Reliable Intelligent Fault Diagnosis System For Electrical Machines
Theory of everything (ToE) Einstein dream: coherent theoretical framework of physics that fully explains and
links together all physical aspects of the universe; Finding a ToE is one of the major unsolved problems in physics.
During the past fifteen years and thanks to computation capacity there has been a substantial amount of research into the
creation of new diagnosis failures techniques and intelligent fault diagnostics methods for electrical machine drives
because of the need to increase reliability and to decrease the possibility of production loss due to machine breakdown.
This paper presents an innovative diagnosis strategy merges several techniques together into a common framework to
achieve these goals and overcome the deficiencies of diagnosis.
A multi-class classifier method based on the statistical Hidden Markov Mode (HMM) and Neural Networks (NN) related
stator fault diagnosis of electrical machines. Current strategy therefore consists of a mix of two levels. The HMM-NN
Reliable Intelligent Fault Diagnosis System is composed of two steps: the Feature Extraction step and the Diagnosis step.
The algorithm of each step is well developed. The model parameters are computed by using the training out puts of the
diagnosis phase. The algorithm estimates the failure state probability for each sampled observation. Time-frequency
features extracted from the machines current is used as the health indicator. The experimental results prove that the
efficiency of the good strategies lies in the integration even different types of machines and equipment parts, and provide
for a consistent diagnostics capability.
Index Terms—Automatic, Electrical Machine, Fault Diagnostics, Induction Motor, Hmm, Multi-Class Classification, Nn,
Time-Frequency, Switched Reluctance Motor