Posters
Come meet the poster presenters to ask them questions and discuss their work
We would like to invite you to come and see the posters at our upcoming conference. The posters will showcase a diverse range of research topics and provide an opportunity for delegates to engage with the authors and learn more about their work. Whether you are a seasoned researcher or simply curious about the latest developments in your field, we believe that the posters will offer something of interest to everyone. So please, join us at the conference and take advantage of this opportunity to learn and engage with your peers in the academic community. We look forward to seeing you there!
PO002: A long-short-term-memory neural network approach to early fault detection of wind turbines' main bearing based only on SCADA data.
Yolanda Vidal, Associate Professor, Universitat Politècnica de Catalunya
Abstract
Wind energy maintenance and operating expenses can cost millions of dollars per year in a typical industrial-sized wind farm. As a result, the transition from preventive and corrective maintenance to predictive maintenance is critical in the wind energy industry. This research contributes to the problem by presenting a main bearing early defect detection system that employs just conventional SCADA data (10-minute average) and a long-short-term-memory (LSTM) neural network. The main contributions are the following ones. i) Based just on healthy data, it is entirely semi-supervised (without requiring data labeling via work order records). ii) Validated using real SCADA data and shown to be robust to seasonality, operational and environmental conditions. iii) Reliable forecasts with few false alarms due to the proposed fault prognosis indicator (FPIs) based on a simple moving average (SMA) filter. iv) The early warning is obtained months in advance, allowing plant operators enough time to plan repairs. v) Finally, the proposed technique is validated in a wind farm consisting of 12 wind turbines.
Follow the event on: