Application of imputation techniques and Adaptive Neuro-Fuzzy Inference System to predict wind turbine power production

Wind Turbine power output prediction can prevent unexpected failure and financial loss, through the detection of anomalies in turbine performance in advance so operators can proactively address potential problems. This study examines common Supervisory Control And Data Acquisition (SCADA) data over a period of 20 months for 21 pitch regulated 2.3 MW turbines. To identify the most influential parameters on power production among more than 150 signals in the SCADA data, correlation coefficient analysis has been applied. Further, an algorithm is proposed to impute values that are missing, out-of-range, or outliers. It is shown that appropriate combinations of decision tree and mean value for imputation can improve the data analysis and prediction performance. A dynamic ANFIS network is established to predict the future performance of wind turbines. These predictions are made on a scale of 1 h intervals for a total of 5 h into the future. The proposed combination of feature extraction, imputation algorithm, and the dynamic ANFIS network structure has performed well with favourable prediction error levels in comparison with existing models. Thus, the combination may be a valuable tool for turbine power production prediction.

[1]  Sofiane Achiche,et al.  Wind turbine condition monitoring based on SCADA data using normal behavior models. Part 1: System description , 2013, Appl. Soft Comput..

[2]  Tariq Samad,et al.  Self–organization with partial data , 1992 .

[3]  Wei Liang,et al.  An integrated safety prognosis model for complex system based on dynamic Bayesian network and ant colony algorithm , 2011, Expert Syst. Appl..

[4]  Andrew Kusiak,et al.  Models for monitoring wind farm power , 2009 .

[5]  Jing Pan,et al.  Numerical Forecasting Experiment of the Wave Energy Resource in the China Sea , 2016 .

[6]  Wenbin Wang.  A two-stage prognosis model in condition based maintenance , 2007, Eur. J. Oper. Res..

[7]  Andrew Kusiak,et al.  On-line monitoring of power curves , 2009 .

[8]  J. Graham,et al.  Missing data analysis: making it work in the real world. , 2009, Annual review of psychology.

[9]  Zhongzhi Shi,et al.  Extended rough set-based attribute reduction in inconsistent incomplete decision systems , 2012, Inf. Sci..

[10]  John W. Sheppard,et al.  A Bayesian approach to diagnosis and prognosis using built-in test , 2005, IEEE Transactions on Instrumentation and Measurement.

[11]  Wenxian Yang,et al.  Wind turbine condition monitoring and reliability analysis by SCADA information , 2011, 2011 Second International Conference on Mechanic Automation and Control Engineering.

[12]  Selin Aviyente,et al.  Discovering the hidden health states in bearing vibration signals for fault prognosis , 2014, IECON 2014 - 40th Annual Conference of the IEEE Industrial Electronics Society.

[13]  David He,et al.  Hidden semi-Markov model-based methodology for multi-sensor equipment health diagnosis and prognosis , 2007, Eur. J. Oper. Res..

[14]  Isao Hayashi,et al.  NN-driven fuzzy reasoning , 1991, Int. J. Approx. Reason..

[15]  Mitra Fouladirad,et al.  A methodology for probabilistic model-based prognosis , 2013, Eur. J. Oper. Res..

[16]  A. Kusiak,et al.  Modeling wind-turbine power curve: A data partitioning and mining approach , 2017 .

[17]  Pietro Vecchio,et al.  Wind energy prediction using a two-hidden layer neural network , 2010 .

[18]  H. Khalil,et al.  Wavelet-based methods for the prognosis of mechanical and electrical failures in electric motors , 2005 .

[19]  Takao Maeda,et al.  Effect of solidity on aerodynamic forces around straight-bladed vertical axis wind turbine by wind tunnel experiments (depending on number of blades) , 2016 .

[20]  Kevin Swingler,et al.  Applying neural networks - a practical guide , 1996 .

[21]  Man Gyun Na,et al.  APPLICATION OF MONITORING, DIAGNOSIS, AND PROGNOSIS IN THERMAL PERFORMANCE ANALYSIS FOR NUCLEAR POWER PLANTS , 2014 .

[22]  Dalibor Petković,et al.  Adaptive neuro-fuzzy approach for wind turbine power coefficient estimation , 2013 .

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

[24]  Wenyuan Lv,et al.  A novel method using adaptive hidden semi-Markov model for multi-sensor monitoring equipment health prognosis , 2015 .

[25]  Sunday O. Olatunji,et al.  Investigating the effect of correlation-based feature selection on the performance of support vector machines in reservoir characterization , 2015 .

[26]  Ao Li,et al.  Missing value estimation for DNA microarray gene expression data by Support Vector Regression imputation and orthogonal coding scheme , 2006, BMC Bioinformatics.

[27]  M. A. Djeziri,et al.  Data driven and model based fault prognosis applied to a mechatronic system , 2013, 4th International Conference on Power Engineering, Energy and Electrical Drives.

[28]  Ahmet Arslan,et al.  A hybrid method for imputation of missing values using optimized fuzzy c-means with support vector regression and a genetic algorithm , 2013, Inf. Sci..

[29]  Siegfried Heier,et al.  Grid Integration of Wind Energy Conversion Systems , 1998 .

[30]  Hui Guo,et al.  Numerical simulation and experimental validation of ultrasonic de-icing system for wind turbine blade , 2016 .

[31]  Asifullah Khan,et al.  Intelligent and robust prediction of short term wind power using genetic programming based ensemble of neural networks , 2017 .

[32]  Lukasz A. Kurgan,et al.  Impact of imputation of missing values on classification error for discrete data , 2008, Pattern Recognit..

[33]  Robert X. Gao,et al.  Prognosis of Defect Propagation Based on Recurrent Neural Networks , 2011, IEEE Transactions on Instrumentation and Measurement.

[34]  Kyung Chun Kim,et al.  CFD study on aerodynamic power output of a 110 kW building augmented wind turbine , 2016 .

[35]  Mimoun Zelmat,et al.  DESIGN OF A FUZZY MODEL-BASED CONTROLLER FOR A DRUM BOILER-TURBINE SYSTEM , 2004 .

[36]  Aníbal R. Figueiras-Vidal,et al.  Pattern classification with missing data: a review , 2010, Neural Computing and Applications.

[37]  Quan Wang,et al.  A new direct design method of wind turbine airfoils and wind tunnel experiment , 2016 .

[38]  Gang Niu,et al.  Dempster–Shafer regression for multi-step-ahead time-series prediction towards data-driven machinery prognosis , 2009 .

[39]  Jyh-Shing Roger Jang,et al.  ANFIS: adaptive-network-based fuzzy inference system , 1993, IEEE Trans. Syst. Man Cybern..

[40]  Shuhui Li,et al.  Comparative Analysis of Regression and Artificial Neural Network Models for Wind Turbine Power Curve Estimation , 2001 .

[41]  Shiyu Zhou,et al.  Evaluation and Comparison of Mixed Effects Model Based Prognosis for Hard Failure , 2013, IEEE Transactions on Reliability.

[42]  Karim Salahshoor,et al.  Fault detection and diagnosis of an industrial steam turbine using fusion of SVM (support vector machine) and ANFIS (adaptive neuro-fuzzy inference system) classifiers , 2010 .

[43]  Asifullah Khan,et al.  Wind power prediction using deep neural network based meta regression and transfer learning , 2017, Appl. Soft Comput..

[44]  Lei Huang,et al.  Prognosis of Hybrid Systems With Multiple Incipient Faults: Augmented Global Analytical Redundancy Relations Approach , 2011, IEEE Transactions on Systems, Man, and Cybernetics - Part A: Systems and Humans.

[45]  Claudomiro Sales,et al.  Multi-objective genetic algorithm for missing data imputation , 2015, Pattern Recognit. Lett..

[46]  Gang Li,et al.  Reconstruction based fault prognosis for continuous processes , 2010 .

[47]  Qinghua Hu,et al.  Transfer learning for short-term wind speed prediction with deep neural networks , 2016 .

[48]  Arun Ross,et al.  A comparison of imputation methods for handling missing scores in biometric fusion , 2012, Pattern Recognit..

[49]  Venkadesh Raman,et al.  Numerical simulation analysis as a tool to identify areas of weakness in a turbine wind-blade and solutions for their reinforcement , 2016 .

[50]  Peter K. Sharpe,et al.  Dealing with missing values in neural network-based diagnostic systems , 1995, Neural Computing & Applications.

[51]  Wenbin Wang,et al.  An off-online fuzzy modelling method for fault prognosis with an application , 2012, Proceedings of the IEEE 2012 Prognostics and System Health Management Conference (PHM-2012 Beijing).

[52]  Zili Zhang,et al.  Missing Value Estimation for Mixed-Attribute Data Sets , 2011, IEEE Transactions on Knowledge and Data Engineering.

[53]  E. H. Mamdani,et al.  Application of Fuzzy Logic to Approximate Reasoning Using Linguistic Synthesis , 1976, IEEE Transactions on Computers.

[54]  Joseph Mathew,et al.  Rotating machinery prognostics. State of the art, challenges and opportunities , 2009 .

[55]  Leila Naderloo,et al.  Modeling the effects of ultrasound power and reactor dimension on the biodiesel production yield: Comparison of prediction abilities between response surface methodology (RSM) and adaptive neuro-fuzzy inference system (ANFIS) , 2016 .

[56]  Bin Zhang,et al.  An integrated architecture for fault diagnosis and failure prognosis of complex engineering systems , 2012, Expert Syst. Appl..

[57]  Jian Hou,et al.  Recent advances on SVM based fault diagnosis and process monitoring in complicated industrial processes , 2016, Neurocomputing.

[58]  Mehrdad Saif,et al.  Improved power curve monitoring of wind turbines , 2017 .

[59]  Md Zahidul Islam,et al.  Missing value imputation using decision trees and decision forests by splitting and merging records: Two novel techniques , 2013, Knowl. Based Syst..

[60]  Joseph Mathew,et al.  Bearing fault prognosis based on health state probability estimation , 2012, Expert Syst. Appl..

[61]  Yaojie Lu,et al.  Generalized expectation–maximization approach to LPV process identification with randomly missing output data , 2015 .

[62]  Michio Sugeno,et al.  Industrial Applications of Fuzzy Control , 1985 .

[63]  Yi Wang,et al.  Prognosis of Underground Cable via Online Data-Driven Method With Field Data , 2015, IEEE Transactions on Industrial Electronics.

[64]  Lin Lin Xia,et al.  An overview of global ocean wind energy resource evaluations , 2016 .

[65]  Ashwani Kumar,et al.  Free Vibration Analysis of Al 2024 Wind Turbine Blade Designed for Uttarakhand Region based on FEA , 2014 .

[66]  Shichao Zhang,et al.  Shell-neighbor method and its application in missing data imputation , 2011, Applied Intelligence.

[67]  Sung-Ho Kim,et al.  Design of wind turbine fault detection system based on performance curve , 2012, The 6th International Conference on Soft Computing and Intelligent Systems, and The 13th International Symposium on Advanced Intelligence Systems.

[68]  Aly M. Elzahaby,et al.  CFD analysis of flow fields for shrouded wind turbine’s diffuser model with different flange angles , 2017 .

[69]  Gene H. Golub,et al.  Missing value estimation for DNA microarray gene expression data: local least squares imputation , 2005, Bioinform..

[70]  Witold Pedrycz,et al.  A Novel Framework for Imputation of Missing Values in Databases , 2007, IEEE Transactions on Systems, Man, and Cybernetics - Part A: Systems and Humans.

[71]  M. Schlechtingen,et al.  Using Data-Mining Approaches for Wind Turbine Power Curve Monitoring: A Comparative Study , 2013, IEEE Transactions on Sustainable Energy.