identified bio-context to implement our concept. Our proposed Bio-interactive healthcare service system adopts the concepts of biological context-awareness with evolutionary computations in working environments modeled and identified as bio-sensors based environmental contexts. We used an unsupervised learning algorithm for lifelog based context modeling and a supervised learning algorithm for context identification.     

RELVEC — a tool for control system reliability analysis

This article will present a computerized reliability analysis tool for large control systems. It will also show a new dynamic representation of system structure. It enables us to model the physical system only once for any number of control tasks. The algorithm for computing minimal cut sets for the control tasks has been developed and automated. The result is RELVEC, an interactive computer program that performs reliability/availability calculation, sensitivity analysis and critical component identification. It can handle two repair policies and common mode failures. Reconfiquring of the physical system or the control tasks is simple. RELVEC is becoming an everyday tool in control system reliability analysis at VTT.     

基于动态神经网络在线辨识的PID控制

针对工业控制领域中复杂非线性时变系统和传统RBF神经网络辨识PID控制的不足,提出了一种基于聚类结合算法的动态RBF神经网络在线辨识PID自适应控制方法.通过优化的动态RBF辨识神经网络更好地描述了控制对象的动态行为,获得PID参数在线调整信息,实现系统的智能控制.仿真结果表明,与常规RBF神经网络辨识的PID控制方法相比该方法具有较高的控制精度,较快的系统响应,较强的适应性和鲁棒性.