Wind turbine generator unit variable pitch system deterioration state online monitoring method and system

By constructing a baseline model library covering multiple health conditions and a Gaussian mixture health model, the problem of difficulty in monitoring early degradation characteristics in wind turbine pitch systems has been solved, enabling accurate quantification of system performance and early warning, thereby improving the operational reliability and safety of wind turbines.

CN122191017APending Publication Date: 2026-06-12HUANENG SHAANXI JINGBIAN ELECTRIC POWER CO LTD +2
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
HUANENG SHAANXI JINGBIAN ELECTRIC POWER CO LTD
Filing Date
2026-03-16
Publication Date
2026-06-12

AI Technical Summary

Technical Problem

Existing technologies are insufficient to effectively monitor early degradation characteristics in wind turbine pitch systems, resulting in the inability to detect system performance degradation in a timely manner, and problems such as low signal-to-noise ratio and lack of stable evaluation benchmarks.

Method used

By constructing a baseline model library covering various health conditions, and using Gaussian mixture health models for dynamic matching and comparison, an adaptive health benchmark is established. Combined with model parameters such as damping and response speed, the precise quantification and early warning of subtle deterioration characteristics are achieved.

Benefits of technology

It enables early fault warning of wind turbine pitch system, improves operational reliability and safety, avoids the lack of evaluation benchmark due to changing operating conditions, and improves monitoring accuracy and reliability.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122191017A_ABST
    Figure CN122191017A_ABST
Patent Text Reader

Abstract

The application discloses a wind turbine variable pitch system degradation state online monitoring method and system, which can establish an adaptive dynamic health benchmark for non-standardized variable pitch process by performing online system identification for each real-time captured variable pitch event, establishing a dynamic mathematical model thereof, and dynamically matching and comparing the dynamic mathematical model with a baseline model library covering multiple health working conditions, effectively solving the technical problem of missing evaluation benchmark caused by variable working conditions; further, the application maps invisible soft degradation into changes of model parameters with clear physical meaning such as damping and response speed, so as to realize accurate quantification of weak degradation characteristics from strong working condition noise, and then realizes early warning of soft failure of the system through real-time calculation of multi-dimensional degradation indexes, thereby improving the operation reliability and safety of the wind turbine.
Need to check novelty before this filing date? Find Prior Art