TY - JOUR
T1 - BNSL GOBNILP algorithm in application to damage intensity prognostic system to RC multistorey residential buildings subjected to negative impacts of the industrial environment of mines
AU - Rusek, Janusz
AU - Alibrandi, Umberto
AU - Słowik, Leszek
AU - Chomacki, Leszek
N1 - Publisher Copyright:
© 2023 Elsevier Ltd
PY - 2023/12
Y1 - 2023/12
N2 - Paper presents a method of predicting the damage intensity of multifamily prefabricated RC buildings located in the range of impacts of the industrial environment of mines. The research studied the effects of mining impacts in the form of large-scale continuous ground deformation and mining tremors. For this purpose, in-situ data collected in the database was used. Additional information in the database included: structural and material features, quality of maintenance and durability of the analysed buildings. Finally, a predictive model represented by an optimal Bayesian network structure was created. To obtain the optimal topology of the DAG network structure, a Bayesian network learning algorithm from data GOBNILP was adapted. According to this algorithm, the optimisation process was carried out through Gurobi Optimizer. Thus, the conducted analyses represent the first time the above-mentioned approach has been applied in the interdisciplinary field of civil and environmental engineering. As part of the analyses, the available metric scores were verified and multiple network structures were examined according to their complexity. This made it possible to select the best Bayesian network in terms of generalizing the knowledge acquired while learning its structure. The possibility of using the obtained model for issues of diagnosis of damage causes and their prediction was also presented.
AB - Paper presents a method of predicting the damage intensity of multifamily prefabricated RC buildings located in the range of impacts of the industrial environment of mines. The research studied the effects of mining impacts in the form of large-scale continuous ground deformation and mining tremors. For this purpose, in-situ data collected in the database was used. Additional information in the database included: structural and material features, quality of maintenance and durability of the analysed buildings. Finally, a predictive model represented by an optimal Bayesian network structure was created. To obtain the optimal topology of the DAG network structure, a Bayesian network learning algorithm from data GOBNILP was adapted. According to this algorithm, the optimisation process was carried out through Gurobi Optimizer. Thus, the conducted analyses represent the first time the above-mentioned approach has been applied in the interdisciplinary field of civil and environmental engineering. As part of the analyses, the available metric scores were verified and multiple network structures were examined according to their complexity. This made it possible to select the best Bayesian network in terms of generalizing the knowledge acquired while learning its structure. The possibility of using the obtained model for issues of diagnosis of damage causes and their prediction was also presented.
UR - http://www.scopus.com/inward/record.url?scp=85174888058&partnerID=8YFLogxK
U2 - 10.1016/j.jobe.2023.107885
DO - 10.1016/j.jobe.2023.107885
M3 - Journal article
AN - SCOPUS:85174888058
SN - 2352-7102
VL - 80
JO - Journal of Building Engineering
JF - Journal of Building Engineering
M1 - 107885
ER -