Adaptive recurrent neural network control using a structure adaptation algorithm

This paper proposes an adaptive recurrent neural network control (ARNNC) system with structure adaptation algorithm for the uncertain nonlinear systems. The developed ARNNC system is composed of a neural controller and a robust controller. The neural controller which uses a self-structuring recurrent neural network (SRNN) is the principal controller, and the robust controller is designed to achieve L ² tracking performance with desired attenuation level. The SRNN approximator is used to online estimate an ideal tracking controller with the online structuring and parameter learning algorithms. The structure learning possesses the ability of both adding and pruning hidden neurons, and the parameter learning adjusts the interconnection weights of neural network to achieve favorable approximation performance. And, by the L ² control design technique, the worst effect of approximation error on the tracking error can be attenuated to be less or equal to a specified level. Finally, the proposed ARNNC system with structure adaptation algorithm is applied to control two nonlinear dynamic systems. Simulation results prove that the proposed ARNNC system with structure adaptation algorithm can achieve favorable tracking performance even unknown the control system dynamics function.     

Adaptive dynamic CMAC neural control of nonlinear chaotic systems with L2 tracking performance

The advantage of using cerebellar model articulation control (CMAC) network has been well documented in many applications. However, the structure of a CMAC network which will influence the learning performance is difficult to select. This paper proposes a dynamic structure CMAC network (DSCN) which the network structure can grow or prune systematically and their parameters can be adjusted automatically. Then, an adaptive dynamic CMAC neural control (ADCNC) system which is composed of a computation controller and a robust compensator is proposed via second-order sliding-mode approach. The computation controller containing a DSCN identifier is the principal controller and the robust compensator is designed to achieve L₂ tracking performance with a desired attenuation level. Moreover, a proportional–integral (PI)-type adaptation learning algorithm is derived to speed up the convergence of the tracking error in the sense of Lyapunov function and Barbalat’s lemma, thus the system stability can be guaranteed. Finally, the proposed ADCNC system is applied to control a chaotic system. The simulation results are demonstrated that the proposed ADCNC scheme can achieve a favorable control performance even under the variations of system parameters and initial point.     

Intelligent position tracking control for LCM drive using stable online self-constructing recurrent neural network controller with bound architecture

In this paper, an intelligent position tracking control (IPTC) is developed for a linear ceramic motor (LCM) drive system. The IPTC system is comprised of a neural controller and a robust controller. The neural controller utilizes a self-constructing recurrent neural network (SCRNN) to mimic an ideal computation controller, and the robust controller is designed to achieve L₂ tracking performance with a desired attenuation level. If the approximation performance of SCRNN is insufficient, SCRNN can create new hidden neurons to increase the learning ability. If the hidden neuron of SCRNN is insignificant, it should be removed to reduce the computation load; otherwise, if the hidden neuron of SCRNN is significant, it should be retained. Moreover, the adaptive laws of controller parameters are derived in the sense of Lyapunov, so system stability can be guaranteed. Finally, the experimental results of the LCM drive system show a perfect tracking response can be achieved using the self-constructing mechanism and the on-line learning algorithm.     

Design of intelligent power controller for DC–DC converters using CMAC neural network

DC–DC converters are the devices which can convert a certain electrical voltage to another level of electrical voltage. They are very popularly used because of the high efficiency and small size. This paper proposes an intelligent power controller for the DC–DC converters via cerebella model articulation controller (CMAC) neural network approach. The proposed intelligent power controller is composed of a CMAC neural controller and a robust controller. The CMAC neural controller uses a CMAC neural network to online mimic an ideal controller, and the robust controller is designed to achieve L ₂ tracking performance with desired attenuation level. Finally, a comparison among a PI control, adaptive neural control and the proposed intelligent power control is made. The experimental results are provided to demonstrate the proposed intelligent power controller can cope with the input voltage and load resistance variations to ensure the stability while providing fast transient response and simple computation.     

Robust adaptive self-structuring fuzzy control design for nonaffine,nonlinear systems

In this article, a robust adaptive self-structuring fuzzy control (RASFC) scheme for the uncertain or ill-defined nonlinear, nonaffine systems is proposed. The RASFC scheme is composed of a robust adaptive controller and a self-structuring fuzzy controller. In the self-structuring fuzzy controller design, a novel self-structuring fuzzy system (SFS) is used to approximate the unknown plant nonlinearity, and the SFS can automatically grow and prune fuzzy rules to realise a compact fuzzy rule base. The robust adaptive controller is designed to achieve an L ₂ tracking performance to stabilise the closed-loop system. This L ₂ tracking performance can provide a clear expression of tracking error in terms of the sum of lumped uncertainty and external disturbance, which has not been shown in previous works. Finally, five examples are presented to show that the proposed RASFC scheme can achieve favourable tracking performance, yet heavy computational burden is relieved.     

Intelligent complementary sliding-mode control with dead-zone parameter modification

This paper proposes an intelligent complementary sliding-mode control (ICSMC) system which is composed of a computed controller and a robust controller. The computed controller includes a neural dynamics estimator and the robust compensator is designed to prove a finite L₂-gain property. The neural dynamics estimator uses a recurrent neural fuzzy inference network (RNFIN) to approximate the unknown system term in the sense of the Lyapunov function. In traditional neural network learning process, an over-trained neural network would force the parameters to drift and the system may become unstable eventually. To resolve this problem, a dead-zone parameter modification is proposed for the parameter tuning process to stop when tracking performance index is smaller than performance threshold. To investigate the capabilities of the proposed ICSMC approach, the ICSMC system is applied to a one-link robotic manipulator and a DC motor driver. The simulation and experimental results show that favorable control performance can be achieved in the sense of the L₂-gain robust control approach by the proposed ICSMC scheme.     

Synchronization and tracking control for multi‐motor driving servo systems with backlash and friction

This paper presents a novel switching controller incorporated with backlash and friction compensations, which is utilized to achieve speed synchronization among multi‐motor and load position tracking. The proposed controller consists of two parts: synchronization and tracking control in contact mode and robust control in backlash mode, where a function characterizing whether backlash occurs is used for switching between two modes. Using the proposed switching controller, several control objectives are achieved. Firstly, the coupling problem of speed synchronization and load tracking in contact mode is addressed by introducing a switching plane. Secondly, based on the switching plane, an improved prescribed performance function is introduced to attain load tracking with prescribed performances, and L_∞ performance of speed synchronization is guaranteed by initialization method, maintaining the transient performance of synchronization behavior. Thirdly, the lumped uncertain nonlinearity including friction and other uncertain functions is compensated by Chebyshev neural network in contact mode. Furthermore, a robust control is adopted in backlash mode to make system traverse backlash at an exponential rate and simultaneously eliminate low‐speed crawling phenomenon of LuGre friction. Finally, comparative simulations on four‐motor driving servo system are provided to verify the effectiveness and reliability. Copyright © 2015 John Wiley & Sons, Ltd.     

Robust L1 output tracking control for uncertain networked control systems described by T-S fuzzy model with distributed delays

This paper concentrates on investigating the robust L₁ output tracking control problem for the networked control systems described by Takagi–Sugeno fuzzy model with distributed delays and uncertainties. First, according to the parallel distributed compensation and Lyapunov theory, a fuzzy delay-dependent and basis-dependent Lyapunov–Krasovskii function that contributes to reducing the conservatism is constructed. Second, the L₁ performance criterion guaranteeing the asymptotic stability of the corresponding tracking control system and satisfying the prescribed tracking performance is derived. Furthermore, the output tracking control problem is converted into a convex optimisation problem. Finally, the results from simulation certify the effectiveness of the designed controller.     

考虑输出约束的机械臂自适应神经网络鲁棒控制

在工业机械臂系统的跟踪控制过程中,由于其结构和工作环境复杂,导致难以建立精确的系统模型,针对此问题提出了基于多层前馈神经网络的自适应鲁棒控制器.通过神经网络在线估计机械臂系统动力学模型,并在控制器中进行补偿,同时设计了一个在线更新的鲁棒项克服神经网络的重构误差;考虑机械臂实际系统的输出约束,采用障碍李雅普诺夫函数设计控制律并证明系统的稳定性从而使系统满足约束条件.仿真实验结果表明:在约束条件下所提出的控制器能够实现系统的一致最终有界稳定,且跟踪性能良好,并具有很好的抗干扰和自适应能力.     

<Emphasis Type="Italic">H</Emphasis><Subscript>∞</Subscript> Control Design Using Dynamic Neural Networks

In this paper, a new approach is investigated for adaptive dynamic neural network-based H _∞ control, which is designed for a class of non-linear systems with unknown uncertainties. Currently, non-linear systems with unknown uncertainties are commonly used to efficiently and accurately express the real practical control process. Therefore, it is of critical importance but a great challenge and still at its early age to design a stable and robust controller for such a process. In the proposed research, dynamic neural networks were constructed to precisely approximate the non-linear system with unknown uncertainties first, a non-linear state feedback H _∞ control law was designed next, then an adaptive weighting adjustment mechanism for dynamic neural networks was developed to achieve H _∞ regulation performance, and last a recurrent neural network was employed as a neuro-solver to efficiently and numerically solve the standard LMI problem so as to obtain the appropriate control gains. Finally, case studies further verify the feasibility and efficiency of the proposed research.     

Inverse optimal sliding mode control of spacecraft with coupled translation and attitude dynamics

This paper proposes two robust inverse optimal control schemes for spacecraft with coupled translation and attitude dynamics in the presence of external disturbances. For the first controller, an inverse optimal control law is designed based on Sontag-type formula and the control Lyapunov function. Then a robust inverse optimal position and attitude controller is designed by using a new second-order integral sliding mode control method to combine a sliding mode control with the derived inverse optimal control. The global asymptotic stability of the proposed control law is proved by using the second method of Lyapunov. For the other control law, a nonlinear H_∞ inverse optimal controller for spacecraft position and attitude tracking motion is developed to achieve the design conditions of controller gains that the control law becomes suboptimal H_∞ state feedback control. The ultimate boundedness of system state is proved by using the Lyapunov stability theory. Both developed robust inverse optimal controllers can minimise a performance index and ensure the stability of the closed-loop system and external disturbance attenuation. An example of position and attitude tracking manoeuvres is presented and simulation results are included to show the performance of the proposed controllers.     

Neural-network-based robust adaptive control for a class of nonlinear systems

In this study, a robust adaptive control (RAC) system is developed for a class of nonlinear systems. The RAC system is comprised of a computation controller and a robust compensator. The computation controller containing a radial basis function (RBF) neural network is the principal controller, and the robust compensator can provide the smooth and chattering-free stability compensation. The RBF neural network is used to approximate the system dynamics, and the adaptive laws are derived to on-line tune the parameters of the neural network so as to achieve favorable estimation performance. From the Lyapunov stability analysis, it is shown that all signals in the closed-loop RBAC system are uniformly ultimately bounded. To investigate the effectiveness of the RAC system, the design methodology is applied to control two nonlinear systems: a wing rock motion system and a Chua’s chaotic circuit system. Simulation results demonstrate that the proposed RAC system can achieve favorable tracking performance with unknown of the system dynamics.     

Eso‐Based Adaptive Robust Control of Dual Motor Driving Servo System

Based on extended state observer (ESO), we propose an adaptive robust control (ARC) for a dual motor driving servo system, in which there exist nonlinearities affecting control performance. To apply ESO and estimate the lumped uncertainty online, backlash and friction are analyzed and the nonlinear model of the plant is derived. We achieve several control objectives. First, the bias torque is considered in order to eliminate the effect of backlash. Second, the speed feedback is used to maintain the speed synchronization of motors. Then, to achieve feedforward control, finite‐time ESO is designed to estimate the unknown nonlinearities online. Furthermore, the ESO‐based adaptive robust controller is designed to guarantee L_∞ of tracking error by an initialization method, maintaining the transient performance of tracking behavior. Finally, extensive experimental results on a practical test rig validate the effectiveness of our proposed method.     

Robust Recurrent Neural Network Control of Biped Robot

In this paper, a recurrent neural network (RNN) control scheme is proposed for a biped robot trajectory tracking system. An adaptive online training algorithm is optimized to improve the transient response of the network via so-called conic sector theorem. Furthermore, L ₂-stability of weight estimation error of RNN is guaranteed such that the robustness of the controller is ensured in the presence of uncertainties. In consideration of practical applications, the algorithm is developed in the discrete-time domain. Simulations for a seven-link robot model are presented to justify the advantage of the proposed approach. We give comparisons between the standard PD control and the proposed RNN compensation method.     

Adaptive recurrent cerebellar model articulation controller for linear ultrasonic motor with optimal learning rates

In this study, an adaptive recurrent cerebellar model articulation controller (ARCMAC) is investigated for the motion control of linear ultrasonic motor (LUSM). The proposed ARCMAC has superior capability to the conventional cerebellar model articulation controller in efficient learning mechanism and dynamic response. The dynamic gradient descent method is adopted to online adjust the ARCMAC parameters. Moreover, the analytical method based on a Lyapunov function is proposed to determine the learning-rates of ARCMAC so that the stability of the system can be guaranteed. Furthermore, the variable optimal learning-rates are derived to achieve the fastest convergence of tracking error. Finally, the effectiveness of the proposed control system is verified by the experiments of LUSM motion control. Experimental results show that high-precision tracking response can be achieved by using the proposed ARCMAC.     

基于强化学习神经网络的车速跟踪控制

提出一种用于汽车排放试验中驾驶机器人对车速跟踪控制的新方法.该控制方法基于神经网络并结合强化学习的自适应能力,通过神经网络的在线学习对车速进行跟踪控制.利用试验汽车所获得的数据,首先开发出用于车速控制的神经网络模型.然后基于强化学习神经网络结构设计神经网络控制器以取得车速跟踪的自适应控制.在仿真研究中,使用神经网络车速控制模型替代实际汽车来训练初始控制器,并用开发与训练好的自学习神经网络控制器用于汽车车速跟踪控制.结果表明,所开发的神经网络控制器具有良好的车速跟踪性能,控制效果明显.     

Adaptive H2/H∞ tracking control for a class of uncertain robotic systems

This paper addresses the problem of designing mixed H₂/H_∞ tracking control for a large class of uncertain robotic systems. Nonlinear H_∞ control theory, H₂ control theory and intelligent adaptive control algorithm are combined to construct a hybrid adaptive/robust H₂/H_∞ tracking control scheme. One adaptive neural network system is constructed to approximate the behaviour of uncertain robot dynamics, and the other adaptive control algorithm is designed to estimate the behaviour of the modelled disturbance. Moreover, a robust H_∞ control algorithm is designed to attenuate the effects of the unmodelled disturbance. Only a set of algebraic matrix Riccati-like equations is required to implement the proposed mixed H₂/H_∞ tracking controller, and so an explicit and closed-form solution is obtained. Consequently, the mixed H₂/H_∞ adaptive/robust tracking controller developed here can be analytically computed and easily implemented. Finally, simulations are presented to illustrate the effectiveness of the proposed control algorithm.     

Asynchronous H∞ Dynamic Output Feedback Control for Markovian Jump Neural Networks with Time-varying Delays

In this paper, the problem of asynchronous robust H_∞ dynamic output feedback control for Markovian jump neural networks with norm-bounded parameter uncertainties and mode-dependent time-varying delays is investigated. The improved delay-dependent stochastic stability conditions and bounded real lemma are obtained by introducing the relaxation variables, which reduces the conservatism caused by boundary technology and model transformation. An improved Lyapunov-Krasovskii functional is constructed using linear matrix inequalities. On this basis, the solution of robust H_∞ dynamic output feedback problem and sufficient conditions for solving the problem of asynchronous dynamic output feedback controller are given respectively. Asynchronous dynamic output feedback controller is constructed to ensure that the closed-loop mode-dependent time-varying delays Markovian jump neural networks achieve different convergence speeds. The given H_∞ performance index is satisfied for the delays not bigger than a given upper bound. Numerical examples are employed to show the effectiveness and correctness of the method presented in this paper.

     

Sliding mode control of drum water level in an industrial boiler unit with time varying parameters: A comparison with H∞-robust control approach

In steam power-plants, to prevent over-heating of drum components or flooding of steam lines, perfect control of drum water level is of great importance. But during the operation, disturbances affecting water level, model uncertainties and parameter mismatch due to variant operating conditions lead to the variation of model parameters. In this paper, under transient conditions and in the presence of model uncertainties, two control strategies are implemented to achieve desired tracking of drum water level: robust sliding mode and H_∞ control. Two transfer functions between drum water level (output variable); feed-water and steam mass rates (input variables) are considered. For the dynamic system with time varying characteristic and parametric uncertainties, a sliding mode controller is developed and an optimal H_∞ controller is designed based on μ-synthesis with DK-iteration algorithm. For different desired commands of drum water level (including a sequence of steps and ramps-steps); it is observed that both control strategies guarantee robust stability and performance of the system without actuators saturation (control signals are bounded). However, using the sliding mode controller leads to the more smooth and rapid time responses of drum water level with less oscillatory behaviour of control efforts (and consequently less energy consumption). In addition, for tracking objectives in short command times, sliding mode controller performs more appropriately.     

Robust H ∞ and adaptive tracking control against actuator faults with a linearised aircraft application

This article studies the problem of designing adaptive fault-tolerant H _∞ tracking controllers for a class of aircraft flight systems against general actuator faults and bounded perturbations. A robust adaptive state-feedback controller is constructed by a stabilising controller gain and an adaptive control gain function. Using mode-dependent Lyapunov functions, linear matrix inequality-based conditions are developed to find the controller gain such that disturbance attenuation performance is optimised. Adaptive control schemes are proposed to estimate the unknown controller parameters on-line for unparametrisable stuck faults and perturbation compensations. Based on Lyapunov stability theory, it is shown that the resulting closed-loop systems can guarantee asymptotic tracking with H _∞ performances in the presence of faults on actuators and perturbations. An application to a decoupled linearised dynamic aircraft system and its simulation results are given.