Prediction of pipeline strain demand under ground movement using a neural network-enhanced finite difference method
Bibliographic record
Abstract
Pipelines are vulnerable to permanent ground movement induced by geohazards, which can lead to excessive strain and potential structural failure. Accurate prediction of strain demand is essential for ensuring pipeline safety and supporting geohazard risk assessment. A recently developed finite difference method (FDM)-based framework for pipeline strain analysis has demonstrated strong potential as a fast and practical tool. However, this framework relies on a bilinear stress–strain assumption that allows closed-form expressions for internal forces. For more general nonlinear hardening models, such closed-form solutions are not available, and internal forces must instead be evaluated through numerical integration, resulting in a substantial increase in computational cost. This study proposes a neural network-enhanced finite difference method (NN-FDM) to address this limitation. Neural network surrogates are trained to replace numerical integration in the evaluation of internal forces, thereby enabling the incorporation of general nonlinear hardening behavior within the FDM framework. Additional robustness enhancement strategies are implemented to ensure stable iterative convergence. Two case studies with both bilinear and nonlinear hardening conditions are conducted to examine the effectiveness of NN-FDM. Results demonstrate that NN-FDM maintains comparable accuracy to original FDM for bilinear cases while showing significant advantages for nonlinear hardening scenarios, achieving high accuracy and substantially improved computational performance. The method’s applicability is further validated against four existing analytical solutions for buried pipelines subjected to strike-slip faulting. The proposed method provides a simple and general framework for evaluating pipeline strain demand across a wide range of constitutive models and shows strong potential as an efficient tool for rapid assessment and pre-screening applications in geohazard-prone areas. • NN-FDM predicts the pipeline response to geohazard-induced ground movement. • NN-FDM replaces costly numerical integration with neural network surrogates. • NN-FDM achieves high accuracy and efficiency under nonlinear hardening behavior. • NN-FDM evaluates pipeline strain demand under a wide range of constitutive models.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".