<scp>CVAE</scp> ‐ <scp>SFA</scp> : A practical dual‐channel and multi‐index comprehensive operating performance assessment method for dynamic nonstationary industrial processes
Bibliographic record
Abstract
Abstract The process operating performance assessment (POPA) of process industry plays a key role in the safe, stable, and efficient operation of production process. However, the actual industrial production process often exhibits nonstationary characteristics, leading to frequent anomalies that complicate POPA. Traditional POPA methods are mostly based on limited stable working conditions and single control limits, so it is difficult to fully evaluate the anomaly degree and lack comprehensive assessment indexes. To address these issues, this paper proposes a CVAE‐SFA dual‐channel multi‐index comprehensive POPA method for nonstationary conditions. It introduces four control limits of ‘optimal, good, general, and poor’ based on the optimal reconstruction error from a conditional variational autoencoder (CVAE) and kernel density estimation (KDE). This creates a CVAE optimal grade classification channel for simultaneous qualitative and quantitative evaluations of current operating conditions. Additionally, to monitor dynamic characteristics under nonstationary conditions, a slow feature analysis (SFA) statistic anomaly monitoring channel is established. By identifying slow‐changing essential features within the system, dynamic anomaly monitoring is achieved. Finally, a comprehensive scoring index (CSI) integrates dual‐channel monitoring results to evaluate quality, yield, energy consumption, and stability. The effectiveness of this method is validated through experiments in the cement clinker production process (CCPP).
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 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| 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 | 0.001 |
| 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".