Industrial equipment strain data multi-channel acquisition system based on fiber grating sensor
By constructing a three-dimensional state vector and a Gaussian mixture model, and dynamically adjusting the exposure level and threshold, the demodulation failure problem caused by the difference in channel reflection spectrum intensity in the fiber Bragg grating sensing system was solved, achieving high accuracy and reliability of strain data and enhancing the system's adaptive capability.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- YUHENG POWER STATION OF SHAANXI HUADIAN YUHENG COAL POWER CO LTD
- Filing Date
- 2026-04-14
- Publication Date
- 2026-07-17
AI Technical Summary
Existing fiber Bragg grating sensing systems in industrial equipment suffer from significant differences in reflectance spectrum intensity due to varying environmental conditions and fiber loss at different measurement points. Unified exposure time and fixed thresholds are insufficient to meet the peak-finding requirements of both strong and weak channels, leading to demodulation failures or increased errors in some channels. Furthermore, the lack of dynamic identification and adaptive parameter adjustment mechanisms affects the continuity and reliability of strain data.
The system employs a baseline construction module, a state determination module, an adaptive demodulation module, and an iterative correction module. By constructing a three-dimensional state vector and a Gaussian mixture model, it dynamically adjusts the exposure level and threshold. Combined with the CA-CFAR algorithm and the Kalman prediction model, it achieves channel-level adaptive demodulation and parameter correction.
It significantly improves the success rate of multi-channel demodulation, ensures that both strong and weak channels can obtain clear and distinguishable reflection peaks, improves the accuracy of strain calculation, enhances the system's robustness to channel characteristic drift, and prevents long-term performance degradation.
Smart Images
Figure CN122408642A_ABST