Airplanes generate severe turbulent airflow, known as trailing vortices, which can have an adverse control impact on following airplanes. Aviation authorities worldwide impose separation standards between leading and following airplanes to reduce the capacity of airports to handle large volumes of traffic. Optimizing these separations is highly sought after. These separations are optimized based on several factors such as airplane size, weight, and design in addition to weather conditions. The recognition of trailing vortices is usually done manually through examination of pilot reports and analysis of flight data recorders (FDRs). This process can be subjective and depends greatly on the analyst's experience. Automated processes based on Artificial Intelligence (AI), such as Machine Learning (ML) and Computational Intelligence (CI), have shown a potential to better deal with such problems. Results obtained from these various techniques are presented to show their degree of appropriateness. Flight event identification, such as encounters with airplane vortices, wind shear, turbulence, and uncommanded control, can help establish aircraft warning and monitoring systems to enhance automatic flying, especially during landing and take-off. The developed model can attain great assurance recognition of the aircraft wake turbulence by supporting the air traffic controllers with the decision information in actual work to ensure aircraft safety. The success rates obtained from the investigated CI models compare favorably well to results obtained by either manual and/or other CI-based techniques when applied to vortex identification.
Read full abstract