Early Detection of Faults in Induction Motors

• Muut tekijät: Morinigo-Sotelo, Daniel (Toimittaja), Romero-Troncoso, Rene (Toimittaja), Pons-Llinares, Joan (Toimittaja)
• Aineistotyyppi: Elektroninen Kirjan osa
• Kieli: englanti
• Julkaistu: Basel MDPI - Multidisciplinary Digital Publishing Institute 2023
• Aiheet: Technology: general issues; History of engineering & technology; fault detection; fault diagnosis; frequency analysis; induction motors; rotating machines; signal processing; spectral analysis; time-frequency decompositions; bearing diagnosis; early damage detection; unlabeled learning; deep learning; dynamic information fusion; induction motor; electric machine; machine learning; supervised learning; data-driven; power connection failures; condition monitoring; induction machines; negative sequence currents; shorted turn faults; phasor compensation; Prony method; broken rotor bar; fast Fourier transform; current signal analysis; artificial intelligence; early detection; fault severity; incipient fault; fault-tolerant control; AC machines; back EMF; feedforward compensation; multiple coupled circuit model; parameter identification; fault classification; measurement techniques; physical variables; signal analysis; ITSC fault; traction motor; apFFT; SVM
• Linkit: DOAB: download the publication; DOAB: description of the publication

In modern industries, induction motors are the backbone of numerous applications, powering everything from manufacturing facilities to transportation systems. While they are known for their reliability, unexpected failures can still occur, leading to increased operational costs, facility damage, or...