Risk assessment of gas pipeline using an integrated Bayesian belief network and <scp>GIS</scp>: Using Bayesian neural networks for external pitting corrosion modelling
Bibliographic record
Abstract
Abstract Corrosion poses a great risk to the integrity of oil and gas pipelines, leading to substantial investments in corrosion control and management. Several studies have been conducted on accurately estimating the maximum pitting depth in oil and gas pipelines using available field data. Some of the frequently employed machine learning techniques include artificial neural networks, random forests, fuzzy logic, Bayesian belief networks, and support vector machines. Despite the ability of machine learning methods to address a variety of problems, traditional machine learning methods have evident limitations, such as overfitting, which can diminish the model's generalization capabilities. Additionally, traditional machine learning models that provide point estimations are incapable of addressing uncertainties. In the current study, a Bayesian neural network is proposed to include uncertainty in estimating the corrosion defect of a pipeline exposed to external pitting corrosion. The results are then incorporated into a Bayesian belief network for evaluating the probability of failure and its corresponding consequences in terms of social impact, thus forming a comprehensive risk assessment framework. The results of the Bayesian neural network are validated using field data and achieved a testing accuracy of 90%. The framework of the study offers a powerful decision‐making tool for the integrity management of pipelines against external corrosion.
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 | 0.001 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| 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".