A Combined Machine Learning and Model Updating Method for Autonomous Monitoring of Bolted Connections in Steel Frame Structures Using Vibration Data

This research paper presents a novel structural health monitoring strategy based on hybrid machine learning and finite element model updating method for the of bolted connections in steel planer frame structures using vibration data. Towards this, support vector is trained with discriminative features obtained from time history data, those are used to distinguish between damaged undamaged joints. An FE considered where fixity factor (FF) joint modeled rational springs FF spring assumed as severity level loosening bolts. The Cat Swarm Optimization technique further applied update calculate factors Initially, laboratory-based experimental single-story structure later extended pseudo-numerical four-story structure. results show that successfully localizes joints estimates their factors.