Abstract
Proactive maintenance is important to keep normal operation of plant and equipment systems. A prognosis system for such a system was developed that includes two functions: remote monitoring which detects anomalies by comparing sensor data with a threshold and data-mining which detects anomalies using statistical analysis. This paper proposes an automatic method of setting up criteria for remote monitoring. First, training data is generated based on the result of data-mining. Next, a decision tree is generated by learning the training data, and an if-then rule is extracted. Usefulness of the proposed method was evaluated using 4 data sets including one type of faults. In those data sets, anomalies are recognizable several days before the day of the fault. Two rules extracted using 2 of 4 data sets were different each other but the 2 sensor outputs corresponding with the 2 rules were highly correlated, and the extracted 2 rules can detect anomalies from the other data sets properly.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: The Proceedings of the National Symposium on Power and Energy Systems
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
