Comments On “Neural Network Modeling of Structured Packing Height Equivalent to a Theoretical Plate” and“HETP and Pressure Drop Prediction for Structured Packing Distillation Columns Using a Neural Network”
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
The two research notes 1,2 recently published in Ind. Eng.Chem.Res. by Eldridge and co-workers describe a currently fashionable approach for correlating a number of macroscopic hydraulic and transport parameters in multiphase reactors.Hence, on the basis of a wide hydrodynamic data set, these authors propose a set of general perceptron-like artificial neural network (ANN) correlations for the prediction of the height equivalent to a theoretical plate (HETP) and the twophase pressure gradient (∆P/H) in counter-current gasliquid structured packing towers.The proposed tools are shown to outperform, in terms of prediction capability, the well-trodden empirical correlations or phenomenological models existing in the field.Although these authors are successful in demonstrating their concept, the impact of their contribution, can, to our opinion, be further reinforced.The procurement in a publication of the full expression and parameters of a correlation is the sole guarantee that such a tool can be useful to readers from industry and academia.In this work, the authors neglect to provide for both the HETP and ∆P/H in their derived correlation equations together with the numerical values of the weights.This unfortunately makes it impossible for users to tangibly take advantage of these two papers.Basically, the most valuable aspect of this work is more the correlation equations rather than the methodology implemented to extract the correlations.For the benefit of the readers of Ind. Eng.Chem.Res., it is highly suggested that the authors provide the complete set of equations allowing for the computation by their tools of the hydrodynamic parameters in the chosen configuration.Neural network computing is becoming increasingly fashionable among the chemical engineering circle.It is a powerful "black-box" approach used to map complex
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.
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 it