An adaptive fast adjustable GRBF modeling method for online prediction of finished gasoline blending quality
Bibliographic record
Abstract
A fast adaptive adjustable gradient radial basis function (GRBF) quality prediction modeling method is suggested to solve excess product quality caused by the challenge of precisely predicting finished gasoline quality in online blending. First, based on the blending component proportions, key attributes influencing product quality indicators in the blending components are newly incorporated while also considering both product performance and environmental protection indicators, thereby determining a single indicator independent prediction scheme with 12 inputs and one output, tailored to meet the requirements of actual engineering applications. A strategy that can adaptively update the hidden layer nodes and output layer weights online based on the prediction error of the finished gasoline blending quality prediction model is proposed in order to address the batch effect and fluctuation caused by factors such as changes in operating conditions and varying crude oil production areas. This strategy is based on a fast adaptive GRBF network architecture. Additionally, the orthogonal least squares method is employed to construct a GRBF neural network with a fixed number of hidden layer neural units in the offline initial modeling stage, taking into account that the prediction model structure used in actual engineering should not be excessively large. The second-order gradient Levenberg-Marquardt algorithm is then combined to expedite the model construction process. Lastly, the fast adaptive adjustable GRBF model in this paper demonstrates superior prediction performance in comparison to the static radial basis function neural network (RBFNN), XGboost, and stacked autoencoder deep neural network with attention mechanism (AT-SAE-DNN) by experimental verification using actual industrial data from a specific refinery. This model can serve as a dependable foundation for the high-efficiency production of finished gasoline and online blending.
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 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| 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".