Asphalt-surface defects detection, based on tyre/road noise analysis and geo-processing

Ramos Romero, CA; Asensio, C

Abstract

A new approach to detect different asphalt defectology based on tyre/road noise analysis by Machine Learning algorithms is proposed. In this way, a probe of concept was carried out to exploit the acoustic signal generated by the tyre-asphalt interaction. The audio data were recorded by an equipped vehicle that had travelled an established route with supervised surface conditions. The acoustic signal decomposition in frequency domain has shown to be relevant on automatic asphalt-defect classification. In this probe of concept, a group of four local and distributed road-surface defects were automatically detected and plotted on map. As a result, it is possible to visualize the asphalt zones with different superficial defectology. This new approach does not require a specific on-board instrumentation setup, so any vehicle could easily be an asphalt status tester with the installation of a microphone. The possibility of an interconnected fleet of sensing vehicles to gain robustness in the final report is also described. © 2019 Proceedings of the International Congress on Acoustics. All rights reserved.

Citation

Ramos Romero, C., & Asensio, C. (2019). Asphalt-surface defects detection, based on tyre/road noise analysis and geo-processing. International Congress on Acoustics, 7195-7199. https://doi.org/10.18154/RWTH-CONV-238915

• Journal Article Type: Article
• Conference Name: 3rd International Congress on Acoustics: Integrating 4th EAA Euroregio, ICA 2019
• Conference Location: Aachen, Germany
• Start Date: Sep 9, 2019
• End Date: Sep 23, 2019
• Publication Date: Sep 1, 2019
• Deposit Date: Dec 16, 2022
• Journal: Proceedings of the International Congress on Acoustics
• Electronic ISSN: 2415-1599
• Pages: 7195-7199
• DOI: https://doi.org/10.18154/RWTH-CONV-238915
• Publisher URL: http://doi.org/10.18154/RWTH-CONV-238915
• Additional Information: Event Type : Conference