Enhancing Maintenance Data Analytics: A Novel Failure Mode and Effect Analysis-Natural Language Processing Integration
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Machine learning models require considerable amounts of data, which is often a significant limitation in many real-world applications due to the scarcity of quality data. Information recorded in management systems, such as enterprise resource planning software (ERP), can nevertheless be supplemented by text fields, which can be used to enhance its quality. Natural language processing (NLP) techniques seem theoretically capable of meeting this challenge. However, the technical nature and structure of industrial text fields require further analysis to fully exploit state-of-the-art NLP models. This article presents a new methodology to leverage already available information to facilitate the implementation of NLP applications. The approach is then tested specifically in the context of reliability and maintenance, by exploiting failure modes and effects analyses (FMEA) to improve the quality of maintenance descriptions, within the framework of an NLP approach. This case study demonstrates the usefulness of the methodology, by applying it to the maintenance data of a power transmission utility.
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.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 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 it