Abstract
The induced draft (ID) fan is a significant piece of auxiliary equipment in thermal power plants. An early detection of possible faults in the ID fan may be used for effective predictive maintenance, thereby reducing the overall maintenance cost and improving the reliability and availability of thermal power plants. This paper proposed a genetic algorithm and long-short term memory network (GA-LSTM)-based condition monitoring approach using normal operation data of the ID fan. Furthermore, the LSTM network and the sliding window technique were introduced to construct double thresholds, which contains a dynamic threshold and a static threshold. The GA-LSTM-double thresholds method was applied to a coal-fired power plant to achieve early fault detection and diagnosis. The results demonstrates that the proposed method is capable of detecting minor anomalies in advance.
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 callDisclaimer: 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.
