Next Article in Journal
Sodium Alginate–Soy Protein Isolate–Chitosan–Capsaicin–Nanosilver Multifunctional Antibacterial Composite Gel
Previous Article in Journal
Experimental Investigation into the Process of Hydraulic Fracture Propagation and the Response of Acoustic Emissions in Fracture–Cavity Carbonate Reservoirs
Previous Article in Special Issue
Robust Observer-Based Proportional Derivative Fuzzy Control Approach for Discrete-Time Nonlinear Descriptor Systems with Transient Response Requirements
 
 
Article
Peer-Review Record

Production Capacity Prediction and Optimization in the Glycerin Purification Process: A Simulation-Assisted Few-Shot Learning Approach

Processes 2024, 12(4), 661; https://doi.org/10.3390/pr12040661
by Tawesin Jitchaiyapoom 1, Chanin Panjapornpon 1,*, Santi Bardeeniz 1 and Mohd Azlan Hussain 2
Processes 2024, 12(4), 661; https://doi.org/10.3390/pr12040661
Submission received: 27 February 2024 / Revised: 13 March 2024 / Accepted: 24 March 2024 / Published: 26 March 2024

Round 1

Reviewer 1 Report

Comments and Suggestions for Authors

Clarify the significance of tight control in chemical processes and the limitations of historical data in adapting to deviations.

Elaborate on the simulation-assisted deep transfer learning approach, detailing the process of generating the base feature extractor and the techniques used for fine-tuning.

Provide comprehensive insights into the improvement metrics, such as discussing the significance of the 99% enhancement in predicting water content and the implications of the 79.72% increase in glycerin prediction accuracy.

Discuss the practical implications of the proposed model, emphasizing its potential impact on process stability, equipment safety, and overall efficiency.

Reiterate the findings and the potential of the proposed model in enhancing both production capacity and final purity of glycerin, thereby reinforcing the significance of the study's contribution.

Comments on the Quality of English Language

Moderate editing of English language required

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 2 Report

Comments and Suggestions for Authors

1. The authors talk in the paper about a substantial amount of data, which ensures that the data simulated by the proposed method, called supporting data, represent the real operational conditions for the proposed model. Taking into account the importance of the data set, I recommend the authors to present more details about this way of estimating this "quantity".

2. Another topic of interest, in my opinion, would be to expand the real/industrial data set analyzed to give more credibility to the proposed model.

3. I recommend the authors to carry out a comparative analysis of the innovative techniques used for the prediction and optimization of the production capacity, aimed at determining/establishing the most beneficial technique.

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Round 2

Reviewer 1 Report

Comments and Suggestions for Authors

Accepted as it is. 

Comments on the Quality of English Language

Moderate editing of English language required

Back to TopTop