An automated approach and virtual environment for generating maintenance instructions
Bibliographic record
Abstract
Maintenance of complex machinery such as aircraft engines requires reliable and accurate documentation, including illustrated parts catalogs (IPCs), exploded views, and technical manuals describing how to remove, inspect, repair and install parts. For new designs, there are often time constraints for getting a new engine to the field, and the available documentation must go with it. Authoring technical manuals is a complex process involving technical writers, engineers, as well as domain experts (mechanics and designers). Often, several revisions are required before a manual has correct IPC figures and maintenance instructions. Compounding this problem is that technical writers often perform tasks better suited for computers, leading to increased costs and error.In this demonstration, we describe a new framework to generate maintenance instructions from solid models (Computer Aided Design/CAD data) and then validate these instructions in a haptics-enabled virtual environment. Our approach utilizes natural language processing techniques to generate a presentation-independent logical form, which can be transformed for display within the virtual environment. During the development of the system, task analyses, human models, usability studies, and domain experts were used to gain insights. The end result is a more integrated and human-centered process for developing technical manuals, providing higher quality documents with less cost.
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 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.000 |
| 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".