Registration of Multimodal Pipeline In-Line Inspection Data Using Generative Adversarial Network-Based Translation
Bibliographic record
Abstract
Detecting and accurately locating defects through nondestructive inspection (NDI) is critical for maintaining pipeline integrity. Employing multiple NDI techniques on the same pipeline enhances inspection reliability, especially when dealing with complex, degraded structures. However, misalignments between data acquired from different sensing modalities present a significant challenge. Achieving effective data registration that ensures spatial alignment of these multimodal measurements is difficult due to the diverse underlying physical principles and the nonlinear, multimodal nature of the resulting signals. This study proposes an automated registration method for magnetic flux leakage (MFL) and ultrasonic testing (UT) inspection data. First, a generative adversarial network (GAN) is employed to translate UT data into the MFL domain, harmonizing the multimodal data into a consistent physical space and improving cross-modality similarity. Next, the registration parameters are optimized by applying a difference metric that minimizes the gradient of the difference map between the translated and measured MFL images. Experimental results demonstrate that this GAN-based translation, combined with the gradient-guided difference metric, improves registration accuracy. The resulting alignment of the MFL and UT data enables reliable subsequent data integration.
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 | 0.004 |
| 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 | 0.001 |
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".