Automated Classification of Surface Properties of Rocks

Rockfall is a hazard in mountainous areas threatening infrastructure and human lives. A major method that is adopted for this issue is inspecting rock surfaces using pry bars. The inspector reaches to rock blocks, hits the rock surface, detect and remove the loose rocks. This method is very labor demanding, unsafe, and challenging. This research presents a method that automatize the inspection of the areas and rock blocks that are prone to rockfall events. A tap testing system on a robot is proposed which collects the sound of the hammer taps on the surface and classifies them using principal component analysis (PCA) scores of each tap sound's signal. This research enables the inspectors to collect data remotely, detect loose rocks, and save data for future references.