Corrosion poses a significant risk to the safety of energy pipelines, while landslide disasters emerge as the primary threat responsible for triggering pipeline failures across mountainous areas. To date, there is limited research focused on the safety of energy pipelines considering the synergistic effect of corrosion and landslides. The present study proposes a finite element (FE)-based model to assess the condition of corroded pipelines under landslides. The effects of corrosion dimensions (length and depth) and location are determined. A novel equation is finally developed to predict the maximum stress and determine the most disadvantageous position for corroded pipelines under various landslide displacements. The results demonstrate that (1) as the landslide progresses, the pipeline’s stress significantly increases; (2) corrosion depth has a more significant impact on the pipeline condition than the corrosion length, and it is positively correlated with the pipe’s stress; (3) the maximum stress exhibits a nonlinear relationship with the landslide-facing position and the corrosion circumferential location; and (4) when the axial position of the corrosion is more than 6.5 m away from the center of the landslide, the location of maximum stress shifts from the corrosion region to the central section of the pipeline within the landslide. This work contributes to helping pipeline owners to understand the applicability of energy pipelines subjected to the combined effects of corrosion and landslides and provides support for future risk assessment efforts in pipeline integrity management.

Dents are a common geometric deformation defect in pipelines where the dented section becomes susceptible to local buckling, significantly threatening the integrity and reliability of the pipeline. This paper developed a novel finite element (FE) machine learning (ML)-based approach to analyze and predict the critical buckling moment (CBM) of dented pipelines under combined internal pressure and bending moment (BM) loading. By quantifying the parametric effects on CBM and developing a dataset, an Extreme Learning Machine (ELM) framework through hybrid algorithm integration, combining Bald Eagle Search (BES), Lévy flight, and Simulated Annealing (SA), was proposed to achieve highly accurate CBM predictions. This study offers valuable insights into evaluating the buckling resistance of dented pipelines subjected to complex loading conditions.

Pipeline safety faces a prevalent threat in mountainous areas due to landslides. The advent of landslides introduces the risk of pipeline leaks or ruptures, posing a significant threat to the environment, with the potential for casualties. Throughout the occurrence of landslides, uncertainties abound, yet few studies have addressed the incorporation of uncertainties in assessing pipeline safety. This work proposes a novel hybrid approach to the safety assessment for pipelines under landslides. The use of finite element analysis (FEA) models the pipeline under the action of landslides. The numerical outcomes, combined with unascertained measure theory (UMT), develop a multi-indicator unascertained measure (UM) matrix. Random forest (RF) algorithm is employed to determine the weight of indicators in the matrix. The hybrid application of set pair theory and the UM evaluation vector finally determine the pipeline safety degree and level. The proposed methodology has been well-validated through a case study on an in-service pipeline. The results indicate that the case pipeline safety degree is 2.777, 2.132, 3.132, 3.904, and 2.240, respectively. The corresponding safety level is III, II, III, IV, and II, respectively, which is consistent with the pipeline's actual condition. Different from the conventional safety assessment approach, the proposed methodology demonstrates the enhanced effectiveness, facilitating a more precise evaluation of the pipeline's safety condition.