Icing condition prediction of wind turbine blade based on neural network technology

doi:10.19936/j.cnki.2096-8000.20221128.014

Abstract

Abstract: Wind turbine blades installed in cold areas are inevitably covered with ice, which affects the normal operation of wind turbines. The natural frequencies of blades vary with the locations and mass of icing. In this paper, the finite element modal analysis of 2 MW wind turbine blade is carried out, and the relationships between the change rate of natural frequency of ice-covered blade and the mass of ice-covered blade at different positions are constructed. The BP artificial neural network is trained with this data set and the prediction ability is analyzed. The research shows that the average relative error rate of predicting all ice-covered blades is 13.21%, which is 1.56% higher than the prediction accuracy of Gantasala et al., by using the relational training artificial neural network which is constructed considering the influence degree of different ice-covered locations on the natural frequency of all ice-covered leaves. The trained artificial neural network model can predict the locations and mass of icing. The result can provide data support for subsequent heating or ultrasonic deicing and improve deicing efficiency and reduce energy consumption.

Key words: wind turbine blade, neural network, natural frequency, ice

CLC Number:

TB332

MA Fei-yu, ZHANG Chun-zhi, LI Fei-yu. Icing condition prediction of wind turbine blade based on neural network technology[J]. COMPOSITES SCIENCE AND ENGINEERING, 2022, 0(11): 96-101.

References

[1] 王建录. 风能与风力发电技术[M]. 北京: 化学工业出版社, 2015.
[2] 国家能源局. 2020年全国电力工业统计数据 [EB/OL]. 2021-01-20[2021-03-09]. http://www.nea.gov.cn/2021-01/20/html..
[3] HABIBI H, CHENG L, ZHENG H T, et al. A dual deicing system for wind turbine blades combining high-power ultrasonic guided waves and low-frequency forced vibrations[J]. Renewable Energy, 2015, 83: 859-870.
[4] 刘胜先, 李录平, 余涛, 等. 基于振动检测的风力机叶片覆冰状态诊断技术[J]. 中国电机工程学报, 2013, 33(32): 88-95, 1.
[5] 龚妙, 李录平, 刘瑞, 等. 基于运行参数特征的风力机叶片覆冰诊断方法[J]. 动力工程学报, 2019, 39(3): 217-219.
[6] GANTASALA S, LUNENO J C, AIDANPAA J O. Identification of ice mass accumulated on wind turbine blades using its natural frequencies[J]. Wind Engineering, 2018, 42(1): 66-84.
[7] CATTIN R, HEIKKILA U. Evaluation of ice detection systems for wind turbines[EB/OL]. 2016-01-03[2021-03-09]. https://www.vgb.org/vgbmultimedia/392 Final+report-p-10476.pdf.
[8] WEI K, YANG Y, ZUO H, et al. A review on ice detection technology and ice elimination technology for wind turbine[J]. Wind Energy, 2020, 23: 433-457.
[9] 沃德·海伦, 斯蒂芬·拉门兹, 波尔·萨斯. 模态分析理论与试验[M]. 白化同, 郭继忠, 译. 北京: 北京理工大学出版社, 2001.
[10] 李飞宇, 崔红梅, 苏宏杰, 等. 基于模态频率的风力机叶片覆冰检测方法[J]. 复合材料科学与工程, 2021(2): 19-23, 64.
[11] Department of Fluid Mechanics. Tjaereborg wind turbine geometric and operational date[EB/OL]. 1990-11-30[2021-03-09]. http://130.226.56.150/extra/web_docs/tjare/VK-184-901130.pdf.
[12] Guideline for the certification of wind turbines: GL—2010[S]. German: Germanischer Lioyd, 2010.
[13] 陈彩凤, 杨杰, 成斌, 等. 覆冰条件下旋转风力机叶片应力与模态分析[J]. 玻璃钢/复合材料, 2018(7): 26-30.
[14] GANTASALA S, LUNENO J C, AIDANPAA J O. Influence of icing on the modal behavior of wind turbine blades[J]. Energies, 2016, 9(11): 862-868.
[15] LEE J C, SHIN S C, KIN S Y. An optimal design of wind turbine and ship structure based on neuro-response surface method[J]. International Journal of Naval Architecture and Ocean Engineering, 2015, 7: 750-769.
[16] CHANG G W, HU H J, CHANG Y R, et al. An improved neural network-based approach for short-term wind speed and power forecast[J]. Renewable Energy, 2017, 105: 301-311.
[17] JIMENEZ A A, MARQUEZ F G, MORALEDA V B, et al. Linear and nonlinear features and machine learning for wind turbine blade ice detection and diagnosis[J]. Renewable Energy, 2019, 132: 1034-1048.
[18] DONG X, GAO D, LI J, et al. Blades icing identification model of wind turbines based on SCADA data[J]. Renewable Energy, 2020, 162: 575-586.