Name: Study of Induction Motor Fault Detection and Diagnosis (en Inglés)
SKU: 57662527
Price: 1727.55 MXN
Availability: InStock
Author: Ghate, Vilas N.
ISBN: 9786202803649

portada Study of Induction Motor Fault Detection and Diagnosis (en Inglés)

Study of Induction Motor Fault Detection and Diagnosis (en Inglés)

Formato

Libro Físico

Autor

Vilas N. Ghate

Editorial

LAP Lambert Academic Publishing

Idioma

Inglés

N° páginas

336

Encuadernación

Tapa Blanda

Dimensiones

22.9x15.2x1.9 cm

Peso

0.49 kg.

ISBN13

9786202803649

Categorías

Electricidad, electromagnetismo y magnetismo

Study of Induction Motor Fault Detection and Diagnosis (en Inglés)

Vilas N. Ghate (Autor) · LAP Lambert Academic Publishing · Tapa Blanda

Libro Nuevo Importado

Envío: 18 a 23 días háb.

$ 3,838.99$ 1,727.55

-55%

Costos de importación incluídos en el precio ✅

Libro Nuevo

Quedan 100 unidades

$ 1,727.55

¡Envío Gratis! Llega entre el 30 Sep y el 08 Oct a CUAUHTÉMOC, Ciudad de México. Seleccionar ubicación

Agregar a lista de deseos

Reseña del libro "Study of Induction Motor Fault Detection and Diagnosis (en Inglés)"

In this book, the authors evaluated the performance of the developed ANN based classifiers for detection of four fault conditions, Healthy (H), Interturn short circuit (I), Eccentricity (E). and Both i.e. Interturn and Eccentricity combine (B) of three phase induction motor and examined the results. Instead of current or vibration spectra simple statistical parameters containing fault information is used, which gives the satisfactory results. MLP NN, RBF NN, RBF-MLP Cascade, SOM NN, GFFD NN, and SVM are optimally designed and after completion of the training, the learned network is tested to detect different types of faults. Sensitivity Analysis and Principal Component Analysis (PCA), these two techniques for dimensionality reduction is applied for each network and reduction in complexity is compared. For the comparison two statistical methods CART and D.A. are verified but results are inferior as compared to NN based schemes. Robustness of proposed classifier to the noise is good which is checked by introducing controlled noise, and for training, cross validation and testing experimental real data is used, so this scheme can be suggested for the real world industrial application.