The rapid classification of building damage states or placards after an earthquake is vital for enabling an efficient emergency response and informed decision-making for rehabilitation and recovery purposes. Traditional methods rely heavily on inspector-led on-site surveys, which are often time-consuming, resource-intensive, and susceptible to human error. This study introduces a machine learning-supported surrogate model designed to streamline the assessment of building damage, focusing on the automated assignment of damage placards within the context of New Zealand's post-earthquake evaluation frameworks. The study evaluates two key safety evaluation protocols—Rapid Building Assessment (RBA) and Detailed Damage Evaluation (DDE)—and integrates corresponding databases derived from the 2010–2011 Canterbury Earthquake Sequence (CES) in Christchurch. Six ML classifiers—Multilayer Perceptron (MLP), Random Forest (RF), Support Vector Machine (SVM), K-Nearest Neighbours (KNN), Gradient Boosting Classifier (GBC), and Gradient Bagging (GBag)—were rigorously tested across both databases. The results indicate that the RF-based surrogate model outperforms the other classifiers across both RBA and DDE protocols. Two distinct sets of critical predictors have been further identified for each protocol, allowing for the rapid retrieval of essential data for future on-site surveys, while retaining the RF model's predictive accuracy. The developed surrogate model provides a pragmatic tool for practising engineers to rapidly assign placards to damaged structures and for policymakers and building owners to make informed recovery decisions for earthquake-affected buildings.
Reinforced concrete buildings that satisfied modern seismic design criteria generally behaved as expected during the recent Canterbury and Kaikoura earthquakes in New Zealand, forming plastic hinges in intended locations. While this meant that life-safety performance objectives were met, widespread demolition and heavy economic losses took place in the aftermath of the earthquakes.The Christchurch central business district was particularly hard hit, with over 60% of the multistorey reinforced concrete buildings being demolished. A lack of knowledge on the post-earthquake residual capacity of reinforced concrete buildings was a contributing factor to the mass demolition.Many aspects related to the assessment of earthquake-damaged reinforced concrete buildings require further research. This thesis focusses on improving the state of knowledge on the post earthquakeresidual capacity and reparability of moderately damaged plastic hinges, with an emphasis on plastic hinges typical of modern moment frame structures. The repair method focussed on is epoxy injection of cracks and patching of spalled concrete. A targeted test program on seventeen nominally identical large-scale ductile reinforced concrete beams, three of which were repaired by epoxy injection following initial damaging loadings, was conducted to support these objectives. Test variables included the loading protocol, the loading rate, and the level of restraint to axial elongation.The information that can be gleaned from post-earthquake damage surveys is investigated. It is shown that residual crack widths are dependent on residual deformations, and are not necessarily indicative of the maximum rotation demands or the plastic hinge residual capacity. The implications of various other types of damage typical of beam and column plastic hinges are also discussed.Experimental data are used to demonstrate that the strength and deformation capacity of plastic hinges with modern seismic detailing are often unreduced as a result of moderate earthquake induced damage, albeit with certain exceptions. Special attention is given to the effects of prior yielding of the longitudinal reinforcement, accounting for the low-cycle fatigue and strain ageing phenomena. A material-level testing program on the low-cycle fatigue behaviour of grade 300E reinforcing steel was conducted to supplement the data available in the literature.A reduction in stiffness, relative to the initial secant stiffness to yield, occurs due to moderate plastic hinging damage. This reduction in stiffness is shown to be correlated with the ductility demand,and a proposed model gives a conservative lower-bound estimate of the residual stiffness following an arbitrary earthquake-type loading. Repair by epoxy injection is shown to be effective in restoring the majority of stiffness to plastic hinges in beams. Epoxy injection is also shown to have implications for the residual strength and elongation characteristics of repaired plastic hinges.
