@article {Park:2020:0736-2935:5651,
title = "ISO 8608-based pavement roughness classification with artificial neural networks using suspension vibration measurements",
journal = "INTER-NOISE and NOISE-CON Congress and Conference Proceedings",
parent_itemid = "infobike://ince/incecp",
publishercode ="ince",
year = "2020",
volume = "261",
number = "1",
publication date ="2020-10-12T00:00:00",
pages = "5651-5661",
itemtype = "ARTICLE",
issn = "0736-2935",
url = "https://ince.publisher.ingentaconnect.com/content/ince/incecp/2020/00000261/00000001/art00073",
author = "Park, Yun Seol and Jeon, Ju Hyun and Kang, Yeon June",
abstract = "Road roughness is an important indicator of road conditions; it affects ride comfort, roadinduced noise, and wear of tires. Existing methods of gauging road roughness are expensive and impractical because they use specific instrumented vehicles to physically measure road irregularities.
This paper proposes a method for estimating road profiles using artificial neural networks with vehicle suspension response as the input parameter. The neural network is trained using experimental data that include the road profile measured by laser profiling sensors and acceleration response
of the vehicle suspension and body under normal operating conditions. The trained neural network renders the road surface profile corresponding to the measured acceleration data and classifies the road roughness according to the ISO 8608 standard with reasonable accuracy. Furthermore, the
proposed methodology correlates well with the international roughness index, which is a well-recognized standard in the field of pavement management. Overall, this automatic classifier is shown to be beneficial for assessing road conditions and maintaining road pavements, thus, constituting
a method that is more costefficient and accurate than previous ones.",
}