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

Abstract

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.

Selected Artificial Intelligence Methods in the Risk Analysis of Damage to Masonry Buildings Subject to Long-Term Underground Mining Exploitation

“…An additional advantage of such a tool, based on AI methodology, is the ability to update the model with access to new data resources. This is especially the case with Bayesian networks, which, in addition to allowing inference in the mode of prediction of the range and intensity of damage and diagnosis of its causes [13,28]. This significantly extends the possibilities of implementing such a tool in other industrial sectors that coexist with the mining industry.…”

“…Although individual tools belonging to this group are still being developed and improved, the effectiveness of many of them has already been confirmed. The validity of AI methods has also been justified by research conducted within the interdisciplinary field of mining and civil engineering [9,13,28,33,34]. Among the available AI methods, the Evaluating the issue addressed in this paper only through the narrow prism of the development of digitalization and the need for optimal planning of the mining exploitation process, it is clear that there is a need to create a tool to improve the work of both mining and civil engineers involved in the process related to the underground exploitation of resources.…”

“…Although individual tools belonging to this group are still being developed and improved, the effectiveness of many of them has already been confirmed. The validity of AI methods has also been justified by research conducted within the interdisciplinary field of mining and civil engineering [9,13,28,33,34]. Among the available AI methods, the methods that allow representation of formal uncertainty during inference are particularly useful for describing the risk of building damage.…”