A Study of Crack Detection Ultrasonic Attributes to Manage Leak Threats Associated With Short Crack-Like Flaws in ERW Pipelines
Bibliographic record
Abstract
Inline Inspection (ILI) tools along with hydrostatic testing have been the primary identification and mitigation techniques for cracking threats on liquids pipelines. Each technique faces detection challenges in relation with the weld type, geometry, and feature types, sizes and orientations. Low frequency electric resistance welds (LF ERWs) are subject to a number of crack-like defects due to the ERW manufacturing process. These defects may include fatigue cracks, lack of fusion, burned metal defects, stitched welds, cold welds, cracks in hard HAZ, surface breaking hook cracks near the weld and selective seam corrosion [1]. Within a population of features in a pipeline, a subpopulation can exist of short, deep defects (>50% wt) that may be undersized by the ILI tool or not detected by a hydrostatic test due to the length of the flaw. For ILI tools, a length detection threshold is set based on the tool speed (which is dictated by the tool type and configuration). A feature may be undersized by the ILI tool if its length is below this tool threshold. For hydrostatic testing, through-wall flaws may be undetected if the flaw length is below the critical length for a significant leak. Through detailed ILI data analysis, Enbridge along with PII Pipeline Solutions has been able to consistently identify short and deep crack-related defects on LF ERW pipe through means other than feature dimensions provided by the ILI tool. In-ditch non-destructive examination and destructive laboratory testing has confirmed these features are critical and fall below current ILI tool’s detection thresholds. This paper discusses unique ILI data attributes that may identify a more severe feature than would conventional ILI sizing practices, and how the identification and selection procedure is being applied across Enbridge’s pipeline system. This analysis effort aligns with Enbridge’s goal to continuously improve its integrity management processes and further enhance the safety of its pipelines.
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 | 0.001 |
| 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".