The search result changed since you submitted your search request. Documents might be displayed in a different sort order.
  • search hit 59 of 172
Back to Result List

ANALYSIS THE TECHNICAL STATE FOR LARGE-PANEL RESIDENTIAL BUILDINGS BEHIND ASSISTANCE OF ARTIFICIAL NEURAL NETWORKS

  • This paper presents two new methods for analysis of a technical state of large-panel residential buildings. The first method is based on elements extracted from the classical methods and on data about repairs and modernization collected from building documentations. The technical state of a building is calculated as a sum of several groups of elements defining the technical state. TheThis paper presents two new methods for analysis of a technical state of large-panel residential buildings. The first method is based on elements extracted from the classical methods and on data about repairs and modernization collected from building documentations. The technical state of a building is calculated as a sum of several groups of elements defining the technical state. The deterioration in this method depends on: - time, which has passed since last repair of element or time which has passed since construction, - estimate of the state of element groups which can be determined on basis of yearly controls. This is a new unique method. it is easy to use, does not need expertise. The required data could be extracted easily from building documentations. For better accuracy the data from building inspections should be applied (in Poland inspections are made every year). The second method is based on the extracted data processing by means of the artificial neural networks. The aim is to learn the artificial neural network configurations for a set of data containing values of the technical state and information about building repairs for last years (or other information and building parameters) and next to analyse new buildings by the instructed neural network. The second profit from using artificial neural networks is the reduction of number of parameters. Instead of more then 40 parameters describing building, about 6-12 are usually sufficient for satisfactory accuracy. This method could have lower accuracy but it is less prone to data errors.show moreshow less

Download full text files

Export metadata

Additional Services

Share in Twitter Search Google Scholar
Metadaten
Document Type:Conference Proceeding
Author: Piotr Knyziak
DOI (Cite-Link):https://doi.org/10.25643/bauhaus-universitaet.2979Cite-Link
URN (Cite-Link):https://nbn-resolving.org/urn:nbn:de:gbv:wim2-20170327-29792Cite-Link
URL:http://euklid.bauing.uni-weimar.de/ikm2006/index.php_lang=de&what=papers.html
Editor: Klaus GürlebeckGND, Carsten KönkeORCiDGND
Language:English
Date of Publication (online):2017/03/25
Date of first Publication:2006/07/14
Release Date:2017/03/27
Publishing Institution:Bauhaus-Universität Weimar
Creating Corporation:Bauhaus-Universität Weimar
Institutes and partner institutions:Bauhaus-Universität Weimar / In Zusammenarbeit mit der Bauhaus-Universität Weimar
Pagenumber:9
GND Keyword:Architektur <Informatik>; CAD; Computerunterstütztes Verfahren
Dewey Decimal Classification:500 Naturwissenschaften und Mathematik / 510 Mathematik
BKL-Classification:56 Bauwesen / 56.03 Methoden im Bauingenieurwesen
Collections:Bauhaus-Universität Weimar / Internationales Kolloquium über Anwendungen der Informatik und Mathematik in Architektur und Bauwesen, IKM, Weimar / Internationales Kolloquium über Anwendungen der Informatik und Mathematik in Architektur und Bauwesen, IKM, Weimar, 17. 2006
Licence (German):License Logo Creative Commons 4.0 - Namensnennung-Nicht kommerziell (CC BY-NC 4.0)