Comparing Deep Learning Against Classic Time Series Analysis and System Identification for Modelling the Kraft Chemical Recovery Process
Bibliographic record
Abstract
In kraft pulp mills, the chemical recovery process often bottlenecks production and is difficult to model. Due to process noise, non-idealities, and scale, first principles and laboratory results are hard to apply. An alternative is to develop models based on process data: process system identification. Recently, machine learning, particularly deep learning, has become a popular approach to process system identification. Unfortunately, the resulting models are typically poorly benchmarked, so their usefulness and relative benefits are unclear. Additionally, the autocorrelation of process data is usually ignored. This thesis has two objectives. First, to develop models that better inform operation of the kraft chemical recovery process. Second, to compare deep learning against classic time series analysis and system identification. Specifically, this thesis addresses estimating lags in the kraft chemical recovery process; forecasting as-fired liquor properties; modelling the relationships between boiler parameters and boiler bank fouling; and monitoring as-fired liquor solids content. For each, classic time series analysis and system identification are sufficient; deep learning performs comparably. This suggests that deep learning is not always necessary for process system identification.
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 | 0.002 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.002 | 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".