Leveraging Failure Modes and Effect Analysis for Technical Language Processing
Bibliographic record
Abstract
With the evolution of data collection technologies, sensor-generated data have become the norm. However, decades of manually recorded maintenance data still hold untapped value. Natural Language Processing (NLP) offers new ways to extract insights from these historical records, especially from short, unstructured maintenance texts often accompanying structured database fields. While NLP has shown promise in this area, technical texts pose unique challenges, particularly in preprocessing and manual annotation. This study proposes a novel methodology combining Failure Mode and Effect Analysis (FMEA), a reliability engineering tool, into the NLP pipeline to enhance Named Entity Recognition (NER) in maintenance records. By leveraging the structured and domain-specific knowledge encapsulated in FMEAs, the annotation process becomes more systematic, reducing the need for exhaustive manual effort. A case study using real-world data from a major electrical utility demonstrates the effectiveness of this approach. The custom NER model, trained using FMEA-informed annotations, achieves high precision, recall, and F1 scores, successfully identifying key reliability elements in maintenance text. The integration of FMEA not only improves data quality but also supports more informed asset management decisions. This research introduces a novel cross-disciplinary framework combining reliability engineering and NLP. It highlights how domain expertise can be used to streamline annotation, improve model accuracy, and unlock actionable insights from legacy maintenance data.
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 | 0.003 | 0.017 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.009 | 0.003 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.004 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 0.002 |
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".