Fault Detection and Smart Monitoring of Industrial Fans Based on Vibration Signals

Please enable javascript in your browser.

Moeeni, Hamed | 2014

528 Viewed

Type of Document: M.Sc. Thesis
Language: Farsi
Document No: 46161 (19)
University: Sharif University of Technology
Department: Computer Engineering
Advisor(s): Manzuri Shalmani, Mohammad Taghi
Abstract:
Data Oriented Smart Monitoring for Industrial Machineries include approaches for fault detection and prognosis which only rely on non-stationary signals sampled from sensors and do not rely on physical model of machineries nor expert knowledge. Fault detection is task of determining state of machinery in present moment using past data. But in Prognosis focus is on predicting future state of machinery using past data. Most researches in this category are based on supervised algorithms, but in many applications labeling data is expensive. In this thesis some approaches for semi-superviseddiagnosis, based on markov random walk an K-NN have been implemented, also some improvements for K-NN have been proposed and their performance have been compared. For prognosis, a hybrid combination of hidden semi-markov models and K-NN have been simulated and an improvement for its performance have been proposed
Keywords:
Semi-Supervised Learning ; K-Nearest Neighbor Method ; Hidden Semi-Markov Model ; Semi-Supervised Learning

No TOC