Robust Adaptive Learning Control Research Articles

Robust adaptive learning control using spiking-based self-organizing emotional neural network for a class of nonlinear systems with uncertainties

For second-order general nonlinear systems with uncertainties, a control scheme combining fractional-order fast terminal sliding mode control (FOFTSMC) and self-organizing emotional neural network (SOENN) is proposed and designed. Firstly, a novel emotional neural network which can approximate the uncertainties in nonlinear systems is constructed and introduced. Meanwhile, in order to optimize the network structure and reduce the computing burden, a novel spiking-based self-organizing mechanism is added. Then the FOFTSMC is designed for second-order general nonlinear systems, and the stability and finite time convergence is proved by Lyapunov theory. Besides, the FOFTSMC and SOENN are combined to form the final control scheme, and adaptive laws of the parameters are also designed. Finally, inverted pendulum and active power filter (APF) are selected as the research objects to carry out a series of simulations and experiments to validate and highlight the effectiveness and superiority of the proposed control scheme.

Robust Adaptive Learning Control of Space Robot for Target Capturing Using Neural Network.

This article investigates the robust adaptive learning control for space robots with target capturing. Based on the momentum conservation theory, the impact dynamics is constructed to derive the relationship of generalized velocity in the pre-impact and post-impact phase. Considering the nonlinear dynamics with contact impact, the robust control using nonsingular terminal sliding mode (NTSM) and fast NTSM is designed to achieve the fast realization of the desired states. Furthermore, for the unknown dynamics of the combination system after capturing a target, the adaptive learning control is developed based on neural network and disturbance observer. Through the serial-parallel estimation model, the prediction error is constructed for the update of adaptive law. The system signals involved in the Lyapunov function are proved to be bounded and the sliding mode surface converges in finite time. Simulation studies present the desired tracking and learning performance.

Emerging robust and data‐driven control methods for uncertain learning systems

Emerging robust and data‐driven control methods for uncertain learning systems

Robust Adaptive Learning-Based Path Tracking Control of Autonomous Vehicles Under Uncertain Driving Environments

This paper investigates the path tracking control problem of autonomous vehicles subject to modelling uncertainties and external disturbances. The problem is approached by employing a 2-degree of freedom vehicle model, which is reformulated into a newly defined parametric form with the system uncertainties being lumped into an unknown parametric vector. On top of the parametric system representation, a novel robust adaptive learning control (RALC) approach is then developed, which estimates the system uncertainties through iterative learning while treating the external disturbances by adopting a robust term. It is shown that the proposed approach is able to improve the lateral tracking performance gradually through learning from previous control experiences, despite only partial knowledge of the vehicle dynamics being available. It is noteworthy that a novel technique targeting at the non-square input distribution matrix is employed so as to deal with the under-actuation property of the vehicle dynamics, which extends the adaptive learning control theory from square systems to non-square systems. Moreover, the convergence properties of the RALC algorithm are analysed under the framework of Lyapunov-like theory by virtue of the composite energy function and the <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\lambda $ </tex-math></inline-formula> -norm. The effectiveness of the proposed control scheme is verified by representative simulation examples and comparisons with existing methods.

Robust learning‐based lateral tracking control for autonomous driving with input constraints

This work investigates the robust lateral tracking control problem of autonomous vehicles subject to unmodeled system uncertainties, external disturbances as well as input constraints that commonly exist in the vehicle dynamics. The tracking controller design under such uncertain environments is challenging due to the under-actuated characteristics of the vehicle dynamics. Targeting at this issue, a nonlinear vehicle model is firstly established and transformed into a novel parametric model to facilitate the controller design. A robust adaptive learning control (RALC) approach is then proposed based on the parametric vehicle model, where an input-dependent auxiliary system is employed to compensate the influence of the input constraints. The convergence of the tracking errors is rigorously analyzed based on the framework of composite energy function. The proposed RALC scheme is proven to be able to achieve an impressive path tracking performance under perturbed and constrained scenarios. Moreover, the proposed technique in tackling the under-actuated dynamics is novel that can be applied to deal with other generic non-square systems. The proposed controller is validated with case studies under various conditions.

GRU-Type LARC Strategy for Precision Motion Control With Accurate Tracking Error Prediction

To simultaneously achieve accurate tracking error prediction, rigorous motion accuracy, and certain robustness to parameter variations and unknown disturbances, this article proposes a data-based learning adaptive robust control (LARC) strategy based on gated recurrent unit (GRU) neural network. Firstly, parameter adaptive control and robust control are utilized to guarantee the robustness against parametric uncertainties and unknown disturbances. A GRU neural network is then constructed and capable of precisely predicting the tracking error after training with data collected from a linear-motor-driven stage. Essentially, the GRU network can be viewed as a data-based model, which captures the tracking error dynamic characteristics and provides a prediction even before implementing the real trajectory. Consequently, a reference modification and a feedforward compensation part can be formed, which is the significant part of the whole LARC control structure. Comparative experimental investigation not only validates the effectiveness of the tracking error prediction ability, but also demonstrates the practically satisfactory transient/steady-state tracking performance of the proposed control strategy.

Robust Intelligent Control of SISO Nonlinear Systems Using Switching Mechanism.

In this article, a robust adaptive learning control strategy for uncertain single-input-single-output systems in strict-feedback form and controllability canonical form (CCF) is studied. For the strict-feedback system, the dynamic surface control is introduced while for the controllability canonical system, sliding-mode control is further constructed. The finite-time design is introduced for fast convergence. Under the switching mechanism, the intelligent design and the robust technique work together to obtain robust tracking performance. Once the states run out of the domain of intelligent control, the robust item will pull the states back while inside the neural working domain, the composite learning is developed to achieve higher approximation precision by building the prediction error for the weight update. The closed-loop system stability is analyzed via the Lyapunov approach. Especially for the CCF, the finite-time convergence is achieved while the system signals are globally uniformly ultimately bounded. Simulation studies on the general nonlinear systems and the flight dynamics show that the new design scheme obtains better tracking performance with higher precision and stronger robustness.

Model-Data Driven Learning Adaptive Robust Control of Precision Mechatronic Motion Systems With Comparative Experiments

In order to meet the rigorous motion accuracy requirement and efficiently utilize the repetitive-task characteristics in modern precision industry, this paper concentrates on the comprehensive research of model-based data-driven learning adaptive robust control (LARC) strategy for precision mechatronic motion systems. The proposed LARC can achieve not only excellent transient/steady-state tracking performance but also adaptation ability and disturbance robustness. Specifically, the LARC strategy contains robust feedback term, adaptive model compensation term, and iterative learning term. Herein, the former two terms are designed based on the system dynamic model under parametric uncertainty and uncertain nonlinearity, and the data-driven iterative learning term is synthesized to generate optimal input to adjust the optimal reference. The whole controller design procedure and stability is presented, while the reason for the practically achievable performance of LARC is analyzed. Comparative experiments, among proportional—integral—differential, adaptive robust control, iterative learning control, and the proposed LARC, are conducted on a developed linear motor stage. The experimental results consistently validate that the proposed LARC scheme simultaneously achieves excellent transient/steady-state tracking performance, parametric adaptation ability, and disturbance robustness. The LARC strategy essentially provides an effective control technology with good potential in industrial applications.

Generalized GTCF Coordination Mechanism Based LARC Contouring Control of Industrial Motion Stages for Complex Contours

To achieve high-performance motion control accuracy for complex contouring tasks even under high-speed and large-curvature, a generalized global task coordinate frame (GGTCF)-based learning adaptive robust control (LARC) strategy is synthesized for the industrial biaxial mechatronic stage systems. Specifically, through the usually known desired trajectory information of each axis, GGTCF is firstly proposed and globally designed based on a synthesized equivalent shape function of the desired contour. Different from conventional GTCF just suitable for simple contours with explicit shape function, the proposed GGTCF can guarantee multi-axis coordination even under complex contouring tasks with high-speed and large-curvature characteristics. After transforming the system dynamics of an industrial biaxial mechatronic stage system into the proposed GGTCF, a LARC contouring controller is constructed for the strongly coupled nonlinearities in GGTCF to achieve great contouring motion performance. In LARC, adaptive compensation term and robust feedback term are, respectively, designed to deal with parametric variation and uncertain disturbances, whereas iterative learning term is designed to further suppress the unmodeled repetitive contouring errors. Comparative experiments under various complex contours are conducted on an industrial linear-motor-driven biaxial motion stage. The experimental results consistently demonstrate that the proposed GGTCF can successfully implement various complex contouring tasks. Furthermore, in comparison with the conventional cross-coupled control and adaptive robust control control algorithm, the proposed GGTCF-LARC simultaneously possesses strong coordination mechanism and excellent transient/steady-state contouring control performance, which actually provides a novel control framework with high-performance nature for contouring motion research field.

Neural Network Learning Adaptive Robust Control of an Industrial Linear Motor-Driven Stage With Disturbance Rejection Ability

In this paper, a neural network learning adaptive robust controller (NNLARC) is synthesized for an industrial linear motor stage to achieve good tracking performance and excellent disturbance rejection ability. The NNLARC scheme contains parametric adaption part, robust feedback part, and radial basis function (RBF) neural network (NN) part in a parallel structure. The adaptive part and the robust part are designed based on the system dynamics to meet the challenge of parametric variations and uncertain random disturbances. It must be noted that in actual industrial machining situations, precision motion equipment is always disturbed by unknown factors, which usually cannot be described by mathematical models but affect the tracking accuracy significantly. Therefore, the RBF NN part is employed to further approximate and compensate the complicated disturbances with high reconstructing accuracy and fast training rate. The stability of the proposed NNLARC strategy is analyzed and proved through the Lyapunov theorem. Comparative experiments under various external disturbances such as completely unknown disturbance added by polyfoam are conducted on an industrial linear motor stage. The experimental results consistently validate that the proposed NNLARC control strategy can excellently meet the challenge of complicated disturbance in practical applications. The proposed scheme also provides a guidance for control strategy synthesis with both good tracking performance and disturbance rejection.

Advanced GTCF-LARC Contouring Motion Controller Design for an Industrial X–Y Linear Motor Stage With Experimental Investigation

In this paper, a global task coordinate frame (GTCF)-based learning adaptive robust contouring controller is proposed for an industrial X–Y linear-motor-driven stage to achieve not only good parametric adaptation ability and disturbance robustness, but also excellent contouring accuracy even under high-speed large-curvature contouring tasks. Specifically, the contouring controller employs GTCF to guarantee the multiaxes motion coordination. After transforming the system dynamics of the X–Y linear-motor-driven stage into the GTCF, a learning adaptive robust control (LARC) scheme is developed to deal with the strongly coupled dynamics under parametric uncertainty and uncertain disturbances. During the LARC, adaptive model compensation term, robust feedback term, and iterative learning term are organically integrated in a serial structure. The controller design process with the stability analysis is presented, while the essence of the practical achievable performance is also introduced for the nature of the GTCF-LARC. Comparative experiments are carried out on an industrial linear-motor-driven stage with different cases. The results consistently verify that the proposed GTCF-LARC contouring controller can simultaneously meet the industrial requirements of excellent transient/steady-state contouring accuracy, parametric adaptation ability, external disturbance robustness, and large-curvature high-speed contouring tasks. The proposed GTCF-LARC scheme actually provides a practical high-performance-oriented contouring control framework, and could be extended to other multiaxes applications.

Robust Adaptive Learning Control for Spacecraft Autonomous Proximity Maneuver

The robust adaptive learning control for spacecraft autonomous proximity is investigated in this paper. The relative motion dynamics is firstly proposed and transformed into the state space representation. An adaptive learning controller that allows performing autonomous proximity maneuvers in the presence of uncertain orbital parameters is then developed. The unknown disturbances are considered, and a modified adaptive learning controller is therefore designed in the presence of uncertain parameters and unknown disturbances. The asymptotic stability of the proposed controllers for the closed-loop systems is proven based on the Lyapunov theory. Different numerical results are finally provided and compared to illustrate the performance of the proposed adaptive learning controllers.

Performance-Oriented Precision LARC Tracking Motion Control of a Magnetically Levitated Planar Motor With Comparative Experiments

Magnetically levitated planar motor is a new-generation motion device in modern precision industry, while its advanced motion controller design is still of main concern. In this paper, a learning adaptive robust control (LARC) motion controller is proposed for a magnetically levitated planar motor developed in our laboratory to achieve good tracking performance. The planar motor consists of a Halbach permanent magnetic array as the stator, and a levitated platen containing four groups of three-phase windings as the mover. Based on the Lorentz force law, the mover placed in the magnetic field is subjected to vertical force for levitation and horizonal force for planar motion through dynamics decoupling and current allocation. An LARC control scheme containing adaptive robust control (ARC) term and iterative learning control (ILC) term in a serial structure is then proposed for the magnetically levitated planar motor to achieve high-performance tracking even there exist parametric variations and uncertain disturbances. Comparative experiments between traditional lead, ARC, ILC, and the proposed LARC are carried out on the planar motor to track sinusoidal, point-to-point, and planar circular motions, respectively. The experimental results consistently validate that the proposed LARC control strategy outperforms other controllers much, and possesses not only good transient/steady-state tracking performance but also parametric adaptation ability and uncertain disturbance robustness. The proposed scheme actually provides a practically effective technique for motion control of magnetically levitated planar motors in industrial applications.

Robust adaptive learning control for nonlinear systems with extended matching unstructured uncertainties

SUMMARYThe exponential output tracking problem for a class of single‐input, single‐output uncertain nonlinear systems, including systems with extended matching unstructured uncertainties and without a well‐defined global relative degree, is addressed. Conditions on the uncertain system dynamics are derived, which allow us to design a state‐feedback learning control achieving semi‐global exponential output tracking of sufficiently smooth and periodic reference signals of known period, while guaranteeing ℒ︁2 and ℒ︁∞ transient performances during the learning phase. The application of the proposed learning approach to the position tracking control problem for uncertain permanent magnet step motors with non‐sinusoidal flux distribution and uncertain position‐dependent load torque allows us to provide a solution to a yet unsolved problem. Copyright © 2011 John Wiley &amp; Sons, Ltd.

Learning control for induction motor servo drives with uncertain rotor resistance

The tracking control problem for induction motor servo drives with mechanical and electrical uncertainties is addressed. Under the assumptions that the reference profile for the rotor angle is periodic of known period and the rotor flux modulus reference signal is persistently exciting, a robust adaptive learning control is designed, which is adaptive with respect to the uncertain rotor resistance and is able to ‘learn’ the periodic disturbance signal due to mechanical uncertainties by identifying the Fourier coefficients of its truncated approximation.

Robust output feedback learning control for induction motor servo drives

AbstractThis paper addresses the output feedback tracking control problem for induction motor servo drives with mechanical uncertainties: rotor angle, rotor speed and stator currents are assumed to be available for feedback. A robust adaptive learning control is designed under the assumption that the reference profile for the rotor angle is periodic with known period: it ‘learns’ the periodic disturbance signal by identifying the Fourier coefficients of any truncated approximation; ℒ︁2 and ℒ︁∞ transient performances are guaranteed in the ‘learning phase’. It is shown that, for any motor initial condition belonging to an arbitrary given compact set, by properly setting the control parameters: (i) the rotor position and flux modulus tracking errors exponentially converge to residual sets, which may be arbitrarily reduced by increasing the number of terms in the truncated Fourier series; (ii) when the unknown periodic disturbance can be represented by a finite Fourier series, the rotor position and flux modulus tracking errors exponentially converge to zero. As in field oriented‐control, the control algorithm generates references for the magnetizing flux component and for the torque component of the stator current leading to significant simplifications for current‐fed motors. Copyright © 2008 John Wiley &amp; Sons, Ltd.

Development of Robust Adaptive Learning Control for Nonlinear System

This paper gives an overview of the relationships between methods of loaming and adaptive control. It is the objective of this paper to develop adaptive learning control algorithms that combine the advantages of adaptive control with those of leaning control to the extent possible for the type of system model used. The robustness of this adaptive loaming control with respect to reinitialization errors and fluctuation of dynamics from disturbance is analyzed extensively. Simulation results have shown to verify the effectiveness of the proposed control algorithm.