TY - JOUR
T1 - Wind Turbine Predictive Fault Diagnostics Based on a Novel Long Short-Term Memory Model
AU - Zhang, Shuo
AU - Robinson, Emma
AU - Basu, Malabika
N1 - Publisher Copyright:
© 2023 by the authors.
PY - 2023/12
Y1 - 2023/12
N2 - The operation and maintenance (O&M) issues of offshore wind turbines (WTs) are more challenging because of the harsh operational environment and hard accessibility. As sudden component failures within WTs bring about durable downtimes and significant revenue losses, condition monitoring and predictive fault diagnostic approaches must be developed to detect faults before they occur, thus preventing durable downtimes and costly unplanned maintenance. Based primarily on supervisory control and data acquisition (SCADA) data, thirty-three weighty features from operational data are extracted, and eight specific faults are categorised for fault predictions from status information. By providing a model-agnostic vector representation for time, Time2Vec (T2V), into Long Short-Term Memory (LSTM), this paper develops a novel deep-learning neural network model, T2V-LSTM, conducting multi-level fault predictions. The classification steps allow fault diagnosis from 10 to 210 min prior to faults. The results show that T2V-LSTM can successfully predict over 84.97% of faults and outperform LSTM and other counterparts in both overall and individual fault predictions due to its topmost recall scores in most multistep-ahead cases performed. Thus, the proposed T2V-LSTM can correctly diagnose more faults and upgrade the predictive performances based on vanilla LSTM in terms of accuracy, recall scores, and F-scores.
AB - The operation and maintenance (O&M) issues of offshore wind turbines (WTs) are more challenging because of the harsh operational environment and hard accessibility. As sudden component failures within WTs bring about durable downtimes and significant revenue losses, condition monitoring and predictive fault diagnostic approaches must be developed to detect faults before they occur, thus preventing durable downtimes and costly unplanned maintenance. Based primarily on supervisory control and data acquisition (SCADA) data, thirty-three weighty features from operational data are extracted, and eight specific faults are categorised for fault predictions from status information. By providing a model-agnostic vector representation for time, Time2Vec (T2V), into Long Short-Term Memory (LSTM), this paper develops a novel deep-learning neural network model, T2V-LSTM, conducting multi-level fault predictions. The classification steps allow fault diagnosis from 10 to 210 min prior to faults. The results show that T2V-LSTM can successfully predict over 84.97% of faults and outperform LSTM and other counterparts in both overall and individual fault predictions due to its topmost recall scores in most multistep-ahead cases performed. Thus, the proposed T2V-LSTM can correctly diagnose more faults and upgrade the predictive performances based on vanilla LSTM in terms of accuracy, recall scores, and F-scores.
KW - Long Short-Term Memory (LSTM)
KW - operation and maintenance (O&M)
KW - predictive fault diagnostic
KW - supervisory control and data acquisition (SCADA)
KW - T2V-LSTM
KW - Time2Vec (T2V)
KW - wind turbines (WTs)
UR - http://www.scopus.com/inward/record.url?scp=85180715469&partnerID=8YFLogxK
U2 - 10.3390/a16120546
DO - 10.3390/a16120546
M3 - Article
AN - SCOPUS:85180715469
SN - 1999-4893
VL - 16
JO - Algorithms
JF - Algorithms
IS - 12
M1 - 546
ER -