Data Preprocessing for Vibration Analysis: Application in Indirect Monitoring of ‘Ship Centrifuge Lube Oil Separation Systems’

Round 1

Reviewer 1 Report

In my opinion the present manuscript should be accepted but after undergoing major revision. My comments and suggestions are appended below:

1) In your result and discussion section, please link your empirical results with a broader and deeper literature review. This is to ensure that the results offer expected outcomes.

2) The conclusion part should be re-written(The conclusion needs to be improved.) Because this section should only contain the SUMMARY of significant outcomes with some numeric values from the research work.

Author Response

On behalf of my coauthors, I would like to thank you for the opportunity to revise and resubmit our manuscript jmse-1866118, entitled “Data preprocessing for vibration analysis: application in indirect monitoring of Ship Centrifuge Lube Oil Separation Systems.” The comments have carefully considered and responded to each suggestion.  We were successful in incorporating the reviewers’ feedback into our revised manuscript.  Corresponding changes are highlighted in the manuscript text in the revised file.

rev1.1 "In your result and discussion section, please link your empirical results with a broader and deeper literature review. This is to ensure that the results offer expected outcomes."

Although the selection of an optimal mother wavelet to carry out a WPT analysis is a novel procedure for this type of machines, so there are no previous expected results, there is a previous related work in which a methodology for the mother wavelet section was proposed for shaft crack detection. This work has been added in the results part, since very similar trends are observed in the procedure. Moreover, for the pattern extraction part, reference has been made to a previous related work in which the frequencies that could indicate changes depending on working hours were determined.

rev1.2. The conclusion part should be re-written (The conclusion needs to be improved.) Because this section should only contain the SUMMARY of significant outcomes with some numeric values from the research work.

Thank you for the suggestion, the conclusions have been re-written highlighting the novelty and improves of the research.

Reviewer 2 Report

The authors have made a concise overview of the topic and a concise reference to existing literature. In general, the text is very well structured and has clearly defined topics. Some comments for improvement:

1. As a general drawback  I could say that authors could add works where the use of vibration monitoring with IoT and data analytics methods have been introduced for condition monitoring of oil pipelines based on time and frequency domain (e.g. [1]): 

[1] Nikolaidis, S., Porlidas, D., Glentis, G. O., Kalfas, A., & Spandonidis, C. (2019). Smart sensor system for leakage detection in pipes carrying oil products in noisy environment: The ESTHISIS Project. In 2019 29th International Symposium on Power and Timing Modeling, Optimization and Simulation (PATMOS) (pp. 125-126). IEEE.

2.       The authors could consider enhancing the introduction section such that it better indicates the main task of the paper among its motivation. Besides, they need to point out the key message the novelty, and the potential benefits of their work.

3.       Besides the authors could include in the results section some validation data regarding the efficiency of the optimum MW to detect the event. Relevant comparisons with other MW and/or similar methods would be fruitful.

4.       Authors could consider enhancing the concluding section with the main outcome of the work amongst its added value. Besides authors are encouraged to add relevant limitations, assumptions, and restrictions to their proposed method. A solid plan for future work could also be fruitful.

Author Response

On behalf of my coauthors, I would like to thank you for the opportunity to revise and resubmit our manuscript jmse-1866118, entitled “Data preprocessing for vibration analysis: application in indirect monitoring of Ship Centrifuge Lube Oil Separation Systems.” We found the comments to be helpful in revising the manuscript and have carefully considered and responded to each suggestion.  We were successful in incorporating the feedback into our revised manuscript. We have included a response to reviewers in which we address each comment the reviewers made. In our response, the reviewer’s comments are numbered and written in bold, and our responses follow below. Corresponding changes are highlighted in the manuscript text in the revised file.  

1) As a general drawback  I could say that authors could add works where the use of vibration monitoring with IoT and data analytics methods have been introduced for condition monitoring of oil pipelines based on time and frequency domain:

More references have been added in the manuscript. They are the following:

• Nikolaidis, S.; Porlidas, D.; Glentis, G.O.; Kalfas, A.; Spandonidis, C. Smart sensor system for leakage detection in pipes carrying oil products in noisy environment: The ESTHISIS Project. In 29th International Symposium on Power and Timing Modeling, Optimization and Simulation (PATMOS) 2019 (pp. 125-126). IEEE.
• Golub, I.; Antonic, R.; Dobrota, D. Optimization of heavy fuel oil separator system by applying diagnostic inference methods. Pomorstvo, scientific journal of maritime research. 2011, 25, 173-188.
• Spandonidis, C.; Theodoropoulos, P.; Giannopoulos, F. A Combined Semi-Supervised Deep Learning Method for Oil Leak Detection in Pipelines Using IIoT at the Edge. Sensors 2022, 22, 4105. Doi: 3390/s22114105

In addition, works that were already referenced have been added in the introduction for a better understanding.

2) The authors could consider enhancing the introduction section such that it better indicates the main task of the paper among its motivation. Besides, they need to point out the key message the novelty, and the potential benefits of their work.

Thank you for the suggestion. The novelty of the research has been enhanced in the introduction. It has been emphasized that with the search for the optimal WM, faster, safer and more reliable signal processing is achieved, which makes pattern monitoring more efficient, also from the energy point of view.

3) Besides the authors could include in the results section some validation data regarding the efficiency of the optimum MW to detect the event. Relevant comparisons with other MW and/or similar methods would be fruitful.

A paragraph has been included at the end of the results section indicating, as an example, a comparison of the increase in energy of the motor speed (between first and second conditions) using the optimal mother wavelet (sym9) with those obtained using the db6 (which has been used in many previous works based on experience of good results). This energy variation is greater for the case of sym9, so it is verified that the objectives sought with the methodology (the greatest energy differentiation between conditions 1 and 2 in the shortest possible calculation time) have been met.

4)  Authors could consider enhancing the concluding section with the main outcome of the work amongst its added value. Besides authors are encouraged to add relevant limitations, assumptions, and restrictions to their proposed method. A solid plan for future work could also be fruitful.

The conclusions section has been modified and a paragraph has been added at the end of the results section indicating, with an example, the usefulness of applying the methodology, as well as future work.

Round 2

Reviewer 1 Report

The paper overall showed a good format in terms of organization and writing. The reviewer does not have major comments, the only concern is that the content seems not technical enough to be journal quality.