Using machine learning to automate ultrasound-based classification of butt-fused joints in medium-density polyethylene gas pipes
Bibliographic record
Abstract
Polyethylene (PE) pipes are widely used in gas distribution. Their joints are prone to various flaws and are the most problematic part of the pipeline, so the infrastructure industry requires an effective inspection technique. Butt-fusion (BF) is the most common method of joining PE pipes. In this research, we investigated the applicability of machine learning (ML) to automate the ultrasonic inspection of PE pipe BF joints. Flawless and defective joints were fabricated. A-scan signals were collected from each group of samples using a customized chord transducer, with the aim of developing and assessing the viability of ML approaches to the problem of joint classification. We compared several ML approaches to the problem and found that convolutional neural networks were most performant, classifying signals with an F1 score of 0.874 in a four-class problem (identifying defect presence and type) and of 0.912 in binary classification (defect presence/absence only). Our results show that an ultrasonic chord-type transducer approach can effectively resolve flawless samples versus those with coarse contaminants or cold fusions and that an ML approach can be used to effectively assess these ultrasonic signals. Our findings can be used to develop a portable, efficient, user-friendly, and inexpensive device for in-field joint inspections.
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 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.001 | 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 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".