A Combined Computational Fluid Dynamics Machine Learning (CFD-ML) Framework for Numerical Design and Optimisation of Turbo Expanders Used in Natural Gas Liquefaction Units
Bibliographic record
Abstract
With the destructive greenhouse gas effects on the rise, there has been a soaring demand for effective strategies that can aid in optimising energy consumption on a global scale. Out of the most attentive strategies in the present market of sustainability and net-zero emission is the application of turbo expanders in the liquefaction process of natural gas (NG). Although the use of turbo expanders has been promising in terms of harvesting energy in liquefied natural gas (LNG) production units compared to traditional equipment such as the Joule-Thomson valve, their complex operation – which is mainly associated with the complex behaviour of NG flows at low-temperature conditions – has challenged not only the related maintenance and condition monitoring procedures, but also the numerical tools regularly utilised for design and optimisation of such machinery. Aiming to address this deficiency, the current work brings together computational fluid dynamics (CFDs) and machine learning (ML) to develop a numerical framework able to effectively predict the performance of low-temperature gaseous NG turbo expanders through fast-response robust surrogate models, while providing an insight into the physical aspects of NG flow inside the turbo expander. The proposed framework can be ultimately extended as a supplemental tool for evaluating the efficiency of relevant industrial turbomachinery, helping to improve their design, implementation and maintenance procedures.
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 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| 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 | 0.002 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 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".