Determining the burial depth for offshore pipelines to resist impact load is challenging owing to the spatial variability of soil strengths, which proves to significantly affect failure behaviours of soils and pipelines. To facilitate the design, accurate and fast evaluation on pipeline damage is required. Here, an integrated surrogate model was developed to forecast impact damage of pipelines buried in spatially varied soils. Through coupling the random field and numerical simulation, a stochastic finite element analysis framework was derived and verified to yield the datasets; Based on the scheme of feature extraction - integration from convolution neural network, the surrogate model was established, which mapped the three-dimensional soil spatial field to the structural response. Prediction mechanism of the developed model was explored, where correlations among soil spatial distribution patterns, failure mechanisms and feature recognitions were discussed. The models enabled to capture the key features representing the failure mechanisms under random soil conditions, including the local failure mode of soil and pipe-soil interactions, which theoretically explained its feasibility in damage estimation. Further, model performance was comprehensively evaluated with regard to prediction accuracy, uncertainty quantification, and transfer learning, and the corresponding causes were investigated. Satisfactory performance and high computation efficiency were demonstrated.

The combined effect of impact load-corrosion causes great damage to offshore pipelines, which has not been sufficiently considered in structural analysis and safety design, raising potential risks. Addressing this point, the failure mechanism of pipelines with corrosion defects under transient impact loads is explored: first, a finite element analysis model is developed. Through a systematical verification, including the performance in describing the mechanical elastic-plastic behaviours of pipelines under impact loads, pipe-soil interactions, and structural failure behaviours influenced by corrosion defects, the model's fidelity is demonstrated. Then, structural responses corresponding to multiple influential factors are investigated, including the corrosion dimensions, pipe-soil interactions, internal pressures and pipeline geometrical parameters. Furthermore, surrogate models are derived to predict pipeline damage. Results show that: with the deterioration in corrosion defects, pipeline dent damage becomes severe, and multiple mechanical behaviours are triggered and coupled, including deformation compatibility, stress-strain concentrations, bending and bulging buckling, which consequently causes various deformation configurations of structures. The pipe-soil interaction can alleviate the impact damage, which is insensitive to soil strengths owing to the strain rate and strain softening effect. The dent damage on pressurized pipelines tends to be localized, but the stress is increased. Increasing wall thickness and pipeline diameter reduce the local dent damage with a gradually weakened effect, owing to the energy dissipation from global responses. With a coefficient of determination over 0.987, the surrogate model of multiple layer perceptron demonstrates promising feasibilities in damage prediction and safety assessment. The developed models and analysis results provide theoretical and technical reserve for pipeline safety design and maintenance.

Burial is an effective approach to offshore pipeline protection for impact loads. However, few studies address the influences of inherent soil spatial variabilities on failure behaviour of soil covers and pipelines, causing deviations. Therefore, a random field-large deformation finite element analysis framework is developed to explore the failure mechanisms of buried pipelines in spatially varying soils. The failure mode of soil cover is conformed to a local mode, where the failure path is insensitive to soil variability. The failure mechanism of pipelines depends on the competition mechanism between soil strengths and pipe-soil interactions, based on which two typical failure modes are summarized. Soil variability not only aggravates the impact damage but also stimulates the diversity of structural responses. Correlations between probabilistic damage degrees and multiple influential factors are discussed. Further, inspired by the principle of energy dissipation, an integrated quantitative risk assessment model is derived to reveal the failure risk evolution, where uncertainties from soil variabilities and structure-related factors are considered. The latter shows a significant influence, which may pose an additional failure probability of over 50 %. Different safety design approaches are compared, and spatial failure probability surfaces are configured for burial depth determination.

Trench and burial, as a primary and effective protection measurement for offshore pipelines from impact loads, has received much research attention recently. Previous studies were usually performed based on the assumption that the soil material was homogeneous with deterministic mechanical properties. The soil spatial variability, which is demonstrated to have significant influences on the soil capacity in marine geotechnical analysis, has not been included. This study was motivated to investigate the response of the buried pipelines subjected to the impact loads, with special address on the soil variability. Firstly, a three-dimensional random large deformation finite element analysis model was developed, which was implemented by the field variable (FV) technique to map the non-stationary random field (NSRF) into the verified Coupled EulerianLagrangian (CEL) model (Hereafter referred to as FVRCEL). Then the FVRCEL model was integrated with the Monte-Carlo simulation (MCS) to obtain the statistical characteristics of the pipeline structural response. The failure mechanisms of the pipeline in the random soil with different fluctuation scales were investigated, and a parametric study was performed to identify the influential factors. Finally, the failure probability curves and surfaces were presented, providing clues for the pipeline safety design. The results revealed that in general, more than 50 % of the realized NSRF scenarios in the random analysis yielded more severe dent damage than the deterministic result, indicating that the latter would underestimate the damage degree, which was more pronounced when the increasing gradient of soil strength was high. The horizontal fluctuation scale had a remarkable influence on the pipeline damage behaviours and the corresponding statistical characteristics, of which the inner mechanisms were discussed. From the probabilistic perspective, at most an extra failure probability of 75 % would be suffered if the soil variability was ignored.