Automatic Prediction of Maintenance Intervention Types in Roads using Machine Learning and Historical Records

Abstract

A methodology to support and automate the prediction of maintenance intervention alerts in transport linear infrastructures is a very useful tool for maintenance planning and managing. This piece of work goes along this track combining the current and predicted state condition of the assets, unit components of the infrastructure, with operational and historical maintenance data, to derive information about the needed maintenance operations to avoid later severe degradation. By means of data analytics and machine learning techniques, the proposed methodology generates a prioritized listing, ranked on severity levels, corresponding to the pre-alerts and alerts generated by all assets of the transport infrastructure. The methodology is applied and tested to a real case consisting of a road network with different section classes. The analysis of the results shows that the algorithms and tools developed have good predicting capabilities.

The Road Performance Analysis of the Tuah Madani Roundabout, Batam-Indonesia

“…Categories of roads are classified based on characteristics such as speed of travel, the volume of traffic, volume of traffic, strategic importance, etc (Morales, Reyes, Caceres, Romero, & Benitez, 2018). Kinds of transportation are substantial to traffic volume and traffic mix.…”

Optimization of the Procedures for Checking the Functionality of the Greek Railways: Data Mining and Machine Learning Approach to Predict Passenger Train Immobilization

“…The reference [28] applies four techniques of machine learning for the automatic prediction of traffic maintenance using functions and historical records. Its purpose is to create a list of prioritizing tasks in order to avoid its future decline.…”

Técnicas de aprendizaje automático para la predicción de intervenciones de mantenimiento en infraestructuras lineales de carretera

“…cuantificación del estado de los activos, gestión de alertas) y un sistema de apoyo a la toma de decisiones que recibe los resultados de estas herramientas y optimiza las intervenciones de mantenimiento. Esta comunicación presenta avances en el marco metodológico y analítico, y se avala con resultados obtenidos en un caso piloto (Infralert, 2016(Infralert, , 2017Morales et al, 2017Morales et al, , 2018Morales et al, , 2020. Las alertas estimadas se evalúan, de acuerdo con la información que brinda el sistema de toma de decisiones, en base a la evolución del estado de los activos de interés, reflejado por sus variables explicativas (e.g.…”