Selected Methods in Angular Rotor Speed Estimation for Induction Motor Drives

Ufnalski, Bartłomiej; Grzesiak, Lech M.

doi:10.1109/eurcon.2007.4400678

Cited by 4 publications

(5 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…By employing the gray box principle, which consisted of exploiting our prior knowledge of the process to control it and make some transformations, we obtained more significant estimator inputs. The transformations used in our case are given in Equations ( 15)-( 20) [25]. These new inputs were obtained from nonlinear transformations of the voltages and currents of the two stator windings [12,24,25]:…”

Section: Gray Box Principlementioning

confidence: 99%

“…The transformations used in our case are given in Equations ( 15)-( 20) [25]. These new inputs were obtained from nonlinear transformations of the voltages and currents of the two stator windings [12,24,25]:…”

Section: Gray Box Principlementioning

confidence: 99%

“…In previous studies, researchers have attempted to enhance the free model approach by incorporating system knowledge and making modifications to estimator inputs to increase their significance. This approach, known as the gray box approach, enables the development of highly accurate estimators [25,26]. The concept of utilizing ML algorithms for designing flux and speed estimators is adopted in this paper.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Hyperparameter Bayesian Optimization of Gaussian Process Regression Applied in Speed-Sensorless Predictive Torque Control of an Autonomous Wind Energy Conversion System

Hamoudi,

Amimeur,

Aouzellag

et al. 2023

Energies

View full text Add to dashboard Cite

This paper introduces a novel approach to speed-sensorless predictive torque control (PTC) in an autonomous wind energy conversion system, specifically utilizing an asymmetric double star induction generator (ADSIG). To achieve accurate estimation of non-linear quantities, the Gaussian Process Regression algorithm (GPR) is employed as a powerful machine learning tool for designing speed and flux estimators. To enhance the capabilities of the GPR, two improvements were implemented, (a) hyperparametric optimization through the Bayesian optimization (BO) algorithm and (b) curation of the input vector using the gray box concept, leveraging our existing knowledge of the ADSIG. Simulation results have demonstrated that the proposed GPR-PTC would remain robust and unaffected by the absence of a speed sensor, maintaining performance even under varying magnetizing inductance. This enables a reliable and cost-effective control solution.

show abstract

Section: Gray Box Principlementioning

confidence: 99%

Section: Gray Box Principlementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Hyperparameter Bayesian Optimization of Gaussian Process Regression Applied in Speed-Sensorless Predictive Torque Control of an Autonomous Wind Energy Conversion System

Hamoudi,

Amimeur,

Aouzellag

et al. 2023

Energies

View full text Add to dashboard Cite

show abstract

“…Artificial neural network (ANN) based flux observer have been used in reference model to detect the thermal variation in stator resistance or in current model to reduce the dependency on the reference model at different operating conditions, through the adaptation of the current model by a PI controller, which can reduce the reliability when operated in hostile environment [15–19]. Artificial intelligence tools, such as fuzzy logic, neural networks and sliding mode control have been used in [20–22] for the speed estimator and the adaptation of the rotor flux estimator. In all these MRAS strategies, the estimation and control methods are developed from the electrical equations of the machine without taking into consideration the mechanical equation and its effect on the overall system under unknown load torques.…”

Section: Introductionmentioning

confidence: 99%

Speed control of sensorless induction generator by artificial neural network in wind energy conversion system

Merabet¹,

Tanvir²,

Beddek

2016

IET Renewable Power Generation

View full text Add to dashboard Cite

This study presents a new strategy for estimating the states (rotor flux and speed) and the load torque to implement a multivariable controller for a sensorless three‐phase squirrel‐cage induction machine in wind energy conversion systems. The multivariable control is carried out using input–output feedback law and its objective is to track profiles of the rotational speed and the rotor flux amplitude. The state estimation considerably improves the performance of rotor flux based model reference adaptive system in the variable speed region of operation. The technique uses Kalman filter as a rotor flux observer and an artificial neural network adaption mechanism to estimate the rotor speed. The state estimation requires only the measurements of the stator voltages and currents. The estimation method, for both states and torque, is not invasive as no mechanical sensors are needed. The wind energy conversion system and the proposed control‐estimation techniques are simulated in Matlab/Simulink software platform and tested using the OPAL‐RT real‐time simulator (OP5600) to verify the accuracy of the proposed control‐estimation method.

show abstract

“…There are no explicit rules on how the spanning vectors should be selected. Nevertheless, their correlation with the ANN desired output signal could serve as one of the hints [33]. Also, auxiliary information on the state of a plant can be passed to the neurocontroller in order to enhance its performance [34].…”

Section: Disturbance Dual Feed-forwardmentioning

confidence: 99%

Repetitive neurocontroller with disturbance feedforward path active in the pass-to-pass direction for a VSI inverter with an output LC filter

Ufnalski

Grzesiak

2016

Bulletin of the Polish Academy of Sciences Technical Sciences

View full text Add to dashboard Cite

Abstract. An enhancement to the previously developed repetitive neurocontroller (RNC) is discussed and investigated in the paper. Originally, the time-base generator (TBG) has been used to produce the only input signal for the neural approximator. The resulting search space makes the dynamic optimization problem (DOP) of shaping the control signal solvable with the help of a function approximator such as the feed-forward neural network (FFNN). The plant under consideration, i.e. a constant-amplitude constant-frequency voltage-source inverter (CACF VSI) with an output LC filter, is assumed to be equipped with the disturbance load current sensor to enable implementation of the disturbance feed-forward (pDFF) path as a part of the non-repetitive subsystem acting in the along the pass p-direction. An investigation has been undertaken to explore potential benefits of using this signal also as an additional input for the RNC to augment the approximation space and potentially enhance the convergence rate of the real-time search process. It is numerically demonstrated in the paper that the disturbance feed-forward path active in the pass-to-pass k-direction (kDFF) improves the dynamics of the repetitive part as well indeed.

show abstract

Selected Methods in Angular Rotor Speed Estimation for Induction Motor Drives

Cited by 4 publications

References 22 publications

Hyperparameter Bayesian Optimization of Gaussian Process Regression Applied in Speed-Sensorless Predictive Torque Control of an Autonomous Wind Energy Conversion System

Hyperparameter Bayesian Optimization of Gaussian Process Regression Applied in Speed-Sensorless Predictive Torque Control of an Autonomous Wind Energy Conversion System

Speed control of sensorless induction generator by artificial neural network in wind energy conversion system

Repetitive neurocontroller with disturbance feedforward path active in the pass-to-pass direction for a VSI inverter with an output LC filter

Contact Info

Product

Resources

About