Eniko Szoke

Dr. Eniko Szoke

orcid

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
13 August 2025 in Applied Sciences
Verified
Journal Article
Open access
PDF file
Eniko SzokeEniko Szoke
Eniko Szoke
CSCsaba Szabo
Csaba Szabo
Lucian Nicolae PintilieLucian Nicolae Pintilie
Lucian Nicolae Pintilie
This paper introduces a speed-sensorless dual-field-oriented control (DFOC) strategy for induction motors (IMs). DFOC combines the advantages or rotor- and stator-field orientation to significantly reduce the parameter sensitivity of the control regarding the generation of the converter control variable. A simplified structure is also proposed, using only two regulators for the flux and speed control, eliminating the two current regulators. Related to sensorless control, the classical adaptation mechanism within an MRAS (model reference adaptive system) observer is replaced with artificial intelligence (AI)-based approaches. Specifically, artificial neural networks (ANNs) and recurrent neural networks (RNNs) are employed for rotor speed estimation. They offer significant advantages in managing complex and nonlinear systems, providing enhanced flexibility and adaptability compared to traditional MRAS methods. The effectiveness of the proposed sensorless control scheme is validated through both simulation and real-time implementation. The paper focuses on the ANN and RNN architectures, as deep learning models, in terms of the reliability and accuracy of rotor speed estimation under various operating conditions.

18 July 2025 in Preprints.org
Verified
Preprint
Open access
PDF file
Eniko SzokeEniko Szoke
Eniko Szoke
CSCsaba Szabo
Csaba Szabo
Lucian Nicolae PintilieLucian Nicolae Pintilie
Lucian Nicolae Pintilie
This paper introduces a speed sensorless Dual Field-Oriented Control (DFOC) strategy for induction motors (IM). DFO combines the advantages or rotor-and stator-field orienta-tion to significantly reduce the parameter sensitivity of the control regarding the generation of the converter control variable. A simplified structure is also proposed, using only two regulators for the flux and speed control, eliminating the two current regulators. Related to sensorless control, the classical adaptation mechanism within the MRAS (Model Reference Adaptive System) observer has been replaced with artificial intelligence (AI)-based approaches. Specifically, artificial neural networks (ANN) and recurrent neural networks (RNN) are employed for rotor speed estimation. The effectiveness of the proposed sensor-less control scheme is validated through both simulation and real-time implementation. The results demonstrate that ANN- and RNN-based observers, as deep learning models, provide reliable and accurate rotor speed estimation under various operating conditions.

1 October 2019
Verified
Conference Paper
Closed access
CSCsaba Szabo
Csaba Szabo
NSNorbert Csaba Szekely
Norbert Csaba Szekely
Eniko SzokeEniko Szoke
Eniko Szoke
VZVlad Zacharias
Vlad Zacharias
Current-feedback modulation based procedures offer the fastest response and provide accurate current control, without tracking errors. The two modulation procedures presented in this paper are working with constant sampling frequency given by a fixed frequency clock signal. Sequential motion of the voltage space phasor can be achieved if the sampling signal is shifted with 1/3 of the sampling period for each phase, that will guarantee only adjacent and zero voltage vector selection. The proposed techniques were tested by simulation as part of a rotor-field oriented vector control structure for a cage induction motor drive.