Search

El ruido de interacción neumático-carretera es un componente determinante en la emisión global del ruido de tráfico rodado, y adquiere relevancia debido a que todos los vehículos que transitan sobre las redes viales dentro y fuera de los entornos urbanos están continuamente contribuyendo a él. Varios factores lo modifican, sobre todo la velocidad de circulación del vehículo, el tipo de banda de rodadura del neumático y tanto las condiciones como características de la materialidad de la capa superficial de la carretera. Dado que el deterioro de la superficie asfáltica es un factor clave en el incremento de los niveles de ruido de tráfico rodado y en la disminución de la calidad operativa de la carretera, se ha detectado la oportunidad de investigar sobre el manejo del ruido de interacción neumático-carretera desde las materialidades implicadas en su generación. Esta tesis plantea un enfoque alternativo para el tratamiento de la señal sonora de rodadura. Es decir, que esta señal, habitualmente abordada como un elemento de contaminación acústica, sea gestionada como una fuente de información para la extracción de parámetros e indicadores relacionados con el diagnóstico de los materiales y los sistemas mecánicos que interactúan durante su generación. Mediante este enfoque fue posible explorar el estado y/o condición de la carretera a partir del análisis de la señal acústica generada durante la rodadura del neumático, a través de un ensayo no invasivo. La técnica incorporada permitió la identificación de la condición de deterioro del asfalto sin interrupciones y sobre largos tramos de carretera. Los resultados de esta investigación mostraron que el método implementado para la identificación automática de zonas deterioradas de la superficie de la carretera puede lograr una clasificación con una exactitud del 92%, para un grupo catalogado de 4 niveles de deterioro. Por otro lado, con la metodología para la inspección de la superficie asfáltica enfrentada desde un enfoque no supervisado, los clusters conformados mediante el análisis de conglomerados fueron capaces de reflejar las zonas de carretera con un comportamiento homogéneo. Adicionalmente, una etapa de procesado geográfico, permitió consolidar múltiples detecciones de la condición superficial de las vías donde se hayan realizado inspecciones reiteradas. Como resultado, se obtuvieron los reportes de las inspecciones mediante mapas viarios, facilitando así la comunicación de los resultados. Finalmente, es posible afirmar que la aplicación del método implementado ha permitido la clasificación y reconocimiento de las zonas deterioradas que contiene una vía operativa. ----------ABSTRACT---------- Tire-Road Interaction Noise (TPIN) is a key component in the overall emissions of the road traffic noise, and its study becomes relevant because all vehicles traveling on the road networks, inside and outside urban environments, are continuously contributing to it. Several factors modify the TPIN, mainly the speed of the vehicle, the type of tire tread pattern, and the conditions and characteristics of the materiality of the road-surface layer. Because deterioration of the asphalt surface is a key factor in increasing road traffic noise levels and decreasing the operational quality of the road, an opportunity has been identified to investigate the management of tire-road interaction noise based on the materials involved in its generation. This thesis proposes an alternative approach for the treatment of the TPIN signal. This rolling noise, usually treated as an element of noise pollution, will be used as a source of information on the parameters and indicators related to the diagnosis of materials and mechanical systems that interact during its generation. The importance of this field of research is due to the fact that the deterioration of the asphalt pavement is a key factor in both the increase in road traffic noise levels and the reduction in the operational quality of the road, with direct consequences on road safety. Through this approach, it was possible to explore the state and/or the condition of the road based on the analysis of the acoustic signal generated during the wheel rolling. As a result, a non-invasive test was implemented for road inspections. The implemented method, which starts with the recording of rolling sound data during normal vehicular traffic, without interruptions and over long stretches of road, made it possible to identify the state of deterioration of the asphalt. The results of this research showed that the implemented method for automatic identification of deteriorated areas of the road surface can achieve an accuracy classification of 92 %, for a cataloged group of 4 levels of deterioration. On the other hand, the unsupervised approach for asphalt surface inspection was able to identify the road areas with a homogeneous surface condition. The identification was based on the estimation of the clusters could be formed in the rolling noise signal data. In addition, a geographic processing stage allowed to handle multiple detections of the road condition where repeated inspections have been performed. As a result, reports were obtained through road maps, which facilitated the communication of the results. Finally, it can be concluded that the application of the implemented method has allowed the classification and identification of the deteriorated areas of an operational road, through the processing of the rolling noise produced by a traveling vehicle.

This paper proposes a novel approach to detect the pavement surface deterioration using tyre/road noise produced from a sensorized test-vehicle during a regular driving. The acoustic data have shown to be relevant on automatic asphalt-damage classification. In this proof of concept, four classes of bituminous road-surface states were classified, showing very promising results. The application of this technique will allow automated inspection, geolocation and prioritization of roads or street areas that may need maintenance and repair, in addition to informing drivers or autonomous vehicles about road safety conditions in order to prevent accidents. With this approach any vehicle can easily become an asphalt status tester with the installation of a microphone, enabling the possibility to transform any fleet of vehicles into a networked signal acquisition system that may form part of the decision support of administrations in the management and maintenance of road infrastructures, at a very low cost., Part of this work was performed within the Ecuadorian Government Granth: “Convocatoria Abierta 2017” of Secretaria de Educación Superior, Ciencia, Tecnología e Innovación (SENESCYT), received by the author C. Ramos-Romero.