Neuro- PI controller based model reference adaptive control for nonlinear systems

Prakash, R.; Anita, R.

doi:10.4314/ijest.v3i6.4s

Cited by 7 publications

(8 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, the reliability of the high speed sensor is low when the whole flywheel (including motor) is floating by magnetic bearing in a vacuum tank. To avoid the problems of the speed sensors, sensorless control schemes have been developed with the several implementation methodologies, including the back-EMF method [10], slip frequency calculation method; [11] [12]; speed estimation using state equation [13]; estimation based on slot space harmonic voltages [14]; Kalman filtering techniques [15]; neural network based or Fuzzy-logic based sensorless control [16]; MRAS observer [17]; high frequency injection technique [18] and etc. The main objective of these sensorless speed estimation schemes is to obtain the flywheel speed and position information without the use of an extra sensor.…”

Section: Motivation and Objectivementioning

confidence: 99%

“…Moreover, it requires precise mathematical model, continuous tuning and accurate gain values of proportional (Kp) and integral (Ki ) to achieve high performance drive. It is quite difficult to gain high performance of a sensorless drive using fixed gain values of PI controller, because of continuous variation in the machine parameters and nonlinearities presents in the voltage source inverter [17].…”

Section: The Adaptive Approachmentioning

confidence: 99%

See 1 more Smart Citation

Sensorless speed estimation for long term flywheel energy storage system in standby mode.

Liu¹

2021

Preprint

View full text Add to dashboard Cite

A novel technique for sensorless speed estimation is presented in this thesis for squirrel cage induction machine (SCIM) drived long-term flywheel energy storage system (FESS) in standby mode. The SCIM model for long-term large-capacity FESS is presented. Based on dynamic model , a hybrid rotor flux observer and speed observer are derived. The hybrid rotor flux observer takes advantages of both the current model and voltage model flux observers by seamlessly incorporating these two models together for a better flux estimation performance even at low speed range. The fundamental speed observer is derived from the dynamic model for speed estimation with a fast response time for a tradeoff of the adaptive capabilities. In order to observe the speed in standby mode, a modified field-oriented control (FOC) scheme is presented. The hybrid flux observer and speed observer are tested in association with the modified FOC. The proposed control technique adopts approaches in an effort to minimize the impact generated by the excitation and speed estimation process to the FESS. Simulation and experiments are conducted to verify the feasibility of the proposed speed estimation at the standby mode. It is also observed that a step change of excitation current has a significant impact to the existing FESS. A ramp control for excitation current is added to avoid the possible oscillation of the estimated speed and the disturbance to the FESS. The speed estimation settling time is optimized based on the experiment and simulation.

show abstract

Section: Motivation and Objectivementioning

confidence: 99%

Section: The Adaptive Approachmentioning

confidence: 99%

Sensorless speed estimation for long term flywheel energy storage system in standby mode.

Liu¹

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…MRAC scheme is a direct adaptive method with adjustable controller parameters and an adjusting mechanism. The selection of suitable reference model and ability of learning mechanism determine the performance of MRAC algorithm . The MRAC technique is used by many researchers in the motor drive system …”

Section: Introductionmentioning

confidence: 99%

“…The selection of suitable reference model and ability of learning mechanism determine the performance of MRAC algorithm. [25][26][27][28][29] The MRAC technique is used by many researchers in the motor drive system. [30][31][32][33] In this study, RBF-based MRAC approach has been developed to increase the performance and efficiency of induction motor drive.…”

mentioning

confidence: 99%

Adaptive controller with RBF neural network for induction motor drive

Kılıç

Özçalık

Şit

2017

Int J Numerical Modelling

View full text Add to dashboard Cite

In this paper, the radial basis function neural network‐based model reference adaptive speed control for vector controlled induction motor drive system is presented. The speed control of induction motors is challenging because of their complex mathematical model, non‐linear structure, and time varying dynamics. The radial basis function neural network is used to compensate the non‐linearity which comes from the non‐linear state equations of induction motor model. Neural network parameters are online updated via gradient descent algorithm to minimize the error. The drive system has been tested under various operating conditions. This paper demonstrated benefits of the proposed control approach by comparing the algorithm to conventional PI controllers. The results show that the proposed controller ensures good robustness and stable operation of the system under variable speed and variable loads than the PI controller.

show abstract

“…The strength of WNN approximation capability is realized by combining the theory of wavelets and the ANN effectiveness of utilizing the conventional MRAC scheme to control such nonlinear systems. In order to mitigate this difficulty, many researchers the nonlinear function approximation capability of artificial neural network (ANN) to form a nonlinear ANN-based MRAC scheme to control nonlinear systems [6][7][8][9][10]. Despite this widespread utilization of ANN, recently a more powerful neural network namely the wavelet neural network (WNN), has received extensive attention in the literature, especially in handling various control 14].…”

Section: Introductionmentioning

confidence: 99%

Model Reference Adaptive Control based on a Self-Recurrent Wavelet Neural Network Utilizing Micro Artificial Immune Systems

Dawood¹,

Lutfy²

2017

alkej

View full text Add to dashboard Cite

This paper presents an intelligent model reference adaptive control (MRAC) utilizing a self-recurrent wavelet neural network (SRWNN) to control nonlinear systems. The proposed SRWNN is an improved version of a previously reported wavelet neural network (WNN). In particular, this improvement was achieved by adopting two modifications to the original WNN structure. These modifications include, firstly, the utilization of a specific initialization phase to improve the convergence to the optimal weight values, and secondly, the inclusion of self-feedback weights to the wavelons of the wavelet layer. Furthermore, an on-line training procedure was proposed to enhance the control performance of the SRWNN-based MRAC. As the training method, the recently developed modified micro artificial immune system (MMAIS) was used to optimize the parameters of the SRWNN. The effectiveness of this control approach was demonstrated by controlling several nonlinear dynamical systems. For each of these systems, several evaluation tests were conducted, including control performance tests, robustness tests, and generalization tests. From these tests, the SRWNN-based MRAC has exhibited its effectiveness regarding accurate control, disturbance rejection, and generalization ability. In addition, a comparative study was made with other related controllers, namely the original WNN, the artificial neural network (ANN), and the modified recurrent network (MRN). The results of these comparison tests indicated the superiority of the SRWNN controller over the other related controllers. Keywords: Artificial neural network, micro artificial immune system, model reference adaptive control, self-recurrent wavelet neural network , Wavelet neural network.

show abstract

Neuro- PI controller based model reference adaptive control for nonlinear systems

Cited by 7 publications

References 0 publications

Sensorless speed estimation for long term flywheel energy storage system in standby mode.

Sensorless speed estimation for long term flywheel energy storage system in standby mode.

Adaptive controller with RBF neural network for induction motor drive

Model Reference Adaptive Control based on a Self-Recurrent Wavelet Neural Network Utilizing Micro Artificial Immune Systems

Contact Info

Product

Resources

About