Access to accurate power production prediction of a wind turbine in future hours enables operators to detect possible underperformance and anomalies in advance. This may enable more proactive and strategic operations optimisation. 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. In this study, an algorithm is proposed to impute values of data that are missing, out-of-range, or outliers. It is shown that an appropriate combination of a decision tree and mean value for imputation can improve the data analysis and prediction performance by the creation of a smoother dataset. In addition, principal component analysis is employed to extract parameters with power production influence based on all available signals in the SCADA data. Then, a new data fusion technique is applied, combining dynamic multilayer perceptron (MLP) and adaptive neuro-fuzzy inference system (ANFIS) networks to predict future performance of wind turbines. This prediction is made on a scale of one-hour intervals. This novel combination of feature extraction, imputation, and MLP/ANFIS fusion performs well with favourably low prediction error levels. Thus, such an approach may be a valuable tool for turbine power production prediction.

References

1. 1)
  - 57. Ding, Y., Ross, A.: ‘A comparison of imputation methods for handling missing scores in biometric fusion’, Pattern Recognit., 2012, 45, (3), pp. 919–933.
2. 2)
  - 52. Frank, A., Asuncion, A.: ‘UCI machine learning repository’, University of California, School of Information and Computer Science. Irvine, CA, 2010, http://archive.ics.uci.edu/ml.
3. 3)
  - 2. Heng, A., Zhang, S., Tan, A.C., et al: ‘Rotating machinery prognostics: state of the art, challenges and opportunities’, Mech. Syst. Signal Process., 2009, 23, (3), pp. 724–739.
4. 4)
  - 65. Liu, X.: ‘Some properties of the weighted OWA operator’, IEEE Trans. Syst. Man Cybern. B, Cybern., 2006, 36, (1), pp. 118–127.
5. 5)
  - 18. Kusiak, A., Zheng, H., Song, Z.: ‘Models for monitoring wind farm power’, Renew. Energy, 2009, 34, (3), pp. 583–590.
6. 6)
  - 47. Farhangfar, A., Kurgan, L.A., Pedrycz, W.: ‘A novel framework for imputation of missing values in databases’, IEEE Trans. Syst. Man Cybern. A, Syst. Humans, 2007, 37, (5), pp. 692–709.
7. 7)
  - 63. Kordestani, M., Saif, M.: ‘Data fusion for fault diagnosis in smart grid power systems’. 2017 IEEE 30th Canadian Conf. on Electrical and Computer Engineering (CCECE), Windsor, 2017, pp. 1–6.
8. 8)
  - 39. Li, G., Qin, S.J., Ji, Y., et al: ‘Reconstruction based fault prognosis for continuous processes’, Control Eng. Pract., 2010, 18, (10), pp. 1211–1219.
9. 9)
  - 71. Waqar, T., Demetgul, M.: ‘Thermal analysis MLP neural network based fault diagnosis on worm gears’, Measurement, 2016, 86, pp. 56–66.
10. 10)
  - 1. Marathe, N., Swift, A., Hirth, B., et al: ‘Characterizing power performance and wake of a wind turbine under yaw and blade pitch’, Wind Energy, 2016, 19, (5), pp. 963–978.
11. 11)
  - 38. Singleton, R.K., Strangas, E.G., Aviyente, S.: ‘Discovering the hidden health states in bearing vibration signals for fault prognosis’. IECON 2014 – 40th Annual Conf. of the IEEE Industrial Electronics Society, Dallas, TX, 2014, pp. 3438–3444.
12. 12)
  - 61. Ng, K.-C., Abramson, B.: ‘Consensus diagnosis: a simulation study’, IEEE Trans. Syst. Man Cybern., 1992, 22, (5), pp. 916–928.
13. 13)
  - 26. Petković, D., Ćojbašič, Ž, Nikolić, V.: ‘Adaptive neuro-fuzzy approach for wind turbine power coefficient estimation’, Renew. Sust. Energy Rev., 2013, 28, pp. 191–195.
14. 14)
  - 76. Potter, C.W., Negnevitsky, M.: ‘Very short-term wind forecasting for Tasmanian power generation’, IEEE Trans. Power Syst., 2006, 21, (2), pp. 965–972.
15. 15)
  - 7. Heo, Y.G., Choi, N.J., Choi, K.H., et al: ‘CFD study on aerodynamic power output of a 110 kW building augmented wind turbine’, Energy Build., 2016, 129, pp. 162–173.
16. 16)
  - 6. Sagol, E., Reggio, M., Ilinca, A.: ‘Issues concerning roughness on wind turbine blades’, Renew. Sustain. Energy Rev., 2013, 23, pp. 514–525.
17. 17)
  - 54. Meng, Z., Shi, Z.: ‘Extended rough set-based attribute reduction in inconsistent incomplete decision systems’, Inf. Sci., 2012, 204, pp. 44–69.
18. 18)
  - 43. Camacho, J., Pérez-Villegas, A., García-Teodoro, P., et al: ‘PCA-based multivariate statistical network monitoring for anomaly detection’, Comput. Secur., 2016, 59, pp. 118–137.
19. 19)
  - 37. Dong, M., He, D.: ‘Hidden semi-Markov model-based methodology for multisensory equipment health diagnosis and prognosis’, Eur. J. Oper. Res., 2007, 178, (3), pp. 858–878.
20. 20)
  - 51. Caselitz, P., Giebhardt, J.: ‘Advanced maintenance and repair for offshore wind farms using fault prediction techniques’. Proc. of the World Wind Energy Conf., Berlin, 2002.
21. 21)
  - 60. Li, W., Yue, H.H., Valle-Cervantes, S., et al: ‘Recursive PCA for adaptive process monitoring’, J. Process Control, 2000, 10, (5), pp. 471–486.
22. 22)
  - 79. Hasiloglu, A., Yilmaz, M., Comakli, O., et al: ‘Adaptive neuro-fuzzy modeling of transient heat transfer in circular duct air flow’, Int. J. Thermal Sci., 2004, 43, (11), pp. 1075–1090.
23. 23)
  - 5. Ju, Y., Zhang, C.: ‘Multi-point robust design optimization of wind turbine airfoil under geometric uncertainty’, Proc. Inst. Mech. Eng. A, J. Power Energy, 2012, 226, (2), pp. 245–261.
24. 24)
  - 48. Blake, R., Mangiameli, P.: ‘The effects and interactions of data quality and problem complexity on classification’, J. Data Inf. Qual., 2011, 2, (2), p. 8.
25. 25)
  - 42. Salahshoor, K., Kordestani, M., Khoshro, M.S.: ‘Design of online soft sensors based on combined adaptive PCA and DMLP neural networks’. Control and Decision Conf., (CCDC'09), Guilin, 2009, pp. 3481–3486.
26. 26)
  - 58. Yang, X., Huang, B., Zhao, Y., et al: ‘Generalized expectation–maximization approach to LPV process identification with randomly missing output data’, Chemometr. Intell. Lab. Syst., 2015, 148, pp. 1–8.
27. 27)
  - 53. Graham, J.W.: ‘Missing data analysis: making it work in the real world’, Annu. Rev. Psychol., 2009, 60, pp. 549–576.
28. 28)
  - 59. Wold, S.: ‘Exponentially weighted moving principal components analysis and projections to latent structures’, Chemometr. Intell. Lab. Syst., 1994, 23, (1), pp. 149–161.
29. 29)
  - 15. McKay, P., Carriveau, R., Ting, D.S.-K.: ‘Wake impacts on downstream wind turbine performance and yaw alignment’, Wind Energy, 2013, 16, (2), pp. 221–234.
30. 30)
  - 27. Lorton, A., Fouladirad, M., Grall, A.: ‘A methodology for probabilistic model-based prognosis’, Eur. J. Oper. Res., 2013, 225, (3), pp. 443–454.
31. 31)
  - 22. Kim, H.-E., Tan, A.C., Mathew, J., et al: ‘Bearing fault prognosis based on health state probability estimation’, Expert Syst. Appl., 2012, 39, (5), pp. 5200–5213.
32. 32)
  - 41. Zhou, B., Ye, H., Zhang, H., et al: ‘Process monitoring of iron-making process in a blast furnace with PCA-based methods’, Control Eng. Pract., 2016, 47, pp. 1–14.
33. 33)
  - 64. Torra, V.: ‘OWA operators in data modeling and reidentification’, IEEE Trans. Fuzzy Syst., 2004, 12, (5), pp. 652–660.
34. 34)
  - 14. Castellani, F., Astolfi, D., Sdringola, P., et al: ‘Analyzing wind turbine directional behavior: SCADA data mining techniques for efficiency and power assessment’, Appl. Energy, 2017, 185, pp. 1076–1086.
35. 35)
  - 72. Takagi, H., Hayashi, I.: ‘NN-driven fuzzy reasoning’, Int. J. Approx. Reason., 1991, 5, (3), pp. 191–212.
36. 36)
  - 74. Schlechtingen, M., Santos, I.F., Achiche, S.: ‘Using data-mining approaches for wind turbine power curve monitoring: a comparative study’, IEEE Trans. Sustain. Energy, 2013, 4, (3), pp. 671–679.
37. 37)
  - 36. Liu, Q., Dong, M., Lv, W., et al: ‘A novel method using adaptive hidden semi-markov model for multi-sensor monitoring equipment health prognosis’, Mech. Syst. Signal Process., 2015, 64, pp. 217–232.
38. 38)
  - 8. El-Zahaby, A.M., Kabeel, A., Elsayed, S., et al: ‘CFD analysis of flow fields for shrouded wind turbine's diffuser model with different flange angles’, Alexandria Eng. J., 2017, 56, (1), pp. 171–179.
39. 39)
  - 4. Li, J., Li, R., Gao, Y., et al: ‘Aerodynamic optimization of wind turbine airfoils using response surface techniques’, Proc. Inst. Mech. Eng. A, J. Power Energy, 2010, 224, (6), pp. 827–838.
40. 40)
  - 67. Filev, D., Yager, R.R.: ‘Learning OWA operator weights from data’. IEEE World Congress on Computational Intelligence. Proc. of the Third IEEE Conf. on Fuzzy Systems, Orlando, 1994, pp. 468–473.
41. 41)
  - 77. Mamdani, E.H.: ‘Application of fuzzy logic to approximate reasoning using linguistic synthesis’. Proc. of the Sixth Int. Symp. on Multiple-Valued Logic, Logan, UT, 1976, pp. 196–202.
42. 42)
  - 16. Djeziri, M., Ananou, B., Ouladsine, M.: ‘Data driven and model based fault prognosis applied to a mechatronic system’. 2013 Fourth Int. Conf. on Power Engineering, Energy and Electrical Drives (POWERENG), Istanbul, 2013, pp. 534–539.
43. 43)
  - 28. Wang, W.: ‘A two-stage prognosis model in condition based maintenance’, Eur. J. Oper. Res., 2007, 182, (3), pp. 1177–1187.
44. 44)
  - 21. Salahshoor, K., Khoshro, M.S., Kordestani, M.: ‘Fault detection and diagnosis of an industrial steam turbine using a distributed configuration of adaptive neurofuzzy inference systems’, Simul. Modelling Pract. Theory, 2011, 19, (5), pp. 1280–1293.
45. 45)
  - 24. Kim, H., Na, M.G., Heo, G.: ‘Application of monitoring, diagnosis, and prognosis in thermal performance analysis for nuclear power plants’, Nucl. Eng. Technol., 2014, 46, (6), pp. 737–752.
46. 46)
  - 66. Soltani, S., Kordestani, M., Aghaee, P.K., et al: ‘Improved estimation for well-logging problems based on fusion of four types of kalman filters’, IEEE Trans. Geosci. Remote Sens., 2018, 56, (2), pp. 647–654.
47. 47)
  - 80. Salahshoor, K., Kordestani, M., Khoshro, M.S.: ‘Fault detection and diagnosis of an industrial steam turbine using fusion of SVM (support vector machine) and ANFIS (adaptive neuro-fuzzy inference system) classifiers’, Energy, 2010, 35, (12), pp. 5472–5482.
48. 48)
  - 31. Liu, S., Wang, Y., Tian, F.: ‘Prognosis of underground cable via online datadriven method with field data’, IEEE Trans. Ind. Electron., 2015, 62, (12), pp. 7786–7794.
49. 49)
  - 12. Chen, J., Wang, Q., Zhang, S., et al: ‘A new direct design method of wind turbine airfoils and wind tunnel experiment’, Appl. Math. Model., 2016, 40, (3), pp. 2002–2014.
50. 50)
  - 73. Jang, J.-S.: ‘ANFIS: adaptive-network-based fuzzy inference system’, IEEE Trans. Syst. Man Cybern., 1993, 23, (3), pp. 665–685.
51. 51)
  - 19. Morshedizadeh, M., Kordestani, M., Carriveau, R., et al: ‘Application of imputation techniques and adaptive neuro-fuzzy inference system to predict wind turbine power production’, Energy, 2017, 138, pp. 394–404.
52. 52)
  - 70. Shrme, A.E.: ‘Hybrid intelligent technique for automatic communication signals recognition using bees algorithm and MLP neural networks based on the efficient features’, Expert Syst. Appl., 2011, 38, (5), pp. 6000–6006.
53. 53)
  - 46. Farhangfar, A., Kurgan, L., Dy, J.: ‘Impact of imputation of missing values on classification error for discrete data’, Pattern Recognit., 2008, 41, (12), pp. 3692–3705.
54. 54)
  - 3. Malhi, A., Yan, R., Gao, R.X.: ‘Prognosis of defect propagation based on recurrent neural networks’, IEEE Trans. Instrum. Meas., 2011, 60, (3), pp. 703–711.
55. 55)
  - 10. Raman, V., Drissi-Habti, M., Guillaumat, L., et al: ‘Numerical simulation analysis as a tool to identify areas of weakness in a turbine wind-blade and solutions for their reinforcement’, Compos. B, Eng., 2016, 103, pp. 23–39.
56. 56)
  - 9. Kumar, A., Dwivedi, A., Paliwal, V., et al: ‘Free vibration analysis of al 2024 wind turbine blade designed for Uttarakhand region based on FEA’, Procedia Technol., 2014, 14, pp. 336–347.
57. 57)
  - 20. Yang, W., Jiang, J.: ‘Wind turbine condition monitoring and reliability analysis by SCADA information’. 2011 Second Int. Conf. on Mechanic Automation and Control Engineering (MACE), Inner Mongolia, 2011, pp. 1872–1875.
58. 58)
  - 23. Yin, Z., Hou, J.: ‘Recent advances on svm based fault diagnosis and process monitoring in complicated industrial processes’, Neurocomputing, 2016, 174, pp. 643–650.
59. 59)
  - 62. Herrera-Viedma, E., Cordón, O., Luque, M., et al: ‘A model of fuzzy linguistic IRS based on multi-granular linguistic information’, Int. J. Approx. Reason., 2003, 34, (2-3), pp. 221–239.
60. 60)
  - 25. Niu, G., Yang, B.-S.: ‘Dempster–Shafer regression for multi-step-ahead time series prediction towards data-driven machinery prognosis’, Mech. Syst. Signal Process., 2009, 23, (3), pp. 740–751.
61. 61)
  - 69. Salahshoor, K., Kordestani, M., Khoshro, M.S.: ‘Design of online soft sensors based on combined adaptive PCA and RBF neural networks’. IEEE Symp. on Computational Intelligence in Control and Automation (CICA 2009), Nashville, TN, 2009, pp. 89–95.
62. 62)
  - 78. Sugeno, M.: ‘Industrial applications of fuzzy control’ (Elsevier Science Inc., New York, NY, 1985).
63. 63)
  - 17. Kim, S.-Y., Ra, I.-H., Kim, S.-H.: ‘Design of wind turbine fault detection system based on performance curve’. 2012 Joint 6th Int. Conf. on Soft Computing and Intelligent Systems (SCIS) and 13th Int. Symp. on Advanced Intelligent Systems (ISIS), Kobe, 2012, pp. 2033–2036.
64. 64)
  - 68. Filev, D., Yager, R.R.: ‘On the issue of obtaining OWA operator weights’, Fuzzy Sets Syst., 1998, 94, (2), pp. 157–169.
65. 65)
  - 75. Sfetsos, A.: ‘A comparison of various forecasting techniques applied to mean hourly wind speed time series’, Renew. Energy, 2000, 21, (1), pp. 23–35.
66. 66)
  - 11. Yin, C., Zhang, Z., Wang, Z., et al: ‘Numerical simulation and experimental validation of ultrasonic de-icing system for wind turbine blade’, Appl. Acoust., 2016, 114, pp. 19–26.
67. 67)
  - 56. García-Laencina, P.J., Sancho-Gómez, J.-L., Figueiras-Vidal, A.R.: ‘Pattern classification with missing data: a review’, Neural Comput. Appl., 2010, 19, (2), pp. 263–282.
68. 68)
  - 81. Schlechtingen, M., Santos, I.F., Achiche, S.: ‘Wind turbine condition monitoring based on SCADA data using normal behavior models. Part 1: system description’, Appl. Soft Comput., 2013, 13, (1), pp. 259–270.
69. 69)
  - 29. Chen, C., Brown, D., Sconyers, C., et al: ‘An integrated architecture for fault diagnosis and failure prognosis of complex engineering systems’, Expert Syst. Appl., 2012, 39, (10), pp. 9031–9040.
70. 70)
  - 55. Zhang, S.: ‘Shell-neighbor method and its application in missing data imputation’, Appl. Intell., 2011, 35, (1), pp. 123–133.
71. 71)
  - 33. Yu, M., Wang, D., Luo, M., et al: ‘Prognosis of hybrid systems with multiple incipient faults: augmented global analytical redundancy relations approach’, IEEE Trans. Syst. Man Cybern. A, Syst. Humans, 2011, 41, (3), pp. 540–551.
72. 72)
  - 35. Hu, J., Zhang, L., Ma, L., et al: ‘An integrated safety prognosis model for complex system based on dynamic Bayesian network and ant colony algorithm’, Expert Syst. Appl., 2011, 38, (3), pp. 1431–1446.
73. 73)
  - 13. Li, Q., Maeda, T., Kamada, Y., et al: ‘Effect of solidity on aerodynamic forces around straight-bladed vertical axis wind turbine by wind tunnel experiments (depending on number of blades)’, Renew. Energy, 2016, 96, pp. 928–939.
74. 74)
  - 44. Rahman, M.G., Islam, M.Z.: ‘Missing value imputation using decision trees and decision forests by splitting and merging records: two novel techniques’, Knowl.-Based Syst., 2013, 53, pp. 51–65.
75. 75)
  - 34. Sheppard, J.W., Kaufman, M.A.: ‘A Bayesian approach to diagnosis and prognosis using built-in test’, IEEE Trans. Instrum. Meas., 2005, 54, (3), pp. 1003–1018.
76. 76)
  - 32. Wang, Z., Hu, C., Wang, W., et al: ‘An off-online fuzzy modelling method for fault prognosis with an application’. 2012 IEEE Conf. on Prognostics and System Health Management (PHM), Beijing, 2012, pp. 1–7.
77. 77)
  - 45. Zhu, X., Zhang, S., Jin, Z., et al: ‘Missing value estimation for mixed-attribute data sets’, IEEE Trans. Knowl. Data Eng., 2011, 23, (1), pp. 110–121.
78. 78)
  - 40. Zanardelli, W.G., Strangas, E.G., Khalil, H.K., et al: ‘Wavelet-based methods for the prognosis of mechanical and electrical failures in electric motors’, Mech. Syst. Signal Process., 2005, 19, (2), pp. 411–426.
79. 79)
  - 49. Schlechtingen, M., Santos, I.F.: ‘Comparative analysis of neural network and regression based condition monitoring approaches for wind turbine fault detection’, Mech. Syst. Signal Process., 2011, 25, (5), pp. 1849–1875.
80. 80)
  - 30. Son, J., Zhou, Q., Zhou, S., et al: ‘Evaluation and comparison of mixed effects model based prognosis for hard failure’, IEEE Trans. Reliab., 2013, 62, (2), pp. 379–394.
81. 81)
  - 50. Swingler, K.: ‘Applying neural networks: a practical guide’ (Morgan Kaufmann, San Francisco, CA, 1996).

Power production prediction of wind turbines using a fusion of MLP and ANFIS networks

References

Related content