Non-Intrusive Low-Cost IoT-Based Hardware System for Sustainable Predictive Maintenance of Industrial Pump Systems

Round 1

Reviewer 1 Report

Comments and Suggestions for Authors

This paper mainly concerns the industrial maintenance. In this paper, the author present a non-intrusive, low-cost IoT hardware platform for sustainable predictive maintenance of rotational machinery. The system integrates an ESP32-S3 sensor node that captures vibration (100 kS/s) and temperature data, performs local logging, and communicates wirelessly. In addition,  the authors introduce an automated spectral band egmentation framework comparing equal-energy, linear-width, nonlinear, clustering, and peak–valley partitioning, followed by a weighted feature scheme that emphasizes high-value bands. Three unsupervised one-class classifiers—Transformer  Autoencoders, GANomaly, and Isolation Forest—are evaluated on these weighted spectral features. Experimental results show the proposed algorithm has a better performance than other algorithms.  However, the following question should be addressed:

1. The Related work section should be further classified and illustrate the advantage and disadvantage of each class.
2. In this paper, the author defines some equation and provides value for variable in equations. It is reasonable for the parameter setting?
3. For the proposed method, it is better for authors to provide a detailed explanation and introduction.
4. In the paper, the authors use the machine learning to conduct experiments. To embody the novelty of the paper, the authors should include the latest and high-quality paper and make some discussions, such as, Reinforcement learning-based edge server placement in the intelligent Internet of Vehicles environment, 2025. Doi:10.1109/TITS.2025.3557259.
5. There are many spelling errors in the manuscript. A thoroughly spelling check is required in the revision.
6. The Figures in the paper should be further improved.

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 2 Report

Comments and Suggestions for Authors

Reviewer Comments

 

Manuscript Title:

Non-Intrusive Low-Cost IoT Based Hardware System for Sustainable Predictive Maintenance of Rotational Machinery

The manuscript is interested but it needs some modifications, my comments are as follows;

 

• The reference section requires updating, as most cited works are relatively outdated and lack high-impact studies from the past five years. Please supplement with relevant post-2020 literature or replace the supporting references in the first and second paragraphs of the introduction (those addressing research background and current status) with more recent publications from the past five years. The following article may be added to the revised manuscript. DOI: https://doi.org/10.1016/j.compind.2024.104109. DOI: https://doi.org/10.1007/s44196-023-00314-6 .

• End the introduction with a strong statement about the significance and potential impact of your findings.
• The conclusion section effectively summarizes the current findings, but it would be enriching to include potential directions for future research, addressing the gaps and unanswered questions in the current study.
• Proofread the whole manuscript for grammatical errors and improved sentence structure where needed to enhance overall readability.
• Improve abstract and add some qualitative data.
• What was the rationale behind selecting the specific ESP32-S3 sensor node for this study? Were there any preliminary simulations or calculations performed to determine this range based on Transformer Autoencoders, GANomaly and Isolation Forest?

 

 

 

Comments on the Quality of English Language

It needs to re-check and improve.

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 3 Report

Comments and Suggestions for Authors

Please see attached file.

Comments for author File: Comments.pdf

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 4 Report

Comments and Suggestions for Authors

The article is very extensive and from a practical point of view the presented information can be very useful. In my opinion the title is a bit too broad "... maintenance of rotating machines" and it concerns mainly pumps, which is a special case. 
The presented methodology is based on vibration measurement. This methodology of detecting damage is quite well developed and there are commercial standards in this area. I think that these issues should be addressed in the introduction and additionally normative indicators used to assess the condition and vibroacoustic diagnostics of rotating machines should be presented. 
In addition, I miss the presentation of damage statistics, in this case for pumps with an indication of which elements are most often damaged. Referring to the extent to which the system proposed by the authors could detect these damages during operation. 
I propose additionally refining the quality of the presented drawings (Figures 15 and 16).

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Round 2

Reviewer 1 Report

Comments and Suggestions for Authors

All of my concerns have been addressed well.

Reviewer 3 Report

Comments and Suggestions for Authors

Manuscript can be accepted in present form.