Adaptive neural dynamic surface control for servo systems with unknown dead-zone

This paper presents an adaptive neural tracking control approach for uncertain stochastic nonlinear time‐delay systems with input and output constraints. Firstly, the dynamic surface control (DSC) technique is incorporated into adaptive neural control framework to overcome the problem of ‘explosion of complexity’ in the control design. By employing a continuous differentiable asymmetric saturation model, the input constraint problem is solved. Secondly, the appropriate Lyapunov‐Krasovskii functional and the property of hyperbolic tangent functions are used to deal with the unknown time‐delay terms, RBF neural network is utilized to identify the unknown systems functions, and barrier Lyapunov functions (BLFs) are designed to avoid the violation of the output constraint. Finally, based on adaptive backstepping technique, an adaptive neural control method is proposed, and it decreases the number of learning parameters. Using Lyapunov stability theory, it is proved that the designed controller can ensure that all the signals in the closed‐loop system are 4‐Moment (or 2 Moment) semi‐globally uniformly ultimately bounded (SGUUB) and the tracking error converges to a small neighborhood of the origin. Two simulation examples are provided to further illustrate the effectiveness of the proposed approach.

A robust adaptive neural dynamic surface control (DSC) approach is presented for the longitudinal dynamics of a morphing aircraft in the presence of unknown dynamics and input constraints. For the altitude subsystem, neural systems are utilized to approximate the unknown nonlinear functions with smooth robust compensations to counteract the lumped approximation errors. By combining dynamic surface control and minimal learning parameter techniques, a robust adaptive neural control scheme is proposed and a simple adaptive algorithm is constructed. Meanwhile, an auxiliary system is incorporated into the control scheme to overcome the problem of input saturation. The highlight is that the proposed neural controller not only owns less updated neural parameters, but also has the ability of handling input constraints. It is proved that all the signals in the closed-loop system are bounded. Simulation results demonstrate the effectiveness of the proposed control scheme.

A novel adaptive neural network dynamic surface control is proposed for hypersonic vehicle. Based on the hypersonic vehicle model characteristics, the adaptive neural network dynamic surface control attitude controller and the neural networks velocity controller are designed, respectively. By combining Nussbaum gain function with decoupled backstepping, the problems of unknown control directions and control singularity from hypersonic vehicles model in strict-feedback form are simultaneously solved. Furthermore, the norm of the ideal weighting vector in neural network systems is considered as the estimation parameter, such that only one parameter is adjusted at each recursive step. Based on decoupled backstepping method and Lyapunov stability theorem, the semi-global stability of the flight control system is proved. Simulation results show that the new controller can guarantee the expected tracking performance.

In this paper, finite time adaptive neural network (NN) tracking control is investigated for a class of uncertain nonstrict feedback systems with unknown dead-zone and unmodeled dynamics as well as full state restrictions. Using the linearized representation of dead-zone, finite-time adaptive control is presented by the aid of dynamic surface control (DSC) technique and the property of Gaussian function. By introducing logarithmic function as invertible nonlinear mapping, the full state restriction problem is solved. The dynamic signal generated by the low-pass filter is used to handle unmodeled dynamics. Through finite-time stability theory and introducing the bounded closed set in the proof, all the signals in the closed-loop system are proved to be semi-globally practical finite time stable (SGPFS). The restriction conditions are not triggered for all the states. Finally, two numerical examples are used to illustrate the feasiability of the finite time adaptive control strategy.

This paper presents a neural adaptive controller for a class of nonlinear system in the presence of input saturation and arbitrary unknown information by integrating the design framework of neural networks (NNs) with the dynamic surface control (DSC) and backstepping technique. NNs are directly used to deal with unknown nonlinear terms. By introducing a well-defined smooth function and a Nussbaum function, a novel robust adaptive control scheme is developed to guarantee the states of system to be semi-globally uniformly ultimately bounded (SGUUB). Owing to the introduction of DSC, the problem of ‘explosion of complexity’ inherent in the backstepping design is effectively eliminated. Simulation results demonstrate the effectiveness and simplicity of the proposed method.

This paper focuses on the problem of adaptive output-constrained neural tracking control for uncertain nonstrict-feedback systems in the presence of unknown symmetric output dead zone and input saturation. A Nussbaum-type function-based dead-zone model is introduced such that the dynamic surface control approach can be used for controller design. The variable separation technique is employed to decompose the unknown function of entire states in each subsystem into a series of smooth functions. Radial basis function neural networks are utilized to approximate the unknown black-box functions derived from Young's inequality. With the help of auxiliary first-order filters, the dimensions of neural network input are reduced in each recursive design. A main advantage of the proposed method is that for an -order nonlinear system, only one adaptation parameter needs to be tuned online. It is rigorously shown that the proposed output-constrained controller guarantees that all the closed-loop signals are semiglobal uniformly ultimately bounded and the tracking error never violates the output constraint.

In this paper, we propose an adaptive neural dynamic surface control (DSC) approach with <TEX>$H_{\infty}$</TEX> tracking performance for full dynamics of nonlinear flight systems. It is assumed that the model uncertainties such as structured and unstrutured uncertainties, and external disturbances influence the nonlinear aircraft model. In our control system, self recurrent wavelet neural networks (SRWNNs) are used to compensate the model uncertainties of nonlinear flight systems, and an adaptive DSC technique is extended for the disturbance attenuation of nonlinear flight systems. All weights of SRWNNs are trained on-line by the smooth projection algorithm. From Lyapunov stability theorem, it is shown that <TEX>$H_{\infty}$</TEX> performance nom external disturbances can be obtained. Finally, we present the simulation results for a nonlinear six-degree-of-freedom F-16 aircraft model to confirm the effectiveness of the proposed control system.

An improved adaptive neural dynamic surface control for pure-feedback systems with full state constraints and disturbance

This paper proposes a new adaptive neural network finite‐time dynamic surface control scheme for inaccurate non‐linear systems subjected to unknown dead zones. The ‘explosion of differentiation’ is eliminated by the first‐order filter in backstepping design. The parameter normalization scheme updates the coefficients of activation functions in the radial basis function neural networks. The dead zone inverse method estimates the dead zone parameters. It is proved that the proposed controller achieves the faster tracking performance and the boundedness of all signals in finite time. The contribution of this paper is that the presented controller not only has the advantages of transient performance and program execution time in comparison with traditional backstepping methods, but also its computational cost is lower than command filtered methods. Simulation experiment results are included to illustrate the effectiveness of the proposed scheme.

In this work, the tracking control problem for a class of nonlinear strict-feedback systems with input nonlinearity is addressed. In response to the influence of input nonlinearity, an auxiliary control system is constructed to compensate for it. To process unknown nonlinear dynamics, radial basis function neural networks (RBFNNs) are introduced to approximate them, and some adaptive updating control laws are designed to estimate unknown parameters. Furthermore, during the dynamic surface control (DSC) design process, first-order low-pass filters are introduced to solve the complexity explosion problems caused by repeated differentiation. After that, an NN-based adaptive dynamic surface tracking controller is proposed to achieve the tracking control. By applying the proposed controller, it can be guaranteed that not only the output of the system can track the desired trajectory, but also that the tracking error can converge to a small neighborhood of zero, while all signals of the closed-loop system are bounded. Finally, the effectiveness of the proposed controller is verified through two examples.

In this paper, a longitudinal model of hypersonic vehicle with variable geometry inlet is established. Because of the strict requirements for the angle of attack of the scramjet during the flight of the aircraft, the uncertainty introduced by the parameter fitting, the rotating lip cover in the longitudinal model, and the uncertain external interference of the aircraft. The dynamic surface control technology is used to design the angle of attack autopilot of the aircraft and the Radial basis function (RBF) neural network is used to realize the adaptive approximation of the uncertain part of the model, to suppress the interference and accurately track the instructions. Finally, the simulation results show that the method can effectively control the angle of attack of hypersonic vehicle with variable geometry inlet, meet the performance requirements and verify the correctness of the method.

Pneumatic servo system is widely applied in many industries, which has advantages comparing with electromechanical and hydraulic system because of its fast response, high-performance quality and low-cost. However, the servo control methods for pneumatic system still have some inevitable drawbacks and problems remaining to be researched. In this paper, a position feedback dynamic surface control is designed which is based on our pneumatic actuator model. More importantly, in order to overcome model uncertainties, noise interference and external force disturbance, an adaptive neural network dynamic surface controller is proposed to overcome the negative effects. Besides, the stability of the pneumatic system is substantiated by Lyapunov stability theorem. Finally, the results of simulation experiment also prove that the adaptive neural network dynamic surface controller has more advantages than the traditional controllers in pneumatic position servo control.

This paper presents a neural adaptive finite-time dynamic surface control for the permanent magnet synchronous motor system with time delays and asymmetric time-varying output constraint. The core challenge is how to address the time delays and asymmetric output constraint when designing a finite-time control scheme. Given this, a proper Lyapunov–Krasovskii functional is introduced to address time delays, and a nonlinear transformation function is considered to convert the output-constrained problem into an unconstrained one. Then, a neural adaptive finite-time dynamic surface control approach is devised in the finite-time backstepping framework, which applies neural networks to estimate the unknown nonlinear functions and introduces first-order filters to solve the “explosion of complexity” problems. Furthermore, it is demonstrated that all the signals of the resulting system are finite-time stable and the tracking error converges to a neighborhood of origin in finite time without violating the output constraint. Finally, the simulation results show that the integration of squared error results, the integral of time and absolute error results as well as the integration of absolute value error results of the proposed scheme is smaller than the tested scheme by 0.3458 , 22.2977 , and 2.2513 , respectively, when the time delays are considered. It further elucidates the availability and superiority of the developed method.

Artificial intelligence and robots have had a profound impact on the healthcare sector. In this paper, an adaptive neural control scheme of a prosthetic thigh simulation robot (PTSR) of gait simulation and evaluation system (GSE) is presented for hip disarticulation prostheses (HDPs) testing. To achieve the L<inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">∞</inf> performance of system tracking error, a simple error modification term in traditional backstepping (BS) design procedure via adaptive neural networks (NNs) approach is employed. Then by using the initialization technique (IT) and error modification term, the initial values of the compact sets used in adaptive NNs control scheme can be reduced by adjusting design parameters, which means that the stability and the tracking performance of the closed loop system can be improved greatly. Furthermore, this approach addresses and resolves the issues of disturbance caused by the tested HDPs and the constraints on PTSR in the stability analysis of previous studies. Additionally, the design procedure is simplified and the computational burden is reduced through the utilization of dynamic surface control technique (DSC) and minimal learning algorithm (MLP). The simulation results demonstrate the effectiveness of the proposed approach.

Hysteresis is a complex nonlinear effect in smart materials-based actuators, which degrades the positioning performance of the actuator, especially when the hysteresis shows asymmetric characteristics. In order to mitigate the asymmetric hysteresis effect, an adaptive neural digital dynamic surface control (DSC) scheme with the implicit inverse compensator is developed in this article. The implicit inverse compensator for the purpose of compensating for the hysteresis effect is applied to find the compensation signal by searching the optimal control laws from the hysteresis output, which avoids the construction of the inverse hysteresis model. The adaptive neural digital controller is achieved by using a discrete-time neural network controller to realize the discretization of time and quantizing the control signal to realize the discretization of the amplitude. The adaptive neural digital controller ensures the semiglobally uniformly ultimately bounded (SUUB) of all signals in the closed-loop control system. The effectiveness of the proposed approach is validated via the magnetostrictive-actuated system.