Neuro-fuzzy Sliding Mode Control Research Articles

Adaptive neuro-fuzzy sliding mode control of the human upper limb during manual wheelchair propulsion: estimation of continuous joint movements using synergy-based extended Kalman filter

Adaptive neuro-fuzzy sliding mode control of the human upper limb during manual wheelchair propulsion: estimation of continuous joint movements using synergy-based extended Kalman filter

Simulation modeling of PMBLDC motor speed control in electric propulsion of EV system using adaptive nonlinear fuzzy sliding mode controller (ANF-SMC)

In the current scenario of transportation system, vehicles of conventional are replaced with Electric Vehicles (EVs) with Permanent Magnet Brushless Direct Control Motors (PMBLDCMs) because of the many advantages of the usage of such motors in EVs. Despite the many advantages of the usage of EVs with PMBLDCMs, there were some disadvantages, among them were speed control and dealing with uncertainty problems in the usage of PMBLDCMs in EVs. In rectifying the above-mentioned problems, this work proposed and implemented an ideology of using the nonlinear controller strategy Adaptive Neuro-Fuzzy Sliding Mode Control (ANF-SMC) in the Electric Propulsion Subsystem (EPSS) of EVs with the usage of the proposed nonlinear controller under not loaded and fully loaded vehicles with constant, variable and sudden disturbance in speed conditions. Simulation was carried out using MATLAB version R2020b with Fuzzy Tool Kit (FTK) and simulation performance comparison was done with the existing four (one linear and three nonlinear) controllers. Comparative simulation results infer that the proposed nonlinear controller performs well with zero overshoot and less settling time than that of the existing four (one linear and three nonlinear controllers).

Adaptive Neuro-Fuzzy Sliding Mode Controller (ANF-SMC) to control speed, electromagnetic torque (EMT), Stator Current, and Back EMF using PMBLDCmotor(PMBLDCM) in Electric Propulsion of Electric Vehicles

Adaptive Neuro-Fuzzy Sliding Mode Controller (ANF-SMC) to control speed, electromagnetic torque (EMT), Stator Current, and Back EMF using PMBLDCmotor(PMBLDCM) in Electric Propulsion of Electric Vehicles

Novel Design and Control of a Crank-Slider Series Elastic Actuated Knee Exoskeleton for Compliant Human–Robot Interaction

The lower-limb assist exoskeleton plays the role of torque assiting and compliant tracking for wearers to perform tasks. Accurate torque generation, backdrivability performance, low output impedance, and hardware compactness are essential factors for lower-limb exoskeleton to achieve better compliant physical interaction. This research studies a crank-slider series elastic actuator (CS-SEA) that can be used as a compact exoskeleton joint module. The device has a unique crank slider mechanism, and a set of linear springs are equipped inside the slider to guarantee the nonlinear stiffness of its physical impedance so that the torque effect can be improved and a high level of transparency can be achieved. The RBF-based sliding mode controller is chosen as the output torque controller of the exoskeleton, and the adaptive neuro-fuzzy sliding mode control law is designed and its stability is verified. The precise output force control performance of CS-SEA is verified by experiments. The actuator is incorporated into a knee exoskeleton prototype and was worn by the subjects. The experimental results demonstrate the precision of the compliant transparent and torque assisting control while interacting with the human wearer.

Design of Neuro Fuzzy Sliding Mode Controller for Active Magnetic Bearing Control System

Design of Neuro Fuzzy Sliding Mode Controller for Active Magnetic Bearing Control System

Support Value-Based NFSMC for Wheeled Mobile Robot Path Tracking in Unknown Environments

Mobile robot navigation is an obscure condition that plays a vital role in different applications such as military purposes, navy, etc. now a day's lot of problems occur during navigation. To solve the navigation problem an RGB-Depth sensor along with support value-based neuro-fuzzy sliding mode controller techniques (SVB-NFSMC) are proposed. The RGB-Depth sensor is used to estimate the depth map using the linear coefficients along with the bilateral filter. Then the angular and linear velocity is calculated to define the angular position and the object movement. Then the calculation of support value is based on the above angular and linear estimation values. Here the depth map and support value as a training data set input are given to the controller. Subsequently, the sliding mode controller provides the guiding commands in terms of guidance law, control law to the robot system. The ANFIS and the GWO algorithm are used to optimize the parameters is given to the controller then the Lyapunov function is used to analyze the stability of the system. Finally, compare the proposed work with the existing AKH-NFIS and the other SMC methods provides better outcomes.

Adaptive Backstepping Hybrid Fuzzy Sliding Mode Control for Uncertain Fractional-Order Nonlinear Systems Based on Finite-Time Scheme

A fractional-order integral fuzzy sliding mode control scheme is proposed for a class of uncertain fractional-order nonlinear systems subject to uncertainties and external disturbances. First, in each step, a neuro-fuzzy network system is developed to approximate the uncertain nonlinear function existing in fractional-subsystem and a fractional sliding mode surface is presented. Second, based on the fractional Lyapunov stability theory and the finite-time stability theory, a fractional adaptive backstepping neuro-fuzzy sliding mode controller is designed to drive the state trajectories of fractional-order systems to the prescribed sliding mode surface. Meanwhile, the finite-time stability of the fractional-order closed-loop system is proved. At last, three numerical examples are given to illustrate the effectiveness of the proposed control method.

Development and implementation of induction motor drive using sliding-mode based simplified neuro-fuzzy control

This paper develops a sliding-mode based simplified structure of neuro-fuzzy speed and torque compensator incorporated with an induction motor (IM) drive deploying feedback linearization (FBL). The intuitive linearization technique with the proposed simplified structure neuro-fuzzy sliding-mode control (NFSMC) considerably improves the torque and speed responses under system uncertainty and outer load disturbance, giving optimal system performance. This proposed technique also has high computational efficiency due to single error input over conventional one and thus can easily be applied for industrial uses. The parameter tuning of the simplified neuro-fuzzy control (NFC) is done by sliding-mode control (SMC) based adaptive mechanism. The proposed simplified method based linearized drive is simulated as well as experimentally investigated using low-cost DSP2812. The responses prove that the drive system performance characteristics using proposed simplified NFSMC is well-preserved compared to that of conventional one. Additionally, it provides optimal dynamic performance and is robust in terms of parameter variations and peripheral load disturbance.

Neuro-fuzzy Sliding Mode Controller Based on a Brushless Doubly Fed Induction Generator

The combination of neural networks and fuzzy controllers is considered as the most efficient approach for different functions approximation, and indicates their ability to control nonlinear dynamical systems. This paper presents a hybrid control strategy called Neuro-Fuzzy Sliding Mode Control (NFSMC) based on the Brushless Doubly fed Induction Generator (BDFIG). This replaces the sliding surface of the control to exclude chattering phenomenon caused by the discontinuous control action. This technique offers attractive features, such as robustness to parameter variations. Simulations results of 2.5 KW BDFIG have been presented to validate the effectiveness and robustness of the proposed approach in the presence of uncertainties with respect to vector control (VC) and sliding mode control (SMC). We compare the static and dynamic characteristics of the three control techniques under the same operating conditions and in the same simulation configuration. The proposed controller schemes (NFSMC) are effective in reducing the ripple of active and reactive powers, effectively suppress sliding-mode chattering and the effects of parametric uncertainties not affecting system performance.

Robust Diving Motion Control of an Autonomous Underwater Vehicle Using Adaptive Neuro-Fuzzy Sliding Mode Technique

This paper presents an adaptive neuro-fuzzy sliding mode control (ANFSMC) scheme for diving motion control of an autonomous underwater vehicle (AUV) in the presence of parameter perturbations and wave disturbances. In the derivation of diving motion equations of an AUV, the pitch angle of the vehicle is often assumed to be small in the vertical plane. This is a quite strong restricting condition in underwater operations and may cause serious modeling inaccuracies in AUV's dynamics. The problem of nonlinear uncertain diving behavior with restricting assumption on the pitch angle directly is resolved by a neural network (NN) based equivalent control. The online NN estimator is designed to approximate a part of the equivalent control term containing nonlinear unknown dynamics and external disturbances. Subsequently, corrective control based on an adaptive fuzzy proportional-integral control is applied to eliminate the chattering phenomenon by smoothing the switching signal and also compensate structured uncertainties. The weights of NN are updated such that the corrective control signal of the ANFSMC converges towards zero. The adaptive laws are developed to compute coefficients of PID sliding manifold and adjust the gain of fuzzy switching control. The simulation results are presented to shows the efficacy of the control performance.

Fractional-order adaptive neuro-fuzzy sliding mode H∞ control for fuzzy singularly perturbed systems

This paper investigates the fractional-order (FO) adaptive neuro-fuzzy sliding mode control issue for a class of fuzzy singularly perturbed systems subject to the matched uncertainties and external disturbances. Firstly, a novel FO fuzzy sliding mode surface is presented. Secondly, by introducing an appropriate ε-dependent Lyapunov function, some H∞ performance analysis criteria are given, which also ensure the robust stability of the sliding mode dynamics. Furthermore, a hybrid neuro-fuzzy network system (HNFNS) is introduced to estimate the matched uncertainty. Moreover, an FO adaptive fuzzy sliding mode controller is designed to drive the state trajectories of fuzzy singularly perturbed systems to the predefined FO sliding mode surface within a finite-time. Finally, two verification examples are presented to illustrate the validity of the proposed FO control scheme.

Robust neuro-fuzzy sliding mode control with extended state observer for an electric drive system

The choice of the control techniques has a positive impact on the traction chain particularly disturbance rejection ability and the energy management in the electric vehicle (electric motor, inverter, transmission, ect.). In this paper, a robust neuro-fuzzy-sliding mode control (RNFSMC) with extended state observer (ESO) technique is applied on the traction chain of the electric vehicle (Permanent magnet synchronous motor PMSM, Inverter, Transmission). However, most of the existing strategies of control that are applied on the traction chain lead to chattering phenomena, reducing the electric motor performance and disturbance rejection ability without forgetting the bad energy management on board the electric vehicle. To further enhance the performance of the traction chain, a hybrid control scheme is used to severally decrease the chattering phenomena in the PMSM electric motor and evolve the disturbance rejection ability which employs two types of controllers: Neuro-fuzzy sliding mode control on the direct current loop and ESO controller on both speed, and quadrature current loops taking into account the dynamic of the vehicle. Simulations by Matlab/Simulink are used to indicate the validity of the planed scheme on the closed-loop system. The simulation results show the effectiveness of the proposed control strategy with desired tracking accuracy.

Design and realization of an auto-tuned modified neuro-fuzzy sliding-mode-based IM drive deploying feedback linearization

ABSTRACTThis paper employs an intuitive feedback linearization (FBL) controlled induction motor (IM) drive incorporated with the modified neuro-fuzzy sliding-mode control (NFSMC) based speed and torque compensators. The proposed method substantially reduces the torque and speed chattering with the optimal drive performance under system uncertainties and disturbance. An intuitive feedback technique-based linearization of IM is designed and simulated in the stationary reference frame. The modified neuro-fuzzy control (NFC) has the benefit of enhanced computational efficiency over classical NFC as the single input introduced here as an error instead of two inputs error and change in error as in classical NFC. Therefore, it is suitable for real-time applications. The parameters of the simple modified NFC is updated by an adaptive mechanism based on sliding-mode control (SMC). The effectiveness of the proposed method using FBL-based IM drive is verified in simulation as well as experiment and is evident from the comparative results that the system performance is not declined using proposed single-input simple NFSMC as compared to the conventional two-input NFSMC, rather it shows enhanced performance over PI-controller based drive. Extensive experimental results have been provided to justify the potentiality of the proposed techniques using DSP2812.

Electronic Differential and Neuro-Fuzzy Sliding Mode Control with Extended State Observer for an Electric Vehicle System

In this paper a neuro-fuzzy-sliding mode control (NFSMC) with extended state observer (ESO) technique; is designed to guarantee the traction of an electric vehicle with two distinct permanent magnet synchronous motor (PMSM). Each PMSM systems (source-convertermotor) are attached to an electronic differential (ED), in order to adjust the senses of direction of the vehicle, and sustain a stable speed by adapting the difference in velocity of each motor-wheel according to the direction in the case of a turn. Two types of controllers are employed by a hybrid control scheme to assure the control and the performance of the vehicle. This hybrid control scheme guarantees the stability of the vehicle by ED, reduces the chattering phenomena in the PMSM electric motor, and improves the disturbance rejection ability which employs tow types of controllers. The neuro-fuzzy sliding mode control on the direct current loop and ESO controller on the speed loop, and the quadratic current loop; taking into account the dynamic of the vehicle. Simulation runs under Matlab/Simulink to assess the efficiency, and strength of the recommended control method on the closed loop system.

Development of a hybrid fuel cell system operated simplified neuro-fuzzy sliding-mode control based IM drive deploying linearization approach: An effort to enhance the performance

This article focuses on the design and implementation of a hybrid fuel cell supply system to deliver the power demanded by the feedback linearization (FBL) based induction motor (IM) drive. The proposed modified simple hybrid neuro-fuzzy sliding-mode control (NFSMC) with intuitive FBL substantially reduces torque chattering and improves speed response, giving optimal drive performance under system uncertainties and disturbances. This novel technique also has the benefit of reduced computational burdens by improving computational efficiency over conventional NFSMC and thus suitable for real-time industrial applications. The parameters of the modified neuro-fuzzy control are tuned by an adaptive mechanism based on sliding-mode control. A fuel cell stack with a dc/dc boost converter is considered here as a separate external source during interruption of main supply for maintaining the supply to the motor drive control through the inverter, thereby reducing the burden and average rating of the inverter. A rechargeable battery used as an energy storage supplements the fuel cell during different operating conditions of the drive system. The effectiveness of the proposed method using the fuel cell-based linearized IM drive is investigated in simulation, and the efficacy of the proposed controller is validated by experiment using DSP2812. It is evident from the results that the system provides optimal dynamic performance in terms of remarkably reduced torque ripple, good load disturbance rejection, and reduced speed settling time responses by around 92%, 50%, and 41%, respectively, compared to the PI-controller. The system is also robust in terms of parameter variation and external load.

PSO based neuro fuzzy sliding mode control for a robot manipulator

This paper presents the control strategy of two degrees of freedom (2DOF) rigid robot manipulator based on the coupling of artificial neuro fuzzy inference system (ANFIS) with sliding mode control (SMC). Initially SMC with proportional integral derivative (PID) sliding surface is adapted to control the robot manipulator. The parameters of the sliding surface are obtained by minimizing a quadratic performance indices using particle swarm optimization (PSO). Variations of SMC i.e. boundary sliding mode control (BSMC) and boundary sliding mode control with PID sliding surface (PIDBSMC) are developed for optimized performance index. Finally an ANFIS adaptive controller is proposed to generate the adaptive control signal and found to be more robust with regard to disturbances in input torque.

An adaptive neuro-fuzzy sliding mode controller for MIMO systems with disturbance

This paper introduces the mathematical model of ammonia and urea reactors and suggested three methods for designing a special purpose controller. The first proposed method is Adaptive model predictive controller, the second is Adaptive Neural Network Model Predictive Control, and the third is Adaptive neuro-fuzzy sliding mode controller. These methods are applied to a multivariable nonlinear system as an ammonia–urea reactor system. The main target of these controllers is to achieve stabilization of the outlet concentration of ammonia and urea, a stable reaction rate, an increase in the conversion of carbon monoxide (CO) into carbon dioxide (CO2) to reduce the pollution effect, and an increase in the ammonia and urea productions, keeping the NH3/CO2 ratio equal to 3 to reduce the unreacted CO2 and NH3, and the two reactors' temperature in the suitable operating ranges due to the change in reactor parameters or external disturbance. Simulation results of the three controllers are compared. Comparative analysis proves the effectiveness of the suggested Adaptive neuro-fuzzy sliding mode controller than the two other controllers according to external disturbance and the change of parameters. Moreover, the suggested methods when compared with other controllers in the literature show great success in overcoming the external disturbance and the change of parameters.

Adaptive Neuro-Fuzzy Sliding Mode Control of Multi-Joint Movement Using Intraspinal Microstimulation

During the last decade, intraspinal microstimulation (ISMS) has been proposed as a potential technique for restoring motor function in paralyzed limbs. A major challenge to restoration of a desired functional limb movement through the use of ISMS is the development of a robust control strategy for determining the stimulation patterns. Accurate and stable control of limbs by functional intraspinal microstimulation is a very difficult task because neuromusculoskeletal systems have significant nonlinearity, time variability, large latency and time constant, and muscle fatigue. Furthermore, the controller must be able to compensate the effect of the dynamic interaction between motor neuron pools and electrode sites during ISMS. In this paper, we present a robust strategy for multi-joint control through ISMS in which the system parameters are adapted online and the controller requires no offline training phase. The method is based on the combination of sliding mode control with fuzzy logic and neural control. Extensive experiments on six rats are provided to demonstrate the robustness, stability, and tracking accuracy of the proposed method. Despite the complexity of the spinal neuronal networks, our results show that the proposed strategy could provide accurate tracking control with fast convergence and could generate control signals to compensate for the effects of muscle fatigue.

Sliding mode control and neuro-fuzzy network observer for induction motor in EVs applications

In order to deal with the major problems of electric vehicle (EV) propelled by an induction motor (IM), a neuro-fuzzy sliding mode control was designed. The proposed scheme uses an adaptive observer that is based on a full order model of the IM in indirect vector-controlled drive. Moreover, it is evaluated on an EV global model taking into account the vehicle dynamics, the thermal effect and the parameters variations. The neuro-fuzzy network is used to adaptively adjust the parameters prediction. However, the sliding mode control can offer many good properties such as good performance against unmodelled dynamics, insensitivity to external disturbance rejection and fast dynamic. Simulations results carried out on a test vehicle, show that the proposed controller is superior to PID one at response speed, steady-state tracking error and resisting perturbation whenever driving or braking. This shows that the proposed scheme is good candidate for EV's propulsion.

A decoupled adaptive neuro-fuzzy sliding mode control system to control rotating stall and surge in axial compressors

A decoupled adaptive neuro-fuzzy (DANF) sliding mode control system is proposed to control rotating stall and surge in jet engine compression systems. In this way, on-line learning ability is employed to deal with the parametric uncertainty and disturbance by adjusting the control parameters. The control objective is to drive the system state to the original equilibrium point and it proves that the control system is asymptotically stable.