Improving Transportation and Connection Safety Through Seismic Damage Prediction for Aging Bridges

Bridges are critical components of transport for any nation. However they may suffer damages due to several reasons which may lead to collapse, and introduce hazards in transportation. Hence, predicting their safety is crucial for safety in road transport. Many existing bridges around the world, especially in seismic zones, were constructed decades ago and are now aging. These aging structures face increased vulnerability during earthquakes due to material deterioration, outdated design standards, and cumulative stress from environmental and traffic loads. However, human inspection in earthquake stricken areas may take a lot of time increasing the risk of using bridges which are severely damaged thereby risking human life. Hence, quick automated tools are required which can predict bridge damages quickly and based on less number of parameters with relatively high accuracy. The proposed model utilizes a large standard corpus of data pertaining to possibility of collapse of aging bridges under seismic impacts. A statistical regression model is proposed which would map the inputs such as age, seismic impact, distance from epicentre to the possibility of collapse. The proposed approach combines Particle Swarm Optimization (PSO) and Statistical Regression. It is expected that the proposed model would be able to render higher prediction accuracy compared to existing research models in the domain. The data set used is the Stanford Earthquake Dataset (STEAD). It has been shown that the proposed work attains high classification accuracy and low computation complexity making the model effective for quick evaluation of bridges from seismic impacts.