New condition monitoring techniques for reliably drive systems operation

The dominant application of electronics today is to process information. The computer industry is the biggest user of semiconductor devices and consumer electronics. Due to the successful development of semiconductors, electronic system and controls have gained wide acceptance in power and computing technology and due to the continuous use of drive systems (rotating machines, controlling thyristors and associated electronic components) in industry and in power stations, and the need to keep such systems running reliably, the detection of defects and anomalies is of increasing importance, and on-line monitoring to detect any fault in these systems is now a strong possibility and certainly periodic monitoring of a drive systems in strategic situations. The principal aim of the paper is to use both software and hardware and develop a fault diagnosis knowledge-based system, which will analyze and manipulate the output obtained from sensors using a microcomputer for acquiring the plant condition data and subsequently interpreting them, data collected can be analyzed using suitable computer programs, and any trends can be identified and compared with the knowledge base. The probability of certain condition can then be diagnosed and compared, providing the necessary information on which subsequent decisions can be based and provide any necessary alarms to the operator. To achieve this objective, the simulation and experimental technique considered is to use sensors placed in the wedges closing the stator slots to sense the induced voltage. The induced voltage and for each fault is shown to have a unique voltage pattern, thus, the fault identification through voltage pattern recognition were the basic rules for the development of the knowledge base. The predicted results are verified by measurements on a model system in which known faults can be established.