Search

found 22 results

Images for machines; more images...

Research papers, University of Canterbury Library

Natural catastrophes are increasing worldwide. They are becoming more frequent but also more severe and impactful on our built environment leading to extensive damage and losses. Earthquake events account for the smallest part of natural events; nevertheless seismic damage led to the most fatalities and significant losses over the period 1981-2016 (Munich Re). Damage prediction is helpful for emergency management and the development of earthquake risk mitigation projects. Recent design efforts focused on the application of performance-based design engineering where damage estimation methodologies use fragility and vulnerability functions. However, the approach does not explicitly specify the essential criteria leading to economic losses. There is thus a need for an improved methodology that finds the critical building elements related to significant losses. The here presented methodology uses data science techniques to identify key building features that contribute to the bulk of losses. It uses empirical data collected on site during earthquake reconnaissance mission to train a machine learning model that can further be used for the estimation of building damage post-earthquake. The first model is developed for Christchurch. Empirical building damage data from the 2010-2011 earthquake events is analysed to find the building features that contributed the most to damage. Once processed, the data is used to train a machine-learning model that can be applied to estimate losses in future earthquake events.

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, Victoria University of Wellington

The suburb of New Brighton in Christchurch Aotearoa was once a booming retail sector until the end of its exclusivity to Saturday shopping in 1980 and the aftermath of the devastating 2011 Christchurch earthquake. The suburb of New Brighton was hit particularly hard and fell into economic collapse, partly brought on by the nature of its economic structure. This implosion created an urban crisis where people and businesses abandoned the suburb and its once-booming commercial economy. As a result, New Brighton has been left with the residue of abandoned infrastructure and commercial propaganda such as billboards, ATM machines, commercial facades, and shopping trolleys that as abandoned fragments, no longer contribute to culture, society and the economy. This design-led research investigation proposes to repurpose the broken objects that were left behind. By strategically selecting objects that are symbols of the root cause of the economic devastation, the repurposed and re-contextualised fragments will seek to allegorically expose the city’s destructive economic narrative, while providing a renewed sense of place identity for the people. This design-led thesis investigation argues that the seemingly innocuous icons of commercial industry, such as billboards, ATM machines, commercial facades, and shopping trolleys, are intended to act as lures to encourage people to spend money; ultimately, these urban and architectural lures can contribute to economic devastation. The aim of this investigation is to repurpose abandoned fragments of capitalist infrastructure in ways that can help to unveil new possibilities for a disrupted community and enhance their awareness of what led to the urban disruption. The thesis proposes to achieve this research aim by exploring three principal research objectives: 1) to assimilate and re-contextualise disconnected urban fragments into new architectural interventions; 2) to anthropomorphise these new interventions so that they are recognisable as architectural ‘inhabitants’, the storytellers of the urban context; and 3) to curate these new architectural interventions in ways that enable a community-scale allegorical and didactic experience to be recognised.

Research papers, The University of Auckland Library

The Screw Driving Sounding (SDS) method developed in Japan is a relatively new insitu testing technique to characterise soft shallow sites, typically those required for residential house construction. An SDS machine drills a rod into the ground in several loading steps while the rod is continuously rotated. Several parameters, such as torque, load and speed of penetration, are recorded at every rotation of the rod. The SDS method has been introduced in New Zealand, and the results of its application for characterising local sites are discussed in this study. A total of 164 SDS tests were conducted in Christchurch, Wellington and Auckland to validate/adjust the methodologies originally developed based on the Japanese practice. Most of the tests were conducted at sites where cone penetration tests (CPT), standard penetration tests (SPT) and borehole logs were available; the comparison of SDS results with existing information showed that the SDS method has great potential as an in-situ testing method for classifying the soils. By compiling the SDS data from 3 different cities and comparing them with the borehole logs, a soil classification chart was generated for identifying the soil type based on SDS parameters. Also, a correlation between fines content and SDS parameters was developed and a procedure for estimating angle of internal friction of sand using SDS parameters was investigated. Furthermore, a correlation was made between the tip resistance of the CPT and the SDS data for different percentages of fines content. The relationship between the SPT N value and a SDS parameter was also proposed. This thesis also presents a methodology for identifying the liquefiable layers of soil using SDS data. SDS tests were performed in both liquefied and non-liquefied areas in Christchurch to find a representative parameter and relationship for predicting the liquefaction potential of soil. Plots were drawn of the cyclic shear stress ratios (CSR) induced by the earthquakes and the corresponding energy of penetration during SDS tests. By identifying liquefied or unliquefied layers using three different popular CPT-based methods, boundary lines corresponding to the various probabilities of liquefaction happening were developed for different ranges of fines contents using logistic regression analysis, these could then be used for estimating the liquefaction potential of soil directly from the SDS data. Finally, the drilling process involved in screw driving sounding was simulated using Abaqus software. Analysis results proved that the model successfully captured the drilling process of the SDS machine in sand. In addition, a chart to predict peak friction angles of sandy sites based on measured SDS parameters for various vertical effective stresses was formulated. As a simple, fast and economical test, the SDS method can be a reliable alternative insitu test for soil and site characterisation, especially for residential house construction.