Intelligent Adaptive Control Research Articles

The design of a new hybrid controller for fractional-order uncertain chaotic systems with unknown time-varying delays

In this paper, the combination of a soft computing technique, i.e., adaptive neuro-fuzzy inference system (ANFIS) with fractional-order robust adaptive control is used to control a class of fractional order uncertain chaotic nonlinear systems with uncertainty, external disturbances and unknown time-varying delays. At first, the fractional-order hyperbolic tangential robust adaptive intelligent controller (FHRAIC) is designed for the system, when the unknown time-varying heterogeneous delays and uncertainties and disturbances exist in system states. Next, the controller design is extended for the case of existence of unknown time-varying delay in the inputs of the system. The hyperbolic tangential sliding surface enables the closed-loop system to safely and effectively avoid large errors in tracking control. Adaptive control parameters are adjusted based on Lyapunov stability analysis ANFIS is used to approximate unknown functions. The stability analysis of this controller has been carried out based on Lyapunov–Krasovskii method and Barbalat’s Lemma. Various simulation examples show the effectiveness of the proposed method for a vast range of systems. To demonstrate the effectiveness of ANFIS on FHRAIC controller, its performance has been compared with that of fractional-order hyperbolic tangential robust adaptive controller (FHRAC).

An adaptive PID controller with an online auto-tuning by a pretrained neural network

This paper describes an intelligent adaptive PID controller design procedure. The controller consists of a discrete time PID and an auto-tuning neural network unit. First system identification with a nonlinear autoregressive model (NARX) was performed. This model was then used to train the neural PID tuner. A special MATLAB toolbox “SmatPID Toolbox” was developed to automate the process of controller synthesis. The resulting controller was tested in a laboratory coal-gas furnace control system to track specified air flow rates.

A Novel Robust Adaptive Intelligent and Compound Control of an Adaptive Neural Network, SMC, FLC and PI for Robot Manipulators

In this paper, a new compound control scheme is proposed for robot manipulators (RMs) based on radial basis function neural network (RBFNNs), sliding mode control (SMC), fuzzy logic control (FLC) and proportional–integral (PI) controller. In this control scheme, the filtered tracking error is the input of the RBFNNs update laws, SMC, FLC and PI controller. The RBFNNs uses three-layer to approximate uncertain nonlinear manipulator dynamics. A robust sliding function is selected as a second controller to guarantee the stability and robustness under various environments. The FLC as the third controller completely removes the chattering signal caused by the sign function in the SMC. By using additional PI controllers, the goal of RMs tuning is to minimize tracking performance and overshoot can be realized. Simulation results highlight performance of the controller to compensate the approximate errors and its simpleness in the adaptive parameter tuning process. To be concluded, the controller is suitable for robust adaptive intelligent control and can be used as supplementary of traditional neural network (NN) controllers.

Intelligently Controlled Flywheel Storage for Enhanced Dynamic Performance

This paper investigates the development and application of a nonlinear adaptive intelligent controller with superior disturbance-rejection capability for a doubly-fed-induction-machine driven flywheel energy storage system (FESS), to mitigate the intermittency in wind power injection, as well as enhance the transient stability of the connected multimachine power system thereby isolating the grid power from fluctuations. Intelligent supervisors for the rotor-side-converter of the FESS have been constructed using a fuzzy rule set. The consequent part in every rule includes a wavelet function for function learning. The novel normalized gradient descent algorithm with adaptive learning rate has been used to derive the update laws for unknown controller parameters. The control law has been derived by minimizing the predictive performance index. Convergence of the developed algorithm is guaranteed as proven via the Lyapunov stability method. Realistic wind speed profile has been used to test the efficacy of the developed control scheme. The sizing strategy has been devised for optimal sizing of FESS for its efficient utilization. Modified WSCC nine-bus test system has been used for the nonlinear time-domain simulations and novel indices have been used for evaluation of controller performance against its predecessors. $\boldsymbol{OP}{\text{5600}}$ Real-Time-Digital-Simulator has been used to demonstrate the real-time implementation of the suggested scheme.

Biologically inspired adaptive intelligent secondary control for MGs under cyber imperfections

In this study, the authors investigate the secondary control of microgrids (MGs) in the presence of cyber imperfections such as delay and/or noise, and system disturbances. The existence of cyber imperfections and disturbance could bring in system uncertainty that will seriously degrade the effectiveness of most existing secondary control such as proportional–integral–derivative (PID), etc. To tackle these issues, a biologically-inspired reinforcement learning technique has been proposed which adjusts its parameters to the perturbed system setpoints generated by the cyber imperfections and system disturbances. The learning capability and low computational complexity of the proposed controller make it a promising approach to take cyber imperfections and system disturbances into account, where traditional control methodologies are not suitable due to their vulnerability to the cyber imperfections. First, an emotional learning-based secondary control structure is proposed, where the impacts of cyber imperfection and disturbance have been captured efficiently. Then, the real-time update laws are developed for generating the proper emotional signals (ESs) to stabilize the frequency and voltage. Ultimately, using the generated ESs, the secondary control of MGs is achieved. The Lyapunov analysis has been provided to prove the stability of the proposed design. Moreover, MATLAB/Simulink-based simulations demonstrate the effectiveness of the proposed algorithm.

Adaptive nonlinear active suspension control based on a robust road classifier with a modified super-twisting algorithm

For the suspension system equipped with nonlinear hydraulic actuators and excited by external road conditions, a road adaptive intelligent suspension control strategy is developed. In this work, (1) a multi-phase intelligent road adaptive control architecture is developed to enhance the ride comfort in the presence of varying road excitations; (2) a modified algorithm is proposed to improve the system performance. Initially based on the nonlinear system dynamics, a sliding mode controller based on an improved super-twisting algorithm is proposed. In the Off-line phase, the optimized control parameters based on particle swarm optimization (PSO) approach for each road level are determined and supplied to a probabilistic neural network (PNN)-based classifier for training. In the On-line phase, the PNN classifier employs the measured unsprung mass acceleration to determine the road level and supplies the information to the controller database. Based on the classified road level, corresponding control parameters as determined by PSO are then selected. These control parameters are then supplied to the nonlinear controller which provides the active control. The closed-loop stability of the proposed approach is proved, and the simulation results for different road levels are presented to show the effectiveness of the proposed approach.

An Intelligent Adaptive Robust Controller Based on Neural Network for a Pneumatic System

Pneumatic actuator systems are widely applied in industrial automation. This paper proposes an intelligent adaptive robust controller(ARC) based on neural network(NN) to improve the applicability in a pneumatic servo system that consists of a pneumatic cylinder which is controlled by a proportional directional control valve. In this design, adaptive robust controller is provided with suitable control parameters automatically by a real-time neural network depending on feedback errors. So the ARC the tuning process that is time consuming and restricts the application of pneumatic systems is avoided. The experimental results show all the control parameters of ARC are converged and good control performance is achieved.

Regularized extreme learning machine–based intelligent adaptive control for uncertain nonlinear systems in networked control systems

Since the learning ability of adaptive control (including multi-model adaptive control) is actually very limited and the persistent excitation (PE) condition is also not satisfied in the design of uncertain nonlinear system controllers, an improved networked control method based on regularized extreme learning machine for a class of nonlinear systems. The networked controller is built to compensate for the modeling error and system uncertainties. In the designed controller, its hidden node parameters are modified using the recently proposed regularized extreme learning machine (ELM), where they are assigned random values. However, different from the original ELM algorithm, the output weight is updated based on the L1/L2 norm penalty to guarantee the stability of the overall control system. The proposed model is finally applied to the internal model control in networked control system. The simulation results demonstrate good tracking performance of the proposed control scheme and have better control performance, anti-interference ability, and robustness for nonlinear system.

Type-2 fuzzy cerebellar model articulation control system design for MIMO uncertain nonlinear systems

This paper aims to propose a more efficient neural network and applies it as an adaptive controller for the multi-input multi-output (MIMO) uncertain nonlinear systems. First, a more efficient fuzzy neural network named as fuzzy cerebellar model articulation controller (CMAC) is introduced, then an adaptive controller is proposed using a novel interval type-2 fuzzy CMAC (T2FCMAC). The T2FCMAC realizes an interval type-2 fuzzy logic system based on the structure of the CMAC. Due to the better ability of handling uncertainties provided by type-2 fuzzy sets, it can solve some complicated problems with outstanding effectiveness than type-1 fuzzy sets. In addition, an intelligent control system is proposed; this control system is comprised of a T2FCMAC and an auxiliary compensation controller. The T2FCMAC is utilized to approximate a perfect controller and the parameters of T2FCMAC are on-line tuned by the derived adaptive laws based on a Lyapunov function. The auxiliary compensation controller is designed to suppress the influence of residual approximation error between the perfect controller and the T2FCMAC. Finally, two MIMO uncertain nonlinear systems, a Chua’s chaotic circuit and a mass-spring-damper mechanical system, are performed to verify the effectiveness of the proposed control scheme. The simulation results confirm that the proposed intelligent adaptive control system can achieve favorable tracking performance with desired robustness.

Intelligent Adaptive Dynamic Surface Control System With Recurrent Wavelet Elman Neural Networks for DSP-Based Induction Motor Servo Drives

In this paper, an intelligent adaptive dynamic surface control system (IADSCS) with recurrent wavelet Elman neural network (RWENN) for induction motor (IM) servo drive is proposed. The IADSCS comprises a dynamic surface controller (DSC), a RWENN uncertainty observer, and a robust controller. First, a computed torque controller (CTC) is designed to stabilize the IM servo drive. Then, a nonlinear disturbance observer (NDO) is designed to estimate the nonlinear lumped parameter uncertainties (PU) existed in the CTC law. However, the IM servo drive performance is degraded by the NDO error due to the PU. To improve the robustness of the IM servo drive due to external load disturbances and PU, an IADSCS is designed to achieve this purpose. In the IADSCS, the DSC is used to overcome the explosion of the complexity in the backstepping design technique and the RWENN identifier is used to approximate the lumped PU and compounded disturbances. In addition, the robust controller is designed to recover the approximation error of the RWENN. The stability of the closed-loop system is guaranteed by the Lyapunov stability theory. All control algorithms are implemented using dSPACE1104 DSP-based control computer. The simulation and experimental results show the superiority of the proposed IADSCS in external load disturbance suppression and the robustness against PU.

Extremum Seeking-based Adaptive PID Control applied to Neuromuscular Electrical Stimulation.

A multivariable deterministic extremum seeking (ES) is being evaluated to construct an adaptive Proportional-Integral-Derivative (PID) control law for the functional Neuromuscular Electrical Stimulation (NMES) of stroke patients. The developed scheme is applied to control the position of the patient's arm so that movements of flexion/extension for its elbow can be produced. The true limitations of a PID controller for these types of applications is that a PID controller is designed for linear systems, but the system which is being controlled is nonlinear. Moreover, it is worth mention that clinicians' knowledge of control systems is limited. Therefore, their expertise in tuning controllers is limited. Also, in NMES applications each patient is unique and requires a unique set of PID parameters. Since it can be time consuming and difficult to find proper parameters for each patient, a better procedure, or a more intelligent adaptive controller, is needed. The PID parameters are updated by means of ES in order to minimize a cost function which brings the desired performance attributes. Experiments are performed with healthy volunteers and stroke patients, including significant advances based on real data and validation. Quantitative results show a reduction of 64:1% in terms of RMSE (Root-Mean-Square Error) - from 8:94º to 3:21º - when comparing the tracking curves of the last cycle to the first cycle in the experiments with all stroke patients.

MRAS speed observer for sensorless adaptive intelligent backstepping controller of induction machines

In this paper, a sensorless adaptive neuro-fuzzy backstepping control scheme is developed for induction machines with unknown model, uncertain load-torque and nonlinear friction where the speed is obtained using the model reference adaptive system (MRAS). Neurofuzzy systems are used to online approximate the uncertain nonlinearities and an adaptive backstepping technique is employed to systematically construct the control law. The MRAS observer is based on two different models, one that is speed independent (reference model) and another that is speed dependent (adjustable model). The speed is estimated via the outputs of the two models. The proposed sensorless controller guarantees the tracking errors converge to a small neighbourhood of the origin and the boundedness of all closed-loop signals what demonstrate the effectiveness of the proposed approach.

MRAS speed observer for sensorless adaptive intelligent backstepping controller of induction machines

In this paper, a sensorless adaptive neuro-fuzzy backstepping control scheme is developed for induction machines with unknown model, uncertain load-torque and nonlinear friction where the speed is obtained using the model reference adaptive system (MRAS). Neurofuzzy systems are used to online approximate the uncertain nonlinearities and an adaptive backstepping technique is employed to systematically construct the control law. The MRAS observer is based on two different models, one that is speed independent (reference model) and another that is speed dependent (adjustable model). The speed is estimated via the outputs of the two models. The proposed sensorless controller guarantees the tracking errors converge to a small neighbourhood of the origin and the boundedness of all closed-loop signals what demonstrate the effectiveness of the proposed approach.

A Comparative Study on Neural Network Based Controllers Used in Grid-Interactive Solar System

Abstract This paper proposes a comparative assessment of NN based current controllers followed by hardware validation towards power quality improvement in grid-interactive VSI controlled solar system. The steady state errors, transient disturbances and high current harmonic effects encountered in conventional linear PI and PR controllers are nullified by employing intelligent adaptive current controller. Three adaptive current control strategies viz. ADALINE-LMS, ALLMS, and VLAS-LMS are identified by using artificial neural network topology having been controlled by different weight-regulating algorithms which helps in minimizing current harmonics generated by the widespread use of VSI, non-linear loads, faults and uncertain polluted grid. A comprehensive comparative study is driven from the proposed adaptive controller's stability and convergence criterion, current magnitudes calculated at different power zones, % overshoot, settling time and power quality and analyzed under numerous operating conditions. From the comparative assessment performed in between conventional and intelligent current controllers, it is confirmed that the intelligent control technique performs best under the non-linear loads and transient conditions whereas all the controllers perform equally good under the linear loads. Proposed methods are simulated in MATLAB/Simulink and their effectiveness is compared in terms of time responses, stability and low-order current harmonics compensation capability. The robustness of the intelligent current controller is established through the experimental performances using dSPACE RTI 1202.

Acrylic polymerization process control and MATLAB simulation based on intelligent adaptive control

The polymerization process of acrylic fiber belongs to multi-input and multi-output nonlinear system. The polymerization continuous stirred reaction kettle temperature and polymerization conversion efficiency are important technological indexes in the polymerization production of acrylic fiber. The control level of the complex nonlinear process directly affects the differentiation rate of products. This study uses an intelligent self-adaptive control method to construct a mathematical model of acrylic fiber polymerization process, and the control method is designed in MATLAB. The corresponding simulation rules are made and the simulation of acrylic fiber polymerization process is completed.

Adaptive Intelligent Sliding Mode Control of a Photovoltaic Grid-Connected Inverter

Adaptive intelligent sliding mode control methods are developed for a single-phase photovoltaic (PV) grid-connected transformerless system with a boost chopper and a DC-AC inverter. A maximum power point tracking (MPPT) method is implemented in the boost part in order to extract the maximum power from the PV array. A global fast terminal sliding control (GFTSMC) strategy is developed for an H-bridge inverter to make the tracking error between a grid reference voltage and the output voltage of the inverter converge to zero in a finite time. A fuzzy-neural-network (FNN) is used to estimate the system uncertainties. Intelligent methods, such as an adaptive fuzzy integral sliding controller and a fuzzy approximator, are employed to control the DC-AC inverter and approach the upper bound of the system nonlinearities, achieving reliable grid-connection, small voltage tracking error, and strong robustness to environmental variations. Simulation with a grid-connected PV inverter model is implemented to validate the effectiveness of the proposed methods.

Adaptive Intelligent Control for Nonlinear Strict-Feedback Systems With Virtual Control Coefficients and Uncertain Disturbances Based on Event-Triggered Mechanism.

This paper investigates the problem of adaptive fuzzy control on the basis of an event-triggered mechanism for nonlinear strict-feedback systems with time-varying external disturbances and virtual control coefficients in the presence of actuator failures. Virtual control coefficients are correlated with the designed adaptive law and control signal. In the backstepping technique procedure, fuzzy logic systems are utilized to approximate an unknown nonlinear function, and the tuning function is implemented to cope with the destabilizing problem of the control design. To save communication resources, an adaptive fuzzy event-triggered control strategy is developed to update the control input when the triggering condition is satisfied. Then, all of the closed-loop signals can remain semi-globally uniformly ultimately bounded. The Zeno behavior can be excluded. Finally, a numerical example and a real system are provided to illustrate the effectiveness of the proposed approach.

Intelligent adaptive control for the large aircraft based on the disturbance compensation under the influence of strong interferences

An intelligent adaptive control scheme based on the disturbance compensation was proposed to solve the stability augmentation control problem of the large under the influence of strong interferences. First, considering the influence of strong wind, the coupling multivariable disturbance observer is designed for the control-oriented model to estimate the synthetical uncertainties and disturbances rapidly and accurately and compensate the close-loop controller. And on the basis of the observer, a novel finite-time robust adaptive controller which is the combination of fast super-twisting algorithm and action dependent heuristic dynamic programming is proposed. The control scheme can obtain good control performance that the large airplane can track the control command accurately and steadily in finite time. Finally, to demonstrate the effectiveness of the proposed intelligent adaptive control scheme, the simulation verification of Boeing 747 is carried out. And the simulation results verify the good control performance in attitude stable and rapid maneuvering of the large aircraft.

INTELLIGENT MACHINING: REAL-TIME TOOL CONDITION MONITORING AND INTELLIGENT ADAPTIVE CONTROL SYSTEMS

Unmanned manufacturing systems has recently gained great interest due to the ever increasing requirements of optimized machining for the realization of the fourth industrial revolution in manufacturing ‘Industry 4.0’. Real-time tool condition monitoring (TCM) and adaptive control (AC) machining system are essential technologies to achieve the required industrial competitive advantage, in terms of reducing cost, increasing productivity, improving quality, and preventing damage to the machined part. New AC systems aim at controlling the process parameters, based on estimating the effects of the sensed real-time machining load on the tool and part integrity. Such an aspect cannot be directly monitored during the machining operation in an industrial environment, which necessitates developing new intelligent model-based process controllers. The new generations of TCM systems target accurate detection of systematic tool wear growth, as well as the prediction of sudden tool failure before damage to the part takes place. This requires applying advanced signal processing techniques to multi-sensor feedback signals, in addition to using ultra-high speed controllers to facilitate robust online decision making within the very short time span (in the order of 10 ms) for high speed machining processes. The development of new generations of Intelligent AC and TCM systems involves developing robust and swift communication of such systems with the CNC machine controller. However, further research is needed to develop the industrial internet of things (IIOT) readiness of such systems, which provides a tremendous potential for increased process reliability, efficiency and sustainability.

Adaptive Neural Controller Design Scheme of Nonlinear Delayed Systems With Completely Unknown Nonlinearities and Non-Strict-Feedback Structure

This paper proposes a novel adaptive intelligent tracking controller design scheme for a type of nonlinear delayed systems with completely unknown nonlinearities and non-strict-feedback structure. In the backsteppping-based design architecture, the intelligent estimation technique is utilized to approximate the unknown nonlinear functions via neural networks, and Lyapunov–Krasovskii functionals are designed to deal with the unknown delay terms. The constructed adaptive intelligent controller guarantees the semi-global boundedness of the resulting closed-loop system and the system output eventually converges to a small neighborhood around the desired reference signal. In the end, the presented simulation results verify the effectiveness of the proposed design method.