Linking Pulp Variations to Tmp Operation by Better Selection and Treatment of Process Data
Bibliographic record
Abstract
Multivariate analysis (MVA) is widely used for troubleshooting, process monitoring, and advanced control. It has become easily accessible through desktop software packages. However, this least-squares statistical technique remains highly susceptible to the adage garbage-in/garbage-out, notably with regard to process disturbances and other outliers. Using a thermomechanical pulp newsprint mill in Eastern Canada as a case study, we compared various ways of selecting and pre-treating raw process data to maximize the realism and usefulness of the black-box pulp quality models. We eliminated start-up and shutdown data to model steady-state conditions. A major conclusion of this work was that the partial least squares models were significantly improved by pre-treating the data, with respect to both statistical significance and physical interpretability. We therefore recommend an overall approach for applying MVA to industrial operating data. This involves a systematic method for removing dubious periods of operation, such as low production and aberrant process behavior, and filtering of all dependent and independent variables. Because no single model was able to cover all process scenarios, it seems that some kind of adaptive controller would be required to automate theTMP refining process. Application: This study presents a straightforward method for selecting and pretreating TMP operating data, to improve statistical tracking of pulp quality variations.
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 | 0.008 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.002 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 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".