不同风况特性对风力机叶片载荷的影响及预测研究

张晓涛; 马剑龙; 苏宏杰; 李秋燕; 赵明博; 高志鹰

doi:doi:10.19912/j.0254-0096.tynxb.2024-1702

English Version Journal Login

您当前的位置：

首页 >

文章列表页 >

不同风况特性对风力机叶片载荷的影响及预测研究

更新时间：2026-03-06

- 不同风况特性对风力机叶片载荷的影响及预测研究
- Vol. 47, Issue 2, Pages: 435-443(2026)
- 作者机构：
- 作者简介：
- 基金信息：
- DOI：doi:10.19912/j.0254-0096.tynxb.2024-1702
  CLC： TK83
- Online First：05 March 2026，
  
  Published：05 March 2026
- 稿件说明：
移动端阅览
张晓涛, 马剑龙, 苏宏杰, et al. 不同风况特性对风力机叶片载荷的影响及预测研究[J]. 2026, 47(2): 435-443.
DOI：

张晓涛, 马剑龙, 苏宏杰, et al. 不同风况特性对风力机叶片载荷的影响及预测研究[J]. 2026, 47(2): 435-443. DOI： doi:10.19912/j.0254-0096.tynxb.2024-1702.

摘要

基于NREL 5 MW风力机组模型

对不同平均风速、湍流强度以及风剪切指数环境组合工况下的风力机叶片载荷进行仿真计算并分析各风况条件下对叶片载荷挥舞摆振方向的合力矩的影响。同时建立反向传播（BP）神经网络

采用预测模型预测“平均风速、湍流强度、风剪切指数-叶片载荷”复杂耦合关系

并与径向基函数（RBF）神经网络、长短期记忆（LSTM）神经网络以及支持向量机（SVM）算法预测模型对比验证BP预测模型的性能。结果表明

湍流强度对叶片平均载荷的影响较小

在高风速区间对叶片极限载荷和等效疲劳载荷的影响很大;风剪切指数在高风速状态下对平均载荷和极限载荷有较为明显的影响;在额定风速范围对等效疲劳载荷影响最大。同时BP神经网络载荷预测模型相较于其他RBF、SVM、LSTM模型具有更好的精准度

验证了预测模型的可行性和准确性

为叶片载荷监测和安全运行提供有效支持。

Abstract

Based on the NREL 5 MW wind turbine model

the simulation calculations of wind turbine blade loads under different average wind speeds

turbulence intensities and wind shear indices are carried out

and analyzing the effects of the blade loads on the combined moments in the swing and oscillation direction of blade loads and swing oscillations under various wind conditions. At the same time

a back-propagation （BP） neural network is established

and a prediction model is used to predict the complex coupling relationship of “average wind speed

turbulence intensity

wind shear index-blade load” The accuracy and reliability of the BP prediction model are compared with those of radial basis function （RBF）neural network

long and short-term memory （LSTM） neural network and support vector machine （SVM）. The results show that the turbulence intensity has a small effect on the average blade load

and has a great effect on the blade ultimate load and equivalent fatigue load in the high wind speed range; the wind shear index has a more obvious effect on the average load and ultimate load in the high wind speed condition; and has the greatest effect on the equivalent fatigue load in the rated wind speed range. Meanwhile

the BP neural network load prediction model has better accuracy than that of RBF

SVM and LSTM models

which verifies the feasibility and accuracy of the prediction model .

关键词

Keywords

references

高俊云. 湍流强度分布对风电机组疲劳载荷的影响研究[J]. 机械工程与自动化, 2024(3): 38-40.

葛君, 陈前, 王瑞良, 等. 不同海域水文环境与风力机疲劳载荷差异性研究[J]. 太阳能学报, 2024, 45(1): 205-209.

张立栋, 石强, 姜铁骝, 等. 不同强度湍流风对风力机气动载荷的影响[J]. 分布式能源, 2023, 8(5): 61-68.

刘为, 王瑞良, 孙勇, 等. 不同风况条件对风力发电机组等效疲劳载荷的影响[J]. 机电工程技术, 2020, 49(12): 114-117.

巫发明, 杨从新, 王靛, 等. 湍流强度对风电机组动力学特性及载荷的影响[J]. 农业工程学报, 2020, 36(13): 48-55.

李伟, 徐伊丽. 风切变等风况特性对风力发电机组载荷影响研究[J]. 机电工程技术, 2022, 51(1): 97-100.

付德义, 张晓东, 王瑞明, 等. 特定场址条件下风电机组载荷适应性评估[J]. 太阳能学报, 2021, 42(6): 425-431.

王伟, 王海云. 基于Adam优化BP神经网络的风机等效疲劳载荷预测[J]. 现代电子技术, 2023, 46(17): 102-106.

许扬, 蔡安民, 张林伟, 等. 基于BP神经网络和多因素权重法的风电机组载荷预测和分析[J]. 热力发电, 2022, 51(8): 42-49.

牟哲岳, 孙勇, 王瑞良, 等. 基于实测数据和机器学习的风电机组载荷预测模型[J]. 太阳能学报, 2023, 44(10): 414-419.

张良, 何山, 艾纯玉. 基于Sine-SSA-BP神经网络模型的风机叶根载荷预测[J]. 可再生能源, 2023, 41(10): 1322-1328.

NATARAJAN A, BERGAMI L.Determination of wind farm life consumption in complex terrain using ten-minute SCADA measurements[J]. Journal of physics: conference series, 2020, 1618(2): 022013.

SCHRÖDER L, KRASIMIROV DIMITROV N, VERELST D R, et al. Wind turbine site-specific load estimation using artificial neural networks calibrated by means of high-fidelity load simulations[J]. Journal of physics: conference series, 2018, 1037(6): 062027.

LIU P F, CHEN H Y, WU T, et al.Fatigue life evaluation of offshore composite wind turbine blades at Zhoushan Islands of China using wind site data[J]. Applied composite materials, 2023, 30(4): 1097-1122.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

NOVEL DYNAMIC STALL PREDICTION MODEL BASED ON THEODORSEN THEORY AND ITS APPLICATION

SENSITIVITY FACTOR ANALYSIS ON INITIAL DAMAGE OF WIND TURBINE BLADE SPAR BASED ON GSA

IEA 15 MW风力机叶片仿生内肋结构设计研究

基于VMD-COMTBO-BiLSTM光伏阵列故障诊断研究

俯仰波浪前缘叶片动态失速主动控制研究

Related Author

Li Zhiguo

Gao Zhiying

Zhang Yajing

Zhang Liru

Wang Jianwen

Sun Ning

Zhou Bo

Zheng Haocheng

Related Institution

College of Energy and Power Engineering, Inner Mongolia University of Technology

Mechanical Engineering College, Inner Mongolia University of Technology

Key Laboratory of Wind and Solar Energy Utilization and Optimization in Inner Mongolia Autonomous Region

School of Transportation and Municipal Engineering, Inner Mongolia Technical College of Construction

School of Mechanical Engineering, Shenyang University of Technology

AI问答

⁰