Wind Turbine Gearbox Failure Identification With Deep Neural Networks
Citations
740 citations
482 citations
Cites methods from "Wind Turbine Gearbox Failure Identi..."
...[112] 2017 SCADA Lubricant pressure monitoring Regression/Normal...
[...]
...[112] built regression-based deep NN models of lubricant pressure based on SCADA data....
[...]
...They used ExponentiallyWeightedMoving Average (EWMA) charts to identify shifts in absolute percentage errors signifying failures and to prevent overfitting they use dropout layers in the network [112]; six wind farms were considered and the trained deep NNs achieved a MAPE between 2....
[...]
266 citations
Cites methods from "Wind Turbine Gearbox Failure Identi..."
...According to [99], a DNN was employed to develop the prediction model for monitoring the wind turbine gearbox health...
[...]
206 citations
193 citations
References
[...]
46,982 citations
40,785 citations
"Wind Turbine Gearbox Failure Identi..." refers methods in this paper
...The Lasso model [29] for predicting the lubricant pressure is written as (9), in this study, and the estimation of its parameters is as follows (10):...
[...]
...To validate the capability of DNN in modeling the lubricant pressure, the DNN model is compared with data-driven models developed by five famous algorithms, the k-Nearest Neighbors (kNN) [28], least absolute shrinkage and selection operator (Lasso) [29], ridge regression (Ridge) [30], support vector machines (SVM) [31], and shallow NN [32]....
[...]
38,681 citations
36,760 citations
"Wind Turbine Gearbox Failure Identi..." refers background in this paper
...The λ yields the smallest BIC considered in training the Lasso model....
[...]
...The optimal λ value is selected from a set {0.001, 0.002, . . . , 0.5} and the Bayes Information criterion (BIC) [37] defined in (11) is considered as the selection criteria BIC = −2 · lnL + v · ln(n) (11) where L and v are two BIC parameters, which can be estimated according to [38]....
[...]
...5} and the Bayes Information criterion (BIC) [37] defined in (11) is considered as the selection criteria...
[...]
33,597 citations
"Wind Turbine Gearbox Failure Identi..." refers methods in this paper
...To prevent the overfitting, a dropout training procedure [27] is utilized to develop the DNN model....
[...]
...The dropout method is an alternative and more efficient option for addressing DNN overfitting [27]....
[...]