Transfer learning for bridge monitoring: model testing of four lab-scale multi-span continuous girder bridges under changing temperatures and damage conditions

This dataset is accompanied by a journal paper: “Transfer Learning in Bridge Monitoring: Laboratory Study on Domain Adaptation for Population-Based SHM of Multispan Continuous Girder Bridges”, Valentina Giglioni, Jack Poole, Robin Mills, Ilaria Venanzia, Filippo Ubertini, Keith Worden, MSSP.

This dataset was collected with the main aim of investigating methods for population-based SHM. Modal testing was performed on a modular bridge kit which allows for modification of the deck length, and support locations. In this dataset, data are available for four configurations of three span bridges, tested under changing temperatures using an environmental chamber. The bridges were also subjected to several damage conditions. Data were collected via twenty uniaxial 100 mV/g accelerometers, organised in two rows of ten on each edge of the underside of the deck, and the response was measured at a sample rate of 256Hz.