Recurrent fuzzy-neural approach for nonlinear control using dynamic structure learning scheme

This paper presents a recurrent fuzzy neural network (RFNN) controller to provide sensorless speed control for the two-phase linear brushless DC motor. It is not easy to arrange current and speed sensors along the linear motor's required railway. The RFNN controller has the capability of tracing the system dynamics due to the inherent learning function. With the help of RFNN controller, the conventional PID control can be made to provide better performance by tracing the system dynamics. The paper will demonstrate dynamic performance improvement scenarios. The recurrent structure also enhances the conventional fuzzy neural network (FNN) controller with embedded memory function. The results from experimental evaluation indicate that the PID with RFNN controller can provide better performance than the conventional PID controller.

The objective of this study is to control rotational angles of a 3-degree freedom robot for tracking to the reference trajectories. That is a parallel robot, named Delta, with complex movements in shaping, processing with high efficiency, high load capacity, widely used in industry. The PID controller has been successfully developed for the Delta robot. However, when changing the robot’s parameters such as load, input coupling and friction, the PID controller is difficult to archive control criteria. This article proposes and tests a solution to improve the PID controller by combining it with a recurrent fuzzy neural network (RFNN) controller, so-called RFNN-PID controller. In the proposed solution, the PID controller plays the main role of controlling the Delta robot and the RFNN controller takes charge of a supplemental role to gain with the changes of control conditions. The RFNN-PID and PID controllers will be tested in the same conditions in MATLAB/Simulink. Simulations illustrate that the proposed controller is better than the traditional one, obtaining a response time of about 3.9 ± 0.1 (s) without steady-state error.KeywordsDelta robotPIDRecurrent fuzzy neural networkIdentification

This paper develops a design method of recurrent fuzzy neural network (RFNN) control system for multi-input multi-output (MIMO) nonlinear dynamic systerns. This control system consists of a state feedback controller and an RFNN controller. The state feedback controller is a basic stabilizing controller to stabilize the system, and the RFNN controller presents a robust controller to deal with uncertain parts of system dynamics and external disturbances. The adaptive laws of the RFNN parameters are derived based on the Lyapunov synthesis approach and a projection algorithm, so that the stability of the system and convergence of the parameters can be guaranteed. The simulation results for a robotic system and an ecological system confirm the effectiveness of the proposed design method.

A hybrid supervisory control system using a recurrent fuzzy neural network (RFNN) is proposed to control the mover of a permanent magnet linear synchronous motor (PMLSM) servo drive for the tracking of periodic reference inputs. First, the field-oriented mechanism is applied to formulate the dynamic equation of the PMLSM. Then, a hybrid supervisory control system, which combines a supervisory control system and an intelligent control system, is proposed to control the mover of the PMLSM for periodic motion. The supervisory control law is designed based on the uncertainty bounds of the controlled system to stabilize the system states around a predefined bound region. Since the supervisory control law will induce excessive and chattering control effort, the intelligent control system is introduced to smooth and reduce the control effort when the system states are inside the predefined bound region. In the intelligent control system, the RFNN control is the main tracking controller which is used to mimic a idea control law and a compensated control is proposed to compensate the difference between the idea control law and the RFNN control. The RFNN has the merits of fuzzy inference, dynamic mapping and fast convergence speed, In addition, an online parameter training methodology, which is derived using the Lyapunov stability theorem and the gradient descent method, is proposed to increase the learning capability of the RFNN. The proposed hybrid supervisory control system using RFNN can track various periodic reference inputs effectively with robust control performance.

A genetic algorithm (GA) based recurrent fuzzy neural network (RFNN) is proposed to control the mover of a linear induction motor (LIM) servo drive for periodic motion in this paper. The GA is developed to search the optimal weights between the membership layer and the rule layer of RFNN. First, the dynamic model of an indirect field‐oriented LIM servo drive is derived. Then, an on‐line training RFNN with backpropagation algorithm is introduced as the tracking controller. Moreover, to guarantee the global convergence of tracking error, analytical methods based on a discrete‐type Lyapunov function are proposed to determine the varied learning rates of the RFNN. In addition, a real‐time GA is developed to search the optimal weights between the membership layer and the rule layer of RFNN on‐line. The theoretical analyses for the proposed GA‐based RFNN controller are described in detail. Finally, simulated and experimental results show that the proposed controller provides good control performance dynamic characteristics and is robust with regard to plant parameter variations and external load disturbance.

For many years, the control approaches for the dc-dc power converters are limited to PI controller structures. However, it gives the overshoot in output voltage as the rise time of response is reduced. To tackle this problem, an adaptive recurrent fuzzy neural network (ARENN) control system is developed in this paper. The on-line adaptive laws of the ARENN control scheme are derived based on the Lyapunov stability theorem, so that the stability of the system can be guaranteed. Experimental results show that the proposed ARFNN control scheme can achieve good regulation performances.

The nonlinear and time-varying characteristics of the V-belt continuously variable transmission system driven by a permanent magnet synchronous motor (PMSM) are unknown, therefore, improving the control performance of the linear control design is time-consuming. To overcome difficulties in the design of a linear controller for the PMSM servo-driven V-belt continuously variable transmission system with the lumped nonlinear load disturbances, a composite recurrent Laguerre orthogonal polynomial neural network (NN) control system which has online learning capability to respond the nonlinear time-varying system, was developed. The composite recurrent Laguerre orthogonal polynomial NN control system can perform inspector control, recurrent Laguerre orthogonal polynomial NN control which involves an adaptation law, and recouped control which involves an estimation law. Moreover, the adaptation law of online weight parameters in the recurrent Laguerre orthogonal polynomial NN is based on Lyapunov stability theorem. The use of modified particle swarm optimization yielded two optimal learning rates for the weight parameters which helped improve convergence. Finally, comparison of the experimental results of the present study with those of previous studies demonstrated the high control performance of the proposed control scheme.

Compared with the classical linear controller, the nonlinear controller can result better control performance for the nonlinear uncertainties of the continuously variable transmission (CVT) system which is spurred by the synchronous reluctance motor (SynRM). The better control performance obtained by use of the proposed novel mingled reformed recurrent Hermite polynomial neural network (MRRHPNN) control system can be presented dynamic behavior for the nonlinear uncertainties of CVT system. The novel MRRHPNN control system can carry out overlooker control system, reformed recurrent Hermite polynomial neural network control (RRHPNN) with an adaptive law, and reimbursed control with an appraised law. Additionally, in accordance with the Lyapunov stability theorem, the adaptive law in the RRHPNN and the appraised law of the reimbursed control are established. Furthermore, two varied learning rates of two weights for the RRHPNN according to increment-type Lyapunov function are derived to help improving convergence. At last the obtained better control performances by use of the proposed control method are verified through the illustrated results by the comparative experimentations.

A field-programmable gate array (FPGA)-based recurrent wavelet neural network (RWNN) control system is proposed to control the mover position of a linear ultrasonic motor (LUSM) in this study. First, the structure and operating principles of the LUSM are introduced. Since the dynamic characteristics and motor parameters of the LUSM are nonlinear and time-varying, an RWNN controller is designed to improve the control performance for the precision tracking of various reference trajectories. The network structure and its on-line learning algorithm using delta adaptation law of the RWNN are described in detail. Moreover, an FPGA chip is adopted to implement the developed control algorithm for possible low-cost and high-performance industrial applications. Finally, the effectiveness of the proposed control system is verified by some experimental results.

Adaptive growing-and-pruning neural network control for a linear piezoelectric ceramic motor

Because an electric scooter driven by permanent magnet synchronous motor (PMSM) servo-driven system has the unknown nonlinearity and the time-varying characteristics, its accurate dynamic model is difficult to establish for the design of the linear controller in whole system. In order to conquer this difficulty and raise robustness, a novel adaptive modified recurrent Legendre neural network (NN) control system, which has fast convergence and provide high accuracy, is proposed to control for PMSM servo-driven electric scooter under the external disturbances and parameter variations in this study. The novel adaptive modified recurrent Legendre NN control system consists of a modified recurrent Legendre NN control with adaptation law and a remunerated control with estimation law. In addition, the online parameter tuning methodology of the modified recurrent Legendre NN control and the estimation law of the remunerated control can be derived by using the Lyapunov stability theorem and the gradient descent method. Furthermore, the modified recurrent Legendre NN with variable learning rate is proposed to raise convergence speed. Finally, comparative studies are demonstrated by experimental results in order to show the effectiveness of the proposed control scheme.

Because an electric scooter driven by permanent magnet synchronous motor (PMSM) servo system has the unknown nonlinearity and the time-varying characteristics, its accurate dynamic model is difficult to establish for the design of the linear controller in whole system. In order to conquer this difficulty and raise robustness, a novel adaptive recurrent Legendre neural network (NN) control system, which has fast convergence and provide high accuracy, is proposed to control for PMSM servo-drive electric scooter under external torque disturbance in this study. The novel adaptive recurrent Legendre NN control system consists of a recurrent Legendre NN control with adaptation law and a remunerated control with estimation law. In addition, the online parameter tuning methodology of the recurrent Legendre NN control and the estimation law of the remunerated control can be derived by using the Lyapunov stability theorem. Finally, comparative studies are demonstrated by experimental results in order to show the effectiveness of the proposed control scheme.

The purpose of this paper is to investigate and implement a novel approach to learning control for torque-ripple reduction of switched reluctance machines (SRM) using a supervisor hybrid recurrent fuzzy neural network (SHRFNN) control. First, the dynamic models of a SRM drive system are builted though SRM experimental tests and parameters measurements. Then, in order to reduce torque ripple and control robustness, a SHRFNN speed control system that combined supervisor control, RFNN and compensated control is developed to control SRM drive system. The SHRFNN control system produces smooth torque up to the motor base speed. The torque is generated over the maximum positive torque-producing region of a phase. Finally, the effectiveness of the proposed control schemes is demonstrated by experimental results.

On the basis of previous research, This article studies the structure and working principle of recurrent fuzzy neural network. The traditional fuzzy controller is not precise enough, does not have simple algorithm but poor timely traceability. The use of the fuzzy neural network is good for fully integrating the fuzzy control feature and neural network control feature. And we can improve the fuzzy neural network into recurrent fuzzy neural network, and apply this in the power flow control of the power converter. Through simulating and contrasting, the experiments show that it can achieve the UPFC trend of dynamic real-time monitoring, it has better tracking control capability and robustness, and preferable effect of power control.

End milling operations are essential to machine complex-contoured parts which are widely used in automobile and aerospace industries. Controlling the cutting force is important in these operations. But this is a difficult task for a number of reasons. A neural network control scheme is developed in this study to control the average resultant cutting force. The control scheme involves a neural identifier and a neural controller. The neural identifier is trained to represent the process accurately, and the neural controller is trained to give an input to the process which will yield the desired output. Recurrent neural networks are employed for both the neural identifier and neural controller, and training is accomplished using a recursive least squares algorithm. Results validating the methodology are presented for one-dimensional milling.