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.

天然气运输基础设施经常位于受人为运动和压力影响的地区。可以适当地评估地面运动对天然气管道在其损坏方面的潜在影响，例如通过预测应变，同时考虑到地形运动的原因。另一方面，危害也与管道设计等技术因素有关。所提出的方法基于人工智能方法，允许评估供气管道部分的故障风险概率。本研究使用了 Mamdani 模糊推理。通过使用三角形隶属函数在模型中考虑了表征天然气管道阻力的变量和预测的地表连续变形的不确定性。基于表面变形和输气管道阻力以及推断模型，可以预测输气管道何时发生危险。估计两条管道有两个最危险的部分。我们证明了所提出的模型可以为设计管道的保护、成本优化和现有天然气管道的维修做出贡献。