Enhancing air traffic safety at airports is crucial for reducing incidents and aircraft accidents. Incidents linked to foreign object debris are related to the emergence and progression of pavement distress. To address efficient maintenance and repairs, a pavement management system is in place at airports. This system involves visual inspections of pavements, which we recommended integrating with cutting-edge smartphone technologies mounted in a maintenance vehicle. We developed an application that utilizes data from smartphone accelerometers to assess the potential of a shallow neural network to inspect airport pavement distresses. The straightforward design of this specific neural network offers benefits such as considerable accuracy and rapid training, while not demanding significant computational resources. Conversely, data processing was reasonably complex and required substantial effort.
Capacities of Shallow Neural Network to Indicate and Clasify Airport Surface Distresses
27.05.2025
919313 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Predicting Airport Capacities Using Neural Networks
IEEE | 2024
|Probabilistic modelling of flexible pavement distresses for network management
Online Contents | 2015
|Probabilistic modelling of flexible pavement distresses for network management
Online Contents | 2017
|Shallow gasoline discovery at airport still puzzle
Engineering Index Backfile | 1938
|Shallow gasoline discovery at airport still puzzle
Engineering Index Backfile | 1938
|