OPGW positioning and early warning method based on a Brillouin distributed optical fiber sensor and machine learning

Area of Science:

• Optical Fiber Sensing
• Machine Learning Applications
• Power Line Monitoring

Background:

• Optical Fiber Composite Overhead Ground Wire (OPGW) cables are critical for power line communication and protection.
• Accurate fault positioning and early warning are essential for maintaining OPGW operational reliability.
• Existing methods for OPGW fault detection can be inefficient and lack precision.

Purpose of the Study:

• To propose an advanced method for OPGW positioning utilizing Brillouin distributed optical fiber sensors and machine learning.
• To enhance the efficiency and accuracy of fault detection and early warning systems for OPGW cables.
• To improve the overall operational reliability of OPGW infrastructure.

Main Methods:

• Implementation of distributed Brillouin optical time-domain reflectometry (BOTDR) and Brillouin optical time-domain analyzer (BOTDA) with ranges up to 110 km and 125 km, respectively.
• Application of unsupervised machine learning, specifically Density-Based Spatial Clustering of Applications with Noise (DBSCAN), for automatic splicing point identification based on Brillouin Frequency Shift (BFS) differences.
• Adaptation of an adaptive parameter selection method using k-distance to mitigate parameter sensitivity issues.

Main Results:

• The proposed DBSCAN algorithm achieved a validity exceeding 96%, validated by external indices and BFS curves.
• Distinguishing connecting towers based on clustering results and OPGW tower schedules demonstrated a 100% recognition rate.
• Distributed strain information was directly extracted from BFS to strain, enabling precise abnormal region positioning and warning.

Conclusions:

• The developed method significantly improves the efficiency of fault positioning and early warning for OPGW cables.
• The integration of Brillouin sensing and machine learning offers a robust solution for real-time OPGW monitoring.
• This approach contributes to enhanced operational reliability and safety of power transmission infrastructure.