Direct Adaptive Neural Network Control Research Articles

Neural Network Identification and Direct Adaptive Fuzzy Neural Network (DAFNN) Controller for Unknown Nonlinear Non-affine Pneumatic Servo System

In this paper, a direct adaptive fuzzy neural network (DAFNN) controller for trajectory tracking control of the non-linear non-affine pneumatic servo system is presented. First, using a neural network identifier, the non-linear dynamics of a real pneumatic servo system is simulated. By comparing the output of the neural network and the output of the experimental setup, it is observed that the non-linear pneumatic actuator system is well-identified using neural networks. By incorporating the Lyapunov stability theorem, the adaptive laws for the parameters of the controller are obtained, parameter boundedness and stability of the closed-loop system are guaranteed. Finally, practical results are successfully implemented for trajectory tracking control of the pneumatic servo system, in which the effect of the simultaneous updating of the antecedent and consequent’s parameters of the fuzzy neural network controller has been investigated. The tracking error ±1.3mm and ±1 mm for proposed updating method compared to ±2.5mm and ±3.5mm, for a case that the weigh parameters are merely adjusted, are obtained. The results indicate the proposed adjustment method improves the performance of the controller in the presence of unknown nonlinearities and dynamics uncertainty.

Robust adaptive sliding mode control of underactuated autonomous underwater vehicles with uncertain dynamics

This paper focuses on adaptive integral sliding mode control for a class of underactuated autonomous underwater vehicles (AUVs) with uncertain dynamics, where the vehicles moving in three-dimensional (3-D) space have only three available control inputs provided by the stern propellers, steering and diving rudders but five degrees of freedom to be controlled. Different from the traditional sliding mode control, the proposed dual closed-loop integral sliding mode control design can be described as comprising two distinct phases: 1) in outer-loop, the virtual velocity commands are determined for the following work; 2) in inner-loop, the actual control inputs are designed to achieve the trajectory tracking. Moreover, the practical situations that there exist systematic parametric uncertainties and external disturbances are also considered, and a novel direct adaptive neural network controller combined with a conditional integrator is presented, which provides the robustness and adaptation for the vehicle. In addition, the rigorous stability analysis based Lyapunov’s method demonstrates the uniform ultimate boundedness of all the tracking errors in the closed-loop system. Finally, simulation results are shown the effectiveness of the proposed controllers.

Direct adaptive neural network control for switched reluctance motors with input saturation

This paper presents a novel direct adaptive neural network controller for switched reluctance motor (SRM) speed control, which takes into account parameter variations, external load disturbances, and input saturation constraint. The radial basis function (RBF) neural network based on the technology of minimal learning parameters (MLP) is employed to approximate an ideal control law that includes parameter variations and external disturbances. An auxiliary dynamic system is constructed to handle the input saturation constraint. Furthermore, uniform ultimate boundedness of all signals in the SRM drive closed‐loop control system is guaranteed through rigorous Lyapunov analysis. Comparative studies are carried out between the proposed control scheme and conventional proportional‐integral (PI) control, and the simulation and experimental results show that the proposed control scheme has better performance for parameter variations and external load disturbances. © 2018 Institute of Electrical Engineers of Japan. Published by John Wiley & Sons, Inc.

Direct adaptive control for a class of MIMO nonlinear discrete-time systems

This paper considers the problem of adaptive control for a class of multiple input multiple output(MIMO) nonlinear discretetime systems based on inputoutput model with unknown interconnections between subsystems. Based on the Taylor expand technology, an equivalent model in affinelike form is derived for the original nonaffine nonlinear system. Then a direct adaptive neural network(NN) controller is implemented based on the affinelike model. By finding an orthogonal matrix to tune the NN weights, the closedloop system is proven to be semiglobally uniformly ultimately bounded. The σmodification technique is used to remove the requirement of persistence excitation during the adaptation. The control performance of the closedloop system is guaranteed by suitably choosing the design parameters.

EFFICIENCY OPTIMIZATION OF AN OPENLOOP CONTROLLED PERMANENT MAGNET SYNCHRONOUS MOTOR DRIVE USING ADAPTIVE NEURAL NETWORKS

When a Permanent Magnet Synchronous Machine (PMSM) is utilized for applications where high dynamic performance is not a requirement, a simple open loop control strategy can be used to control them. PMSMs however are prone to instability when operated open loop in a variable speed drive, particularly at mid-frequencies/speeds. This paper presents an open-loop control strategy based on a direct adaptive neural network controller is developed for efficiency optimization of open-loop controlled PMSM drive. Stability constraints of the drive system which was previously reported are used to maintain both stable and highly efficient operation of the drive system. The adopted neural network can be viewed as a method for nonlinear adaptive system identification, relying on pattern recognition of stability limits and maximum obtainable efficiency. Results from computer simulation show that a stable and highly efficient operation can be maintained for the drive system under study irrespective of load and supply variations. The obtained results are also found in correlation with previously reported experiments and observations.

Direct adaptive type-2 fuzzy neural network control for a generic hypersonic flight vehicle

A direct adaptive interval type-2 fuzzy neural network (IT2-FNN) controller is designed for the first time in hypersonic flight control. The generic hypersonic flight vehicle is a multi-input multi-output system whose longitudinal model is high-order, highly nonlinear, tight coupling and most of all includes big uncertainties. Interval type-2 fuzzy sets with Gaussian membership functions are used in antecedent and consequent parts of fuzzy rules. The IT2-FNN directly outputs elevator deflection and throttle setting which make the GHFV track the altitude command signal and meanwhile maintain its velocity. The parameter adaptive law of IT2-FNN is derived using backpropagation method. The deviation of the control signal from the nominal dynamic inversion control signal is used as the reference output signal of IT2-FNN. The tracking errors of velocity and altitude are used as inputs of IT2-FNN. Tracking differentiator is designed to form an arranged transition process (ATP) of the command signal as well as ATP's high-order derivatives. Nonlinear state observer is designed to get the approximations of velocity, altitude as well as their high-order derivatives. Simulation results validate the effectiveness and robustness of the proposed controller especially under big uncertainties.

Direct adaptive neural network controller for a class of nonlinear systems based on fuzzy estimator of the control error

A new approach of direct adaptive control of single input single output nonlinear systems in affine form using single-hidden layer neural network (NN) is introduced. In contrast to the algorithms in the literature, the weights adaptation laws are based on the control error and not on the tracking error or its filtered version. Since the control error is being expressed in terms of the NN controller, hence its weights updating laws are obtained via back-propagation concept. A fuzzy inference system (FIS) with heuristically defined rules is introduced to provide an estimate of this error based on the past history of the system behaviour. The stability of the closed loop is studied using Lyapunov theory. A fixed structure is then proposed for the FIS and the design parameters reduce to the parameters of the NN. The method is reproducible and does not require any pre-training of the network weights.

Direct adaptive robust NN control for a class of discrete-time nonlinear strict-feedback SISO systems

In this paper, a direct adaptive neural network control algorithm based on the backstepping technique is proposed for a class of uncertain nonlinear discrete-time systems in the strict-feedback form. The neural networks are utilized to approximate unknown functions, and a stable adaptive neural network controller is synthesized. The fact that all the signals in the closed-loop system are semi-globally uniformly ultimately bounded is proven and the tracking error can converge to a small neighborhood of zero by choosing the design parameters appropriately. Compared with the previous research for discrete-time systems, the proposed algorithm improves the robustness of the systems. A simulation example is employed to illustrate the effectiveness of the proposed algorithm.

Synchronization of uncertain chaotic systems based on adaptive type-2 fuzzy sliding mode control

A novel direct adaptive interval type-2 fuzzy neural network (FNN) controller in which linguistic fuzzy control rules can be directly incorporated into the controller is developed to synchronize chaotic systems with training data corrupted by noise or rule uncertainties involving external disturbances, in this paper. By incorporating direct adaptive interval type-2 FNN control scheme and sliding mode approach, two non-identical chaotic systems can be synchronized based on Lyapunov stability criterion. Moreover, the chattering phenomena of the control efforts can be reduced and the external disturbance on the synchronization error can be attenuated. The stability of the proposed overall adaptive control scheme will be guaranteed in the sense that all the states and signals are uniformly bounded. From the simulation example, to synchronize two non-identical Chua’s chaotic circuits, it has been shown that type-2 FNN controllers have the potential to overcome the limitations of tpe-1 FNN controllers when training data is corrupted by high levels of uncertainty.

Direct adaptive NN control for a class of discrete-time nonlinear strict-feedback systems

Based on the backstepping technique, a direct adaptive neural network control algorithm is proposed for a class of uncertain nonlinear discrete-time systems in the strict-feedback form. Neural networks are utilized to approximate unknown functions, and a stable adaptive neural backstepping controller is synthesized. It is proven that all the signals in the closed-loop system are semi-globally uniformly ultimately bounded (SGUUB) and the tracking error converges to a small neighborhood of zero by choosing the design parameters appropriately. Compared with the existing results for discrete-time systems, the proposed algorithm needs only less parameters to be adjusted online, therefore, it can reduce online computation burden. A simulation example is employed to illustrate the effectiveness of the proposed algorithm.

NEURAL ADAPTIVE CONTROL FOR VIBRATION SUPPRESSION IN COMPOSITE FIN-TIP OF AIRCRAFT

In this paper, we present a neural adaptive control scheme for active vibration suppression of a composite aircraft fin tip. The mathematical model of a composite aircraft fin tip is derived using the finite element approach. The finite element model is updated experimentally to reflect the natural frequencies and mode shapes very accurately. Piezo-electric actuators and sensors are placed at optimal locations such that the vibration suppression is a maximum. Model-reference direct adaptive neural network control scheme is proposed to force the vibration level within the minimum acceptable limit. In this scheme, Gaussian neural network with linear filters is used to approximate the inverse dynamics of the system and the parameters of the neural controller are estimated using Lyapunov based update law. In order to reduce the computational burden, which is critical for real-time applications, the number of hidden neurons is also estimated in the proposed scheme. The global asymptotic stability of the overall system is ensured using the principles of Lyapunov approach. Simulation studies are carried-out using sinusoidal force functions of varying frequency. Experimental results show that the proposed neural adaptive control scheme is capable of providing significant vibration suppression in the multiple bending modes of interest. The performance of the proposed scheme is better than the H(infinity) control scheme.

Direct Adaptive NN Control of MIMO Nonlinear Discrete-Time Systems using Discrete Nussbaum Gain

In this paper, direct adaptive neural network (NN) control is developed for a class of multi-input and multi-output (MIMO) nonlinear systems in discrete-time. To solve the difficulty of nonaffine appearance of control, implicit function theorem is exploited to assert the existence of an ideal desired feedback control (IDFC). Then, high-order-neural-network (HONN) is employed to approximate the IDFC. Under the assumption that the inverse control gain matrix has an either positive definite or negative definite symmetric part, the obstacle in NN weights tuning for the MIMO systems is transformed to as similar as unknown control direction problem for SISO system. Then, the difficulty in NN weights tuning is overcame by exploiting the discrete Nussbaum gain, which is combined with deadzone method to treat with external disturbance with unknown upper bound. All signals in the closed-loop system are guaranteed to be semi-globally-uniformly-ultimately-bounded (SGUUB). The effectiveness of the proposed control is demonstrated in the simulation.

Stable direct adaptive neural network controller with a fuzzy estimator of the control error for a class of perturbed nonlinear systems

A state feedback direct adaptive control algorithm for single input single output perturbed nonlinear systems in affine form using single hidden layer neural network is introduced. The weights adaptation laws are based on an estimated control error provided by a fuzzy inference system composed of heuristically determined rules. It provides a bounded estimate of the control error, which affects only the step size of the updating laws. It is shown that under mild conditions the state variables and the control input are bounded and the tracking error and its derivatives converge to a bounded compact set. The method does not require any preliminary off line training of the network weights. All states are supposed to be measurable. Two simulation studies are presented for testing the proposed algorithm.

Decentralized direct adaptive neural network control for a class of interconnected systems

The problem of direct adaptive neural network control for a class of large-scale systems with unknown function control gains and the high-order interconnections is studied in this paper. Based on the principle of sliding mode control and the approximation capability of multilayer neural networks, a design scheme of decentralized direct adaptive sliding mode controller is proposed. The plant dynamic uncertainty and modeling errors are adaptively compensated by adjusted the weights and sliding mode gains on-line for each subsystem using only local information. According to the Lyapunov method, the closed-loop adaptive control system is proven to be globally stable, with tracking errors converging to a neighborhood of zero. Simulation results demonstrate the effectiveness of the proposed approach.

Direct Adaptive Control for a Class of MIMO Nonlinear Systems Using Neural Networks

In this note, direct adaptive neural network (NN) control is studied for a class of multiple-input-multiple-output nonlinear systems based on input-output discrete-time model with unknown interconnections between subsystems. By finding an orthogonal matrix to tune the NN weights, the closed-loop system is proven to be semiglobally uniformly ultimately bounded. The control performance of the closed-loop system is guaranteed by suitably choosing the design parameters.

DIRECT MNN CONTROL OF A CLASS OF DISCRETE-TIME NON-AFFINE NONLINEAR SYSTEMS

In this paper, direct adaptive neural network control is presented for a class of discrete-time SISO non-affme nonlinear systems. Based on the input-output model, multi-layer neural networks are used to emulate the implicit desired feedback control. For the multi-layer neural network control, projection algorithms are used to guarantee the boundness of the neural network weights. The stability of the closed-loop system is proved by using Lyapunov theorem.

Direct adaptive NN control of a class of nonlinear systems

In this paper, direct adaptive neural-network (NN) control is presented for a class of affine nonlinear systems in the strict-feedback form with unknown nonlinearities. By utilizing a special property of the affine term, the developed scheme,avoids the controller singularity problem completely. All the signals in the closed loop are guaranteed to be semiglobally uniformly ultimately bounded and the output of the system is proven to converge to a small neighborhood of the desired trajectory. The control performance of the closed-loop system is guaranteed by suitably choosing the design parameters. Simulation results are presented to show the effectiveness of the approach.

A direct adaptive neural-network control for unknown nonlinear systems and its application

In this paper a direct adaptive neural-network control strategy for unknown nonlinear systems is presented. The system considered is described by an unknown NARMA model, and a feedforward neural network is used to learn the system. Taking the neural network as a neural model of the system, control signals are directly obtained by minimizing either the instant difference or the cumulative differences between a set point and the output of the neural model. Since the training algorithm guarantees that the output of the neural model approaches that of the actual system, it is shown that the control signals obtained can also make the real system output close to the set point. An application to a flow-rate control system is included to demonstrate the applicability of the proposed method and desired results are obtained.

Direct adaptive neural network control of robots

Neural network modelling of robots is introduced using the GL matrices and operator (Ge et al. 1994), and a new adaptive neural network controller for robots is presented. The controller is based on direct adaptive techniques, and there is no need for matrix inversion. Unlike many neural network controllers in the literature, inverse dynamical model evaluation is not required and no time-consuming training process is necessary, except for initializing the neural networks based on approximate parameters of the initial posture at time t = 0. It is shown that if gaussian radial basis function networks are used, uniformly stable adaptation is assured and asymptotic tracking is achieved.

Neural network modelling and control strategies for a pH process

The control of a pH process using neural networks is examined. The neural network as a universal approximator is used to good effect in this nonlinear problem, as is shown in the simulation results. In the modelling task, the dynamics of the process was carefully examined to determine a suitable structure for the net. In particular, a multilayer net consisting of two single hidden layers was constructed to reflect the Wiener model of the pH process. This led to much simpler training compared to similar modelling attempts by other researchers. For the control task, two schemes were simulated. In one approach, a net was used to deal with the static nonlinearity to achieve control over a wide working range. The dynamic controller used was the PID, with its parameters tuned on a relay auto-tuner. This control design was compared with the strong acid equivalent method. In the second approach, a direct model reference adaptive neural network control scheme was proposed. The training procedure uses the more efficient least squares algorithm developed by Loh and Fong.