TY - GEN
T1 - Time-series deep learning fault detection with the application of wind turbine benchmark
AU - Rahimilarki, Reihane
AU - Gao, Zhiwei
AU - Jin, Nanlin
AU - Zhang, Aihua
N1 - Funding Information:
The work is partially supported by the RDF studentship, at the E&E faculty in Northumbria University, and the NSFC under grant 61673074.
PY - 2019/7
Y1 - 2019/7
N2 - In this paper, a deep learning fault detection approach is proposed based on the convolutional neural network in order to cope with one class of faults in wind turbine systems. Fault detection is very vital in nowadays industries due to the fact that instantly detection can prevent waste of cost and time. Deep learning as one of the powerful approaches in machine learning is a promising method to identify and classify the intrigued problems, which are hard to solve by classical methods. In this case, less than 5% performance reduction in generator torque along with sensor noise, which is challenging to identify by an operator or classical diagnosis methods is studied. The proposed algorithm, which is evolved from convolutional neural network idea, is evaluated in simulation based on a 4.8 MW wind turbine benchmark and the accuracy of the results confirms the persuasive performance of the suggested approach.
AB - In this paper, a deep learning fault detection approach is proposed based on the convolutional neural network in order to cope with one class of faults in wind turbine systems. Fault detection is very vital in nowadays industries due to the fact that instantly detection can prevent waste of cost and time. Deep learning as one of the powerful approaches in machine learning is a promising method to identify and classify the intrigued problems, which are hard to solve by classical methods. In this case, less than 5% performance reduction in generator torque along with sensor noise, which is challenging to identify by an operator or classical diagnosis methods is studied. The proposed algorithm, which is evolved from convolutional neural network idea, is evaluated in simulation based on a 4.8 MW wind turbine benchmark and the accuracy of the results confirms the persuasive performance of the suggested approach.
KW - Convolutional neural networks
KW - Deep learning
KW - Fault detection
KW - Time-series data
KW - Wind turbines
UR - http://www.scopus.com/inward/record.url?scp=85079068704&partnerID=8YFLogxK
U2 - 10.1109/INDIN41052.2019.8972237
DO - 10.1109/INDIN41052.2019.8972237
M3 - Conference contribution
AN - SCOPUS:85079068704
T3 - IEEE International Conference on Industrial Informatics (INDIN)
SP - 1337
EP - 1342
BT - 2019 IEEE 17th International Conference on Industrial Informatics (INDIN)
PB - IEEE
CY - Piscataway, NJ
T2 - 17th IEEE International Conference on Industrial Informatics, INDIN 2019
Y2 - 22 July 2019 through 25 July 2019
ER -