Facilitating Energy Monitoring and Fault Diagnosis of Pneumatic Cylinders with Exergy and Machine Learning
Bibliographic record
Abstract
Pneumatic systems are widely used in industrial production sectors. Increasing penetrations of Intelligent Manufacturing and Green Manufacturing are highlighting the drawbacks of pneumatic technology in terms of particularly low energy efficiency and low-level fault diagnosis intelligence. Here we propose that a combined energy-based maintenance and fault diagnostic approach for pneumatic systems could be a game-changer for pneumatics. In this study, a pneumatic cylinder with internal and external leakages is examined and a typical pneumatic experimental system is built. Exergy is adopted for evaluating the available energy of compressed air. Data-driven machine learning models, SAE + SoftMax neural network model and SAE + SVM model, are developed for fault detection and diagnosis. By comparing different machine learning methods with various pressure, flowrate, and exergy data, it is found that the diagnostic accuracy when using pressure and flowrate data is highly dependent on operating conditions, while the diagnostic accuracy when using exergy data is always high regardless of operating conditions. This indicates the promise of developing an exergy-based maintenance paradigm in pneumatic systems. Besides, with exergy and machine learning, more downstream faults can be detected and diagnosed with fewer upstream sensors. This study is the first attempt to develop an exergy-based maintenance paradigm in pneumatic systems. We hope it could inspire the following investigations in other energy domains.
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 | 0.000 | 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 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| 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".