Intelligent system applied to load torque and efficiency estimation in three-phase induction motors

• Grant number: 18/05214-2
• Support Opportunities: Regular Research Grants
• Start date: September 01, 2018
• End date: February 28, 2021
• Field of knowledge: Engineering - Electrical Engineering - Electrical, Magnetic and Electronic Measurements, Instrumentation
• Principal Investigator: Cleber Gustavo Dias
• Grantee: Cleber Gustavo Dias
• Host Institution: Universidade Nove de Julho (UNINOVE). Campus Vergueiro. São Paulo , SP, Brazil
• Associated researchers: Fabio Henrique Pereira

Abstract

Three-phase induction motors (MIT) with squirrel cage rotor still figure as the main electrical machines in the industrial environment. Such equipment is widely used in a wide variety of applications, and is often operated under low load conditions, i.e., undersized, or even above the manufacturer specifications, thus oversized. In the last decades, numerous works have been devoted to the study and development of new techniques capable of estimating not only the load torque, but also the MIT's efficiency. However, state-of-the-art solutions still offer some important limitations, such as the need for mechanical coupling of a torquemeter to the motor shaft, the use of complex mathematical models and / or knowledge of the parameters that make up the machine's equivalent electrical circuit. In addition, such studies do not take into account the fact that MIT can operate powered below or above its rated voltage, as well as in faulted conditions, such as broken rotor bars that form the rotor structure of the motor. In this sense, the present research proposes an intelligent approach, using at least one artificial intelligence technique capable of estimating the torque and the performance of a MIT in real time, from a dedicated hardware and software. The proposal is also to investigate variations in load torque on the motor shaft, when subjected to fluctuations in its supply voltage (sub and overvoltage), and also in the condition of broken bars with the rotor end-ring. The validation of the present study will be carried out from the experimental data collected from the apparatus to be assembled, consisting of a three-phase 7.5 kW motor, a dynamic eddy current brake (Foucault), a load cell and a voltage variator. (AU)

Scientific publications

(4)

(References retrieved automatically from Web of Science and SciELO through information on FAPESP grants and their corresponding numbers as mentioned in the publications by the authors)

DIAS, CLEBER GUSTAVO; DA SILVA, LUIZ CARLOS; LUZ ALVES, WONDER ALEXANDRE. A Histogram of Oriented Gradients Approach for Detecting Broken Bars in Squirrel-Cage Induction Motors. IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT, v. 69, n. 9, p. 6968-6981, SEPT 2020. (16/02547-5, 16/02525-1, 18/05214-2)

DIAS, CLEBER GUSTAVO; DA SILVA, LUIZ CARLOS; CHABU, IVAN EDUARDO. Fuzzy-Based Statistical Feature Extraction for Detecting Broken Rotor Bars in Line-Fed and Inverter-Fed Induction Motors. ENERGIES, v. 12, n. 12, JUN 2 2019. (16/02525-1, 18/05214-2)

DIAS, CLEBER GUSTAVO; RODRIGUES, KESSIA LUCAS; MENEGASSE, NATAN COLOMBO; ALVES, WONDER ALEXANDRE LUZ; DA SILVA, LUIZ CARLOS. Histogram of Oriented Gradients for Rotor Speed Estimation in Three-Phase Induction Motors. IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT, v. 72, p. 11-pg., 2023-01-01. (18/05214-2, 16/02525-1)

DIAS, CLEBER GUSTAVO; DA SILVA, LUIZ CARLOS. Induction Motor Speed Estimation Based on Airgap Flux Measurement Using Hilbert Transform and Fast Fourier Transform. IEEE SENSORS JOURNAL, v. 22, n. 13, p. 10-pg., 2022-07-01. (18/05214-2, 16/02525-1)