Neural Network Control Scheme Research Articles

Adaptive neural network auto-berthing control of marine ships

To solve the auto-berthing control problem for underactuated marine ships subject to unknown dynamics and external disturbances under the circumstance of the restricted waters in port, firstly, an additional control method is adopted to solve the underacruated problem. Secondly, a robust neural network (NN) adaptive approach based on the navigation dynamic deep-rooted information (DRI) is proposed to reconstruct the lumped uncertainties caused by unknown ship dynamics and external disturbances. Meanwhile, the dynamic surface control (DSC) and the minimum learning parameter (MLP) techniques are used to reduce the computational load of the adaptive NN control scheme. Considering the input saturation effects of control actuator (rudder, propeller, etc) and the coupling characteristics of uncertainties, this approach integrates neural network weights, approximation errors and external disturbance term as the composite uncertain parameters, which is estimated online by parameter adaptive technique. Finally, simulations are carried out on an underactuated model ship to verify the effectiveness of the proposed auto-berthing control scheme.

Fuzzy Tracking Control for a Class of Uncertain MIMO Nonlinear Systems With State Constraints

In this paper, an adaptive fuzzy neural network (FNN) control scheme is developed for a class of multiple-input and multiple-output (MIMO) nonlinear systems subject to unknown dynamics and state constraints. FNNs are used to approximate the unknown dynamics that comprises the effects of uncertain parameters and functions. Also, integral Lyapunov functions are introduced to address state constraints. A neural-network-based observer is designed to estimate the unmeasurable states. With state-feedback and output feedback tracking control, the stability of closed-loop system is guaranteed via Lyapunov’s stability theory. Two cases of simulations for MIMO systems with state constraints are conducted to verify the effectiveness of the proposed control.

Adaptive control of non‐affine MIMO systems with input non‐linearity and unmodelled dynamics

In this study, an adaptive neural network control scheme is proposed for a class of multi-input multi-output (MIMO) non-affine systems with unmodelled dynamics and dead-zone non-linear input. This scheme solves the complexity of computation problem, broadens the variables of unmodelled dynamics and cancels the assumption of the neural network approximation error to be bounded. Using the mean value theorem and Young's inequality, only one adaptive parameter is adjusted for the whole MIMO system. By theoretical analysis, all the signals in the closed-loop systems are proved to be semi-globally uniformly ultimately boundedness. The numerical simulation illustrates the effectiveness of the proposed scheme.

Pattern-based NN control for uncertain pure-feedback nonlinear systems

Implementing human-like learning and control for nonlinear dynamical systems operating in different control situations is an important and challenging issue. This paper presents a pattern-based neural network (NN) control strategy for nonlinear pure-feedback systems via deterministic learning (DL). Firstly, an appropriately designed adaptive neural dynamic surface controller is proposed to achieve the finite time tracking control. By analyzing the recurrent property of NN input signals, a partial persistent excitation (PE) condition for radial basis function (RBF) network is established, the implicit desired control dynamics under different control situations are accurately identified via DL in the case that the dimension of NN input is reduced. And a set of pattern-based experienced actual and virtual controllers is constructed using the learned knowledge. Secondly, to classify different control situations, when the system is operating in different control situations but controlled by current normal experienced controller, the dynamics of each subsystem are accurately identified via DL, n sets of dynamical estimators are constructed using the learned knowledge. Thirdly, in the recognition phase, n sets of residuals are achieved by comparing each set of estimators with the monitored system, sudden change in the control situation is rapidly recognized based on the principle of the earliest occurrence of the minimum residual. Finally, in the control phase, according to the recognition result, the correct experienced actual and virtual controllers will be selected to control the plant, guaranteed stability and superior control performance are achieved without any further re-adaptation online. Simulation studies are given to verify the proposed scheme can not only acquire and memorize knowledge like humans, but also reuse the learned knowledge to achieve rapid recognition and control of current control situation.

A Neural Network Control Strategy for Composite Braking System of Electric Vehicle

The composite braking system is significant to improve the total energy efficiency of electric vehicles by recycling braking energy. A neural network controller for the CBS is proposed to improve the energy regeneration rate and braking stability of EVs in this paper. The regenerative and hydraulic braking torques were optimized offline by using Downhill-Simplex method, and the NN model related to the driving state parameters were trained. Compared with a parallel braking strategy, the energy economy of NN is improved by 4.64% than the parallel controller’s in 3 NEDC cycles, and performs more closely to the I curve in a specific braking condition with a decreasing braking severity.

An improved radial basis function neural network control strategy-based maximum power point tracking controller for wind power generation system

This literature presents an improved maximum power point tracking (MPPT) controller based on radial basis function neural network (RBFNN) control strategy to extract optimal power for wind power generation system. The proposed RBFNN controller is trained online using gradient descent algorithm and its network learning rate modification is carried out by the modified particle swarm optimization algorithm. The proposed MPPT controller uses optimal torque control methodology to extract optimal power available in the wind by upholding the generated torque at an optimal level. The most promising aspects of the proposed controller are that it not only extracts maximum available power from wind, but it also rapidly responses to the change in wind speeds and maintains converter with negligible converter losses. To evaluate the performance of the proposed MPSO-RBFNN-based MPPT controller, an extensive simulation study and experimental analysis is performed. The attained results confirm the enhanced performance of the proposed MPPT controller.

An improved adaptive online neural control for robot manipulator systems using integral Barrier Lyapunov functions

ABSTRACTConventional Neural Network (NN) control for robots uses radial basis function (RBF) and for n-link robot with online control, the number of nodes and weighting matrix increases exponentially, which requires a number of calculations to be performed within a very short duration of time. This consumes a large amount of computational memory and may subsequently result in system failure. To avoid this problem, this paper proposes an innovative NN robot control using a dimension compressed RBF (DCRBF) for a class of n-degree of freedom (DOF) robot with full-state constraints. The proposed DCRBF NN control scheme can compress the nodes and weighting matrix greatly and provide an output that meets the prescribed tracking performance. Additionally, adaption laws are designed to compensate for the internal and external uncertainties. Finally, the effectiveness of the proposed method has been verified by simulations. The results indicate that the proposed method, integral Barrier Lyapunov Functions (iBLF), avoids the existing defects of Barrier Lyapunov Functions (BLF) and prevents the constraint violations.

Performance Enhancement of DFIG Based Grid Connected SHPP Using ANN Controller

In the current span of time, Small Hydro Power Plant(SHPP) is gaining more attention due to its numerous pros among all the various renewable energy sources. The prime objective of this paper to present the comparative analysis of Proportional Integral (PI)control and Artificial neural network (ANN) control strategy which is used in doubly fed induction generator-based SHPP. Traditionally presented PI control scheme has numerous limitations due to nonlinear model of DFIG, as well as PI control scheme, needs plentiful mathematical equations. To significantly improve the transient response of the DFIG system as well as reduce the computational time of the system, ANN control scheme is implemented in the rotor side and grid side of the small hydropower plant system. The proposed ANN scheme significantly improves the transient behavior of active and reactive power in the rotor side and reactive power and dc bus voltage in the grid side as compared to the PI control scheme. MATLAB/SIMULINK is used for testing, analyzing and comparison of dynamic and steady-state realization of the proposed controller scheme. The stability of the system is constant under various load circumstances and it is scrutinized with the help of model and simulated results.

Adaptive neural network control of uncertain robotic manipulators with external disturbance and time-varying output constraints

Abstract This paper presents an adaptive neural network control scheme for a class of uncertain robotic manipulators with external disturbance and time-varying output constraints. A system transformation technique is applied to convert a constrained system into an equivalent unconstrained one for solving the time-varying output constraint problem. A model-based (MB) control scheme and an adaptive neural network (NN) control scheme, respectively, are designed by using backstepping technique. All the signals in the closed-loop system are proved to be uniformly ultimately bounded (UUB) via Lyapunov synthesis. In the adaptive control scheme, neural networks are employed to approximate the unknown closed-loop dynamics and external disturbance. A planar two degrees of freedom rigid robotic manipulator is used to be an illustrative case, where the robotic manipulator is controlled respectively by the proposed schemes and an existing robust adaptive NN control method without considering time-varying output constraints. Simulation results verify that the proposed adaptive NN controller yields better control performances in comparison to the robust adaptive NN controller without considering time-varying output constraints.

Experimental study on active vibration control for a kind of two-link flexible manipulator

This paper presents experimental investigations on active vibration control of a two-link flexible manipulator (TLFM), utilizing a generalized minimum variance self-tuning control (GMVSTC) and Takagi-Sugeno model based fuzzy neural network control (TS-FNN) schemes. The GMVSTC algorithm consists of an on-line identifier in the form of controlled autoregressive moving average model and a vibration control signal generator, and the TS-FNN control algorithm generates control actions taking full advantages of fuzzy logic controller and a neural controller. Experimental setup of the two-link flexible manipulator is constructed. Experimental comparison research on vibration attenuation is conducted during and after the motor motion, to verify the designed controllers. The effectiveness of the designed controllers is evaluated in terms of vibration suppression as compared to that of the classical PD control. The experimental results demonstrate that the designed controller can damp out both the large and the small amplitude vibration of a two-link flexible manipulator more quickly than that the traditional linear PD controller, especially for the small amplitude residual vibration.

A Model-Based Recurrent Neural Network With Randomness for Efficient Control With Applications.

Recently, Recurrent Neural Network (RNN) control schemes for redundant manipulators have been extensively studied. These control schemes demonstrate superior computational efficiency, control precision, and control robustness. However, they lack planning completeness. This paper explains why RNN control schemes suffer from the problem. Based on the analysis, this work presents a new random RNN control scheme, which 1) introduces randomness into RNN to address the planning completeness problem, 2) improves control precision with a new optimization target, 3) improves planning efficiency through learning from exploration. Theoretical analyses are used to prove the global stability, the planning completeness, and the computational complexity of the proposed method. Software simulation is provided to demonstrate the improved robustness against noise, the planning completeness and the improved planning efficiency of the proposed method over benchmark RNN control schemes. Real-world experiments are presented to demonstrate the application of the proposed method.

Adaptive fuzzy control for a marine vessel with time‐varying constraints

An adaptive fuzzy neural network (FNN) control scheme is proposed for a marine vessel with time-varying constraints, guaranteed transient response and unknown dynamics. A series of continuous constraint functions are introduced to shape the motion of a marine vessel. To deal with the constraint problems and transient response problems, an asymmetric time-varying barrier Lyapunov function is designed to ensure that the system states are upper bounded by the considered constraint functions. FNNs are constructed to identify the unknown dynamics. Considering existing approximation errors when FNNs approximating the unknown dynamics, an adaptive term is designed to compensate the approximation errors in order to obtain accurate control. Via Lyapunov stability theory, it has been proved that all the states in the closed-loop system are uniformly bounded ultimately without violating the corresponding prescribed constraint region. Two comparative simulations are carried out to verify the effectiveness of the proposed control.

Control of Switched Reluctance Motors based on Improved BP Neural Networks

Background: Switched reluctance motors have a strong nonlinear performance due to their structure and operation mode. The performance and control strategy of this kind of motor are obviously different from those traditional strategies. As a result, the accurate model and high performance control of the switched reluctance motor prove to be very important and has obtained wide researches. Method: A kind of switched reluctance motor based on PID neural network control strategy is proposed, which combines artificial fish swarm and particle swarm optimization to optimize weights and thresholds of BP neural networks. Results: Speed responses of the improved BP algorithm have no overshoot, have a smooth transition to the steady state and eliminate the oscillation phenomena which is in the PID control. Conclusion: Besides, it reduces time of transient process to improve the response speed. Antiinterference ability and robustness are obviously superior to the PID control. Keywords: Switched reluctance motor, BP neural network, artificial fish swarm, particle swarm optimization, BP algorithm, global optical value.

Adaptive fuzzy-neural-network based on RBFNN control for active power filter

In this paper, an adaptive fuzzy-neural-network (FNN) control scheme based on a radial basis function (RBF) neural network (NN) is proposed to enhance the performance of a shunt active power filter (APF). APF can efficiently eliminate harmonic contamination and improve the power factor compared with traditional passive filter. The proposed approach gives a RBF NN control scheme, which is utilized on the approximation of a nonlinear function in APF dynamic model, the weights of the RBF NN are adjusted online according to adaptive law from the Lyapunov stability analysis. In addition, adaptive fuzzy-neural-network systems is employed to compensate the neural approximation error and eliminate the existing chattering, enhancing the robust performance of the system. Simulation results confirm the effectiveness of the proposed controller, demonstrating that APF with the proposed method has strong robustness and the outstanding compensation performance.

Neural Network Based Maximum Power Point Tracking Control with Quadratic Boost Converter for PMSG—Wind Energy Conversion System

This paper proposes an artificial neural network (ANN) based maximum power point tracking (MPPT) control strategy for wind energy conversion system (WECS) implemented with a DC/DC converter. The proposed topology utilizes a radial basis function network (RBFN) based neural network control strategy to extract the maximum available power from the wind velocity. The results are compared with a classical Perturb and Observe (P&O) method and Back propagation network (BPN) method. In order to achieve a high voltage rating, the system is implemented with a quadratic boost converter and the performance of the converter is validated with a boost and single ended primary inductance converter (SEPIC). The performance of the MPPT technique along with a DC/DC converter is demonstrated using MATLAB/Simulink.

Neural network adaptive tracking control for a class of uncertain switched nonlinear systems

The paper is concerned with the tracking control problem of the switched nonlinear systems under arbitrary switchings. Multilayer neural networks are used as a tool for modeling nonlinear functions up to a small error tolerance. In order to improve the tracking performance, through the expansion of the traditional neural network controller design, a multilayer neural network adaptive controller with multilayer weight norm adaptive estimation has been designed. Further, the weight norm adaptive laws are not only used to approximate the first layer network but also every layers. The adaptive updated laws of the controller have been derived from the Lyapunove function method, and the adaptive neural network control schemes have been developed to achieve more smaller semi-global ultimate boundedness of all the signals in the closed-loop than ever before. Finally, the simulation examples of two theorems are given to illustrate the effectiveness of the proposed control scheme separately.

SGD-Based Adaptive NN Control Design for Uncertain Nonlinear Systems.

In this paper, a stochastic gradient descent (SGD)-based adaptive neural network (NN) control scheme is presented for a class of uncertain nonlinear systems. The introduction of the SGD algorithm results in a better tracking performance compared with some other adaptive NN methods without using SGD. This is because the proposed SGD-based adaptive NN control strategy provides optimization algorithms for the weights, the widths, and the centers of the NNs, which can achieve a good function approximation performance. In order to implement the proposed method, extended differentiators are introduced to get the differential estimations of error signals, such that the loss function of the optimization algorithm can be constructed approximatively. Moreover, adaptive laws are designed to reduce the overall approximation errors, such that the tracking performance is further improved. By using the Lyapunov stability theory, it can be proved that the target signal is tracked by the system output within a small error. Finally, simulation and comparison results are given to show the effectiveness and advantages of the proposed method.

Global approximation based adaptive RBF neural network control for supercavitating vehicles

A global approximation based adaptive radial basis function (RBF) neural network control strategy is proposed for the trajectory tracking control of supercavitating vehicles (SV). A nominal model is built firstly with the unknown disturbance. Next, the control scheme is established consisting of a computed torque controller (CTC) for the practical vehicle and an RBF neural network controller to estimate model error between the practical vehicle and the nominal model. The network weights are adapted by employing a Lyapunov-based design. Then it is shown by the Lyapunov theory that the trajectory tracking errors asymptotically converge to a small neighborhood of zero. The control performance of the proposed controller is illustrated by simulation.

Adaptive Neural Control for Hysteresis Motor Driving Servo System with Bouc‐Wen Model

An adaptive high‐order neural network (HONN) control strategy is proposed for a hysteresis motor driving servo system with the Bouc‐Wen model. To simplify control design, the model is rewritten as a canonical state space form firstly through coordinate transformation. Then, a high‐gain state observer (HGSO) is proposed to estimate the unknown transformed state. Afterward, a filter for the tracking errors is adopted which converts the vector error e into a scalar error s. Finally, an adaptive HONN controller is presented, and a Lyapunov function candidate guarantees that all the closed‐loop signals are uniformly ultimately bounded (UUB). Simulations verified the effectiveness of the proposed neural network adaptive control strategy for the hysteresis servo motor system.

Self-learning interval type-2 fuzzy neural network controllers for trajectory control of a Delta parallel robot

Abstract This paper presents a self-learning interval type-2 fuzzy neural network (SLIT2FNN) control scheme for trajectory tracking problem of a Delta robot. This intelligent control scheme is computationally efficient and can be easily applied to existing equipment. The controller has a parallel structure, which combines an interval type-2 fuzzy neural network (IT2FNN) controller and a traditional proportional-derivative (PD) controller. We use the PD controller to compensate the transient performance, and use the IT2FNN to learn the dynamic characteristics of the system. A novel arrangement of trapezoidal interval type-2 fuzzy membership functions (IT2MF) is proposed, the arrangement enables the adaptation laws to have an analytical form. A learning algorithm based on sliding mode control (SMC) theory is proposed for the parameter training of the IT2FNN system. The control algorithm learns from the feedback error online and tunes the parameters of the IT2FNN, and will become the main source of the control signal after several learning iterations. Unlike model-based control, this control method has no requirement of prior information and constraint conditions from the robot plant. Lyapunov stability method is employed to prove asymptotic stability of the proposed approach. The structure of the SLIT2FNN and the operations in each layer are introduced in detail. The performance and robustness of the proposed controller is demonstrated on the Delta robot trajectory tracking problems in the presence of structured and unstructured uncertainties. Simulation results illustrate that the proposed SLIT2FNN control approach produces higher trajectory tracking accuracy and more robust to uncertainties as compared to its counterparts.