Abstract
The pavement condition index (PCI) calculates pavement conditions based on current distresses. In traditional PCI calculation, a visual inspection method collects field data such distresses and stiffness. Data helps anticipate PCI values, a lengthy and difficult process. This research aims to create a simple, adaptable model that shows how PCIs, torments, and stiffness relate. Artificial neural networks (ANN) forecast PCI values for various parts, eliminating manual labour and specialized procedures. Based on distresses, the PCI estimates pavement conditions. For typical PCI intentions, a visual inspection device collects field data such distresses and stiffness. The data allows time-consuming and complicated PCI estimation. This study seeks to construct a simple, extensible model that links PCIs, torments, and rigidity. ANN prediction part PCI values, eliminating the need for manual labour and specialized technologies.