Application of machine learning in monitoring fouling in heat exchangers in chemical engineering: A systematic review
Bibliographic record
Abstract
Abstract The present work consists of a systematic literature review that examines studies on using machine learning to monitor fouling in heat exchangers in the chemical engineering area. The research was conducted in four renowned databases: SCOPUS, Science Direct, IEEE, and Web of Science. The main objective of the investigation was to identify the most prevalent machine learning methods, evaluate their performance, and analyze the challenges associated with their implementation and prospects. Using the StArt software, seven relevant scientific papers from the established review protocol. The most frequently identified methods were support vector machine (SVM) and k‐nearest neighbours (k‐NN), followed by decision tree. However, long‐term and short‐term predictors and long short‐term memory (LSTM) and non‐linear autoregressive with exogenous inputs (NARX) algorithms were the most successful, followed by Gaussian process regression (GPR), SVM, k‐NN, and improved grey wolf optimization–support vector regression (IGWO‐SVR) algorithms. Although these methods inspire confidence, it is important to highlight that they are still in the software testing phase. Key gaps identified include the need for further studies on real industrial applications and the integration of advanced sensors and measurement systems. Future directions point to developing more robust and generalized algorithms capable of dealing with the complexity of real 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 | 0.005 | 0.016 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.004 | 0.004 |
| Bibliometrics | 0.008 | 0.007 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 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".