Retrofitting Health and Usage Monitoring Systems (HUMS) for Unmanned Aerial Vehicles
Bibliographic record
Abstract
With the global drone market expected to reach USD 40.9 billion by 2027, increased system reliability has become critical not only to protect public safety and ensure mission success, but also to demonstrate risk controls as part of licensing. Health and Usage Monitoring Systems (HUMS) were primarily developed for real-time condition monitoring and machinery diagnostics of aircraft, naval vessels, and other civilian and military systems. HUMS on lightweight and low-cost Unpiloted Aerial Vehicles (drones) is a comparatively recent phenomenon. Incorporating existing HUMS used for other rotorcrafts directly into UAVs is very challenging, as the size, mass, and cost of such systems often do not match the capabilities of traditional drone structures, nor can they be easily integrated. Several health monitoring technologies geared specifically for UAVs have been developed, including Fiber Bragg Grating (FBG)-based strain and temperature sensors, Piezoelectric (PZT) sensors, and ultrasonic propagation imaging sensors, among others. This paper discusses and evaluates the recent research on five classes of health and usage monitoring systems for UAVs currently in use, namely for structural, electrical, temperature-related, vibration-related, and environment-related failure modes. We then develop some general requirements for a HUMS prototype system that is easily retrofittable with a broad range of small to midsize UAVs, investigate which of the sensor systems may be most suitable for the prototype HUMS, make a comparative analysis of these systems, and identify their limitations. Lastly, we present work in progress on System Architecture options for integrating the different classes of sensors into a single, comprehensive HUMS.
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 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.002 | 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".