Novel technique for precise derating torque of induction motors using ANFIS

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F61989100%3A27730%2F25%3A10257452" target="_blank" >RIV/61989100:27730/25:10257452 - isvavai.cz</a>

Výsledek na webu

<a href="https://www.nature.com/articles/s41598-025-92821-z" target="_blank" >https://www.nature.com/articles/s41598-025-92821-z</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1038/s41598-025-92821-z" target="_blank" >10.1038/s41598-025-92821-z</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Novel technique for precise derating torque of induction motors using ANFIS

Popis výsledku v původním jazyce

Induction motors (IMs), as essential components in industrial operations, are subject to various operational abnormalities, such as voltage unbalance, harmonic distortions, under/over voltage supply, and ambient temperature variations. These factors necessitate the de-rating of torque to ensure motor reliability, efficiency, and safe operation within rated power loss limits. Traditional methods for estimating de-rated torque often involve complex and time-intensive calculations, creating challenges in real-time applications. To address these limitations, this manuscript introduces the Adaptive Neuro-Fuzzy Inference System (ANFIS) as a robust predictive tool for de-rated torque estimation under abnormal conditions. This study defines and quantifies main de-rating factors (Dfs), including voltage unbalance, harmonic distortions, and temperature rise, employing MATLAB/Simulink simulations for performance analysis. The proposed ANFIS controller integrates neural networks and fuzzy logic, enabling efficient evaluation of de-rated torque by dynamically adjusting to real-time operating conditions. Validation of the ANFIS predictions against Simulink outcomes highlights its reliability and accuracy, with minimal deviations observed. Results reveal the significant impact of DFs on induction motor (IM) performance. Voltage unbalance and harmonic distortions emerged as primary contributors to reduced torque output, while temperature rise exacerbates power losses and thermal stress on IM components. By mitigating the need for extensive calculations, ANFIS simplifies the process of assessing torque de-rating and ensures rapid, precise predictions. ANFIS controller is trained offline to assess the de-rated torque of the IM under different operating conditions. The results from this training have been validated against Simulink outcomes, confirming the reliability and accuracy of the ANFIS technique. This research advances the understanding of IM performance under non-ideal conditions, offering a practical framework for de-rating torque evaluation and management. The integration of ANFIS as a control mechanism not only optimizes motor efficiency but also extends operational longevity, underscoring its potential for real-world industrial applications.

Název v anglickém jazyce

Novel technique for precise derating torque of induction motors using ANFIS

Popis výsledku anglicky

Induction motors (IMs), as essential components in industrial operations, are subject to various operational abnormalities, such as voltage unbalance, harmonic distortions, under/over voltage supply, and ambient temperature variations. These factors necessitate the de-rating of torque to ensure motor reliability, efficiency, and safe operation within rated power loss limits. Traditional methods for estimating de-rated torque often involve complex and time-intensive calculations, creating challenges in real-time applications. To address these limitations, this manuscript introduces the Adaptive Neuro-Fuzzy Inference System (ANFIS) as a robust predictive tool for de-rated torque estimation under abnormal conditions. This study defines and quantifies main de-rating factors (Dfs), including voltage unbalance, harmonic distortions, and temperature rise, employing MATLAB/Simulink simulations for performance analysis. The proposed ANFIS controller integrates neural networks and fuzzy logic, enabling efficient evaluation of de-rated torque by dynamically adjusting to real-time operating conditions. Validation of the ANFIS predictions against Simulink outcomes highlights its reliability and accuracy, with minimal deviations observed. Results reveal the significant impact of DFs on induction motor (IM) performance. Voltage unbalance and harmonic distortions emerged as primary contributors to reduced torque output, while temperature rise exacerbates power losses and thermal stress on IM components. By mitigating the need for extensive calculations, ANFIS simplifies the process of assessing torque de-rating and ensures rapid, precise predictions. ANFIS controller is trained offline to assess the de-rated torque of the IM under different operating conditions. The results from this training have been validated against Simulink outcomes, confirming the reliability and accuracy of the ANFIS technique. This research advances the understanding of IM performance under non-ideal conditions, offering a practical framework for de-rating torque evaluation and management. The integration of ANFIS as a control mechanism not only optimizes motor efficiency but also extends operational longevity, underscoring its potential for real-world industrial applications.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

20200 - Electrical engineering, Electronic engineering, Information engineering

Projekt

<a href="/cs/project/TN02000025" target="_blank" >TN02000025: Národní centrum pro energetiku II</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2025

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

Scientific Reports

ISSN

2045-2322

e-ISSN

2045-2322

Svazek periodika

15

Číslo periodika v rámci svazku

1

Stát vydavatele periodika

US - Spojené státy americké

Počet stran výsledku

21

Strana od-do

nestránkováno

Kód UT WoS článku

001443934300042

EID výsledku v databázi Scopus

—