Due to growth of mechanisation and automation, today's industrial systems are becoming more complex. A small breakdown of any non-redundant machine component affects the operation of the entire system. To increase the availability and reliability, automated health monitoring and self-diagnostic capability (SDC) becoming essential to many industrial machineries like pumps, motors, etc. Condition monitoring does not prevent the failure, but it can predict the possibility of future failure by measuring certain machine parameters. Though there are various condition monitoring techniques, vibration analysis and motor current signature analysis (MCSA) are most suitable for detection of faults and abnormalities in machine systems. This work attempts to develop an SDC framework and diagnose the impeller condition of a centrifugal pump using MCSA. Time and frequency domain analyses are done for different impeller conditions of the pump, such as normal impeller and defective impellers. Significant differences are observed and a fault prediction strategy is recommended. Nitaigour P. Mahalik has expertise in the field of distributed control, FDI and soft computing. With 20 years of teaching experiences, he has published about 100 papers, 5 books, and 12 chapters. He has supervised five PhD and 30 MS theses/projects. He is the editor and committee members of several journals. He was the recipient of NOS and Brain-Korea fellowships and member of ISTE, ATMAE, ASABE, and ISA. Keywords

Online fault detection and diagnosis of rotating machinery requires a number of transducers which can be significantly expensive for industrial processes. The sensitivity of various transducers and their appropriate positioning are dependent on different types of fault conditions. It is critical to formulate a method to systematically determine the effectiveness of transducer locations for monitoring the condition of a machine. In this paper, Number of Independent Sources analysis is used as an effective tool for reducing the number of vibration sources within the system which is then followed by Principal Component Analysis to identify the incoherent transducers to be employed for fault detection. This experiment is conducted on a machine fault simulator for unbalanced rotor, 1 misaligned shaft and cracked shaft. The validation of the proposed selection process is illustrated using spectral analysis for each defect.