GPR-based high-precision passive-support fiber ice coating detection method for power transmission lines

Area of Science:

• Electrical Engineering
• Materials Science
• Environmental Monitoring

Background:

• Ice accumulation on power transmission lines poses significant risks, including structural damage and power outages.
• Accurate monitoring of ice thickness is crucial for preventing failures and ensuring grid stability.
• Existing methods often rely on direct line measurements, which can be complex and costly.

Purpose of the Study:

• To propose and demonstrate a novel monitoring method for detecting ice coating on power transmission lines.
• To utilize fiber Bragg grating sensors and machine learning for predicting ice thickness.
• To establish a cost-effective and accurate method for ice monitoring using only environmental data.

Main Methods:

• Installation of fiber Bragg grating sensors on transmission line towers to collect micrometeorological data.
• Application of Gaussian process-based machine learning algorithms to analyze real-time sensor data.
• Development of a predictive model for ice thickness based on environmental parameters.

Main Results:

• The proposed method successfully predicted ice thickness on power transmission lines.
• Experimental validation showed mean squared error and mean absolute percentage error values below 1%.
• This represents the first instance of monitoring ice thickness using solely micrometeorological information.

Conclusions:

• The developed fiber Bragg grating sensor and machine learning approach offers a highly accurate and novel solution for monitoring ice on power lines.
• The method's reliance on micrometeorological data makes it a potentially scalable and cost-effective solution for grid operators.
• This breakthrough in monitoring technology enhances the reliability and safety of power transmission infrastructure.