PONE-D-25-34707Residual-Aware Health Prediction of Power Transformers via Spatiotemporal Graph Neural NetworksPLOS ONE

Dear Dr. Chu,

Thank you for submitting your manuscript to PLOS ONE. After careful consideration, we feel that it has merit but does not fully meet PLOS ONE’s publication criteria as it currently stands. Therefore, we invite you to submit a revised version of the manuscript that addresses the points raised during the review process.

Please note that the comments provided by Reviewer 2 appear to be unrelated to your manuscript and likely refer to a different paper. Therefore, you can disregard the comments from Reviewer 2 during the revision process.

Please submit your revised manuscript by Sep 23 2025 11:59PM. If you will need more time than this to complete your revisions, please reply to this message or contact the journal office at plosone@plos.org. When you're ready to submit your revision, log on to https://www.editorialmanager.com/pone/ and select the 'Submissions Needing Revision' folder to locate your manuscript file.

Please include the following items when submitting your revised manuscript:

• A rebuttal letter that responds to each point raised by the academic editor and reviewer(s). You should upload this letter as a separate file labeled 'Response to Reviewers'.
• A marked-up copy of your manuscript that highlights changes made to the original version. You should upload this as a separate file labeled 'Revised Manuscript with Track Changes'.
• An unmarked version of your revised paper without tracked changes. You should upload this as a separate file labeled 'Manuscript'.

If you would like to make changes to your financial disclosure, please include your updated statement in your cover letter. Guidelines for resubmitting your figure files are available below the reviewer comments at the end of this letter.

If applicable, we recommend that you deposit your laboratory protocols in protocols.io to enhance the reproducibility of your results. Protocols.io assigns your protocol its own identifier (DOI) so that it can be cited independently in the future. For instructions see: https://journals.plos.org/plosone/s/submission-guidelines#loc-laboratory-protocols. Additionally, PLOS ONE offers an option for publishing peer-reviewed Lab Protocol articles, which describe protocols hosted on protocols.io. Read more information on sharing protocols at https://plos.org/protocols?utm_medium=editorial-email&utm_source=authorletters&utm_campaign=protocols.

We look forward to receiving your revised manuscript.

Kind regards,

Dandan Peng

Academic Editor

PLOS ONE

Journal Requirements:

When submitting your revision, we need you to address these additional requirements.

1. Please ensure that your manuscript meets PLOS ONE's style requirements, including those for file naming. The PLOS ONE style templates can be found at

https://journals.plos.org/plosone/s/file?id=wjVg/PLOSOne_formatting_sample_main_body.pdf and

https://journals.plos.org/plosone/s/file?id=ba62/PLOSOne_formatting_sample_title_authors_affiliations.pdf

2. Please note that PLOS One has specific guidelines on code sharing for submissions in which author-generated code underpins the findings in the manuscript. In these cases, we expect all author-generated code to be made available without restrictions upon publication of the work. Please review our guidelines at https://journals.plos.org/plosone/s/materials-and-software-sharing#loc-sharing-code and ensure that your code is shared in a way that follows best practice and facilitates reproducibility and reuse.

3. We note that you have indicated that there are restrictions to data sharing for this study. PLOS only allows data to be available upon request if there are legal or ethical restrictions on sharing data publicly. For more information on unacceptable data access restrictions, please see http://journals.plos.org/plosone/s/data-availability#loc-unacceptable-data-access-restrictions.

Before we proceed with your manuscript, please address the following prompts:

a) If there are ethical or legal restrictions on sharing a de-identified data set, please explain them in detail (e.g., data contain potentially identifying or sensitive patient information, data are owned by a third-party organization, etc.) and who has imposed them (e.g., a Research Ethics Committee or Institutional Review Board, etc.). Please also provide contact information for a data access committee, ethics committee, or other institutional body to which data requests may be sent.

b) If there are no restrictions, please upload the minimal anonymized data set necessary to replicate your study findings to a stable, public repository and provide us with the relevant URLs, DOIs, or accession numbers. For a list of recommended repositories, please see

https://journals.plos.org/plosone/s/recommended-repositories. You also have the option of uploading the data as Supporting Information files, but we would recommend depositing data directly to a data repository if possible.

We will update your Data Availability statement on your behalf to reflect the information you provide.

4. When completing the data availability statement of the submission form, you indicated that you will make your data available on acceptance. We strongly recommend all authors decide on a data sharing plan before acceptance, as the process can be lengthy and hold up publication timelines. Please note that, though access restrictions are acceptable now, your entire data will need to be made freely accessible if your manuscript is accepted for publication. This policy applies to all data except where public deposition would breach compliance with the protocol approved by your research ethics board. If you are unable to adhere to our open data policy, please kindly revise your statement to explain your reasoning and we will seek the editor's input on an exemption. Please be assured that, once you have provided your new statement, the assessment of your exemption will not hold up the peer review process.

5. If the reviewer comments include a recommendation to cite specific previously published works, please review and evaluate these publications to determine whether they are relevant and should be cited. There is no requirement to cite these works unless the editor has indicated otherwise. 

[Note: HTML markup is below. Please do not edit.]

Reviewers' comments:

Reviewer's Responses to Questions

Comments to the Author

1. Is the manuscript technically sound, and do the data support the conclusions?

The manuscript must describe a technically sound piece of scientific research with data that supports the conclusions. Experiments must have been conducted rigorously, with appropriate controls, replication, and sample sizes. The conclusions must be drawn appropriately based on the data presented.

Reviewer #1: Partly

Reviewer #2: Partly

Reviewer #3: Yes

Reviewer #4: Partly

**********

2. Has the statistical analysis been performed appropriately and rigorously?

Reviewer #1: No

Reviewer #2: N/A

Reviewer #3: Yes

Reviewer #4: Yes

**********

3. Have the authors made all data underlying the findings in their manuscript fully available?

The PLOS Data policy requires authors to make all data underlying the findings described in their manuscript fully available without restriction, with rare exception (please refer to the Data Availability Statement in the manuscript PDF file). The data should be provided as part of the manuscript or its supporting information, or deposited to a public repository. For example, in addition to summary statistics, the data points behind means, medians and variance measures should be available. If there are restrictions on publicly sharing data—e.g. participant privacy or use of data from a third party—those must be specified.

Reviewer #1: No

Reviewer #2: No

Reviewer #3: No

Reviewer #4: Yes

**********

4. Is the manuscript presented in an intelligible fashion and written in standard English?

PLOS ONE does not copyedit accepted manuscripts, so the language in submitted articles must be clear, correct, and unambiguous. Any typographical or grammatical errors should be corrected at revision, so please note any specific errors here.

Reviewer #1: No

Reviewer #2: Yes

Reviewer #3: Yes

Reviewer #4: Yes

**********

5. Review Comments to the Author

Please use the space provided to explain your answers to the questions above. You may also include additional comments for the author, including concerns about dual publication, research ethics, or publication ethics. (Please upload your review as an attachment if it exceeds 20,000 characters)

Reviewer #1: You have done some research work, but the scientific writing was very weak.

1. The statement of the problem is not adequate, how this paper is similar or different from the relevant to other research papers (there are more than 100 papers you can find via Scopus search by fault detection of power transformers plus graph neural network).

2. Design of Spatiotemporal Graph Neural Network for Health Status Prediction; You reported what you have done, but no reference adequately to existing papers, and not adequately justify your approach. Consequently, your claims are not born out.

3. The implement is not adequately described; reader is not adequately informed to judge or repeat;

4. The claim of contributions is too general and is assertation. You should have compared the most relevant papers and make specific claim.

Reviewer #2: 1. The paper describes a two-branch framework using time-domain features and wavelet-transformed features from the same source (charging data). However, both branches originate from identical sensor modalities, differing only in representation. This may not strictly qualify as "multimodal" learning in the conventional sense, which usually refers to integrating inherently different data sources (e.g., images + text, or voltage + temperature).

I recommend clarifying this distinction and, if appropriate, revising the title or using terms such as "multi-view" or "hybrid feature fusion" instead.

2. Please clarify whether any data leakage may occur due to the use of sliding window and normalization. Specifically:

Are the sliding windows strictly constructed within each training battery (i.e., no window overlaps or knowledge from the test battery during training)?

Are normalization parameters (e.g., mean, std) computed exclusively from the training set?

Are time–frequency images generated independently for each battery cycle without using future or test cycle information?

3. Equation (11) and (12) are mislabeled: Equation (10) seems to define the cell state, not the output gate.

4. All figures should include axis labels and legends (e.g., Fig. 2 and Fig. 11).

5. Be consistent with acronym usage. For example, “CVT-V” is used before being explicitly defined.

6. Redundant content: Sections 1.1 and 1.2 are overly descriptive and could be more concise. For instance, the entire derivation of IC curves and CCCT/CVCT descriptions may be shortened.

7. Lack of baseline implementation details: For models A–C, implementation specifics (e.g., hyperparameters, source code, or training protocol) are missing. Were they re-implemented by the authors or adopted from original papers? This is crucial for reproducibility.

8. Please refer to 'MSRCN: A cross-machine diagnosis method for the CNC spindle motors with compound faults' and ‘M2BIST-SPNet: RUL prediction for railway signaling electromechanical devices’

Reviewer #3: The paper presents a residual-aware spatiotemporal graph neural network (STGNN) framework that jointly models the dynamic topological dependencies among multivariate Supervisory control and data acquisition (SCADA) signals and their temporal evolution. It's interesting! To further improve the manuscript, the following suggestions are given:

1、In Introduction, a paragraph should be added to introduce the structure of the paper.

2、The formulas in the article are missing numbering.

3、Since there are some papers in this topic, the contributions of the manuscript should be better summarized and listed.

4、While the introduction sets the context, a more explicit literature review section could better situate the study within the broader research landscape, such as Residual-based attention Physics-informed Neural Networks for spatio-temporal ageing assessment of transformers operated in renewable power plants, EVADE Targeted Adversarial False Data Injection Attacks for State Estimation in Smart Grid, LESSON Multi-Label Adversarial False Data Injection Attack for Deep Learning Locational Detection, Joint Adversarial Example and False Data Injection Attacks for State Estimation in Power Systems, and so on. These references could provide valuable insights into your research.

5、Although experimental results are provided, more in depth comparison and analysis should be given in the manuscript.

6、What are the possible shortcomings of the research in this paper if any? Add a section on the limitations of the work and future work in this paper.

7、The manuscript contains a number of linguistic errors that hinder comprehension. The authors are advised to make careful revisions and improvements.

Reviewer #4: Dear Editor and Authors,

I have carefully reviewed the manuscript titled "Residual-Aware Health Prediction of Power Transformers via Spatiotemporal Graph Neural Networks." I believe the paper presents a novel and innovative spatiotemporal graph neural network (STGNN) framework for power transformer health prediction and fault detection, incorporating graph neural networks (GNNs), residual connections, and temporal modeling. The proposed method demonstrates significant potential both in theory and application. However, after reviewing the manuscript, I have identified several areas that require substantial improvement. Below are my detailed comments:

The main strengths of the manuscript lie in its innovation and practical application potential. The paper introduces a novel STGNN framework that effectively models spatiotemporal dependencies in transformer health prediction. This approach combines graph convolutions, attention mechanisms, and residual connections, making a significant contribution to the field. The method is not only theoretically valuable but also highly applicable to real-world power systems, providing an interpretable and scalable solution for transformer health monitoring. Additionally, the paper includes experimental results based on synthetic datasets, which demonstrate that the proposed method outperforms baseline models such as LSTM and GCN-LSTM in terms of forecasting accuracy.

Areas Needing Improvement and Deficiencies:

1. Limitations in Experimental Validation

Currently, the experimental validation relies solely on synthetic datasets, which lack real-world data verification from actual industrial environments. While synthetic data is useful for initial validation, it does not capture the complexity of real-world operational conditions. I recommend incorporating real-world SCADA datasets into the experiments to demonstrate the method’s performance under actual operational conditions. This would not only validate the model but also show its potential for real-world deployment.

2. Narrow Scope of Comparison Experiments

The manuscript only compares the proposed method with LSTM and GCN-LSTM, without including other models for comparison. To provide a more comprehensive evaluation of the proposed method’s strengths, I suggest adding more diverse comparison experiments, including traditional statistical methods (e.g., PCA, SVM) and other advanced GNN variants (e.g., GraphSAGE, GAT). This will allow a more thorough assessment of the proposed method’s advantages and limitations in various scenarios, demonstrating its robustness and generalizability.

3. Need for Improvement in Visuals

The quality of Figure 1 in the manuscript is suboptimal. The font size, line thickness, and overall design do not meet the academic standards expected in journal publications. A clear, professional figure is crucial for the overall presentation of the paper. I recommend redesigning Figure 1, with attention to improving font clarity, line thickness, color contrast, and ensuring a more professional and academic design. The figure should be simple, clear, and visually appealing to meet academic publishing standards.

4. Lack of Clarity in Method Description

While the manuscript introduces the STGNN framework, some technical details on how spatiotemporal dependencies and residual connections are modeled are not sufficiently explained. To help readers better understand the methodology, I recommend providing a more detailed explanation of the modeling process, including training procedures, feature extraction, and how spatiotemporal dependencies are modeled. This can be supplemented with mathematical formulas and diagrams to further clarify the technical details.

Conclusion

In conclusion, this paper introduces an innovative and promising method for transformer health prediction and fault detection. However, the paper requires significant revisions in terms of experimental validation, clarity of methodology, visual quality, and scope of comparison experiments. I recommend major revision of the manuscript. Once these issues are addressed, I believe the paper will make a valuable contribution to the field of power transformer monitoring and fault detection.

**********

6. PLOS authors have the option to publish the peer review history of their article (what does this mean?). If published, this will include your full peer review and any attached files.

If you choose “no”, your identity will remain anonymous but your review may still be made public.

Do you want your identity to be public for this peer review? For information about this choice, including consent withdrawal, please see our Privacy Policy.

Reviewer #1: No

Reviewer #2: No

Reviewer #3: No

Reviewer #4: Yes: Shilin Wang

**********

[NOTE: If reviewer comments were submitted as an attachment file, they will be attached to this email and accessible via the submission site. Please log into your account, locate the manuscript record, and check for the action link "View Attachments". If this link does not appear, there are no attachment files.]

While revising your submission, please upload your figure files to the Preflight Analysis and Conversion Engine (PACE) digital diagnostic tool, https://pacev2.apexcovantage.com/. PACE helps ensure that figures meet PLOS requirements. To use PACE, you must first register as a user. Registration is free. Then, login and navigate to the UPLOAD tab, where you will find detailed instructions on how to use the tool. If you encounter any issues or have any questions when using PACE, please email PLOS at figures@plos.org. Please note that Supporting Information files do not need this step.

Residual-Aware Health Prediction of Power Transformers via Spatiotemporal Graph Neural Networks

PONE-D-25-34707R1

Dear Dr. Chu,

We’re pleased to inform you that your manuscript has been judged scientifically suitable for publication and will be formally accepted for publication once it meets all outstanding technical requirements.

Within one week, you’ll receive an e-mail detailing the required amendments. When these have been addressed, you’ll receive a formal acceptance letter and your manuscript will be scheduled for publication.

An invoice will be generated when your article is formally accepted. Please note, if your institution has a publishing partnership with PLOS and your article meets the relevant criteria, all or part of your publication costs will be covered. Please make sure your user information is up-to-date by logging into Editorial Manager at Editorial Manager® and clicking the ‘Update My Information' link at the top of the page. For questions related to billing, please contact billing support.

If your institution or institutions have a press office, please notify them about your upcoming paper to help maximize its impact. If they’ll be preparing press materials, please inform our press team as soon as possible -- no later than 48 hours after receiving the formal acceptance. Your manuscript will remain under strict press embargo until 2 pm Eastern Time on the date of publication. For more information, please contact onepress@plos.org.

Kind regards,

Dandan Peng

Academic Editor

PLOS ONE

Additional Editor Comments (optional):

Reviewer #2:

Reviewer #3:

Reviewer #4:

Reviewers' comments:

Reviewer's Responses to Questions

Comments to the Author

1. If the authors have adequately addressed your comments raised in a previous round of review and you feel that this manuscript is now acceptable for publication, you may indicate that here to bypass the “Comments to the Author” section, enter your conflict of interest statement in the “Confidential to Editor” section, and submit your "Accept" recommendation.

Reviewer #2: All comments have been addressed

Reviewer #3: (No Response)

Reviewer #4: All comments have been addressed

**********

2. Is the manuscript technically sound, and do the data support the conclusions?

The manuscript must describe a technically sound piece of scientific research with data that supports the conclusions. Experiments must have been conducted rigorously, with appropriate controls, replication, and sample sizes. The conclusions must be drawn appropriately based on the data presented.

Reviewer #2: Yes

Reviewer #3: (No Response)

Reviewer #4: Yes

**********

3. Has the statistical analysis been performed appropriately and rigorously?

Reviewer #2: N/A

Reviewer #3: (No Response)

Reviewer #4: Yes

**********

4. Have the authors made all data underlying the findings in their manuscript fully available?

The PLOS Data policy requires authors to make all data underlying the findings described in their manuscript fully available without restriction, with rare exception (please refer to the Data Availability Statement in the manuscript PDF file). The data should be provided as part of the manuscript or its supporting information, or deposited to a public repository. For example, in addition to summary statistics, the data points behind means, medians and variance measures should be available. If there are restrictions on publicly sharing data—e.g. participant privacy or use of data from a third party—those must be specified.

Reviewer #2: Yes

Reviewer #3: (No Response)

Reviewer #4: Yes

**********

5. Is the manuscript presented in an intelligible fashion and written in standard English?

PLOS ONE does not copyedit accepted manuscripts, so the language in submitted articles must be clear, correct, and unambiguous. Any typographical or grammatical errors should be corrected at revision, so please note any specific errors here.

Reviewer #2: Yes

Reviewer #3: (No Response)

Reviewer #4: Yes

**********

6. Review Comments to the Author

Please use the space provided to explain your answers to the questions above. You may also include additional comments for the author, including concerns about dual publication, research ethics, or publication ethics. (Please upload your review as an attachment if it exceeds 20,000 characters)

Reviewer #2: (No Response)

Reviewer #3: The paper can be accepted.

Please use the space provided to explain your answers to the questions above. You may also include additional comments for the author, including concerns about dual publication, research ethics, or publication ethics.

Reviewer #4: Thank you for your thorough revisions in response to the reviewers' comments. After reviewing the manuscript, I believe significant improvements have been made in experimental validation, model comparison, figure quality, and methodological clarity. You have adequately addressed my suggestions, and the quality of the paper has greatly improved.

One small suggestion: Please carefully review the English expressions, as some sentences may not be as natural or clear. Ensuring that the language is polished and fluent before formal publication will further enhance the manuscript’s readability and academic tone.

Therefore, I believe the paper now meets the publication standards and recommend it for acceptance. I look forward to your final version.

**********

7. PLOS authors have the option to publish the peer review history of their article (what does this mean?). If published, this will include your full peer review and any attached files.

If you choose “no”, your identity will remain anonymous but your review may still be made public.

Do you want your identity to be public for this peer review? For information about this choice, including consent withdrawal, please see our Privacy Policy.

Reviewer #2: No

Reviewer #3: No

Reviewer #4: Yes: Shilin Wang

**********