Sensorless vector-controlled induction motor drives: Boosting performance with Adaptive Neuro-Fuzzy Inference System integrated augmented Model Reference Adaptive System
MethodsX · 2024-12 · 13 · 102992
DOI: 10.1016/j.mex.2024.102992 ↗Kurz gefasst
Übersichtsarbeit in der Zeitschrift MethodsX, 2024-12. Verfasst von Govindharaj I und 7 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science and Engineering, Vel Tech Rangarajan Dr.Sagunthala R&D Institute of Science and Technology, Tamil Nadu 600062, India. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 29 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
The Model Reference Adaptive System (MRAS) is effective for speed control in sensorless Induction Motor (IM) drives, particularly at zero and very low speeds. This study enhances MRAS's resilience and dynamic performance by integrating an Adaptive Neuro-Fuzzy Inference System (ANFIS) controller into sensorless vector-controlled IM drives. The research addresses challenges related to parameter uncertainties, load variations, and external disturbances through the combination of MRAS and ANFIS. The ANFIS controller enhances dynamic performance by adjusting its parameters based on the error between estimated and measured rotor speeds, which improves reference speed tracking and ensures smoother drive operation. This integration of ANFIS with MRAS reduces the sensitivity of the sensorless control system to parameter variations, such as changes in motor parameters or load torque, thereby enhancing system stability. The primary goal is to ma-intain stability and mitigate the impact of parameter variations on the sensorless control system. The proposed MRAS-ANFIS scheme was evaluated using MATLAB and compared with existing systems. Results show that the ANFIS-enhanced MRAS delivers superior dynamic performance and robustness, proving to be an effective solution for applications demanding precise speed control and high reliability. •ANFIS integration for improved control: integrating an Adaptive Neuro-Fuzzy Inference System (ANFIS) with MRAS enhances the dynamic performance and resilience of sensorless Induction Motor (IM) drives, particularly at zero and very low speeds.•Increased stability and robustness: The ANFIS controller adapts to parameter uncertainties, load variations, and disturbances, improving speed tracking and reducing sensitivity to motor parameter changes, thus enhancing system stability.•Superior performance Validated: MATLAB simulations show that the ANFIS-enhanced MRAS outperforms existing systems, offering superior dynamic performance and robustness, making it ideal for precise speed control applications.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Computer Science and Engineering, Vel Tech Rangarajan Dr.Sagunthala R&D Institute of Science and Technology, Tamil Nadu 600062, India.
- School of Computer Science and IT, JAIN (Deemed-to-be University), Karnataka 560069, India.
- Department of Electronics and Communication Engineering, Vel Tech Rangarajan Dr.Sagunthala R&D Institute of Science and Technology, Tamil Nadu 600062, India.
- Department of Artificial Intelligence and Data Science, Vel Tech Rangarajan Dr.Sagunthala R&D Institute of Science and Technology, Tamil Nadu 600062, India.
- Department of Computer Science and Engineering (Artificial Intelligence), Madanapalle Institute of Technology & Science, Andhra Pradesh 517325, India.
- Faculty of Engineering And Technology, Department of Computer Science and Engineering, Annamalai University, Tamil Nadu 608002, India.
Zitieren
APA
I, G., K, D. K., S, B., S, Y., R, A., R, R., G, K., & G, M. (2024). Sensorless vector-controlled induction motor drives: Boosting performance with Adaptive Neuro-Fuzzy Inference System integrated augmented Model Reference Adaptive System. MethodsX, 13, 102992. https://doi.org/10.1016/j.mex.2024.102992
Vancouver
I G, K DK, S B, S Y, R A, R R, et al. Sensorless vector-controlled induction motor drives: Boosting performance with Adaptive Neuro-Fuzzy Inference System integrated augmented Model Reference Adaptive System. MethodsX. 2024;13:102992. doi:10.1016/j.mex.2024.102992
BibTeX
@article{I2024,
author = {I, Govindharaj and K, Dinesh Kumar and S, Balamurugan and S, Yazhinian and R, Anandh and R, Rampriya and G, Karthick and G, Michael},
title = {Sensorless vector-controlled induction motor drives: Boosting performance with Adaptive Neuro-Fuzzy Inference System integrated augmented Model Reference Adaptive System},
journal = {MethodsX},
year = {2024},
volume = {13},
pages = {102992},
doi = {10.1016/j.mex.2024.102992}
}
EUVIMED