Acoustic Emission-Based Decision Support for Bridge Safety in Smart Cities

Abstract

This paper presents an acoustic emission (AE) based Identification of Active Anomalies (IAA) system, using signal clustering, image recognition, and machine learning, for monitoring the condition of a highway overpass near a large urban agglomeration. The monitoring results provide the basis for assessing the structural condition of the asset and for the automated load (traffic) control necessary to ensure its safe operation. Acoustic emission (AE) signals recorded during service loads undergo multi-parametric signal analysis using pattern recognition and are assigned classes corresponding to specific anomalies in the material or structure. Each class is associated with a level of structural hazard, ranging from safe operation to loss of safety. Corresponding traffic control measures, including vehicle speed and weight limits, ensure safe operation. The method was experimentally applied to monitor an A2 highway overpass, part of the Łódź city transport hub, facilitating north-south and east-west travel in Poland. This enables highway administration services and agencies to prevent sudden, unforeseen structural failures proactively. The IAA system proves to be an effective diagnostic tool for the efficient and safe operation of a Smart City, enabling the rational allocation of funds for road infrastructure maintenance