A Statistical Model for the Prediction of SCC Formation Along a Pipeline
Bibliographic record
Abstract
Near-neutral stress corrosion cracking (SCC) is an operational integrity problem experienced by pipeline transporation companies since the 1970’s. Current in-line inspection (ILI) technology allows for the detection of SCC in pipelines using ultrasonic measurement. However, these tools have size limitations (not available for small diameter pipelines) and can only accurately detect cracks above a certain threshold dimension. Predictive modeling of SCC has been used when direct detection was not feasible. To date, predictive models have focused mainly on establishing quantitative relationships between environmental factors and SCC formation or growth. In general, models used to predict SCC growth have been more successful than models used to predict the location of SCC formation. A model to predict locations of SCC formation has been developed, in conjunction with a pipeline operator, by statistically analyzing data related to locations where SCC was either found or not found during investigative digs on a particular pipeline. Data acquired at the investigative dig sites (such as soil conditions, drainage patterns and local geography) was incorporated into the analysis. In addition, data acquired for the entire length of the pipeline (such as geometry, metal loss features, close-interval cathodic protection readings and operating pressures) was combined with the dig site data in the analysis process. The combined data set was analyzed using statistical regression techniques and various multi-variable logistic regression models were created. Misclassification analysis and regression tress were used to determine the most accurate model for application to the pipeline. The model was then applied to the pipeline to determine probabilities of SCC at specified increments along its length (approximately every 20 metres). Ten locations with high SCC probabilities were selected for verification excavation. In addition, one site with a lower SCC probability was chosen for excavation. Of the ten high-probability locations, SCC was discovered at seven sites. At the lower probability site, SCC was not discovered. The combined success rate of themodel was 73%, a significant improvement over predictive models previously applied to the pipeline. Additional investigative digs are planned to further test the model and to compare its predictions to SCC detected by a recently developed ultrasonic ILI tool. By examining the occurrence of SCC using statistical methods, the ability to make an unbiased prediction of the probability of SCC along a pipeline of interest has been achieved. The pipeline operator has gained an increased ability to assess the likelihood of SCC along its pipeline, showing due diligence in mitigating the risks associated with this pipeline integrity concern.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 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 | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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 teacher head, 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".