风机叶片的健康状态监测方法、系统、设备及介质
By combining physical information neural network (PINN) with sensor data, a surrogate model of blade aeroelastic response is constructed, which solves the shortcomings of existing wind turbine blade modeling methods in terms of accuracy and efficiency, and realizes high-precision monitoring and evaluation of the health status of flexible blades.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- SHANGHAI INVESTIGATION DESIGN & RES INST CO LTD
- Filing Date
- 2025-10-30
- Publication Date
- 2026-07-17
AI Technical Summary
Existing wind turbine blade modeling methods, such as the Euler-Bernoulli beam model, are insufficient in terms of computational accuracy and efficiency, especially in the aeroelastic analysis of large flexible blades.
By combining physical information neural network (PINN) with sensor data and optimizing the neural network parameters, a surrogate model of the blade's aeroelastic response is constructed. This model is then used to solve the nonlinear structural dynamics equations of the flexible blade. By combining data-driven and physical information-driven loss functions, the health status of the blade can be monitored.
It significantly improves the accuracy and reliability of blade load calculation, enabling more accurate reconstruction of the full-field load and strain distribution of the blade, and achieving precise assessment and prediction of the operating status of flexible blades.
Smart Images
Figure CN121765422B_ABST