A machine learning approach for modelling and optimization of complex systems: Application to condensate stabilizer plants
Bibliographic record
Abstract
Abstract Recent advancements in supervised machine learning tools have demonstrated their ability to achieve accurate and efficient prediction results. In this paper, we leverage these tools as alternative approaches to model a specific application in the gas industry, based on operating data. The chosen application is a natural gas condensate stabilization process, in which light end components are removed to reduce condensate vapour pressure, meeting storage and transportation specifications. Here, we develop and evaluate various supervised machine learning models to predict the performance of two industrial condensate stabilizer units. By utilizing large datasets from these units and encompassing comprehensive operating data of input–output variables, we not only demonstrate the capability of these techniques to offer reliable and accurate predictions but also shed light on their potential impacts and implementations. The impacts of applying selected AI and machine learning algorithms are two‐fold. First, our research presents an innovative approach to process modelling and optimization in the gas industry, showing the potential for enhanced operational efficiency, profitability, and safety. Second, we propose a data‐driven surrogate‐based optimization framework, where the generated machine learning models can replace detailed first‐principle models, offering a streamlined method to find optimal values for variables to reduce operational energy consumption. Furthermore, we address the validation requirements of our machine learning models, ensuring their robustness and reliability in real‐world applications. By incorporating rigorous validation procedures, we guarantee the quality of our predictions and support their practical implementation. In conclusion, our research not only highlights the capabilities of machine learning in gas industry applications but also emphasizes their potential impacts and contributions to operational excellence. So, the presented approach can pave the way for improved performance, efficiency, and profitability in the gas industry.
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 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 | 0.000 |
| 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 itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, 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".