Virtual rotating speed meter: extracting machinery rotating speed from vibration signals based on deep learning and transfer learning
Bibliographic record
Abstract
Rotating machinery like wind turbines often operates under varying speed conditions. Measuring speed signals is critical for vibration-based condition monitoring of rotating machines. However, in real applications, sometimes it is difficult to install speed sensors to collect speed signals due to physical space and/or cost restrictions. Considering vibration signals are widely collected for condition monitoring, this paper proposes a virtual rotating speed meter which can extract the rotating speed of a rotating machine from its vibration signals. The proposed virtual speed meter is a framework of deep neural network in nature, which takes the vibration signal as the input, and directly outputs the corresponding speed signal. The training of this neural network is based on transfer learning across two machines: a source machine and a target machine. The source machine has massive historically measured vibration and speed signals available, while the target machine only has vibration available. The virtual speed meter is firstly trained with historical vibration signals and speed signals of the source machine, and then fine-tuned to fit a target machine to extract its speed from its vibration signals. Limited speed labels of the target machine for transfer learning are estimated using a reported signal processing method named Path Optimization. Case studies on two experimental datasets validate the effectiveness of the proposed virtual rotating speed meter.
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) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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 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".