Extracting structure of Bayesian network from data in predicting the damage of prefabricated reinforced concrete buildings in mining areas

• Autorzy: Rusek Janusz , Firek Karol , Słowik Leszek

Identyfikatory

DOI

10.17531/ein.2020.4.9

Warianty tytułu

PL

Wyodrębnianie struktury sieci Bayesowskiej z danych w prognozowaniu uszkodzeń żelbetowych budynków prefabrykowanych na terenach górniczych

• Języki publikacji: EN PL

Abstrakty

EN

This article presents the results of the research on the construction of a model for assessing the risk of damage to building structures located in mining areas. The research was based on the database on the structure, technical condition and mining impacts regarding 129 prefabricated reinforced concrete buildings erected in the industrialised large-block system, located in the mining area of the Legnica-Glogow Copper District (LGCD). The methodology of the Bayesian Belief Network (BBN) was used for the analysis. Using the score-based Bayesian structure learning approach (Hill-Climbing and Tabu-Search) as well as the selected optimisation criteria, 16 Bayesian network structures were induced. All models were subjected to quantitative and qualitative evaluation by verifying their features in the context of accuracy of prediction, generalisation of acquired knowledge and cause-effect relationships. This allowed to select the best network structure together with the corresponding optimisation criterion. The analysis of the results demonstrated that the Tabu-Search method adopting the optimisation criterion in the form of Locally Averaged Bayesian Dirichlet score (BDla) led to obtaining a model with the best features among all the selected models. The results justified the adoption of the BBN methodology as effective in the context of assessing the extent of damage to building structures in mining areas.

PL

W artykule zaprezentowano wyniki badań dotyczących budowy modelu do oceny ryzyka powstawania uszkodzeń budynków usytuowanych na terenach górniczych. Podstawą do badań była baza danych nt. konstrukcji, stanu technicznego oraz wpływów górniczych dla 129 żelbetowych prefabrykowanych budynków wznoszonych w uprzemysłowionym systemie wielkoblokowym zlokalizowanych na terenie górniczym Legnicko-Głodowskiego Okręgu Miedziowego (LGOM). Do analiz zastosowano metodykę sieci przekonań Bayesa (BBN – Belief Bayesian Networks). Stosując podejście score-based Bayesian structure learning (Hill-Climbing oraz Tabu-Search) oraz wyselekcjonowane kryteria optymalizacyjne, wyłoniono 16 struktur sieci Bayesowskich. Wszystkie modele poddano ocenie ilościowej i jakościowej, weryfikując ich własności w kontekście trafności predykcji, generalizacji nabytej wiedzy oraz zależności przyczynowo-skutkowych. Pozwoliło to na wyselekcjonowanie najlepszej struktury sieci wraz z odpowiadającym kryterium optymalizacyjnym. Analiza wyników wykazała, że metoda Tabu-Search przy przyjęciu kryterium optymalizacyjnego w postaci Locally Averaged Bayesian Dirichlet score (BDla), prowadzi do uzyskania modelu o najlepszych własnościach spośród wszystkich wyłonionych modeli. Uzyskane rezultaty uzasadniają przyjęcie metodyki BBN, jako efektywnej w kontekście oceny zakresu uszkodzeń budynków na terenach górniczych.

Słowa kluczowe

EN

Bayesian network; damage; risk; prefabricated reinforced concrete structures

PL

sieci bayesowskie; uszkodzenia; ryzyko; prefabrykowane budynki żelbetowe

• Wydawca: Polskie Naukowo-Techniczne Towarzystwo Eksploatacyjne
• Czasopismo: Eksploatacja i Niezawodność
• Rocznik: 2020
• Tom: Vol. 22, no. 4
• Strony: 658--666
• Opis fizyczny: Bibliogr. 44 poz., rys., tab.

Twórcy

autor

Rusek Janusz

• AGH University of Science and Technology, al. Mickiewicza 30, 30-059 Krakow, Poland

autor

Firek Karol

• AGH University of Science and Technology, al. Mickiewicza 30, 30-059 Krakow, Poland

autor

Słowik Leszek

• Building Research Institute ITB, ul. Filtrowa 1, 00-611 Warsaw, Poland

Bibliografia

• 1. Abdelkader EM, Zayed T, Marzouk M. A computerized hybrid Bayesian-based approach for modelling the deterioration of concrete bridge decks. Structure and Infrastructure Engineering 2019; 15: 1178-99, https://doi.org/10.1080/15732479.2019.1619782.
• 2. Carvalho AM. Scoring functions for learning Bayesian networks. Inesc-id Tec. Rep 2009; 12.
• 3. Chung H, Lee I-M, Jung J-H, Park J. Bayesian networks-based shield TBM risk management system: Methodology development and application. KSCE Journal of Civil Engineering 2019; 23: 452-65, https://doi.org/10.1007/s12205-018-0912-y.
• 4. Dahire S, Tahir F, Jiao Y, Liu Y. Bayesian Network inference for probabilistic strength estimation of aging pipeline systems. International Journal of Pressure Vessels and Piping 2018; 162: 30-9, https://doi.org/10.1016/j.ijpvp.2018.01.004.
• 5. Fang S-E, Tan J, Zhang X-H. Safety evaluation of truss structures using nested discrete Bayesian networks. Structural Health Monitoring-an International Journal 2020, https://doi.org/10.1177/1475921720907888.
• 6. Fedorowicz J, Słowik L. Interpretation of the behavior of a system building object-difficult subsoil in modern numerical modeling. Proceedings of the 11th International Conference on New Trends in Statics and Dynamics of Buildings 2013; 3.
• 7. Fereshtehnejad E, Banazadeh M, Shafieezadeh A. System reliability-based seismic collapse assessment of steel moment frames using incremental dynamic analysis and Bayesian probability network. Engineering Structures 2016; 118: 274-86, https://doi.org/10.1016/j.engstruct.2016.03.057.
• 8. Firek K. Proposal for classification of prefabricated panel building damage intensity rate in mining areas. Archives of Mining Sciences 2009.
• 9. Gogoshin G, Boerwinkle E, Rodin AS. New algorithm and software (BNOmics) for inferring and visualizing bayesian networks from heterogeneous big biological and genetic data. Journal of Computational Biology 2017; 24: 340-56, https://doi.org/10.1089/cmb.2016.0100.
• 10. Golewski GL. Measurement of fracture mechanics parameters of concrete containing fly ash thanks to use of Digital Image Correlation (DIC) method. Measurement 2019; 135: 96-105, https://doi.org/10.1016/j.measurement.2018.11.032.
• 11. Heckerman D, Geiger D, Chickering DM. Learning Bayesian networks: The combination of knowledge and statistical data. Machine learning 1995; 20: 197-243, https://doi.org/10.1007/BF00994016.
• 12. Jin Y, Zhang J, Sun L. Safety Risk Assessment of Prefabricated Building Construction Based on Bayesian Network. IOP Conference Series: Earth and Environmental Science 2019; 371: 32052, https://doi.org/10.1088/1755-1315/371/3/032052.
• 13. Ravikumar K, Rajiv Kannan A. Survey of Spatial Datamining Methods for Natural Disaster Management. Middle-East Journal of Scientific Research 2017; 25: 217-27.
• 14. Kembłowski MW, Grzyl B, Kristowski A, Siemaszko A. Risk Modelling with Bayesian Networks - Case Study: Construction of Tunnel under the Dead Vistula River in Gdansk. Procedia Engineering 2017; 196: 585-91, https://doi.org/10.1016/j.proeng.2017.08.046.
• 15. Knyziak P, Kanoniczak M. Difficulties in Operation of Elevations in Large-Panel Buildings. IOP Conference Series: Materials Science and Engineering 2019; 661: 12059, https://doi.org/10.1088/1757-899X/661/1/012059.
• 16. Lee S, Choi M, Lee H-S, Park M. Bayesian Network-based Seismic Damage Estimation for Power and Potable Water Supply Systems. Reliability Engineering & System Safety 2020: 106796, https://doi.org/10.1016/j.ress.2020.106796.
• 17. Marsili F, Croce P, Klawonn F, Vignoli A, Boschi S, Landi F. A Bayesian network for the definition of probability models for masonry mechanical parameters. 14th International Probabilistic Workshop. 2017: 253-68, https://doi.org/10.1007/978-3-319-47886-9_18.
• 18. Nagarajan R, Scutari M, Lèbre S. Bayesian networks in r. Springer 2013; 122: 125-7, https://doi.org/10.1007/978-1-4614-6446-4.
• 19. Niedojadło Z, Gruszczynski W. The impact of the estimation of the parameters values on the accuracy of predicting the impacts of mining exploitation. Archives of Mining Sciences 2015, https://doi.org/10.1515/amsc-2015-0012.
• 20. Nielsen JS, Sørensen JD. Computational framework for risk-based planning of inspections, maintenance, and condition monitoring using discrete Bayesian networks. Structure and Infrastructure Engineering 2018; 14: 1082-94, https://doi.org/10.1080/15732479.2017.1387155.
• 21. Nielsen JS, Tcherniak D, Ulriksen MD. A case study on risk-based maintenance of wind turbine blades with structural health monitoring. Structure and Infrastructure Engineering 2020: 1-17, https://doi.org/10.1080/15732479.2020.1743326.
• 22. Niewiadomski P, Hoła J. Failure process of compressed self-compacting concrete modified with nanoparticles assessed by acoustic emission method. Automation in Construction 2020; 112: 103111, https://doi.org/10.1016/j.autcon.2020.103111.
• 23. Pachla F, Tatara T. Dynamic Resistance of Residential Masonry Building with Structural Irregularities. Seismic Behaviour and Design of Irregular and Complex Civil Structures III 2020: 335-47, https://doi.org/10.1007/978-3-030-33532-8_26.
• 24. Pearl J. Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference. Elsevier, 2014.
• 25. Rusek J. Application of Support Vector Machine in the analysis of the technical state of development in the LGOM mining area. Eksploatacja i Niezawodnosc – Maintenance and Reliability 2017; 19 (1): 54–61, http://dx.doi.org/10.17531/ein.2017.1.8.
• 26. Rusek J, Firek K. Assessment of technical condition of prefabricated large-block building structures located in mining area using the Naive Bayes classifier. International Multidisciplinary Scientific GeoConference Surveying Geology and Mining Ecology Management SGEM 2016; 2.
• 27. Rusek J. The Point Nuisance Method as a Decision-Support System Based on Bayesian Inference Approach. Archives of Mining Sciences 2020; 65: 117-27.
• 28. Sadowski L. Non-destructive investigation of corrosion current density in steel reinforced concrete by artificial neural networks. Archives of Civil and Mechanical Engineering 2013; 13: 104-11, https://doi.org/10.1016/j.acme.2012.10.007.
• 29. Sadowski Ł, HoŁa J, Czarnecki Sł. Non-destructive neural identification of the bond between concrete layers in existing elements. Construction and Building Materials 2016; 127: 49-58, https://doi.org/10.1016/j.conbuildmat.2016.09.146.
• 30. Sari DP, Rosadi D, Effendie AR, others. Application of Bayesian network model in determining the risk of building damage caused by earthquakes. 2018 International Conference on Information and Communications Technology (ICOIACT) 2018: 131-5, https://doi.org/10.1109/ICOIACT.2018.8350776.
• 31. Schabowicz K, Gorzelańczyk T. A nondestructive methodology for the testing of fibre cement boards by means of a non-contact ultrasound scanner. Construction and Building Materials 2016; 102: 200-7, https://doi.org/10.1016/j.conbuildmat.2015.10.170.
• 32. Scutari M. Dirichlet Bayesian network scores and the maximum relative entropy principle. Behaviormetrika 2018; 45: 337-62, https://doi.org/10.1007/s41237-018-0048-x.
• 33. Scutari M. Learning Bayesian networks with the bnlearn R package. https://doi.org/10.18637/jss.v035.i03.
• 34. Scutari M, Graafland CE, Gutiérrez JM. Who learns better Bayesian network structures: Accuracy and speed of structure learning algorithms. International Journal of Approximate Reasoning 2019; 115: 235-53, https://doi.org/10.1016/j.ijar.2019.10.003.
• 35. Scutari M, Vitolo C, Tucker A. Learning Bayesian networks from big data with greedy search: computational complexity and efficient implementation. Statistics and Computing 2019: 1-14, https://doi.org/10.1007/s11222-019-09857-1.
• 36. Siemaszko A, Jakubczyk-Gałczyńska A, Jankowski R. The Idea of Using Bayesian Networks in Forecasting Impact of Traffic-Induced Vibrations Transmitted through the Ground on Residential Buildings. Geosciences 2019; 9: 339, https://doi.org/10.3390/geosciences9080339.
• 37. Sperotto A, Molina J-L, Torresan S, Critto A, Marcomini A. Reviewing Bayesian Networks potentials for climate change impacts assessment and management: A multi-risk perspective. Journal of Environmental Management 2017; 202: 320-31, https://doi.org/10.1016/j.jenvman.2017.07.044.
• 38. Tajduś K, Misa R, Sroka A. Analysis of the surface horizontal displacement changes due to longwall panel advance. International Journal of Rock Mechanics and Mining Sciences 2018; https://doi.org/10.1016/j.ijrmms.2018.02.005.
• 39. Tran T-B, Bastidas-Arteaga E, Aoues Y et al. Reliability assessment and updating of notched timber components subjected to environmental and mechanical loading. Engineering Structures 2018; 166: 107-16, https://doi.org/10.1016/j.engstruct.2018.03.053.
• 40. Wang F, Li H, Dong C, Ding L. Knowledge representation using non-parametric Bayesian networks for tunneling risk analysis. Reliability Engineering & System Safety 2019; 191: 106529, https://doi.org/10.1016/j.ress.2019.106529.
• 41. Wodyński A, Lasocki S. Assessment of mining tremor influence on the technical wear of building. Acta Geodynamica et Geomaterialia. Ser. A and Ser. B 2004; 50: 187-94.
• 42. Wu L, Wang J, Zhou J et al. Multi-scale geotechnical features of dredger fills and subsidence risk evaluation in reclaimed land using BN. Marine Georesources & Geotechnology 2019: 1-23, https://doi.org/10.1080/1064119X.2019.1644406.
• 43. Yazdani A, Shahidzadeh M-S, Takada T. Bayesian networks for disaggregation of structural reliability. Structural Safety 2020; 82: 101892, https://doi.org/10.1016/j.strusafe.2019.101892.
• 44. Yuan M, Liu Y, Yan D, Liu Y. Probabilistic fatigue life prediction for concrete bridges using Bayesian inference. Advances in Structural Engineering 2019; 22: 765-78, https://doi.org/10.1177/1369433218799545.

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa Nr 461252 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2021).