Neural Control Algorithm Research Articles

Neuroadaptive fault-tolerant control of state constrained pure-feedback systems: A collective backstepping design

In this work, we present a neuroadaptive and fault-tolerant tracking control scheme for uncertain nonlinear pure-feedback systems in the presence of time-varying and asymmetric full state constraints and unanticipated actuation failures. Instead of using multi-step recursive backstepping design, we employ a one-step approach for control development. By introducing a nonlinear coordinate transformation, we convert the original nonlinear system with asymmetrical state constraints into a new augmented one free from state constraints, which allows for the complete obviation of the feasibility conditions in the strategy. Furthermore, by making use of the feature from skew symmetric matrix in the augmented system, we develop the neural adaptive control algorithms collectively without the need for repetitive design procedure, in which only one Lyapunov function and one step derivation are involved, leading to a design approach whose synthesis complexity does not increase with the order of the system.

Event-triggered robust neural control for unmanned sail-assisted vehicles subject to actuator failures

This note focus on the waypoints-based path-following control for the unmanned sail-assisted vehicles (USAV), aiming to release the constraints of the actuator failures and gain uncertainties. The proposed scheme is formulated as two components, i.e., the composite guidance part and the control part. By utilizing the sign self-selection algorithm, the composite Logic Virtual Ship (LVS) guidance law is developed in the scheme to program the real-time heading angle for the USAV. The main superiorities of this design are to ensure the USAV navigating efficiently and choose the corresponding sailing mode: upwind mode, downwind mode or crosswind mode. Furthermore, to improve the effectiveness of the closed-loop control system, an event-triggered robust neural control algorithm is targetly designed for the rudder actuator and the sail actuator by fusing the robust neural damping technique and the input event-triggered mechanism. In this algorithm, the unknown terms of the system are tackled requiring no information of the system model and the external disturbances. The transmission burden from the controller to the actuator is reduced. And the unknown actuator failures and the gain uncertainties are compensated through four adaptive updated parameters. Based on the Lyapunov analysis, sufficient effort has been made to guarantee that all the signals of the closed-loop control system are the semi-global uniform ultimate bounded (SGUUB). Finally, the simulated results demonstrate the validity of the proposed control strategy.

Design of an Adaptive Neural Predictive Nonlinear Controller for Nonholonomic Mobile Robot System Based on Posture Identifier in the Presence of Disturbance

This paper proposes an adaptive neural predictive nonlinear controller to guide a nonholonomic wheeled mobile robot during continuous and non-continuous gradients trajectory tracking. The structure of the controller consists of two models that describe the kinematics and dynamics of the mobile robot system and a feedforward neural controller. The models are modified Elman neural network and feedforward multi-layer perceptron respectively. The modified Elman neural network model is trained off-line and on-line stages to guarantee the outputs of the model accurately represent the actual outputs of the mobile robot system. The trained neural model acts as the position and orientation identifier. The feedforward neural controller is trained off-line and adaptive weights are adapted on-line to find the reference torques, which controls the steady-state outputs of the mobile robot system. The feedback neural controller is based on the posture neural identifier and quadratic performance index optimization algorithm to find the optimal torque action in the transient state for N-step-ahead prediction. General back propagation algorithm is used to learn the feedforward neural controller and the posture neural identifier. Simulation results show the effectiveness of the proposed adaptive neural predictive control algorithm; this is demonstrated by the minimised tracking error and the smoothness of the torque control signal obtained with bounded external disturbances.

Robust neural event-triggered control for dynamic positioning ships with actuator faults

This paper presents a novel robust neural event-triggered control algorithm to achieve the dynamic positioning operation of marine surface ships in the presence of actuator faults. In the algorithm, the model uncertainty and the “explosion of complexity” are addressed by fusion of the robust neural damping and dynamic surface control techniques. The gain related adaptive law is constructed to compensate the gain uncertainties and the unknown actuator faults, which improved the stability of the ship dynamic loop system. Furthermore, the event-triggered mechanism is introduced to reduce the communication load between the controller and actuator. For merits of the aforementioned design, the proposed algorithm is with the advantages of concise form and easy to be implemented in practical ocean engineering. Based on the Lyapunov theory, rigorous analysis is proved to guarantee the semi-global uniform ultimate boundedness (SGUUB) of the closed-loop system. Finally, numerical simulations are conducted to demonstrate the validity and feasibility of the proposed algorithm.

RBFNN-Based Adaptive Iterative Learning Fault-Tolerant Control for Subway Trains With Actuator Faults and Speed Constraint

In this article, a radial basis function neural network-based adaptive iterative learning fault-tolerant control (RBFNN-AILFTC) algorithm is developed for subway trains subject to the time-iteration-dependent actuator faults and speed constraint by using the multiple-point-mass dynamic model. First, the RBFNN is utilized to approximate the time-iteration-dependent unknown nonlinearity of the subway train system; then, the iterative learning mechanism is used to tackle the outstanding repetitive operational pattern of a subway train which runs from one station to the next strictly according to the operation timetable schedule every day within the finite time interval, and the adaptive mechanism is designed for dealing with the time and the iteration-varying factors of the subway train. Second, a barrier composite energy function technique is exploited to obtain the convergence property of the proposed RBFNN-AILFTC scheme for subway train system, which can guarantee that the tracking error is asymptotic convergence along the iteration axis, meanwhile keep the speed profile of the subway train system satisfies the constraint. Finally, a subway train simulation is shown to verify the effectiveness of the theoretical studies.

Adaptive neural tracking control for automotive engine idle speed regulation using extreme learning machine

The automotive engine idle speed control problem is a compromise among low engine speed for fuel saving, minimum emissions and disturbance rejection ability to prevent engine stall. However, idle speed regulation is very challenging due to the presence of high nonlinearity and aging-caused uncertainties in the engine dynamics. Therefore, the engine idle speed system is a typical uncertain nonlinear system. To address the problems of inherent nonlinearity and uncertainties in idle speed regulation, an extreme learning machine (ELM)-based adaptive neural control algorithm is proposed for tracking the target idle speed adaptively. The purpose of ELM is to rapidly deal with the uncertain nonlinear engine system. Since the original ELM is not designed for adaptive control, a new adaptation law is designed to update the weights of ELM in the sense of Lyapunov stability. Experiment is conducted to validate the performance of the proposed control method. Experimental result indicates that the ELM-based adaptive neural control outperforms the classical proportional–integral–derivative (PID), fuzzy-PID and back-propagation-neural-network-based controllers in terms of tracking performance under the variation of engine load.

A Comparative Study of Various Intelligent Optimization Algorithms Based on Path Planning and Neural Controller for Mobile Robot

In this paper, a cognitive system based on a nonlinear neural controller and intelligent algorithm that will guide an autonomous mobile robot during continuous path-tracking and navigate over solid obstacles with avoidance was proposed. The goal of the proposed structure is to plan and track the reference path equation for the autonomous mobile robot in the mining environment to avoid the obstacles and reach to the target position by using intelligent optimization algorithms. Particle Swarm Optimization (PSO) and Artificial Bee Colony (ABC) Algorithms are used to finding the solutions of the mobile robot navigation problems in the mine by searching the optimal paths and finding the reference path equation of the optimal path. As well as, PSO algorithm is used to find and tune on-line the neural control gains values of the nonlinear neural controller to obtain the best torques actions of the wheels for the mining autonomous mobile robot. Simulation results by matlab showed that the proposed cognitive system is more accurate in terms of planning reference path to avoid obstacles and online finding and tuning parameters of the controller which generated smoothness control action without saturation state for tracking the reference path equation as well as minimize the mobile robot tracking pose error to zero value.

Research on the Operation Control Strategy of a Low-Voltage Direct Current Microgrid Based on a Disturbance Observer and Neural Network Adaptive Control Algorithm

Low-voltage direct current (DC) microgrid based on distributed generation (DG), the problems of load mutation affecting the DC bus under island mode, and the security problems that may arise when the DC microgrid is switched from island mode to grid-connected mode are considered. Firstly, a DC bus control algorithm based on disturbance observer (DOB) was proposed to suppress the impact of system load mutation on DC bus in island mode. Then, in a grid-connected mode, a pre-synchronization control algorithm based on a neural network adaptive control was proposed, and the droop controller was improved to ensure better control accuracy. Through this pre-synchronization control, the microgrid inverters output voltage could quickly track the power grid’s voltage and achieve an accurate grid-connected operation. The effectiveness of the algorithms was verified by simulation.

Adaptive Neural Funnel Control for Nonlinear Two-Inertia Servo Mechanisms With Backlash

This paper proposes a modified adaptive neural control algorithm with a funnel function for nonlinear two-inertia servomechanisms with backlash and external disturbance. A continuous tracking differentiator is employed to replace the first-order filter in the traditional dynamic surface control design. A novel funnel function is employed and used in control design to improve the control performance. Then, an adaptive neural dynamic surface controller based on funnel control is presented to guarantee the tracking performance of two-inertia servomechanisms. In addition, the unknown dynamics, including backlash, nonlinear friction, and external disturbance, are approximated by using the echo state neural network and compensated online. The comparative experimental results validate the effectiveness of the developed control algorithm based on a two-inertia servo mechanism.

Neural network based adaptive dynamic surface control of nonaffine nonlinear systems with time delay and input hysteresis nonlinearities

In this paper, neural networks (NNs)-based adaptive dynamic surface control is investigated for a class of pure-feedback nonlinear systems with unknown time delay and input hysteresis nonlinearities. The design difficulty appeared in this paper due to time delay is handled by combining neural networks with finite covering lemma instead of using Krasovskii functionals, and the assumptions on the time-delay functions are removed based the finite covering lemma and NNs. Meanwhile, completely unknown backlash-like hysteresis control input that frequently exists in practice is also considered. By combining the adaptive backstepping recursive design technique with the universal approximation ability of neural networks, an adaptive neural control algorithm is systemically designed for the system under consideration, and the explosion of complexity exists in traditional backstepping design is avoided by using dynamic surface technique. It is shown that the designed adaptive controller can guarantee that all the signals are ultimately uniformly bounded and the desired signal can be tracked with a small domain of the origin. A numerical example and an example of a real plant for adjustable metal cutting system are provided to show the feasibility of the proposed method.

Research on load sensitive pressure control strategy of electro-hydraulic joint

In this paper, the mathematical and the state space model of the electro-hydraulic joint load sensitive pressure system are established. Combined with the perfect performance on optimization of RBF neural network and sliding mode variable structure control algorithm in the complex hydraulic system, this paper proposes a RBF neural network adaptive sliding-mode control algorithm. This paper designs a controller with the electro-hydraulic proportional overflow valve as the control object. The simulation results show that the RBF neural network adaptive sliding-mode controller has the advantages of high control accuracy, excellent dynamic response property and strong robustness in the complex electro-hydraulic system.

Adaptive robust backstepping attitude control for a multi-rotor unmanned aerial vehicle with time-varying output constraints

Output constraints and uncertainties are the main factors that degrade the control performance of the multi-rotor unmanned aerial vehicle (MUAV). In this paper, an adaptive neural network backstepping dynamic surface control algorithm based on asymmetric time-varying Barrier Lyapunov Function is proposed for the attitude system of a novel MUAV under asymmetric time-varying output constraints, model uncertainties and external disturbances. The asymmetric time-varying Barrier Lyapunov Function, which will grow infinite when its arguments approach some limit, is introduced to keep the output under time-varying asymmetric constraints. Considering the derivation problem of the virtual control function in backstepping, the dynamic surface control is applied to simplify the algorithm. The adaptive neural network is used to approximate the dynamic model of the attitude system, and the minimal learning parameters are employed at the same time to reduce online computation burden. In order to balance out the external disturbance and further reduce the approximate error of the adaptive neural network, a robust term is designed to compensate the above negative impacts. The proposed algorithm guarantees that all the signals of the closed-loop system bounded by Lyapunov theory. Finally, some contrast simulation experiments are given to illustrate the effectiveness and superiority of the control scheme.

Robust Adaptive Neural Prescribed Performance Control for MDF Continuous Hot Pressing System With Input Saturation

This paper presents a novel nonlinear control approach for medium-density fiberboard continuous hot pressing electro-hydraulic servo system (EHSS). The EHSS is subject to input saturation and unknown external disturbance. The approach is developed in the framework of the prescribed performance control design. The transient and steady behaviors are both considered by virtue of an appropriate performance function. A new robust adaptive neural control algorithm is then developed by introducing a dynamic surface control scheme. Moreover, the compensation control is designed for the nonlinear term arising from the input saturation. It is shown with the Lyapunov stability analysis that all the signals in the closed-loop system are semi-globally uniformly ultimately bounded. In addition, the system tracking performance regarding transient and steady-state behaviors is guaranteed effectively with input saturation via the designed control approach. Finally, numerical simulation results are presented to authenticate and validate the effectiveness of the proposed control scheme.

Designing an Intelligent Rehabilitation Wheelchair Vehicle System Using Neural Network-based Torque Control Algorithm

This paper proposes a novel intelligent wheelchair vehicle system that enables upper limb exercises, lower limb standing exercises and rehabilitation training in a daily life. The proposed system, which can be used to prevent at least the degeneration of body movements and further atrophy of musculoskeletal system functions, considers the characteristics and mobility of the old and the disabled. Its main purpose is to help the old and the disabled perform their daily activities as much as they can, minimizing the extent of secondary disabilities. In other words, the system will provide the old and the disabled with regular and quantitative rehabilitation exercises and diagnosis using the wheelchair-based upper/lower limb rehabilitation vehicle system and then verify their effectiveness. The system comprises an electric wheelchair, a biometric module to identify individual characteristics, and an upper/lower limb rehabilitation vehicle. In this paper the design and configuration of the developed vehicle is described, and its operation method is presented. Moreover, to verify the tracking performance of the proposed system, dangerous situations according to biosignal changes occurring during the rehabilitation exercise of a non-disabled examinee are analyzed and the performance of the upper/lower limb rehabilitation exercise function depending on muscle strength is evaluated through a neural network algorithm.

Neural Adaptive Sliding-Mode Control of a Vehicle Platoon Using Output Feedback

This paper investigates the output feedback control problem of a vehicle platoon with a constant time headway (CTH) policy, where each vehicle can communicate with its consecutive vehicles. Firstly, based on the integrated-sliding-mode (ISM) technique, a neural adaptive sliding-mode control algorithm is developed to ensure that the vehicle platoon is moving with the CTH policy and full state measurement. Then, to further decrease the measurement complexity and reduce the communication load, an output feedback control protocol is proposed with only position information, in which a higher order sliding-mode observer is designed to estimate the other required information (velocities and accelerations). In order to avoid collisions among the vehicles, the string stability of the whole vehicle platoon is proven through the stability theorem. Finally, numerical simulation results are provided to verify its effectiveness and advantages over the traditional sliding-mode control method in vehicle platoons.

Adaptive Neural Control of Nonlinear Systems With Unknown Control Directions and Input Dead-Zone

This paper presents an adaptive neural control approach for nonstrict-feedback nonlinear systems in presence of unmodeled dynamics, unknown control directions and input dead-zone nonlinearity. To handle the difficulty due to uncertain control directions, Nussbaum gain functions are applied. Based on the structural characteristic of radial basis function neural networks, a backstepping-based adaptive neural control algorithm is developed. The main contributions of this paper lie in the fact that a backstepping-based neural control algorithm is developed for nonstrict-feedback nonlinear systems with unmodeled dynamics, unknown control directions and actuator dead-zone, and the total number of adaptive laws is not greater than the order of control system. As a beneficial result, the controller is much easier to be implemented in practice with less computational burden. A simulation example is given to reveal the viability of the presented approach. It is demonstrated by both theoretical analysis and simulation study that the presented control strategy ensures the semiglobally uniform ultimate boundedness of all closed-loop system signals.

Adaptive Control for a Class of Partially Unknown Non-Affine Systems: Applied to Autonomous Surface Vessels

In this paper, a neural network-based adaptive control algorithm is proposed for a class of non-affine systems where the nonlinear influence of the system input on the states is unknown. The algorithm transforms the problem of controlling non-affine systems to control of nonlinear affine systems and then, by approximating the inverse of the input function, calculates feasible control input. Lyapunov technique, Uniform Ultimate Boundedness and Matrix Singular Values are used for stability analysis and design of the controller. In order to investigate the performance of the algorithm, it is applied to an autonomous vessel where the dynamics of the propeller is unknown.

Robust Neural Control for Dynamic Positioning Ships With the Optimum-Seeking Guidance

This paper deals with the optimum dynamic positioning control problem for marine ships in the presence of actuator gain uncertainties and unknown environmental disturbances. The proposed approach is formulated as two modules, i.e., the guidance part and the control part. By utilizing the improved extremum seeking algorithm, the optimum-seeking guidance is developed in this note to generate the reasonable heading guidance for dynamic positioning ships. The main purpose of this design is to ensure the closed-loop system running efficiently and environment-friendly in practice. Combined with the proposed guidance principle, a robust neural control algorithm is developed based on the dynamic surface control, neural networks, and the robust neural damping technique. In this algorithm, the strong couplings of state variables and the gain uncertainty of actuators are tackled, and the system uncertainties are compensated requiring less (or no) information of the hydrodynamic structure, the actuator model and the external disturbances. Considerable effort is made to guarantee the semiglobal uniform ultimate bounded stability by employing the Lyapunov theory. The advantages of the proposed control scheme could be summarized as two points. First, the control approach is with the properties of optimization and energy-saving, which is meaningful for applying the theoretical algorithm. Second, the pitch ratio of thrusters is selected as the control inputs of interest, which is measurable in the practical plant. These characteristics would facilitate the implementation of the algorithm in engineering. Two examples are provided to verify the performance of the proposed scheme.

Neural Network Control for Column Processing System of the Four-Single Pipe Rig

With the oil and gas exploration, the drilling is developed toward the deeper and more complex stratigraphic, the number of super deep well has been continued growth. In order to improve the tripping efficiency of deep wells and complex wells, equipment manufacturers develop four-single pipe rig to reduce the times of make-and-break during tripping, tripping operations efficiency is greatly improved. The four-single pipe rig is 10 meter higher than three single pipe conventional rig, pipe rack size of four-single pipe rig is smaller which be decision by K type derrick structure, so it is asked the control precision of the pipe string processing system is more higher, the conventional PID control precision cannot meet the requirements of the pipe string movement system. Combined with PID control in real-time data, pipe string position data and pipe string moving model, embedded in the physical model of artificial neural network adaptive control algorithm is established, and the model error sensitivity of propagation equation is derived. Simulation results show that the model has higher accuracy, robust adaptable, can meet the pipe moving automatic control system requirements of the four-single pipe rig.

Intelligent Neural Network-Based Controller for Single-Phase Wind Energy Conversion System Using Two Winding Self-Excited Induction Generator

This paper deals with a single-phase standalone wind energy conversion system using a two winding self-excited induction generator (SEIG). The proposed controller consists of a two leg voltage source converter (VSC) and a battery energy storage system (BESS) connected at its dc bus. The VSC-BESS system is controlled using an intelligent neural network-based control (INNBC) algorithm with a dynamic learning rate, depending upon the rate of change of load current to achieve an excellent dynamic as well as steady-state response of the system. The proposed control algorithm is implemented in real time using a digital signal processor. Simulated and experimental steady state and dynamic performances of proposed SEIG are presented with the proposed controller using the INNBC algorithm. The system voltage and frequency are maintained constant in all types of steady-state and dynamic loading conditions.