Open AccessConvolutional Neural Network for Wind Turbine Failure Classification Based on SCADA Data
Author(s) -
Bryan Puruncajas,
W. Alava,
Encalada Dávila,
Christian Tutivén,
Yolanda Vidal
Publication year - 2021
Publication title -
renewable energy and power quality journal
Language(s) - English
Resource type - Journals
ISSN - 2172-038X
DOI - 10.24084/repqj19.316
Subject(s) - scada , wind power , turbine , convolutional neural network , reliability engineering , reliability (semiconductor) , fault (geology) , renewable energy , computer science , fault detection and isolation , offshore wind power , condition monitoring , real time computing , automotive engineering , engineering , artificial intelligence , power (physics) , actuator , electrical engineering , mechanical engineering , physics , quantum mechanics , seismology , geology
As a renewable energy source and an alternative to fossil fuels, the wind power industry is growing rapidly. However, due to harsh weather conditions, wind turbines (WT) still face many failures that raise the price of energy produced and reduce the reliability of wind energy. Hence, the use of reliable monitoring and diagnostic systems of WTs is of great importance. Operation and maintenance expenses represent 30% of the total cost of large wind farms. The installation of offshore and remote wind farms has increased the need for efficient fault detection and condition monitoring systems. In this work, without using specific custom devices for monitoring conditions, but only increasing the sampling frequency in the sensors already available (in all commercial WT) of the supervisory control and data acquisition system (SCADA), datadriven multiple fault detection is performed, and a classification strategy is developed. The data is processed, and subsequently, using a convolutional neural network (CNN), six faults are classified and evaluated with different metrics. Finally, it should be noted that the classification speed allows the implementation of this strategy to monitor conditions online in real under-production WTs.