Abstract
-- In general, induction motors predictive maintenance is well suited for small to large-scale industries to minimize failure, maximize performance, and improve reliability. The vibration of an induction motor was investigated in this paper in order to gather precise details that can be used to forecast motor bearing failure. With this in view, an induction motor carrying fault detection scheme has been attempted. machine learning algorithms in addition to wavelet transform (WT) and fast fourier transform (FFT), an advanced signal processing technique, are used in this study to analyze frame vibrations during initialization. the Internet of Things (IoT) is at the core of today's accelerated technological growth. A large number of items are interconnected efficiently, particularly in industrial-automation, resulting in condition and monitoring to boost efficiency to capture and process the parameters of induction motor, the proposed approach uses an IoT-based platform. The details gathered can be saved in the cloud platform and viewed via a web page.
Highlights
T HE induction motors are workhorses of manufacturing industry, are subjected to a variety of inappropriate stresses during their working lives, leading to faults and setbacks [1]
In a modern extraction of the signal function and the method of fault detection for the low-speed machinery fault diagnosis, a statistical filter and wavelet package transform (WPT) are mixed with the hold of moving peak technique has been proposed to extract features of the fault signal, and specific symptom parameters for bearing diagnostic in frequency-domain are described that are sensitive to bearing fault diagnosis [7]
This paper begins by providing a brief overview of the vibration signal fault diagnostic mechanism by the using of Discrete Wavelet Transform and Support Victor Machine analysis, followed by an introduction to the modern standard architecture bearing fault
Summary
T HE induction motors are workhorses of manufacturing industry, are subjected to a variety of inappropriate stresses during their working lives, leading to faults and setbacks [1]. The use of the Discrete Wavelet Transform and Fast Fourier Transform theories to calculate the simple bearing defect frequencies' amplitude in the vibration signal of a rotating system has been proposed [8]. These parameters were used by Neural Fuzzy Inference System the Adaptive ANFIS to facilitate the fault catching and diagnostic method. This paper begins by providing a brief overview of the vibration signal fault diagnostic mechanism by the using of Discrete Wavelet Transform and Support Victor Machine analysis, followed by an introduction to the modern standard architecture bearing fault. Through using (SVM) as a classifier of fault to classify device defects [13]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
