Wind turbine blade natural frequency self-learning and trend analysis method and system

By combining the variable cross-section equivalent beam model and the self-learning model with the multi-physics field correction method, the problems of frequency identification accuracy and adaptability in wind turbine blade monitoring were solved, and high-precision blade health status assessment and prediction were achieved.

CN122413233APending Publication Date: 2026-07-17HUANENG RENEWABLES CORP LTD HEBEI BRANCH
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202610597743.4
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2026-04-30
Publication Date
2026-07-17

AI Technical Summary

Technical Problem

Existing wind turbine blade monitoring technologies suffer from low frequency identification accuracy and poor reliability, are unable to adapt to different operating conditions and aging levels, fail to effectively eliminate the influence of speed and wind speed, and lack trend analysis and multi-blade collaborative diagnostic capabilities.

Method used

Modal decoupling is achieved by using a variable cross-section equivalent beam model, combined with a kernel density estimation self-learning model and a multi-physics correction method, and through wavelet packet trend decomposition and collaborative diagnostic techniques, accurate frequency decoupling and trend analysis are realized.

Benefits of technology

It improves frequency identification accuracy and system adaptability, can accurately reflect changes in blade structural stiffness, predict remaining runtime, reduce false alarms and missed alarms, and enhance operation and maintenance prediction capabilities.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122413233A_ABST
    Figure CN122413233A_ABST
Patent Text Reader

Abstract

本发明公开了一种风电机组叶片固有频率自学习与趋势分析方法及系统,通过采集叶片振动信号,基于变截面等效梁模型与回传射线矩阵法进行模态解耦,提取并评估固有频率置信度;利用稳态数据经核密度估计构建自学习模型,确定基准频率与动态预警边界;采用多物理场耦合修正剔除气动与运动干扰,经小波包分解获取刚度演化趋势,结合损伤映射实现健康判别与剩余运行时长预测;同时支持多叶片协同诊断与集成学习损伤分类。本发明可提升频率识别准确性,降低工况干扰,实现叶片结构损伤早期预警与寿命预测,适用于风电机组叶片在线健康监测。
Need to check novelty before this filing date? Find Prior Art