Wyniki wyszukiwania - BazTech

Ograniczanie wyników

Znaleziono wyników: 2

Liczba wyników na stronie

Wyniki wyszukiwania

Sortuj według:

Ogranicz wyniki do:

Unraveling Induction Motor State through Thermal Imaging and Edge Processing : A Step towards Explainable Fault Diagnosis

Piechocki Mateusz, Pajchrowski Tomasz, Kraft Marek, Wolkiewicz Marcin, Ewert Paweł

Eksploatacja i Niezawodność

2023

Vol. 25, no. 3

art. no. 170114

Equipment condition monitoring is essential to maintain the reliability of the electromechanical systems. Recently topics related to fault diagnosis have attracted significant interest, rapidly evolving this research area. This study presents a non-invasive method for online state classification of a squirrel-cage induction motor. The solution utilizes thermal imaging for non-contact analysis of thermal changes in machinery. Moreover, used convolutional neural networks (CNNs) streamline extracting relevant features from data and malfunction distinction without defining strict rules. A wide range of neural networks was evaluated to explore the possibilities of the proposed approach and their outputs were verified using model interpretability methods. Besides, the top-performing architectures were optimized and deployed on resource-constrained hardware to examine the system's performance in operating conditions. Overall, the completed tests have confirmed that the proposed approach is feasible, provides accurate results, and successfully operates even when deployed on edge devices.

Application of Neural Networks and Axial Flux for the Detection of Stator and Rotor Faults of an Induction Motor

Ewert Paweł

Power Electronics and Drives

2019

Vol. 4 (39)

201--213

The paper presents the possibility of using neural networks in the detection of stator and rotor electrical faults of induction motors. Fault detection and identification are based on the analysis of symptoms obtained from the fast Fourier transform of the voltage induced by an axial flux in a measurement coil. Neural network teaching and testing were performed in a MATLAB–Simulink environment. The effectiveness of various neural network structures to detect damage, its type (rotor or stator damage) and damage levels (number of rotor bars cracked or stator winding shorted circuits) is presented.