With the construction of large-scale wind turbines, how to reduce the operation and maintenance costs has become an urgent problem to be solved. In this paper, by extracting the actual operation data of the wind turbine in Supervisory Control and Data Acquisition (SCADA) system, the Bidirectional Recurrent Neural Networks (BRNN) is used to establish the wind turbine operation prediction model. By eliminating abnormal data points caused by accidental factors through box diagram, the fault risk threshold of wind turbine components is optimized. Then, based on the residual between the actual value and the measured value of the large sliding window, the early fault warning is realized according to Wright criterion. Finally, the model proposed in this paper is applied to the actual wind turbine, which proves the reliability and accuracy of the method.
Fausto PedroGarcía Márquez, MarkTobias Andrew, PérezJesús María Pinar and MayorkinosPapaelias, Condition monitoring of wind turbines: Techniques and methods, Renewable Energy46 (2012), 169–78.
2.
MilborrowD., Operation and maintenance costs compared and revealed, Wind Stats19(3) (2006), 3.
3.
YangMa, ChengbingHe and XinxinFeng, Institutions Function and Failure Statistic and Analysis of Wind Turbine, Physics Procedia24 (2012), 25–30.
4.
YeX., LuZ., QiaoY., MinY. and O’MalleyM., “Identification and Correction of Outliers in Wind Farm Time Series Power Data,” in, IEEE Transactions on Power Systems31(6) (2016), 4197–4205.
5.
YangH.-H., HuangM.-L. and YangS.-W., Integrating auto-associative neural networks with hotelling t2 control charts for wind turbine fault detection, Energies8(10) (2015), 12100–12115.
6.
YuliangDong, YaqiongLi and HaibinCao, He Chengbing and Gu Yuhuang, Real-time health assessment method for wind turbine based on operation condition identification[J], Journal of Electrical Engineering of China33(11) (2013), 88–95.
7.
HuidongGuo, WeiWang and MingchaoXia, [J]. On-line Deterioration State Identification Method for Wind Turbine Propeller System Based on Data Mining, Journal of Electrical Engineering of China36(09) (2016), 2389–2397.
8.
SchlechtingenMeik, SantosIlmar Ferreira and AchicheSofiane, Wind turbine condition monitoring based on SCADA data using normal behavior models. Part 1: System description, Applied Soft Computing13(1) (2013), 259–270.
9.
LiangT. and ZhangY., Variable Pitch Fault Prediction of Wind Power System Based on LS-SVM of Parameter Optimization[C]. Chinese Intelligent Automation Conference. Springer, Singapore, (2017): 303–312.
10.
OrsaghR.F., SheldoJ. and KlenlieC.J., Prognostics/diagnostics for gas turbine engine bearings, in: Proceedings of the 2003 IEEE Aerospace Conference, 2003, pp. 3095–3103.
11.
HerbertG.M.J., IniyanS. and GoicR., Performance, reliability and failure analysis of wind farm in a developing country, Renewable Energy35(12) (2010), 2739–51.
12.
YangW., CourtR. and JiangJ., Wind turbine condition monitoring by the approach of SCADA data analysis[J], Renewable Energy53 (2013), 365–376.
13.
YampikulsakulN., ByonE., ShuaiH., et al., Condition Monitoring of Wind Power System With Nonparametric Regression Analysis[J], IEEE Transactions on Energy Conversion29(2) (2014), 288–299.
14.
HongL., DhupiaJ.S. and ShengS., An explanation of frequency features enabling detection of faults in equally spaced planetary gearbox, Mech Mach Theory73 (2014), 169–183.
15.
KusiakA. and VermaA., Analyzing bearing faults in wind turbines: a data-mining approach, Renew Energy48 (2012), 110–116.
16.
PamucarD. and ĆirovićG., Vehicle route selection with an adaptive neuro fuzzy inference system in uncertainty conditions[J], Decision Making: Applications in Management and Engineering1(1) (2018), 13–37.
17.
StojčićM., StjepanovićA. and StjepanovićĐ., ANFIS model for the prediction of generated electricity of photovoltaic modules[J], Decision Making: Applications in Management and Engineering2(1) (2019), 35–48.
18.
PamučarD., VasinL., AtanaskovićP., et al., Planning the City Logistics Terminal Location by Applying the Green-Median Model and Type-2 Neurofuzzy Network[J], Computational intelligence and neuroscience2016 (2016).
19.
LukovacV., PamučarD., PopovićM., et al., Portfolio model for analyzing human resources: An approach based on neuro-fuzzy modeling and the simulated annealing algorithm[J], Expert Systems with Applications90 (2017), 318–331.
20.
StojčićM., Application of ANFIS model in road traffic and transportation: A literature review from to [J], Operational Research in Engineering Sciences: Theory and Applications1(1) (2018), 40–61.
21.
ShannonC.E., A mathematical theory of communication [J], ACM SIGMOBILE Mobile Computing and Communications Review5(1) (2001), 3–55.
22.
GrayR.M., Entropy and information theory[M], Springer Science&Business Media, 2011.
23.
MaC.W. and MaY.G., Shannon information entropy in heavy-ion collisions[J], Progress in Particle and Nuclear Physics99 (2018), 120–158.
24.
de Jesus RubioJ., LughoferE., Meda-CampañaJ.A., et al., Neural network updating via argument Kalman filter for modeling of Takagi-Sugeno fuzzy models, Journal of Intelligent & Fuzzy Systems35(2) (2018), 2585–2596.
25.
SoaresA.M., FernandesB.J.T. and Bastos-FilhoC.J.A., Pyramidal neural networks with evolved variable receptive fields, Neural Computing and Applications29(12) (2018), 1443–1453.
26.
de Jesús RubioJ., Interpolation neural network model of a manufactured wind turbine, Neural Computing and Applications28(8) (2017), 2017–2028.
27.
LiuY., WangZ., YuanY., et al., Partial-Nodes-Based State Estimation for Complex Networks With Unbounded Distributed Delays, IEEE Transactions on Neural Networks and Learning Systems29(8) (2018), 3906–3912.
28.
de Jesús RubioJ., SOFMLS: online self-organizing fuzzy modified least-squares network, IEEE Transactions on Fuzzy Systems17(6) (2009), 1296–1309.
29.
LiX., LiH., SunB., et al., Assessing information security risk for an evolving smart city based on fuzzy and grey FMEA, Journal of Intelligent & Fuzzy Systems34(4) (2018), 2491–2501.
30.
LinZhao, JiushunLi and JianhuaCheng, New adaptive integrated navigation algorithm based on sliding window [J], Systems Engineering and Electronic Technology39(11) (2017), 2541–2545.
31.
DieboldF. and MarianoR., Comparing Predictive Accuracy, Journal of Business & Economic Statistics13 (1995), 253–263.
