Bayesian network structure extraction algorithms from data in damage risk assessment of buildings in mining areas


openaccess, Vol. 603 (11) 2022 / poniedziałek, 28 listopada, 2022

(Open Access)

DOI: 10.15199/33.2022.11.18

Rusek Janusz, Chomacki Leszek, Słowik Leszek, Firek Karol. 2022. Bayesian network structure extraction algorithms from data in damage risk assessment of buildings in mining areas. Volume 603. Issue 11. Pages 66-69. Article in PDF file

Accepted for publication: 21.09.2022 r.

The article presents the results of research that was undertaken to create a model to assess the damage risk of buildings subjected to static and dynamic mining impacts. The justification of the adopted methodology on the basis of machine learning (ML) methods is given. The specificity of the problem was discussed and, on this basis, the main assumptions of the applied approach were presented, especially the methodology allowing for autonomous extraction of the Bayesian network structure from data (BSL – Bayesian Structure Learning). The results obtained in the research were presented in relation to multi-storey prefabricated and masonry buildings located in LGDC and USB mining terrain. The paper also indicates the possibility of universal application of the adopted methodology in the case of damage risk prediction and diagnosis of the causes of damage.
  1. Nowogońska B, Mielczarek M. Renovation management method in neglected buildings. Sustain. 2021. DOI: 10.3390/su13020929.
  2. Firek K. Proposal for classification of prefabricated panel building damage intensity rate inmining areas.Arch.Min. Sci. 2009;Vol. 54, no. 3: 467 – 479.
  3. Wodyński A. Zużycie techniczne budynków na terenach górniczych. Kraków. AGH Publishing House, 2007.
  4. Knyziak P. The impact of construction quality on the safety of prefabricated multi-family dwellings. Eng. Fail.Anal. 2019. DOI: 10.1016/j. engfailanal.2019.02.042.
  5. McIntosh B.S et al. Environmental decision support systems (EDSS) development – Challenges and best practices. Environ. Model. Softw. 2011.DOI: 10.1016/j.envsoft.2011.09.009.
  6. Sharafi P, Rashidi M, Samali B, Ronagh H, Mortazavi M. Identification of Factors and DecisionAnalysis of the Level ofModularization in Building Construction. J. Archit. Eng. 2018. DOI: 10.1061/(asce)ae.1943-5568.0000313.
  7. Leśniak A, Radziejowska A. Supporting bidding decision using multi-criteria analysis methods. 2017. DOI: 10.1016/j.proeng.2017.11.023.
  8. Rusek J. Application of support vector machine in the analysis of the technical state of development in the LGOM mining area. Eksploat. i Niezawodn. 2017. DOI: 10.17531/ein.2017.1.8.
  9. Chomacki L, Rusek J, Słowik L. Selected Artificial Intelligence Methods in the Risk Analysis of Damage to Masonry Buildings Subject to Long-Term Underground Mining Exploitation.Minerals. 2021. DOI: 10.3390/min11090958.
  10. Rusek J. Computational intelligence methods in the problem of modelling technical wear of buildings in mining areas. Geomatics Environ. Eng. 2013. DOI: 10.7494/ geom. 2012.6.3.83.
  11.  Kawulok M. Szkody górnicze w budownictwie. Warszawa. Inst. Tech. Bud. 2015.
  12. ScutariM,GraaflandCE,Gutiérrez JM.Who learns better Bayesian network structures: Accuracy and speed of structure learning algorithms. Int. J.Approx. Reason. 2019.DOI: 10.1016/j.ijar.2019.10.003.
  13.  Koller D, Friedman N. Probabilistic graphicalmodels: principles and techniques. USA.MIT press. 2009.
  14.  ScutariM. Bayesian network constraint-based structure learning algorithms: Parallel and optimized implementations in the bnlearn R package. J. Stat. Softw. 2017. DOI: 10.18637/jss. v077.i02.
  15.  Rusek J, Firek K, Słowik L. Extracting structure of bayesian network from data in predicting the damage of prefabricated reinforced concrete buildings in mining areas. Eksploat. i Niezawodn. 2020. DOI: 10.17531/ein. 2020.4.9.
  16.  Nagarajan R, Scutari M, Lebre S. Bayesian Networks in R. New York. Springer. 2013.
  17. Rusek J, Tajduś K, Firek K, Jędrzejczyk A. Score-based Bayesian belief network structure learning in damage risk modelling of mining areas building development J. Clean. Prod. 2021. DOI: 10.1016/j.jclepro. 2021.126528.
  18. KawulokM. Diagnozowanie budynków zlokalizowanych na terenach górniczych. Warszawa. Inst. Tech. Bud. 2021.
  19.  CholewickiA, KawulokM, Lipski Z, Szulc J. Zasady ustalania obciążeń i sprawdzania stanów granicznych budynków zlokalizowanych na terenach górniczych w nawiązaniu do Eurokodów. Warszawa. Inst. Tech. Bud. 2012.
  20.  Wodyński A, Lasocki S. Assessment of mining tremor influence on the technical wear of building.Acta Geodyn. Geomaterialia. 2004; vol. 50. no. 2: 187 – 194.
  21. Scutari M. Learning Bayesian Networks with the bnlearn R Package. J. Stat. Softw. 2010. DOI: 10.18637/jss.v035.i03.
  22.  Long Y, Wang L,. Sun M. Structure extension of tree-augmented naive bayes. Entropy. 2019. DOI: 10.3390/e21080721.
dr hab. inż. Janusz Rusek, prof. uczelni, AGH Akademia Górniczo-Hutnicza, Wydział Geodezji Górniczej i Ochrony Środowiska ORCID: 0000-0003-0368-2580
dr inż. Leszek Chomacki, Instytut Techniki Budowlanej ORCID: 0000-0002-2291-3826
dr inż. Leszek Słowik, Instytut Techniki Budowlanej ORCID: 0000-0001-8770-1595
dr hab. inż. Karol Firek, prof. uczelni, AGH Akademia Górniczo-Hutnicza, Wydział Geodezji Górniczej i Ochrony Środowiska ORCID: 0000-0002-0985-6003

dr hab. inż. Janusz Rusek, prof. uczelni, AGH Akademia Górniczo-Hutnicza, Wydział Geodezji Górniczej i Ochrony Środowiska ORCID: 0000-0003-0368-2580

rusek@agh.edu.pl

Full paper:

DOI: 10.15199/33.2022.11.18

Article in PDF file