Wei Yen Wang

Observer-based adaptive fuzzy-neural control for unknown nonlinear dynamical systems

In this paper, an observer-based adaptive fuzzy-neural controller for a class of unknown nonlinear dynamical systems is developed. The observer-based output feedback control law and update law to tune on-line the weighting factors of the adaptive fuzzy-neural controller are derived. The total states of the nonlinear system are not assumed to be available for measurement. Also, the unknown nonlinearities of the nonlinear dynamical systems are not restricted to the system output only. The overall adaptive scheme guarantees that all signals involved are bounded. Simulation results demonstrate the applicability of the proposed method in order to achieve desired performance.

Observer-based direct adaptive fuzzy-neural control for nonaffine nonlinear systems

In this paper, an observer-based direct adaptive fuzzy-neural control scheme is presented for nonaffine nonlinear systems in the presence of unknown structure of nonlinearities. A direct adaptive fuzzy-neural controller and a class of generalized nonlinear systems, which are called nonaffine nonlinear systems, are instead of the indirect one and affine nonlinear systems given by Leu et al. By using implicit function theorem and Taylor series expansion, the observer-based control law and the weight update law of the fuzzy-neural controller are derived for the nonaffine nonlinear systems. Based on strictly-positive-real (SPR) Lyapunov theory, the stability of the closed-loop system can be verified. Moreover, the overall adaptive scheme guarantees that all signals involved are bounded and the output of the closed-loop system will asymptotically track the desired output trajectory. To demonstrate the effectiveness of the proposed method, simulation results are illustrated in this paper.

H/sub /spl infin// tracking-based sliding mode control for uncertain nonlinear systems via an adaptive fuzzy-neural approach

A novel adaptive fuzzy-neural sliding-mode controller with H(infinity) tracking performance for uncertain nonlinear systems is proposed to attenuate the effects caused by unmodeled dynamics, disturbances and approximate errors. Because of the advantages of fuzzy-neural systems, which can uniformly approximate nonlinear continuous functions to arbitrary accuracy, adaptive fuzzy-neural control theory is then employed to derive the update laws for approximating the uncertain nonlinear functions of the dynamical system. Furthermore, the H(infinity) tracking design technique and the sliding-mode control method are incorporated into the adaptive fuzzy-neural control scheme so that the derived controller is robust with respect to unmodeled dynamics, disturbances and approximate errors. Compared with conventional methods, the proposed approach not only assures closed-loop stability, but also guarantees an H(infinity) tracking performance for the overall system based on a much relaxed assumption without prior knowledge on the upper bound of the lumped uncertainties. Simulation results have demonstrated that the effect of the lumped uncertainties on tracking error is efficiently attenuated, and chattering of the control input is significantly reduced by using the proposed approach.

Robust adaptive fuzzy-neural controllers for uncertain nonlinear systems

A robust adaptive fuzzy-neural controller for a class of unknown nonlinear dynamic systems with external disturbances is proposed. The fuzzy-neural approximator is established to approximate an unknown nonlinear dynamic system in a linearized way. The fuzzy B-spline membership function (BMF) which possesses a fixed number of control points is developed for online tuning. The concept of tuning the adjustable vectors, which include membership functions and weighting factors, is described to derive the update laws of the robust adaptive fuzzy-neural controller. Furthermore, the effect of all the unmodeled dynamics, BMF modeling errors and external disturbances on the tracking error is attenuated by the error compensator which is also constructed by fuzzy-neural inference. We prove that the closed-loop system which is controlled by the robust adaptive fuzzy-neural controller is stable and the tracking error will converge to zero under mild assumptions. Several examples are simulated in order to confirm the effectiveness and applicability of the proposed methods.

Fuzzy B-spline membership function (BMF) and its applications in fuzzy-neural control

A general methodology for constructing fuzzy membership functions via B-spline curves is proposed. By using the method of least-squares, the authors translate the empirical data into the form of the control points of B-spline curves to construct fuzzy membership functions. This unified form of fuzzy membership functions is called a B-spline membership function (BMF). By using the local control property of a B-spline curve, the BMFs can be tuned locally during the learning process. For the control of a model car through fuzzy-neural networks, it is shown that the local tuning of BMFs can indeed reduce the number of iterations tremendously. This fuzzy-neural control of a model car is presented to illustrate the performance and applicability of the proposed method. >

An online GA-based output-feedback direct adaptive fuzzy-neural controller for uncertain nonlinear systems

In this paper, we propose a novel design of a GA-based output-feedback direct adaptive fuzzy-neural controller (GODAF controller) for uncertain nonlinear dynamical systems. The weighting factors of the direct adaptive fuzzy-neural controller can successfully be tuned online via a GA approach. Because of the capability of genetic algorithms (GAs) in directed random search for global optimization, one is used to evolutionarily obtain the optimal weighting factors for the fuzzy-neural network. Specifically, we use a reduced-form genetic algorithm (RGA) to adjust the weightings of the fuzzy-neural network. In RGA, a sequential-search -based crossover point (SSCP) method determines a suitable crossover point before a single gene crossover actually takes place so that the speed of searching for an optimal weighting vector of the fuzzy-neural network can be improved. A new fitness function for online tuning the weighting vector of the fuzzy-neural controller is established by the Lyapunov design approach. A supervisory controller is incorporated into the GODAF controller to guarantee the stability of the closed-loop nonlinear system. Examples of nonlinear systems controlled by the GODAF controller are demonstrated to illustrate the effectiveness of the proposed method.

On-line tuning of fuzzy-neural network for adaptive control of nonlinear dynamical systems

The adaptive fuzzy-neural controllers tuned online for a class of unknown nonlinear dynamical systems are proposed. To approximate the unknown nonlinear dynamical systems, the fuzzy-neural approximator is established. Furthermore, the control law and update law to tune on-line both the B-spline membership functions and the weighting factors of the adaptive fuzzy-neural controller are derived. Therefore, the control performance of the controller is improved. Several examples are simulated in order to confirm the effectiveness and applicability of the proposed methods in this paper.

Soft Computing for Battery State-of-Charge (BSOC) Estimation in Battery String Systems

In this paper, a soft computing technique for estimating battery state-of-charge of individual batteries in a battery string is proposed. The soft computing approach uses a fusion of a fuzzy neural network (FNN) with B-spline membership functions (BMFs) and a reduced-form genetic algorithm (RGA). The algorithm is employed to tune both control points of the BMFs and the weights of the FNNs. The traditional multiple-input multiple-output FNN (MIMOFNN) cannot directly be used in this paper. The main reason is that there are too many free parameters in the MIMOFNN to be trained if many inputs are required. In this paper, a merged multiple-input single-output (MISO) FNN is proposed and can be trained by the RGA optimization approach. The merged MISO FNN with RGA (FNNRGA) can achieve faster convergence and lower estimation error than neural networks with the back propagation method. From experimental results, the proposed merged MISO FNNRGA is superior, more robust than the traditional method, and the overfitting suppression features are significantly improved.

Function approximation using fuzzy neural networks with robust learning algorithm

The paper describes a novel application of the B-spline membership functions (BMFs) and the fuzzy neural network to the function approximation with outliers in training data. According to the robust objective function, we use gradient descent method to derive the new learning rules of the weighting values and BMFs of the fuzzy neural network for robust function approximation. In this paper, the robust learning algorithm is derived. During the learning process, the robust objective function comes into effect and the approximated function will gradually be unaffected by the erroneous training data. As a result, the robust function approximation can rapidly converge to the desired tolerable error scope. In other words, the learning iterations will decrease greatly. We realize the function approximation not only in one dimension (curves), but also in two dimension (surfaces). Several examples are simulated in order to confirm the efficiency and feasibility of the proposed approach in this paper.

A Merged Fuzzy Neural Network and Its Applications in Battery State-of-Charge Estimation

To solve learning problems with vast number of inputs, this paper proposes a novel learning structure merging a number of small fuzzy neural networks (FNNs) into a hierarchical learning structure called a merged-FNN. In this paper, the merged-FNN is proved to be a universal approximator. This computing approach uses a fusion of FNNs using B-spline membership functions (BMFs) with a reduced-form genetic algorithm (RGA). RGA is employed to tune all free parameters of the merged-FNN, including both the control points of the BMFs and the weights of the small FNNs. The merged-FNN can approximate a continuous nonlinear function to any desired degree of accuracy. For a practical application, a battery state-of-charge (BSOC) estimator, which is a twelve input, one output system, in a lithium-ion battery string is proposed to verify the effectiveness of the merged-FNN. From experimental results, the learning ability of the newly proposed merged-FNN with RGA is superior to that of the traditional neural networks with back-propagation learning.