AUTOMATIC PREDICTION OF MAINTENANCE INTERVENTION TYPES IN ROADS USING MACHINE LEARNING AND HISTORICAL RECORDS

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