A novel fuzzy approach to gas pipeline risk assessment under influence of ground movement

Abstract

The gas transport infrastructure is frequently localized in areas subjected to anthropogenic movements and strains. The potential impact of the ground movements on the gas pipeline in the aspect of its damage can be properly assessed e.g. by predicting strains, taking into account the causes of terrain movement. On the other hand, the hazard is also related to technological factors like design of the pipeline. The presented method is based on artificial intelligence methods allowing for evaluation of probability of failure risk in gas supply pipeline sections. The Mamdani fuzzy inference was used in this study. Uncertainty of variables characterizing the resistance of the gas pipeline and predicted continuous deformations of ground surface were accounted for in the model by using triangular-shaped membership functions. Based on the surface deformations and gas pipeline resistance and the inference model one can make prediction when the gas pipeline is hazarded. There were estimated two the most hazarded parts for two pipelines. We proved that the proposed model can contribute to the protection, costoptimization of the designed pipelines and to the repairs of the existing gas pipelines.