Agnieszka Malinowska

Classification and regression tree theory application for assessment of building damage caused by surface deformation

A framework of applying the classification and regression tree theory (CART) for assessing the concrete building damage, caused by surface deformation, is proposed. The prognosis methods used for approximated building hazard estimation caused by continuous deformation are unsatisfactory. Variable local soil condition, changing intensity of the continuous deformation and variable resistance of the concrete buildings require the prognosis method adapted to the local condition. Terrains intensely induced by surface deformation are build-up with hundreds of building, so the method of their hazard estimation needs to be approximated and relatively fast. Therefore, promising might be addressing problems of reliable building damage risk assessment by application of classification and regression tree. The presented method based on the classification and regression tree theory enables to establish the most significant risk factors causing the building damage. Chosen risk factors underlie foundation for the concrete building damage prognosis method, which was caused by the surface continuous deformation. The established method enabled to assess the severity of building damage and was adapted to the local condition. High accuracy of shown approach is validated based on the independent data set of the buildings from the similar region. The research presented introduces the CART to determination of the risk of building damage with the emphasis on the grade of the building damage. Since presented method bases on the observations of the damages from the previous subsidence, the method might be applied to any local condition, where the previous subsidence is known.

Fuzzy inference-based approach to the mining-induced pipeline failure estimation

The correct evaluation of failure hazard in water and gas supply pipelines has been a great problem in areas which are subject to considerable surface movements. The complexity of elements from which pipeline network consists allows only for an approximated evaluation of their resistance. It is practically impossible to precisely determine the places of failures, and therefore attempts were made in the paper to construe a fuzzy system of evaluation of water supply network hazard which would be integrated with the geographic information system (GIS). The uncertainty factor was to be accounted for in the system through the use of linguistic variables, e.g., resistance of water pipeline and hazard of the terrain in the form of fuzzy sets. The reasoning was based on a Mamdani-type fuzzy model. The inferences of variables relating to the resistance of the pipeline supply network and hazards generated by continuous surface strains could be integrated in the presented fuzzy model. The ultimately scaled model was integrated with the geographic information system. The model was presented on the example of hazard evaluation of water supply network located in a mining area.

Application of Land Subsidence Inversion for Salt Mining-Induced Rock Mass Movement

Modelling of strains and deformations in salt mine areas encounters considerable difficulties because of the varying strength properties of salt, complex morphological formation of dome deposits and rheological properties of salt. Due to such properties the impact of salt extraction increases over hundreds of years and accurate determination of strains at a given moment and place is burdened with high uncertainty. Numerical modelling is useful when the model is reduced to one or several chambers. A broader range considerably lowers the accuracy and efficiency of calculations in such models. Stochastic models allow for 3D modelling of an entire mining complex, provided the model has been parametrized in detail. The process of strain and deformation modelling was presented on the example of one of the biggest salt mines in Europe, where the volume of over 21 million m3 of salt deposit was extracted. The stochastic model could be parametrized thanks to the documented measurements results of panel convergence and levelling on the surface. The use of land subsidence inversion in the least squares method allowed to estimate the optimum values of the model parameters. The correctness of the evaluation was qualitatively and quantitatively confirmed graphically by comparing modelled and measured values of subsidence. The presented model can be applied in the future extraction projects for predicting strains and deformations for an arbitrary moment