Wind Turbine Prognosis Models Based on SCADA Data and Extreme Learning Machines

In this paper, a method to build models to monitor and evaluate the health status of wind turbines using Single-hidden Layer Feedforward Neural networks (SLFN) is presented. The models are trained using the Extreme Learning Machines (ELM) strategy. The data used is obtained from the SCADA systems, easily available in modern wind turbines. The ELM technique requires very low computational costs for the training of the models, and thus allows for the integration of a grid-search approach with parallelized instances to find out the optimal model parameters. These models can be built both individually, considering the turbines separately, or as an aggregate for the whole wind plant. The followed strategy consists in predicting a target variable using the rest of the variables of the system/subsystem, computing the error deviation from the real target variable and finally comparing high error values with a selection of alarm events for that system, therefore validating the performance of the model. The experimental results indicate that this methodology leads to the detection of mismatches in the stages of the system’s failure, thus making it possible to schedule the maintenance operation before a critical failure occurs. The simplicity of the ELM systems and the ease with which the parameters can be adjusted make it a realistic option to be implemented in wind turbine models to work in real time.

[1]  F. Fleuret.  Fast Binary Feature Selection with Conditional Mutual Information , 2004, J. Mach. Learn. Res..

[2]  Ke Li,et al.  Knee Point Identification Based on Trade-Off Utility , 2020, ArXiv.

[3]  Chee Kheong Siew,et al.  Universal Approximation using Incremental Constructive Feedforward Networks with Random Hidden Nodes , 2006, IEEE Transactions on Neural Networks.

[4]  Yong Wang,et al.  Conditional Mutual Information‐Based Feature Selection Analyzing for Synergy and Redundancy , 2011, ETRI Journal.

[5]  Karina Gibert,et al.  A Text-Mining Approach to Assess the Failure Condition of Wind Turbines Using Maintenance Service History , 2019 .

[6]  Yibing Liu,et al.  DNN‐based approach for fault detection in a direct drive wind turbine , 2018, IET Renewable Power Generation.

[7]  Mayorkinos Papaelias,et al.  Wind turbine reliability analysis , 2013 .

[8]  Michael Wilkinson,et al.  Comparison of methods for wind turbine condition monitoring with SCADA data , 2014 .

[9]  Jordi Cusidó,et al.  Feature Selection Algorithms for Wind Turbine Failure Prediction , 2019, Energies.

[10]  Andrew Kusiak,et al.  The prediction and diagnosis of wind turbine faults , 2011 .

[11]  Jordi Solé i Casals,et al.  Effects of the pre-processing algorithms in fault diagnosis of wind turbines , 2018, Environ. Model. Softw..

[12]  Chee Kheong Siew,et al.  Extreme learning machine: Theory and applications , 2006, Neurocomputing.

[13]  Susana Ferreiro,et al.  A Context-Aware Oil Debris-Based Health Indicator for Wind Turbine Gearbox Condition Monitoring , 2019, Energies.

[14]  Gianluca Bontempi,et al.  On the Use of Variable Complementarity for Feature Selection in Cancer Classification , 2006, EvoWorkshops.

[15]  Roberto Battiti,et al.  Using mutual information for selecting features in supervised neural net learning , 1994, IEEE Trans. Neural Networks.

[16]  James Carroll,et al.  Failure rate, repair time and unscheduled O&M cost analysis of offshore wind turbines , 2016 .

[17]  Lina Bertling Tjernberg,et al.  An Artificial Neural Network Approach for Early Fault Detection of Gearbox Bearings , 2015, IEEE Transactions on Smart Grid.

[18]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[19]  Meik Schlechtingen,et al.  Comparative analysis of neural network and regression based condition monitoring approaches for wind turbine fault detection , 2011 .

[20]  Pinjia Zhang,et al.  A Survey of Condition Monitoring and Fault Diagnosis toward Integrated O&M for Wind Turbines , 2019, Energies.

[21]  B. Kowalski,et al.  Partial least-squares regression: a tutorial , 1986 .

[22]  Fuhui Long,et al.  Feature selection based on mutual information criteria of max-dependency, max-relevance, and min-redundancy , 2003, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[23]  Huan Long,et al.  Wind Turbine Gearbox Failure Identification With Deep Neural Networks , 2017, IEEE Transactions on Industrial Informatics.

[24]  Hongzhou Wang,et al.  A survey of maintenance policies of deteriorating systems , 2002, Eur. J. Oper. Res..

[25]  David Infield,et al.  Online wind turbine fault detection through automated SCADA data analysis , 2009 .

[26]  Zhifeng Sun,et al.  Gearbox Fault Prediction of Wind Turbines Based on a Stacking Model and Change-Point Detection , 2019, Energies.