Selection of Parameters for Updating in On-line Models
Bibliographic record
Abstract
Predictions from dynamic mechanistic models used for process monitoring and control often exhibit sustained offset from process measurements. This offset is caused by imperfect measurements and by model deficiencies that result from simplifying assumptions, unmodeled disturbances, and uncertain parameter estimates. Extended Kalman filter (EKF) state estimation can eliminate offset by on-line updating of a subset of the model parameters. Offset elimination is accomplished by incorporating nonstationary stochastic states in the model equations. A difficult problem faced by practitioners when implementing state estimators is deciding which model parameters to update using on-line measurements. In this article, simple screening tools are developed to aid in updateable parameter selection. These tools are extensions of the relative gain array (RGA), the relative disturbance gain (RDG), and the disturbance condition number (DCN), which have been used in multivariable control applications to determine appropriate manipulated variable/control variable pairings and to examine disturbance effects. The application of these techniques for updateable parameter selection is demonstrated using simulations of a gas-phase polyethylene reactor system. A benefit of these screening tools over past trial-and-error parameter screening practices is that neither tuning of the state estimator nor running of simulations is required. We show that the RGA is an effective tool for determining when problems will arise due to correlated effects of different parameters on model outputs. The RDG is shown to be an effective tool for reducing the number of adjustable parameters when only particular types of disturbances are anticipated. We demonstrate that the DCN can be used to screen out parameter sets that will lead to excessive and physically unrealistic adjustment of model parameters.
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 | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| 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".