This paper presents the results of a comparative analysis of Convolutional Neural Network (CNN) and Support Vector Machine (SVM) models created for the prediction of the extent and intensity of damage caused to multi-storey reinforced concrete (RC) buildings. The research was conducted on a group of residential buildings, which were subjected to mining impacts in the form of surface deformations and rock mass tremors during their technical life cycle. Damage to buildings poses a significant threat to the safety of the structure and the serviceability of the buildings. They are often the cause of breaks in thermal insulation, which leads to excessive consumption of thermal energy used for space heating, which in turn contributes to over-emissions of CO₂ into the atmosphere. Therefore, this problem is important, not only from a technical dimension, but also includes social, economic, and environmental aspects, which allows it to be classified as an issue of sustainable development in the building industry. As a result of the conducted analysis, among the CNN models, the highest level of classification accuracy was the model obtained using the ADAM (derived from adaptive moment estimation) algorithm, which was also characterized by a very high level of generalization, obtaining 80.35% correctly classified patterns for the training set and 80.52% for the test set. However, its accuracy level was slightly lower than that of the SVM model (85.15% for the training set and 84.42% for the test set), in which Bayesian optimization was used to determine the parameters. The analysis confirmed the effectiveness of the adopted methodology for predicting the extent and intensity of damage. The developed tool can support the optimization of building maintenance management, resulting in reduced economic and environmental expenditures for renovations.

During their life cycle, buildings are subjected to damage that reduces their performance and can pose a significant threat to structural safety. This paper presents the results of research into the creation of a model for predicting damage intensity of buildings located in mining terrains. The basis for the research was a database of technical and mining impact data for 185 masonry residential buildings. The intensity of damage to buildings was negligible and ranged from 0 to 6%. The Convolutional Neural Network (CNN) methodology was used to create the model. The Support Vector Machine (SVM) methodology, which is commonly used for analysis of this type of issue, was used for comparisons. The resulting models were evaluated by comparing parameters such as accuracy, precision, recall, and F₁ score. The comparisons revealed only minor differences between the models. Despite the small range of damage intensity, the models created were able to achieve prediction results of around 80%. The SVM model had better results for training set accuracy, while the CNN model achieved higher values for F₁ score and average precision for the test set. The results obtained justify the adoption of the CNN methodology as effective in the context of predicting the damage intensity of masonry residential buildings located in mining terrains.

This article presents the results of the analysis of the extent of damage to 138 multi-storey buildings with reinforced concrete prefabricated structure, which are located in the mining terrain of the Legnica-Głogów Copper District. These objects are residential and public utility buildings of up to 43 years old, erected in industrialized prefabricated technologies: large-block and large-panel systems. The research was based on the results of technical condition inventory carried out in 2002, 2007 and 2012. As part of the analysis, the damage intensity index w_u was established for individual structural and finishing elements of the studied buildings. This index is defined on a six-point scale, which includes a detailed description of the extent of damage that corresponds to the successive degrees of intensity. As part of the research, the databases were significantly expanded and the generalized formulas of the damage intensity index w_u for individual groups of buildings were verified. For this purpose, the partial least squares regression (PLSR) method was applied. Thereafter, the analysis of changes of this intensity in time was carried out and the relations between the extent of damage and the impacts of mining exploitation were examined. The approach presented in this paper and obtained research results are characterized by a high degree of utilitarianism and can be applied to increase the efficiency in the optimal maintenance management of buildings, including planning of repairs and retrofits throughout the technical life cycle of the buildings.

Buildings located in mining areas are subject to impacts that can negatively affect their technical condition. This mostly leads to the formation of new damage or an increase in the extent of existing damage. In Poland, mining exploitation is carried out, among others, in the mining area of the Lublin Coal Basin (LZW). In recent years, buildings located in this area have been subjected to a detailed architectural and construction inventory and assessment of their technical condition. The information thus obtained was used to create a database of 413 masonry residential buildings, which formed the basis for the research. The objective of the work was to analyse the impact of continuous land surface deformation on the technical condition of buildings. The research was conducted using data exploration and machine learning (ML) methods. Initial assessments consisted of analysing the relationship between indicators of mining impacts and indicators characterizing technical condition. It was found that the level of relations was higher for unrenovated and unprotected buildings compared to renovated and/or preventively protected buildings. In addition, it was found that the relationship with the damage intensity index wu is stronger than with technical wear sz. The research conducted in the following section can be divided into two stages. In the first stage, the research was carried out on a group of unrenovated and unprotected buildings. Using a multiple linear regression model, the effect of mining impacts on the intensity of damage to buildings was assessed. In the further part of first stage, models were created and analysed to predict the category of damage intensity index wu, depending on the technical parameters of the building and horizontal deformation of the terrain. It was found that among the created models, the SVM classifier was optimal to predict the category of damage intensity index wu. The selected model was subjected to further analysis, which confirmed its correctness. In the second stage, research was conducted to assess the impact of the renovation work and preventive structural protection on the course of technical wear. As a result of the analyses, the positive impact of renovation works on the technical condition of buildings was confirmed. It manifests in a slower growth of technical wear over time and an extended durability. It was found that the use of preventive structural protection against mining impacts at the stage of building erection also has a positive effect on the course of technical wear. In addition, using information on the expenditures on the realization of preventive structural protections, and their contribution to the total building costs, an assessment of the effectiveness of the protection application was made. It was also determined that the costs associated with the use of preventive structural protection are compensated by lower technical wear of buildings. The research carried out in first stage confirmed the possibility of predicting the intensity of damage based on technical parameters and indicators of mining impacts. Second stage demonstrated the positive effect of renovation work and preventive structural protection against mining impacts on the technical condition of buildings.

W artykule przedstawiono wyniki analizy zakresuuszkodzeń wielokondygnacyjnych budynków mieszkalnych i użytecznościpublicznej. Przedmiotem badań były obiekty zlokalizowanena terenie górniczym Legnicko-Głogowskiego OkręguMiedziowego. Utworzona baza danych obejmowała informacjeo 56 murowanych budynkach wielokondygnacyjnych w wiekudo 25 lat, zabezpieczonych przeciw wpływom górniczym na etapiebudowy. Dla każdego budynku wyznaczono wskaźniki opisująceintensywność uszkodzeń ich elementów konstrukcyjnychi wykończeniowych. Podstawą wyznaczenia wskaźników byłycztery inwentaryzacje stanu technicznego budynków przeprowadzonew latach 2002–2017. W wyniku badań ustalono zmiennośćzakresu uszkodzeń w okresie 15 lat oraz ich udział w zużyciutechnicznym budynków.