Research on the Application of Neural Networks on Wind Turbine SCADA Data Analysis

被引：0

作者：

Du M. ^{[1
]}

Yi J. ^{[2
]}

Guo J. ^{[2
]}

Cheng L. ^{[1
]}

Ma S. ^{[2
]}

He Q. ^{[2
]}

机构：

[1] Dept. of Electrical Engineering, Tsinghua University, Haidian District, Beijing

[2] State Key Laboratory of Power Grid Safety and Energy Conservation (China Electric Power Research Institute Co., Ltd.), Haidian District, Beijing

来源：

Du, Mian (dm13@mails.tsinghua.edu.cn) | 2018年 / Power System Technology Press卷 / 42期

关键词：

Markov chain; Neural network; Performance evaluation; Self-organizing map; Wind power generation;

D O I：

10.13335/j.1000-3673.pst.2016.3283

中图分类号：

学科分类号：

摘要：

With the rapid development of offshore wind farms, the high cost of operation and maintenance is one of the important challenges for wind power development. Reducing the cost of operation and maintenance, and improving the availability of wind turbines draw widely attention from both domestic and worldwide. This paper proposed a data-driven performance evaluation method for wind turbine to improve the operation and maintenance efficiency and reduce the cost. This method combined neural network technology and stochastic process theory. It was adopted to analyze the wind turbine SCADA data, establish the wind turbine operation behavior model, and put forward the index to evaluate the fan performance. On the basis of this, the performance of the wind turbine was evaluated based on the SCADA data of 9 wind turbines. In view of the abnormal state of the wind turbine operation, the possible reasons were analyzed, and the corresponding maintenance suggestions were put forward. The results show that the method can effectively analyze the SCADA data, and the proposed indexes have important reference value for improving the operation and maintenance efficiency of the wind farm. © 2018, Power System Technology Press. All right reserved.

引用

页码：2200 / 2205

页数：5

共 22 条

[1]

Martin J., Ramsey D., The economics of wind energy, Journal of Applied Corporate Finance, 21, 2, pp. 100-109, (2009)

[2]

Marugan A.P., Marquez F.P.G., Perez J.M.P., Optimal maintenance management of offshore wind farms, Energies, 9, 46, pp. 1-20, (2016)

[3]

Liu L., Fu Y., Ma S., Et al., Maintenance strategy for offshore wind turbine based on condition monitoring and prediction, Power System Technology, 39, 11, pp. 3292-3297, (2015)

[4]

Nie M., Wang L., Review of condition monitoring and fault diagnosis technologies for wind turbine gearbox, Procedia Cirp, 11, pp. 287-290, (2013)

[5]

Sinha Y., Steel J.A., A progressive study into offshore wind farm maintenance optimization using risk based failure analysis, Renewable & Sustainable Energy Reviews, 42, pp. 735-742, (2015)

[6]

Sinha Y., Steel J.A., Failure prognostic schemes and database design of a software tool for efficient management of wind turbine maintenance, Wind Engineering, 39, pp. 453-478, (2015)

[7]

Du M., Ma S.C., He Q., A SCADA data based anomaly detection method for wind turbines, 2016 China International Conference on Electricity Distribution(CICED), pp. 2283-2288, (2016)

[8]

Du M., Ma S.C., He Q., Et al., A SOM based anomaly detection method for wind turbines health management through SCADA data, International Journal of Prognostics and Health Management, 29, pp. 1-13, (2016)

[9]

Yan Y., Nacelle orientation based health indicator for wind turbines, 2015 IEEE Conference on Prognostics and Health Management (PHM), pp. 326-333, (2015)

[10]

Castellani F., Astolfi D., Sdringola P., Et al., Analyzing wind turbine directional behavior: SCADA data mining techniques for efficiency and power assessment, Applied Energy, 83, pp. 112-120, (2015)

← 1 2 3 →