Adaptive design of a fuzzy cerebellar model arithmetic controller neural network

We developed a posture control system for an electric wheelchair equipped with active suspension, using CMAC, which is a neural network type of control. Testing of the posture control of the wheelchair, which considers a learning results as an output to the target value inputted on-line using the learning function of CMAC (cerebellar model arithmetic controller), was performed. In this paper, testing of the learning control, which holds the posture horizontally both by the simulation and in the experiment by the system, is performed, and the validity of CMAC is verified compared with conventional method.

Over the last few decades, fuzzy logic has been shown as a powerful methodology for dealing with imprecision and nonlinearity efficiently. Applications can be found in a wide context ranging from medicine to finance, from human factors to consumer products, from vehicle control to computational linguistics, and so on (Wang 1997; Dubois and Prade 2000; Passino and Yurkovich 1998; Jang et al. 1997; Sugeno 1985; Pedrycz 1993). However, one of the shortcomings of fuzzy logic is the lack of systematic design. To circumvent this problem, fuzzy logic is usually combined with Neural Networks (NNs) by virtue of the learning capability of NNs. NNs are networks of highly interconnected neural computing elements that have the ability of responding to input stimuli and learning to adapt to the environment. Both fuzzy systems and NNs are dynamic and parallel processing systems that estimate input-output functions (Mitra and Hayashi 2000). The merits of both fuzzy and neural systems can be integrated in Fuzzy Neural Networks (FNNs) (Lee and Lee 1974, 1975; Pal and Mitra 1999; Zanchettin and Ludermir 2003). Therefore, the integration of fuzzy and neural systems leads to a symbiotic relationship in which fuzzy systems provide a powerful framework for expert knowledge representation, while NNs provide learning capabilities.

An interval-valued fuzzy cerebellar model neural network (IV-FCMNN) is proposed for the identification and control of uncertain systems. It is a more general model that uses the framework of a cerebellar model neural network (CMNN) and Atanassov intuitionistic fuzzy sets (AIFSs), so that the mathematical representation of a fuzzy event is more complete and the fuzzy neural network is more general. In some special cases, this neural network can be reduced to an interval-valued fuzzy neural network (IV-FNN), a fuzzy neural network (FNN), a fuzzy cerebellar model neural network (FCMNN) or a CMNN. Since the interval-type input data are used to realize this algorithm, the IV-FCMNN copes better with uncertainty and allows greater freedom of design. Therefore, the ability to learn, the approximation precision and the fuzzy semantic description of this network are much better than those of other models. In the proposed IV-FCMNN, a training algorithm that uses a gradient descent method is proposed to adjust the parameters and convergence is proved using the Lyapunov stability theorem. The variable learning rates are analyzed and the optimal learning rates are also determined. For demonstrating the effectiveness of the proposed IV-FCMNN, three types of applications, including multiple functions approximation, multi-dimensional classification and nonlinear dynamic system feedback control, are performed and the comparison with other models are also provided.

The paper is concerned with the application of quadratic optimization for motion control to feedback control of robotic systems using neural networks. Explicit solutions to the Hamilton-Jacobi-Bellman (HJB) equation for optimal control of robotic systems are found by solving an algebraic Riccati equation. It is shown how neural networks can cope with nonlinearities through optimization with no preliminary off-line learning phase required. The adaptive learning algorithm is derived from Lyapunov stability analysis, so that both system tracking stability and error convergence can be guaranteed in the closed-loop system. The filtered tracking error or critic gain and the Lyapunov function for the nonlinear analysis are derived from the user input in terms of a specified quadratic performance index. Simulation results on a two-link robot manipulator show the satisfactory performance of the proposed control schemes even in the presence of large modeling uncertainties and external disturbances.

Neural network approximation-based backstepping sliding mode control for spacecraft with input saturation and dynamics uncertainty

The paper is concerned with the application of reinforcement learning techniques to feedback control of nonlinear systems using adaptive fuzzy logic systems (FLS). Even if a good model of the nonlinear system is known, it is often difficult to formulate a control law. The work in this paper addresses this problem by showing how an adaptive FLS can cope with nonlinearities through reinforcement learning with no preliminary off-line learning phase required. The reinforcement learning rules for finding proper fuzzy rules and tuning membership functions (MFs) do not assume that there is a supervisor to decide whether the current control action is correct. Instead, the FLS is indirectly told about the affect of its control action on the system performance. The learning is performed online based on a binary reinforcement signal from a critic without knowing the nonlinearity appearing in the system, and so is called direct reinforcement adaptive learning (DRAL). The learning algorithm is derived from Lyapunov stability analysis, so that both system tracking stability and error convergence can be guaranteed in the closed-loop system.

On the basis of previous research, This article studies the structure and working principle of recurrent fuzzy neural network. The traditional fuzzy controller is not precise enough, does not have simple algorithm but poor timely traceability. The use of the fuzzy neural network is good for fully integrating the fuzzy control feature and neural network control feature. And we can improve the fuzzy neural network into recurrent fuzzy neural network, and apply this in the power flow control of the power converter. Through simulating and contrasting, the experiments show that it can achieve the UPFC trend of dynamic real-time monitoring, it has better tracking control capability and robustness, and preferable effect of power control.

This article proposes a fault diagnosis method for closed-loop satellite attitude control systems based on a fuzzy model and parity equation. The fault in a closed-loop system is propagated with the feedback loop, increasing the difficulty of fault diagnosis and isolation. The study uses a Takagi-Sugeno (T-S) fuzzy model and parity equation to diagnose and isolate a fault in a closed-loop satellite attitude control system. A fully decoupled parity equation is designed for the closed-loop satellite attitude control system to generate a residual that is sensitive only to a specific actuator and sensor. A T-S fuzzy model is used to describe the nonlinear closed-loop satellite attitude control system. With the combination of the T-S fuzzy model and fully decoupled parity equation, the fuzzy parity equation (FPE) of the nonlinear system can be obtained. Then this article uses a parameter estimator based on a Kalman filter to identify deviations and scale factor changes from information contained in the residuals generated by the FPE. The actuator and sensor fault detection and isolation simulation of the three-axis stable satellite attitude control system is provided for illustration.

Over the last decade, an extensive research has been carried out in the areas of fuzzy logic and neural networks. Fuzzy logic has emerged as a mathematical tool to deal with the uncertainties in human perception and reasoning. It also provides a framework for an inference mechanism that allows for approximate human reasoning capabilities to be applied to knowledge-based systems. On the other hand, artificial neural networks have emerged as fast computation tools with learning and adaptivity capabilities. Recently, these two fields have been integrated into a new emerging technology called fuzzy neural networks which combines the benefits of each field. The objective of the paper is to establish the similarities and differences between fuzzy systems and neural networks and to discuss possible models for fuzzy neural networks which can be applied to system modeling and control.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>

This paper presents a design method of adaptive fuzzy controllers using dual-fuzzy neural networks (DFNNs). For the convenience of adaptive control, the structure of the two-fuzzy neural-network controller is divided into two parts. Each part is a fuzzy neural-network (FNN). The adaptive controller uses two FNNs. One FNN is used to identify a fuzzy model of controlled object. The fuzzy control rule is designed with the linguistic rules of the fuzzy model and is incorporated into the other FNN. Simulations using a controlled object with an non-monotonic input-output characteristics are done to verify the proposed design method.

Fuzzy control has a distinctive feature in that it can incorporate experts' control rules using linguistic expressions. The authors have presented various types of fuzzy neural networks (FNNs) called Type I-V. The FNNs can automatically identify the fuzzy rules and tune the membership functions of fuzzy controllers by utilizing the learning capability of neural networks. In particular, the Type IV FNN has a simple structure and can express the identified fuzzy rules linguistically. The authors have also proposed a method to describe the behavior of fuzzy control systems based on the fuzzy models. The method can comprehensively express the dynamic behavior of fuzzy control systems and makes easy to know how to modify the fuzzy controllers. This paper studies an acquisition of fuzzy controller for an inverted pendulum using the Type IV FNNs and presents a new method for describing of the behavior of the fuzzy control system. The new method expresses the dynamic ehavior of the fuzzy control system more clearly by incorporating the change of the output of the controlled object. This new rule-to-rule mapping method enables easy modification of the fuzzy control rules. The experimental results illustrate that the method is effective in designing the fuzzy controllers having good performance.

A fuzzy control system for multivariable complex nonlinear systems is presented, which is based on a fuzzy dynamic model. Firstly, the fuzzy state feedback control law is designed for each local linear model and the control law for the overall system is determined through fuzzy inference. A set of local linear models are linked together by a fuzzy membership function to obtain the continuous global model. By considering the fuzzy system as a set of nominal linear systems subject to perturbations contributed by other interacting subsystems, a sufficient condition for the stability of the closed-loop fuzzy system is derived via the concept of connective stability in decentralized control of a large-scale system. The validity of the fuzzy model based control technique is illustrated by a simulation example.

In this paper, a reconfiguration approach using fuzzy logic algorithm and neural network modelling is proposed. When failure has been detected, the state of the degraded system is evaluated by comparing the output of the system with the estimation provided by a neural model. Therefore, we propose to use the neural network in order to cover all the operating zone of the faulty system. By combining neural network capabilities and fuzzy logic for fault evaluation, a new control law is determined taking into account the impact of the failure on the system. Its potentialities are illustrated through simulation studies on a thermal plant presenting bilinear characteristics. >

In this paper, a intelligent RBF neural network (RBFNN) tracking control system with reinforcement learning (RL) compensation methods control technique is proposed for a class of chaos systems. The proposed adaptive control scheme is developed for a class of chaotic systems with unknown bounded uncertainties. The adaptation laws are derived using a gradient descent, so that both system tracking stability and error convergence can be guaranteed in the closed-loop system. It are used to demonstrate the effectiveness and performance of proposed hybrid control technique.

This chapter provides a comprehensive review of fuzzy neural network models. Existing methods to combine fuzzy logic and neural networks are presented. Several classifications of fuzzy neural networks are provided. Those classifications are based on the type of application of the fuzzy neural network. Fuzzy neural network models with supervised learning features are also reviewed in detail. A review of various biomedical engineering applications that use fuzzy neural networks is also presented. Some future medical science applications of fuzzy neural networks are described. A complete bibliography is listed at the end of the chapter.