Bibliographic record
Abstract
Faults with the internal elements of rotating equipment are notoriously difficult to diagnose while the equipment is in service, and so maintainers often have to rely on indirect assessment based on changes in performance and vibrations. A novel approach to visualizing faults with rotating components is presented based on penetrating electromagnetic radiation and image construction. The basic concept of operations is to generate photons from a collimated source that is relocatable so as to illuminate the rotating component in a piecewise fashion along its radius, preferably but not necessarily parallel to the axis of rotation. Subimage acquisition captures stationary parts through which photons pass as well as part of the rotating component. Registration of rotating sub-images is then done as the machine rotates at quasi-steady-state speed to construct the complete image. Widefield high-resolution Fourier ptychographic tomography is employed to stitch together variably illumined low-resolution sub-images in Fourier space to improve resolution and reduce vignetting effects and other artifacts (such as shadowing due to the stationary components). Image acquisition rate and source power can be adjusted to reduce smearing of the parts that are rotating. From the final image, artifact feature extraction is then used to create fault primitives from which fault detection and identification can be done. A proof-of-concept system is presented with experimental characterization using idealized geometries (black line segments and polygons, gray-scale images). A path to practical implementation using x-ray sources and robotic detector positioning is described.
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 | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| 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) | 0.006 | 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".