Fault detection and diagnosis of induction motors based on hidden Markov model

2012 ◽  
Author(s):  
A. Soualhi ◽  
G. Clerc ◽  
H. Razik ◽  
A. Lebaroud
Keyword(s):  
Fault Detection ◽  
Markov Model ◽  
Hidden Markov Model ◽  
Induction Motors ◽  
Hidden Markov ◽  
Fault Detection And Diagnosis ◽  
Detection And Diagnosis

A hybrid hidden Markov model towards fault detection of rotating components

2016 ◽  
Vol 23 (19) ◽  
pp. 3175-3195 ◽  
Author(s):  
Ayan Sadhu ◽  
Guru Prakash ◽  
Sriram Narasimhan
Keyword(s):  
Fault Detection ◽  
Markov Model ◽  
Hidden Markov Model ◽  
Time Scale ◽  
Hidden Markov ◽  
Energy Operator ◽  
Fault Classification ◽  
Multiple Faults ◽  
Condition Indicators ◽  
Model Based

A robust hybrid hidden Markov model-based fault detection method is proposed to perform multi-state fault classification of rotating components. The approach presented in this paper enhances the performance of the standard hidden Markov model (HMM) for fault detection by performing a series of pre-processing steps. First, the de-noised time-scale signatures are extracted using wavelet packet decomposition of the vibration data. Subsequently, the Teager Kaiser energy operator is employed to demodulate the time-scale components of the raw vibration signatures, following which the condition indicators are calculated. Out of several possible condition indicators, only relevant features are selected using a decision tree. This pre-processing improves the sensitivity of condition indicators under multiple faults. A Gaussian mixing model-based hidden Markov model (HMM) is then employed for fault detection. The proposed hybrid HMM is an improvement over traditional HMM in that it achieves better separation of the feature space leading to more robust state estimation under multiple fault states and measurement noise scenarios. A simulation employing modulated signals and two experimental validation studies are presented to demonstrate the performance of the proposed method.

Detection and Diagnosis of Broken Rotor Bars in Induction Motors Using the Fuzzy Min-Max Neural Network

2012 ◽  
Vol 3 (1) ◽  
pp. 44-55 ◽  
Author(s):  
Manjeevan Seera ◽  
Chee Peng Lim ◽  
Dahaman Ishak
Keyword(s):  
Neural Network ◽  
Fault Detection ◽  
Induction Motor ◽  
Induction Motors ◽  
Fault Detection And Diagnosis ◽  
Broken Rotor Bars ◽  
Power Spectral ◽  
Motor Current Signature Analysis ◽  
Detection And Diagnosis ◽  
Current Signatures

In this paper, a fault detection and diagnosis system for induction motors using motor current signature analysis and the Fuzzy Min-Max (FMM) neural network is described. The finite element method is first employed to generate experimental data for predicting the changes in stator current signatures of an induction motor due to broken rotor bars. Then, a series real laboratory experiments is for broken rotor bars detection and diagnosis. The induction motor with broken rotor bars is operated under different load conditions. In all the experiments, the FMM network is used to learn and distinguish between normal and faulty states of the induction motor based on the input features extracted from the power spectral density. The experimental results positively demonstrate that the FMM network is useful for fault detection and diagnosis of broken rotor bars in induction motors.

Sign in / Sign up

Export Citation Format

Share Document