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.