Learning from adaptive neural output feedback control of robot manipulators

This paper presents the problems of accurate identification and learning control of ocean surface ship in uncertain dynamical environments. Thanks to the universal approximation capabilities, radial basis function neural networks (NNs) are employed to approximate the unknown ocean surface ship dynamics. A stable adaptive NN tracking controller is first designed using backstepping and Lyapunov synthesis. Partial persistent excitation (PE) condition of some internal signals in the closed-loop system is satisfied during tracking control to a recurrent reference trajectory. Under the PE condition, the proposed adaptive NN controller is shown to be capable of accurate identification/learning of the uncertain ship dynamics in the stable control process. Subsequently, a novel NN learning control method which effectively utilizes the learned knowledge without re-adapting to the unknown ship dynamics is proposed to achieve closed-loop stability and improved control performance. Simulation studies are performed to demonstrate the effectiveness of the proposed method.

Data-based adaptive neural network optimal output feedback control for nonlinear systems with actuator saturation

In this paper, adaptive neural network (NN) control is investigated for a class of multiinput and multioutput (MIMO) nonlinear systems with unknown bounded disturbances in discrete-time domain. The MIMO system under study consists of several subsystems with each subsystem in strict feedback form. The inputs of the MIMO system are in triangular form. First, through a coordinate transformation, the MIMO system is transformed into a sequential decrease cascade form (SDCF). Then, by using high-order neural networks (HONN) as emulators of the desired controls, an effective neural network control scheme with adaptation laws is developed. Through embedded backstepping, stability of the closed-loop system is proved based on Lyapunov synthesis. The output tracking errors are guaranteed to converge to a residue whose size is adjustable. Simulation results show the effectiveness of the proposed control scheme.

In this paper, a novel adaptive neural network (NN) control scheme is proposed for a class of nonlinear systems with unknown control direction. By introducing some differentiable functions and high-order Lyapunov functions, the obstacle caused by unknown control direction in NN control is successfully circumvented and all closed-loop signals are shown to be uniformly bounded up to infinite time. Meanwhile, by introducing an error transformation technique, it is rigorously proved that the argument of the unknown nonlinearities remains within a compact set which can be explicitly calculated a priori, making the NN approximation always valid. Moreover, with the aid of a bound estimation approach, we effectively compress the impact of approximation errors and external disturbances and steer the tracking error into a predefined small residual set. Simulation results illustrate the effectiveness of the proposed scheme.

Adaptive neural network based controller for robots

This article presents an adaptive-adaptive radial basis function (RBF) neural network (AANNRBF) control strategy for lower limb rehabilitation robot (LLRR), which to adapts the uncertainty of the physical parameters caused by different patients or the same patient's muscle tension changes in different training periods. The load disturbance changes and the uncertainty of the system physical parameters generated in the human-machine interaction are controlled by parameter adaptive control, which solves the problem that the neural net¬work approximation domain of the traditional purely adaptive RBF neural network (ANNRBF) control algorithm is easily a¬ffected by the change of the load. ADAMS (automatic dynamic analysis of mechanical system)-MATLAB co-simulation results show that the control method proposed can achieve accurate gait trajectory tracking training, and has good adaptability and robustness to system load fluctuations caused by changes in muscle tension during patient training.

This paper presents the implementation of adaptive fuzzy neural network controller (FNNC) for accurate speed control of a permanent magnet synchronous motor (PMSM). FNNC includes neural network controller (NC) and fuzzy logic controller (FC). It combines the capability of fuzzy reasoning in handling uncertain information and the capability of neural network in learning from processes. The initial weights and biases of the artificial neural network (ANN) are obtained by offline training method. Using the output of the fuzzy controller (FC), online training is carried out to update the weights and biases of the ANN. Several results of simulation are provided to demonstrate the effectiveness of the proposed FNNC under the occurrence of parameter variations and external disturbance.KeywordsFuzzy ControllerFuzzy Logic ControllerProportional IntegralReference SpeedFuzzy Logic RuleThese keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Because an electric scooter driven by permanent magnet synchronous motor (PMSM) servo system has the unknown nonlinearity and the time-varying characteristics, its accurate dynamic model is difficult to establish for the design of the linear controller in whole system. In order to conquer this difficulty and raise robustness, a novel adaptive recurrent Legendre neural network (NN) control system, which has fast convergence and provide high accuracy, is proposed to control for PMSM servo-drive electric scooter under external torque disturbance in this study. The novel adaptive recurrent Legendre NN control system consists of a recurrent Legendre NN control with adaptation law and a remunerated control with estimation law. In addition, the online parameter tuning methodology of the recurrent Legendre NN control and the estimation law of the remunerated control can be derived by using the Lyapunov stability theorem. Finally, comparative studies are demonstrated by experimental results in order to show the effectiveness of the proposed control scheme.

This paper mainly introduces the modeling based on Cosserat rod theory and focuses on the adaptive neural network controller design based on model. In dealing with the external interference with the environment and the unmodeled dynamics of the system, a neural network (NN) is introduced to compensate it, and using Backstepping method to design the adaptive controller, finally the stability of the closed-loop system and the convergence of the signal in the system is proved with Lyapunov function theory, ensuring the end of the manipulator can track the given signal. In addition, the simulation experiment of soft manipulator swing and constant angle tracking control are carried out, and the simulation shows the rationality of the proposed controller.

Three adaptive neural network control structures to regulate a biological wastewater treatment process are introduced: indirect, inverse model, and direct adaptive neural control. The objective is to keep the concentration of the recycled biomass proportional to the influent flow rate in the presence of periodically acting disturbances, process parameter variations, and measurement noise. This is achieved by the so-called Jordan Canonical Recurrent Trainable Neural Network, which is a completely parallel and parametric neural structure, permitting the use of the obtained parameters, during the learning phase, directly for control system design. Comparative simulation results confirmed the applicability of the proposed control schemes. © 2005 Wiley Periodicals, Inc. Int J Int Syst 20: 173–193, 2005.

In this paper, stable adaptive neural network (NN) control, a combination of weighted one-step-ahead control and adaptive NN is developed for a class of multi-input-multi-output (MIMO) nonaffine nonlinear discrete-time systems. The weighted one-step-ahead control is designed to stabilize the nominal linear system, while the adaptive NN compensator is introduced to deal with the nonlinearities. 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 unknown control direction problem for single-input-single-output (SISO) system. Discrete Nussbaum gain is introduced into the NN weights adaptation law to overcome the unknown control direction problem. It is proved that all signals of the closed-loop system are bounded, while the tracking error converges to a compact set. Simulation result illustrates the effectiveness of the proposed control.

Adaptive control using neural network processors is proposed for use in a highly distributed CIM environment. First, neural network concepts are used to represent and to model knowledge in robotics and factory automation. Then, the model loaded into a neurocomputer serves as the distributed, adaptive, real-time controller in a CIM environment. The adaptive control problem is defined, and the neural network approach is presented. >

Magnetic levitation system is a typical nonlinear and instable system. Based on the complexity and inaccuracy of modelling, in this paper identified magnetic levitation system using the speciality that neural network(NN) can approach any nonlinear function. A Radial Basis Function neural network (RBFNN) controller is designed based on the neural network adaptive control principle. This paper proposes a control method which combine neural network adaptive control method and state feedback control method based on RBFNN. A simulation of the system is proposed, and the result shows that RBFNN could approach magnetic levitation system very well, neural network adaptive state feedback controller has a good effect on this nonlinear system; this control system has a preferable stability and control property.

ABSTRACTIn this study, we propose a novel adaptive control architecture that provides dramatically better transient response performance compared to conventional adaptive control methods. This is accomplished by the synergistic employment of a traditional adaptive neural network (ANN) controller and a long short‐term memory (LSTM) network. LSTM structures can take advantage of the dependencies in an input sequence, which can help predict uncertainty. We introduce a training approach through which the LSTM network learns to compensate for the deficiencies of the ANN controller. This improves the transient response of the system and allows the controller to quickly react to unexpected events. Through careful simulation studies, we demonstrate that this architecture improves the estimation accuracy on a diverse set of uncertainties. We also provide an analysis of the contributions of the ANN controller and the LSTM network, identifying their roles in compensating low‐ and high‐frequency error dynamics. This analysis provides insight into why and how the LSTM augmentation improves the system's transient response. The stability of the overall system is analyzed via a rigorous Lyapunov analysis.

Learning from adaptive neural network control of an underactuated rigid spacecraft