Application of Machine Learning in Computational Fluid Dynamics-based Design and Optimisation of Turboexpanders Used in Natural Gas Pressure Reduction Stations
Bibliographic record
Abstract
A recently proposed resolution in the market of natural gas (NG) supply in urban areas considers the installation of energy-saving machinery such as turbo expanders in pressure reduction stations (PRSs) of NG distribution networks. The use of turboexpanders in these networks has successfully shown pronounced benefits over the traditional Joule-Thompson (J-T) valves, by effectively recovering the waste energy of the gas during the expansion process. On the negative side, however, turboexpanders are often exposed to off-design operations, ie mainly due to inefficient design causing an improper response to instantaneous variations of upstream pressure in a given NG distribution cycle, which may eventually compromise their advantages, if running uncontrolled. Towards addressing this very complexity, the present work is intended to introduce and examine a cost-effective, yet reliable, numerical framework that integrates machine learning (ML) with computational fluid dynamics (CFD) to improve re-design and optimisation of existing NG turboexpanders in PRS facilities, with the ultimate goal of upgrading traditional procedures frequently used for maintaining such machinery. Considering the high granularity of the proposed framework, it is anticipated that it could be conveniently extended as a robust supplemental tool for related industrial maintenance procedures dealing with NG turbomachinery and energy systems.
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 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 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".