Title :
External fault identification experienced by 3-phase induction motor using PSVM
Author :
Mittal, A.P. ; Malik, Hasmat ; Rastogi, Saarang ; Talur, Vihan
Author_Institution :
Dept. of Instrum. & Control Eng., Netaji Subhas Inst. of Technol. (NSIT), New Delhi, India
Abstract :
Fault diagnosis and condition assessment (FDCA) of rotating machines becomes important due to the age of machine in service. Proper FDCA enhance the machine´s operational life, efficiency and reducing catastrophic failure. This paper describes a realistic FDCA method for three phase induction motors (IMs) using readily available data. External faults experienced by IM are monitored by proximal support vector machine (PSVM) and compared its performance with standard support vector machine and artificial neural network which revealed that PSVM algorithm is quite faster in investigations leading to reduction in computational load. RMS value of 3-phase voltages and currents are utilized as input variable in PSVM model to identify six types of external faults experienced by IM and normal operating (NF) condition. Testing analysis of 160 samples has been carried out to represent the robustness of the investigated seven status conditions for wide changes in operating and loading condition perturbation.
Keywords :
fault diagnosis; induction motors; neural nets; power engineering computing; support vector machines; 3-phase induction motor; FDCA; IM; NF condition; PSVM; artificial neural network; computational load reduction; external fault identification; fault diagnosis and condition assessment; loading condition perturbation; normal operating condition; proximal support vector machine; rotating machines; Accuracy; Artificial neural networks; Fault diagnosis; Induction motors; Mathematical model; Noise measurement; Support vector machines; Induction motor; MCSA; artificial intelligence; fault identification; proximal support vector machine (PSVM);
Conference_Titel :
Power India International Conference (PIICON), 2014 6th IEEE
Print_ISBN :
978-1-4799-6041-5
DOI :
10.1109/34084POWERI.2014.7117762
