TY - JOUR
T1 - Reduced neural network based ensemble approach for fault detection and diagnosis of wind energy converter systems
AU - Dhibi, Khaled
AU - Mansouri, Majdi
AU - Bouzrara, Kais
AU - Nounou, Hazem
AU - Nounou, Mohamed
N1 - Publisher Copyright:
© 2022 The Authors
PY - 2022/7
Y1 - 2022/7
N2 - Wind energy (WE) is one of the most important technology to produce energy and an efficient source of renewable energy (RE) available in the atmospheric environment due to different air-currents spread over the stratosphere and troposphere. Wind energy conversion (WEC) system has become a focal point in the research of RE in recent years. Moreover, fault detection and diagnosis (FDD) plays an important role in ensuring WEC safety. In the past decades, neural networks (NN) has provided an effective performance in fault diagnosis. On the other hand, ensemble learning (EL) techniques have gained significant attention from the scientific community. EL is a technique that creates and combines multiple machine learning models in order to produce one optimal predictive model which gives improved results. The goal of this paper is to develop and validate effective neural networks based ensemble approach. First, an ensemble classifier based on neural networks techniques and using bagging, boosting, and random subspace combination techniques is proposed. Second, an improved extension of the proposed neural networks-based ensemble technique is presented. Finally, the results obtained from the proposed neural networks-based ensemble techniques are compared with other methods to illustrate and validate the advantages of the proposed techniques.
AB - Wind energy (WE) is one of the most important technology to produce energy and an efficient source of renewable energy (RE) available in the atmospheric environment due to different air-currents spread over the stratosphere and troposphere. Wind energy conversion (WEC) system has become a focal point in the research of RE in recent years. Moreover, fault detection and diagnosis (FDD) plays an important role in ensuring WEC safety. In the past decades, neural networks (NN) has provided an effective performance in fault diagnosis. On the other hand, ensemble learning (EL) techniques have gained significant attention from the scientific community. EL is a technique that creates and combines multiple machine learning models in order to produce one optimal predictive model which gives improved results. The goal of this paper is to develop and validate effective neural networks based ensemble approach. First, an ensemble classifier based on neural networks techniques and using bagging, boosting, and random subspace combination techniques is proposed. Second, an improved extension of the proposed neural networks-based ensemble technique is presented. Finally, the results obtained from the proposed neural networks-based ensemble techniques are compared with other methods to illustrate and validate the advantages of the proposed techniques.
KW - Ensemble learning (EL)
KW - Fault detection and diagnosis (FDD)
KW - Hierarchical K-Means (H–K-Means)
KW - Neural network (NN)
KW - Wind energy conversion (WEC)
UR - http://www.scopus.com/inward/record.url?scp=85131418475&partnerID=8YFLogxK
U2 - 10.1016/j.renene.2022.05.082
DO - 10.1016/j.renene.2022.05.082
M3 - Article
AN - SCOPUS:85131418475
SN - 0960-1481
VL - 194
SP - 778
EP - 787
JO - Renewable Energy
JF - Renewable Energy
ER -