A Neural Network-Based Method for Fast Capture and Tracking of Laser Links between Nonorbiting Platforms

Area of Science:

• Optical Engineering
• Artificial Intelligence
• Telecommunications

Background:

• Fast capture tracking is crucial for laser links between non-orbiting platforms.
• Wavefront distortion and atmospheric turbulence degrade link performance.
• Existing methods may be limited by structural factors and environmental conditions.

Purpose of the Study:

• To investigate the performance of a convolutional neural network (CNN) for wavefront correction in free-space optical communication (FSO) systems.
• To analyze the impact of CNN-based correction on coupling power loss and tracking accuracy.
• To develop a quantitative method for evaluating and predicting laser link tracking stability.

Main Methods:

• An indoor experimental platform for a CNN-based FSO wavefront correction system was established.
• The CNN model's accuracy was validated by comparing simulation and experimental data.
• A tracking correlation equation was developed to analyze beam far-field dynamic characteristics' influence on link stability.

Main Results:

• The CNN method significantly reduced coupling power loss under both weak and strong turbulence.
• Coordinate decoupling of the coarse aiming mechanism was achieved, minimizing structural factor influence on tracking accuracy.
• A quantitative analysis method for link tracking stability was established, considering factors like beam divergence and atmospheric turbulence.

Conclusions:

• CNN-based wavefront correction is effective for improving laser link tracking stability in FSO systems.
• The proposed method offers a robust solution for optimizing laser link performance under various environmental conditions.
• Accurate modeling and quantitative analysis enhance the prediction and improvement of laser link tracking stability.