Prediction of Time Until Failure for a Micro Turbine With Unspecified Faults
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
The potential extensive use of micro turbines in distributed power generation will produce a requirement for maintenance scheduling. The wide variety of operating environments and loads will demand that simple hour counters be overly conservative. Additionally, more advanced techniques, such as producing databases of the engine history or metallography, would have expenditures that far outweigh the benefit for such low cost engines. The technique presented in this paper predicts the remaining life of the engine based on operating data since the last overhaul. The technique is independent of the component degrading and uses specific fuel consumption as the determinant of failure, but does not require the measurement of fuel flow or power. The prime advantages of this technique are the requirement for few additional sensors beyond those needed for engine control, and the ability to predict the time until failure without knowledge of the fault occurring or input from the engine user. The system utilizes an algorithm to determine the form of the trend the path to failure is taking and applies exponential smoothing, which is then extrapolated forward to the failure conditions. Since the prediction is based on the operating data since the last overhaul, it initially performs very poorly, but as the engine approaches failure it improves. Depending on the form of the trend, good predictions begin between 30% and 70% through the life of the engine. The system was tested with a computer model of a micro turbojet engine with five different faults ranging from blockage of inlet filters to turbine degradation. Both single and combined faults were tested with similar success. The engine model, including healthy baseline and degraded operation, was validated with an experimental program.
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 | 0.000 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.000 | 0.000 |
| 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