Abstract

Bangladesh is a developing country where bridges are a crucial part for daily transportation. Unfortunately, Bangladesh's geological location makes it a hotspot for various natural calamities which can eventually compromise the lon-gevity of various infrastructures over time. Therefore, structural health monitor-ing becomes a crucial factor for improving the longevity of structures and avoid-ing disasters of large magnitudes. Thanks to the emerging advancements in technology, there are various tools and sensors which allows for monitoring of specific factors which can help predict distress within a structure. Such integration can help engineers to monitor the conditions of structures and can allow them to intervene at the correct time to avoid collapse and further damage. The case studies reviewed in this research paper which used predictive structural health monitoring solutions like the Geumdand Bridge of South Korea and the Tamar Bridge in United Kingdom (UK) showed significant improvement of longevity, safety and condition monitoring. With the correct integration of appropriate structural health monitoring sensors like tilt sensors, orientation sensors, strain sensors, temperature sensors etc. can gather appropriate data which can be pro-cessed using a capable machine learning algorithm like Random Forest or similar algorithm to give accurate readings of structural integrity status and give early warnings regarding possibilities of a structural collapse. This research papers ex-plores this integration in a more dynamic manner by integration an EWS system and hopefully sheds light in the importance of structural health monitoring for large complex bridges and implementation of an early warning system (EWS).