Improving TDOA Radar Performance in Jammed Areas through Neural Network-Based Signal Processing.

Area of Science:

• Signal Processing
• Artificial Intelligence
• Navigation Systems

Background:

• Traditional Time Difference of Arrival (TDOA) methods face significant challenges in accurately estimating target positions under electromagnetic jamming.
• Jamming degrades signal quality, leading to increased positioning errors and reduced system reliability.

Purpose of the Study:

• To develop and evaluate a novel algorithm for robust target positioning in the presence of jamming using TDOA.
• To leverage deep neural networks to enhance the performance of TDOA-based localization under adverse signal conditions.

Main Methods:

• The proposed method employs a deep neural network trained to process TDOA measurements corrupted by jamming signals.
• Simulations were conducted to compare the performance of the deep learning-based TDOA against conventional TDOA techniques.

Main Results:

• The deep neural network-based TDOA method demonstrated superior accuracy in target position estimation compared to traditional methods when subjected to jamming.
• The algorithm showed improved efficiency, providing reliable positioning solutions under challenging signal environments.

Conclusions:

• Deep neural networks offer a promising approach to overcome the limitations of traditional TDOA methods in jammed environments.
• The developed algorithm provides a more accurate and efficient solution for target localization in electronic warfare and other applications susceptible to jamming.