Enhancing quality control of polyethylene in industrial polymerization plants through predictive multivariate data‐driven soft sensors
Bibliographic record
Abstract
Abstract Measuring polyethylene properties in the laboratory is time‐consuming and usually unavailable in real‐time, posing significant challenges for controlling product quality in polymerization plants. This research focuses on developing multivariate data‐driven soft sensors for online monitoring and prediction of key characteristics. The targeted properties for prediction include the melt flow index (MFI), density, and average particle diameter in the gas‐phase fluidized bed reactor, as well as the MFI and flow rate ratio (FRR) in the slurry‐phase process. We conducted an exhaustive examination using an ensemble learning approach to quantify the impact of process variables on the model's responses. Various machine learning (ML) algorithms were trained and validated using datasets from industrial ethylene polymerization plants. The precision of the ML models was improved by splitting the datasets into categories comprising high and low MFI and FRR, as well as linear low‐density and high‐density clusters. Then, segmented ML models were developed for each cluster. The results demonstrated that the segmented ML models utilizing optimized Gaussian process regression models with suitable kernel functions and ensemble bagged tree models offered the highest accuracy in predicting the MFI, FRR, and density. Additionally, the comprehensive ML model without clustering, utilizing Gaussian process regression with an isotropic exponential kernel function, proved to be the most effective at predicting the average particle diameter.
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 | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| 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".