Search

found 2 results

Research papers, The University of Auckland Library

This thesis presents the application of data science techniques, especially machine learning, for the development of seismic damage and loss prediction models for residential buildings. Current post-earthquake building damage evaluation forms are developed for a particular country in mind. The lack of consistency hinders the comparison of building damage between different regions. A new paper form has been developed to address the need for a global universal methodology for post-earthquake building damage assessment. The form was successfully trialled in the street ‘La Morena’ in Mexico City following the 2017 Puebla earthquake. Aside from developing a framework for better input data for performance based earthquake engineering, this project also extended current techniques to derive insights from post-earthquake observations. Machine learning (ML) was applied to seismic damage data of residential buildings in Mexico City following the 2017 Puebla earthquake and in Christchurch following the 2010-2011 Canterbury earthquake sequence (CES). The experience showcased that it is readily possible to develop empirical data only driven models that can successfully identify key damage drivers and hidden underlying correlations without prior engineering knowledge. With adequate maintenance, such models have the potential to be rapidly and easily updated to allow improved damage and loss prediction accuracy and greater ability for models to be generalised. For ML models developed for the key events of the CES, the model trained using data from the 22 February 2011 event generalised the best for loss prediction. This is thought to be because of the large number of instances available for this event and the relatively limited class imbalance between the categories of the target attribute. For the CES, ML highlighted the importance of peak ground acceleration (PGA), building age, building size, liquefaction occurrence, and soil conditions as main factors which affected the losses in residential buildings in Christchurch. ML also highlighted the influence of liquefaction on the buildings losses related to the 22 February 2011 event. Further to the ML model development, the application of post-hoc methodologies was shown to be an effective way to derive insights for ML algorithms that are not intrinsically interpretable. Overall, these provide a basis for the development of ‘greybox’ ML models.

Research papers, The University of Auckland Library

Soil-structure interaction (SSI) has been widely studied during the last decades. The influence of the properties of the ground motion, the structure and the soil have been addressed. However, most of the studies in this field consider a stand-alone structure. This assumption is rarely justifiable in dense urban areas where structures are built close to one another. The dynamic interaction between adjacent structures has been studied since the early 1970s, mainly using numerical and analytical models. Even though the early works in this field have significantly contributed to understanding this problem, they commonly consider important simplifications such as assuming a linear behaviour of the structure and the soil. Some experimental works addressing adjacent structures have recently been conducted using geotechnical centrifuges and 1g shake tables. However, further research is needed to enhance the understanding of this complex phenomenon. A particular case of SSI is that of structures founded in fine loose saturated sandy soil. An iconic example was the devastating effects of liquefaction in Christchurch, New Zealand, during the Canterbury earthquake in 2011. In the case of adjacent structures on liquefiable soil, the experimental evidence is even scarcer. The present work addresses the dynamic interaction between adjacent structures by performing multiple experimental studies. The work starts with two-adjacent structures on a small soil container to expose the basics of the problem. Later, results from tests considering a more significant number of structures on a big laminar box filled with sand are presented. Finally, the response of adjacent structures on saturated sandy soil is addressed using a geotechnical centrifuge and a large 1g shake table. This research shows that the acceleration, lateral displacement, foundation rocking, damping ratio, and fundamental frequency of the structure of focus are considerably affected by the presence of neighbouring buildings. In general, adjacent buildings reduced the dynamic response of the structure of focus on dry sand. However, the acceleration was amplified when the structures had a similar fundamental frequency. In the case of structures on saturated sand, the presence of adjacent structures reduced the liquefaction potential. Neighbouring structures on saturated sand also presented larger rotation of the footing and lateral displacement of the top mass than that of the stand-alone case.