Machine learning-aided model for predicting oily sludge pyrolysis under various feedstock and operating conditions
Bibliographic record
Abstract
Oily sludge pyrolysis technology has the advantages of potential recovery of valuable resources and safe disposal of non-recoverable residues. However, experimentally determining the optimal pyrolysis operating conditions is time-consuming and expensive. In this study, a machine learning (ML) approach was developed to predict and optimize the oily sludge pyrolysis process. Among the six machine learning models, eXtreme Gradient Boosting (XGB) was found to have the best prediction results. A multi-task XGB model was then developed with oily sludge ultimate and proximate composition and pyrolysis operating conditions as the modeling inputs. The modeling results indicated that the sludge ash and hydrogen contents as well as the pyrolysis temperature are the most critical factors affecting pyrolysis process and its performance. The contribution of sludge ultimate composition to the pyrolysis performance is 42.5 %, followed by sludge proximate properties (35.8 %) and pyrolysis operating conditions (21.7 %). The multi-task XGB ML model achieved an average R 2 of 0.90 through model verification. The ML-aided modeling approach provides new insights for understanding and optimizing the oily sludge pyrolysis. • Machine learning models were developed to predict oily sludge pyrolysis products. • XGB showed optimal performance (test R 2 of 0.93–0.94) for single-/multi-task models. • Pyrolysis is most affected by sludge ash and hydrogen content and pyrolysis temperature. • The Multi-task XGB model can be used to optimize the pyrolysis oil and gas yield. • Model validation was conducted to verify the accuracy of multi-task XGB modeling.
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 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.001 | 0.000 |
| 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".