Adaptive Sliding-Mode Neuro-Fuzzy Control of the Two-Mass Induction Motor Drive Without Mechanical Sensors

In this paper, the concept of a model reference adaptive control of a sensorless induction motor (IM) drive with elastic joint is proposed. An adaptive speed controller uses fuzzy neural network equipped with an additional option for online tuning of its chosen parameters. A sliding-mode neuro-fuzzy controller is used as the speed controller, whose connective weights are trained online according to the error between the estimated motor speed and the speed given by the reference model. The speed of the vector-controlled IM is estimated using the $hbox{MRAS}^{rm CC}$ rotor speed and a flux estimator. Such a control structure is proposed to damp torsional vibrations in a two-mass system in an effective way. It is shown that torsional oscillations can be successfully suppressed in the proposed control structure, using only one basic feedback from the motor speed given by the proposed speed estimator. Simulation results are verified by experimental tests over a wide range of motor speed and drive parameter changes.      

Control of the Drive System With Stiff and Elastic Couplings Using Adaptive Neuro-Fuzzy Approach

In the paper a robust control system with the fuzzy-neural network is proposed. A model reference adaptive control system is applied to the one- and two-mass systems. Different aspects of application of the examined control structure are discussed. The influence of the number of neuro-fuzzy controller (NFC) rules to the drive system performance is shown. The impact of the electromagnetic torque limit to the adaptive structure stability is discussed. Further, the comparison of the dynamical characteristics of the different NFC structures is done. The control structure with constant and changeable parameters of the adaptive rule is also examined. The torsional vibration suppression in the two-mass system is obtained in the developed adaptive structure with only one basic feedback from the motor speed     

Fuzzy adaptive vector control of induction motor drives

This paper deals with the design and experimental realization of a model reference adaptive control (MRAC) system for the speed control of indirect field-oriented (IFO) induction motor drives based on using fuzzy laws for the adaptive process and a neuro-fuzzy procedure to optimize the fuzzy rules. Variation of the rotor time constant is also accounted for by performing a fuzzy fusion of three simple compensation strategies. A performance comparison between the new controller and a conventional MRAC control scheme is carried out by extensive simulations confirming the superiority of the proposed fuzzy adaptive regulator. A prototype based on an induction motor drive has been assembled and used to practically verify the features of the proposed control strategy     

A simple direct-torque neuro-fuzzy control of PWM-inverter-fedinduction motor drive

In this paper, the concept and implementation of a new simple direct-torque neuro-fuzzy control (DTNFC) scheme for pulsewidth-modulation-inverter-fed induction motor drive are presented. An adaptive neuro-fuzzy inference system is applied to achieve high-performance decoupled flux and torque control. The theoretical principle and tuning procedure of this method are discussed. A 3 kW induction motor experimental system with digital signal processor TMS 320C31-based controller has been built to verify this approach. The simulation and laboratory experimental results, which illustrate the performance of the proposed scheme, are presented. Also, nomograms for controller design are given. It has been shown that the simple DTNFC is characterized by very fast torque and flux response, very-low-speed operation, and simple tuning capability     

Fuzzy adaptive speed control of a permanent magnet synchronous motor

A fuzzy adaptive speed controller is proposed for a permanent magnet synchronous motor (PMSM). The proposed fuzzy adaptive speed regulator is insensitive to model parameter and load torque variations because it does not need any accurate knowledge about the motor parameter and load torque values. The stability of the proposed control system is also proven. The proposed adaptive speed regulator system is implemented by using a TMS320F28335 floating point DSP. Simulation and experimental results are presented to verify the effectiveness of the proposed fuzzy adaptive speed controller under uncertainties such as motor parameter and load torque variations using a prototype PMSM drive system.     

Decoupled stator-flux-oriented induction motor drive with fuzzyneural network uncertainty observer

A stator-flux-oriented induction motor drive using online rotor time-constant estimation with a robust speed controller is introduced in this paper. The estimation of the rotor time constant is made on the basis of the model reference adaptive system using an energy function. The estimated rotor time-constant is used in the current-decoupled controller, which is designed to decouple the torque and flux in the stator-flux-field-oriented control. Moreover, a robust speed controller, which is comprised of an integral-proportional speed controller and a fuzzy neural network uncertainty observer, is designed to increase the robustness of the speed control loop. The effectiveness of the proposed control scheme is demonstrated by simulation and experimental results     

Performance Improvement of Industrial Drives With Mechanical Elasticity Using Nonlinear Adaptive Kalman Filter

This paper deals with the application of the adaptive control structure for torsional vibration suppression in the drive system with an elastic coupling. The proportional-integral speed controller and gain factors of two additional feedback loops, from the shaft torque and load side speed, are tuned on-line according to the changeable load side inertia. This parameter, as well as other mechanical variables of the drive system (load side speed, torsional and load torques), are estimated with the use of the developed nonlinear extended Kalman filter (NEKF). The initial values of the Kalman filter covariance matrices are set using the genetic algorithm. Then, to ensure the smallest state and parameter estimation errors, the on-line adaptation law for the chosen element of the state covariance matrix of the NEKF is proposed. The described control strategy is tested in an open and a closed-loop control structure. The simulation results are confirmed by laboratory experiments.     

一种新颖的基于内模电流控制的矢量控制系统

无速度传感器矢量控制系统中存在两个关键性的问题，即速度辨识的稳定性问题和控制器结构问题。本文提出一种新型的基于模型参考自适应的内模电流控制的矢量控制系统。首先，利用MRAS理论，保证了速度辨识的全局稳定性。然后通过内模控制实现动态解耦，克服了PI控制不能动态解耦和其他解耦方法中对参数敏感的问题。仿真结果表明：系统对参数变化具有较强的鲁棒性，取得较好的解耦效果和系统控制性能。     

Neuro-Fuzzy Dynamic-Inversion-Based Adaptive Control for Robotic Manipulators—Discrete Time Case

In this paper, we present a stable discrete-time adaptive tracking controller using a neuro-fuzzy (NF) dynamic-inversion for a robotic manipulator with its dynamics approximated by a dynamic T-S fuzzy model. The NF dynamic-inversion constructed by a dynamic NF (DNF) system is used to compensate for the robot inverse dynamics for a better tracking performance. By assigning the dynamics of the DNF system, the dynamic performance of a robot control system can be guaranteed at the initial control stage, which is very important for enhancing system stability and adaptive learning. The discrete-time adaptive control composed of the NF dynamic-inversion and NF variable structure control (NF-VSC) is developed to stabilize the closed-loop system and ensure the high-quality tracking. The NF-VSC enhances the stability of the controlled system and improves the system dynamic performance during the NF learning. The system stability and the convergence of tracking errors are guaranteed by the Lyapunov stability theory, and the learning algorithm for the DNF system is obtained thereby. An example is given to show the viability and effectiveness of the proposed control approach     

New robust adaptive control algorithm for high-performance ACdrives

This paper presents a new robust structure for a model reference adaptive control (MRAC) controller for field-oriented-controlled (FOC) drives which requires no prior knowledge of the drive parameters and is guaranteed to provide global asymptotic stability of the closed-loop system. This structure simplifies the design and implementation of the adaptive controller requiring less effort to synthesis than a standard MRAC system. Discussion on theoretical aspects, such as selection of a reference model, stability analysis proof, gain adaptive process, steady-state error elimination, and robustness to unmodeled dynamics are included. The paper describes many practical aspects of the implementation, such as adaptive gain analysis, adaptive rate selection, the gain variation limits, gain windup prevention measure, and initial values. The new robust adaptive controller has been successfully implemented on an FOC drive and experiment results for dynamic tracking, sudden loading and unloading, and gains adaptation under different operation conditions are presented to support the robustness of the proposed controller     

Integrated design of speed-sensorless and adaptive speed controller for a brushless DC motor

The study develops a design of an integrated new speed-sensorless approach that involves a torque observer and an adaptive speed controller for a brushless dc motor (BLDCM). The system is based on the vector control drive strategy. The speed-sensorless approach first employs a load observer to estimate the disturbed load torque, and then the estimated load torque is substituted into the mechanical dynamic equation to determine the rotor speed, and thus develop a speed-sensorless algorithm. Additionally, the mechanical rotor inertia constant and the friction coefficient, which are the inputs of the load observer, are estimated using the recursive least-square rule. Therefore, the proposed speed-sensorless approach is unaffected by the time-variant motor parameters nor is affected by the integrator drift problem. It also has a simpler computing algorithm than the extended Kalman filter for estimating the speed. The modified model reference adaptive system algorithm, an adaptive control algorithm, is adopted as a speed controller of the BLDCM to improve the performance of the speed-sensorless approach. Simulation and experimental results confirm that the performance of the design of a new integrated speed-sensorless approach and the adaptive speed controller is good.     

Adaptive neuro-fuzzy control of a flexible manipulator

This paper describes an adaptive neuro-fuzzy control system for controlling a flexible manipulator with variable payload. The controller proposed in this paper is comprised of a fuzzy logic controller (FLC) in the feedback configuration and two dynamic recurrent neural networks in the forward path. A dynamic recurrent identification network (RIN) is used to identify the output of the manipulator system, and a dynamic recurrent learning network (RLN) is employed to learn the weighting factor of the fuzzy logic. It is envisaged that the integration of fuzzy logic and neural network based-controller will encompass the merits of both technologies, and thus provide a robust controller for the flexible manipulator system. The fuzzy logic controller, based on fuzzy set theory, provides a means for converting a linguistic control strategy into control action and offering a high level of computation. On the other hand, the ability of a dynamic recurrent network structure to model an arbitrary dynamic nonlinear system is incorporated to approximate the unknown nonlinear input–output relationship using a dynamic back propagation learning algorithm. Simulations for determining the number of modes to describe the dynamics of the system and investigating the robustness of the control system are carried out. Results demonstrate the good performance of the proposed control system.     

Lateral stabilization of a four wheel independent drive electric vehicle on slippery roads

In this paper, a new controller is proposed for lateral stabilization of four wheel independent drive electric vehicles without mechanical differential. The proposed controller has three levels including high, medium and low control levels. Desired vehicle dynamics such as reference longitudinal speed and reference yaw rate are determined by higher level of controller. Moreover, using a neural network observer and a fuzzy logic controller, a novel reference longitudinal speed generator system is presented. This system guarantees the vehicle’s stable motion on the slippery roads. In this paper, a new sliding mode controller is proposed and its stability is proved by Lyapunov stability theorem. This sliding mode control structure is faster, more accurate, more robust, and with smaller chattering than classic sliding mode controller. Based on the proposed sliding mode controller, the medium control level is designed to determine the desired traction force and yaw moment. Therefore, suitable wheel forces are calculated. Finally, the effectiveness of the introduced controller is investigated through conducted simulations in CARSIM and MATLAB software environments.     

Fuzzy two-degrees-of-freedom speed controller for motor drives

A fuzzy two-degrees-of-freedom (2-DOF) controller and its application to the speed control of an induction motor drive are presented in this paper. The proposed controller is composed of two fuzzy controllers to obtain good tracking and regulating responses. Unlike the conventional fuzzy controller, the error between the outputs of a reference model and the controlled drive is used to drive the proposed fuzzy controller. The drive rotor speed response can closely follow the trajectory produced by the reference model, and good load speed regulating response can also be obtained simultaneously owing to the possession of two-degrees-of-freedom in structure. Moreover, these performances are rather insensitive to the operating condition changes. The dynamic signal analysis as well as the construction of fuzzy control algorithms are described in detail. Some simulated and measured results are provided to demonstrate the effectiveness of the proposed fuzzy controller     

A VSS speed controller with model reference response for inductionmotor drive

This paper is mainly concerned with the development of a variable-structure system (VSS) controller with model reference speed response for an induction motor drive. An indirect-field-oriented (IFO) induction motor drive is first implemented, and its dynamic model at a nominal operating condition is estimated from measured data. Then, a two-degrees-of-freedom linear model-following controller (2DOFLMFC) is designed to meet the prescribed tracking and load regulation speed responses at the nominal case. As the variations of system parameters and operating condition occur, the prescribed control specifications may not be satisfied further. To improve this, a VSS controller is developed to generate a compensation control signal to reduce the control performance degradation. The proposed VSS controller is easy to implement, since only the output variable is sensed. The existence condition of sliding-mode control is derived, and the chattering suppression during the static period is also considered. Good model-following tracking and load regulation speed responses are obtained by the designed VSS controller. Effectiveness of the proposed controller and the performance of the resulting drive system are confirmed by some simulation and measured results     

An ANFIS controller for the car-following collision preventionsystem

This paper presents a controller based on an adaptive network fuzzy inference system (ANFIS) for the car-following collision prevention system to nonlinearly control the speed of the vehicle. The distance and speed relative to the car in front are measured by a radar sensor and applied to the controller. The output acceleration or deceleration rate of the controller is based on the characteristics of the vehicles. The initial input and output membership functions and 25 rules of ANFIS are constructed by a fuzzy inference system (FIS). The design method of the reference signals, which is used to update on-line the consequent parameters of ANFIS according to recursive least square (RLS) algorithm, are proposed. The presented ANFIS controller can solve the problems of the oscillations for final distance between the leading vehicle (LV) and the following vehicle (FV) and relative speed. The required processing time to achieve safe distance between the LV and the FV is about 7-8 s, which is faster than the other models. The ANFIS controller of the car-following collision prevention system proposed in this paper can provide a safe, reasonable, and comfortable drive     

Development of new training algorithms for neuro-wavelet systems on the robust control of induction servo motor drive

A robust wavelet neural network control (RWNNC) system is proposed to control the rotor position of an induction servo motor drive in this paper. In the proposed RWNNC system, a wavelet neural network controller is the main tracking controller that is used to mimic a computed torque control law, and a robust controller is designed to recover the residual approximation for ensuring the stable control performance. Moreover, to relax the requirement for a known bound on lumped uncertainty, which comprises a minimum approximation error, optimal network parameters and higher order terms in a Taylor series expansion of the wavelet functions, an RWNNC system with adaptive bound estimation was investigated for the control of an induction servo motor drive. In this control system, a simple adaptive algorithm was utilized to estimate the bound on lumped uncertainty. In addition, numerical simulation and experimental results due to periodic commands show that the dynamic behaviors of the proposed control systems are robust with regard to parameter variations and external load disturbance.     

A fault-tolerant control architecture for induction motor drives in automotive applications

This paper describes a fault-tolerant control system for a high-performance induction motor drive that propels an electrical vehicle (EV) or hybrid electric vehicle (HEV). In the proposed control scheme, the developed system takes into account the controller transition smoothness in the event of sensor failure. Moreover, due to the EV or HEV requirements for sensorless operations, a practical sensorless control scheme is developed and used within the proposed fault-tolerant control system. This requires the presence of an adaptive flux observer. The speed estimator is based on the approximation of the magnetic characteristic slope of the induction motor to the mutual inductance value. Simulation results, in terms of speed and torque responses, show the effectiveness of the proposed approach.     

A discrete adaptive field-oriented induction motor drive

A discrete model reference adaptive controller (MRAC) is designed and implemented. This MRAC makes the performance of the field-oriented induction motor drives insensitive to parameter changes. Only the information of the reference model and the plant output are required. Hence, the proposed controller is easy to implement practically. For designing the proposed adaptive controller, the dynamic model of the drive system is estimated from the sampled input-output data using the stochastic modeling technique. The theoretical basis of the adaptive control is derived and simulation is made. The hardware of the drive system and the microprocessor-based adaptive controller are discussed. Some experimental results are given to demonstrate the effectiveness of the proposed controller     

ANFIS based quadrotor drone altitude control implementation on Raspberry Pi platform

The unmanned aerial vehicles can have complicated dynamics and kinematics that governs the flight of such multirotor devices. PID type controllers are one of the most popular approaches with Raspberry Pi 3 platform for stability of the flight. However, in dynamic environment they are limited in performance and response times. The autonomous tuning of the controller parameters according to the state of the environment with assistance of the adaptive neuro-fuzzy inference system is a well known approach. This paper provides implementation details and feasibility of such a controller with Raspberry Pi 3 platform for use in geological wireless sensing environments. The proposed neuro-fuzzy controller is developed for a Raspberry Pi 3 platform and tested on a physical quadrotor drone and compared to the conventional PID controller during flight.