Integrated structural health monitoring system based on SIF analysis and Artificial Intelligence: a methodological proposal

Abstract

The fast development of technology for structural monitoring has brought to light the need of developing methods that are both more efficient and accurate in order to identify and evaluate flaws in steel structures during their construction. In the realm of engineering, one of the most significant challenges is to guarantee the safety and integrity of essential infrastructures, which include crucial structures like bridges, buildings, and utilities. Variations in stress, unfavourable climatic conditions, and the formation of faults are all factors that might contribute to the degeneration of a structure, which can have potentially catastrophic effects. For the purpose of overcoming this obstacle, sophisticated monitoring systems have been created. These systems integrate contemporary sensor technologies with analyses that are based on artificial intelligence (AI). In this paper, an Integrated Structural Health Monitoring System (ISHMS) is proposed. This system makes use of a sensor network and machine learning algorithms in order to continually analyse the Stress Intensity Factor (SIF) of infrastructures. As a result of the system's capability to identify, localise, and estimate the progression of major flaws, preventative measures and risk reduction are made possible [1].