Publication

Digital Twins of Stone Masonry Buildings for Damage Assessment

Katrin Beyer, Radhakrishna Achanta, Bryan German Pantoja Rosero
2024
Conference Papers

Abstract

Digital twins are virtual models of physical objects or systems that enable real-time monitoring and analysis. In the ﬁeld of stone masonry buildings, digital twins can be used to assess damage, predict maintenance needs, and opti- mize building performance. However, creating and analyzing digital twins of stone masonry buildings can be a complex and time-consuming process that requires specialized skills and equipment. In this paper, we present various methodolo- gies for the generation of damage augmented digital twins (DADTs) of stone masonry buildings that involve the use of machine learning and computer vision techniques to automate the process. These methodologies include crack segmen- tation using convolutional neural networks, crack characterization using machine learning, automatic generation of simpliﬁed geometries of buildings, generation of DADTs containing geometrical and damage information, generation of ﬁnite element models for stone masonry buildings, and geometrical digital twins for stone masonry elements for numerical modeling. We demonstrate the effective- ness of these methodologies using a variety of datasets and show that they can signiﬁcantly improve the accuracy and speed of damage assessment compared to traditional methods. Our work contributes to the development of a framework for real-time damage assessment of stone masonry buildings and lays the foundation for future research in this area.

Official source

https://infoscience.epfl.ch/entities/publication/d2ca5892-2b31-483b-b8e1-5b83371f81ee

About this result

This page is automatically generated and may contain information that is not correct, complete, up-to-date, or relevant to your search query. The same applies to every other page on this website. Please make sure to verify the information with EPFL's official sources.

Katrin Beyer, Radhakrishna Achanta, Bryan German Pantoja Rosero
2024
Conference Papers

Abstract

Official source

https://infoscience.epfl.ch/entities/publication/d2ca5892-2b31-483b-b8e1-5b83371f81ee

About this result

Related concepts (32)

Convolutional neural network

Convolutional neural network (CNN) is a regularized type of feed-forward neural network that learns feature engineering by itself via filters (or kernel) optimization. Vanishing gradients and exploding gradients, seen during backpropagation in earlier neural networks, are prevented by using regularized weights over fewer connections. For example, for each neuron in the fully-connected layer 10,000 weights would be required for processing an image sized 100 × 100 pixels.

Parallel (geometry)

In geometry, parallel lines are coplanar infinite straight lines that do not intersect at any point. Parallel planes are planes in the same three-dimensional space that never meet. Parallel curves are curves that do not touch each other or intersect and keep a fixed minimum distance. In three-dimensional Euclidean space, a line and a plane that do not share a point are also said to be parallel. However, two noncoplanar lines are called skew lines. Parallel lines are the subject of Euclid's parallel postulate.

Line (geometry)

In geometry, a line is an infinitely long object with no width, depth, or curvature. Thus, lines are one-dimensional objects, though they may exist embedded in two, three, or higher dimensional spaces. The word line may also refer to a line segment in everyday life that has two points to denote its ends (endpoints). A line can be referred to by two points that lie on it (e.g. ) or by a single letter (e.g. ).

Related publications (31)

Robust machine learning for neuroscientific inference

Steffen Schneider

Modern neuroscience research is generating increasingly large datasets, from recording thousands of neurons over long timescales to behavioral recordings of animals spanning weeks, months, or even years. Despite a great variety in recording setups and expe ...

EPFL2024

Aggregating Spatial and Photometric Context for Photometric Stereo

David Honzátko

Photometric stereo, a computer vision technique for estimating the 3D shape of objects through images captured under varying illumination conditions, has been a topic of research for nearly four decades. In its general formulation, photometric stereo is an ...

EPFL2024

Topics in statistical physics of high-dimensional machine learning

Hugo Chao Cui

In the past few years, Machine Learning (ML) techniques have ushered in a paradigm shift, allowing the harnessing of ever more abundant sources of data to automate complex tasks. The technical workhorse behind these important breakthroughs arguably lies in ...

EPFL2024