Enbridge Comparison of Crack Detection In-Line Inspection Tools
Bibliographic record
Abstract
Enbridge Pipelines Inc. operates the world’s longest and most complex liquids pipeline network. As part of Enbridge’s Integrity Management Program In-Line Inspections have been and will continue to be conducted on more than 15,000 km of pipeline. This extensive program is comprised of a mature metal loss and geometry inspection component as well as a crack inspection program utilizing the most sophisticated In-Line Inspection (ILI) tools available. Enbridge conducted its first ultrasonic crack inspection with the British Gas Elastic Wave Vehicle (Now GE Power Systems – Oil & Gas – PII Pipeline Solutions) in September 1993 on a Canadian portion of it’s 864–mm (34”) diameter line. The Elastic Wave Vehicle was also used for crack detection on additional segments of this same 864–mm (34”) diameter line during the following years, 1994, 1995 and 1996. Enbridge then conducted its first crack inspection with the Pipetronix UltraScan CD tool (Now also GE Power Systems – Oil & Gas – PII Pipeline Solutions) in November 1997 on a segment of this 864–mm (34”) diameter line that was previously inspected with the Elastic Wave Vehicle. The UltraScan CD tool was then utilized again in 1999, 2000 and 2001 completing crack inspection of the Canadian portion of this 864–mm (34”) diameter line. Enbridge conducted its first magnetic crack inspection with the PII TranScan (TFI) Circumferential Magnetic inspection tool in December 1998 on a United States portion of another 864–mm (34”) diameter line. This same section of line was subsequently inspected with the PII UltraScan CD tool in July 2001. This paper discusses the comparison of results from overlapping crack inspection data analysis from these three PII crack detection tools. Specifically, the overlap of the UltraScan CD and Elastic Wave Vehicle along with the overlap of the UltraScan CD and TranScan (TFI) tool. The relative performance of each crack detection tool will be explored and conclusions drawn.
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 | 0.006 | 0.013 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.006 | 0.002 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.003 | 0.003 |
| Open science | 0.003 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.012 | 0.005 |
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".