Next Article in Journal
Purification of Produced Water by Solvents to Enhance Oil Recovery and Reuse Separated Droplets
Next Article in Special Issue
Deep Learning Utilization for In-Line Monitoring of an Additive Co-Extrusion Process Based on Evaluation of Laser Profiler Data
Previous Article in Journal
Conception of a System-on-Chip (SoC) Platform to Enable EMG-Guided Robotic Neurorehabilitation
Previous Article in Special Issue
Fault Diagnosis of Rolling Bearings Based on Acoustic Signals in Strong Noise Environments
 
 
Article
Peer-Review Record

A Temporal Convolutional Network–Bidirectional Long Short-Term Memory (TCN-BiLSTM) Prediction Model for Temporal Faults in Industrial Equipment

Appl. Sci. 2025, 15(4), 1702; https://doi.org/10.3390/app15041702
by Jinyin Bai, Wei Zhu *, Shuhong Liu, Chenhao Ye, Peng Zheng and Xiangchen Wang
Reviewer 1: Anonymous
Reviewer 2: Anonymous
Appl. Sci. 2025, 15(4), 1702; https://doi.org/10.3390/app15041702
Submission received: 4 January 2025 / Revised: 3 February 2025 / Accepted: 6 February 2025 / Published: 7 February 2025

Round 1

Reviewer 1 Report

Comments and Suggestions for Authors

the manuscript does not provide sufficient comparative discussion on how this model addresses shortcomings of prior methods beyond accuracy metrics. Could the authors elaborate on how their model’s architecture specifically contributes to solving practical challenges such as noise robustness or fault imbalance in real-world scenarios?

Please include detailed preprocessing steps (e.g., imputation techniques, feature scaling) and explain whether these steps are generalizable across different datasets.

Please clarify the rationale for selecting the specific activation function (Leaky ReLU) and kernel size (4) in the TCN layer.

The manuscript primarily discusses Precision, Recall, and F1-Score but does not provide an error analysis. Could the authors include visualizations such as confusion matrices or explain misclassified instances to better understand the model's limitations?

The comparative performance of other models (CNN, BiLSTM, etc.) is discussed but lacks statistical significance tests. Adding such tests (e.g., paired t-tests, Wilcoxon tests) would strengthen the validity of the claims.

Author Response

Thank you for your detailed review and valuable feedback on my manuscript. Your suggestions have been extremely helpful in improving the paper. 

I have made the necessary revisions in response to your comments, and the specific changes are outlined in the attached document. I hope these adjustments will enhance the quality of the paper.

Thank you once again for your time and effort, and I would greatly appreciate any further suggestions you may have.

Author Response File: Author Response.pdf

Reviewer 2 Report

Comments and Suggestions for Authors

My comments are in the attached file.

Comments for author File: Comments.pdf

Author Response

Thank you for your detailed review and valuable feedback on my manuscript. Your suggestions have been extremely helpful in improving the paper. 

I have made the necessary revisions in response to your comments, and the specific changes are outlined in the attached document. I hope these adjustments will enhance the quality of the paper.

Thank you once again for your time and effort, and I would greatly appreciate any further suggestions you may have.

Author Response File: Author Response.pdf

Round 2

Reviewer 1 Report

Comments and Suggestions for Authors

The authors improved the manuscript.

Reviewer 2 Report

Comments and Suggestions for Authors

The authors addressed my main remarks. I think the paper can now be accepted for publication.

Back to TopTop