Improving aviation navigation using dme, neural networks, and real-time radio and non-radio sensor fusion

Abstract

Distance measuring equipment (DME), which gauges the distance between an aircraft and a ground station, is an essential navigational tool in aviation. However, because of instrument constraints, multipath interference, and ambient conditions, DME measurements are frequently noisy and prone to errors. This study introduces a framework that integrates machine learning (ML), sensor fusion, neural networks (NNs), and real-time processing with the aim at enhancing the accuracy and reliability of distance estimation, with particular emphasis on regression models. To boost robustness, the suggested system uses sensor fusion to combine DME data with inputs from additional sensors, such as GPS and Inertial Navigation Systems (INS). The intricate correlations between sensor inputs and actual distance are modelled by NNs because of their ability to produce precise predictions even in the presence of noise and they provide a very accurate distance calculation with minimal latency. ML based regression models further improve system reliability by detecting and correcting anomalies in the sensor data. When tested in MATLAB and compared with standalone DME measurements, the proposed system shows higher accuracy of distance estimation. In addition, the real-time sensor fusion ensures precise and timely outputs for essential aviation applications. Using this method not only improves the DME system, but also provides a scalable and flexible solution for different navigation and positioning systems in dynamic scenarios. The system is measured based on significant metrics including mean squared error (MSE), peak signal-to-noise ratio (PSNR) and signal-to-noise ratio (SNR).