Data-Quality Assessment for Digital Twins Targeting Multi-Component Degradation in Industrial Internet of Things (IIoT)-Enabled Smart Infrastructure Systems

Round 1

Reviewer 1 Report

Comments and Suggestions for Authors

The authors provided experimental data of the water distribution system for healthy condition (HC), Single Component Degradation (SCD) and Multi-Component Degradation (MCD) scenarios, further assessing data quality, and finally data-driven methods were tested to enhance fault detection and isolation (FDI) in multi-component degradation scenarios within smart infrastructure systems. However, the reviewer has a few concerns before the paper can be considered for publication.

 1. Introduction part, what is the current research state of this topic? Please review relevant studies, containing domestic and international publications.

 2. Page 3, did the water distribution system testbed produce all experiment data? In the process of data capture, are the following cases considered or executed? Could you provide more details about the system's operation?

v Two or more fault types occur simultaneously

v The sequence of faults

v Permutation and combination of five fault types

 3. In the multi-component degradation (mcd) scenarios, what is the distribution of experiment data? How many experimental samples are generated? How many fault combinations are produced in this scenario? How many samples are there for each fault combination? I would suggest the authors to provide more details about experiment data.

 4. Line 239, the authors claimed that “equation (7) is used to calculate the upper and lower bounds for pressure and flow measurements”. How is equation 7 calculated? What do the symbols σ and μ mean? The meanings of symbols in all formulas should be provided.

 5. Several data-driven approaches are employed in this study. Please provide model parameters, especially for the best classifier.

 6. Detailed result analysis needs to be provided in each experimental scenario. Elaborate on the meaning indicated by figures and tables, for example, Figure 6, Figure 7 and Table 2.

Comments on the Quality of English Language

The quality of English language is fine.

Author Response

Thank you very much for your feedback on our paper ‘Data Quality Assessment for Digital Twins targeting Multi-Component Degradation in Industrial Internet of Things (IIoT) enabled Smart Infrastructure Systems’. Kindly find our responses to the issues you raised in the table in the attached document and also in the revised manuscript

Author Response File: Author Response.pdf

Reviewer 2 Report

Comments and Suggestions for Authors

See the attached file.

Comments for author File: Comments.pdf

Comments on the Quality of English Language

Check the grammatical and typographical errors.

Author Response

Thank you very much for your feedback on our paper ‘Data Quality Assessment for Digital Twins targeting Multi-Component Degradation in Industrial Internet of Things (IIoT) enabled Smart Infrastructure Systems’. Kindly find our responses to the issues you raised in the table in the attached document and also in the revised manuscript

Author Response File: Author Response.pdf

Reviewer 3 Report

Comments and Suggestions for Authors

This paper focuses on data quality assessment for digital twins targeting multi-component degradation in IIOT enabled smart infrastructure systems. In general, this paper sounds interesting and my comments are listed as follows:

A. Introduction Section

1. In the introduction section of the paper, we usually want to see some of your own work, which can be placed in the closing paragraph.

2. It is suggested that machine learning based model prediction control method in manufacturing systems can be added in the literature review part, e.g., Machine Learning-Based Model Predictive Control for Collaborative Production Planning Problem with Unknown Information, Electronics 10 (15), 1818

 

B. Methodology Section

1. In the section of Methodology, we usually focus on the main methods used in the paper and the proof and analysis of such methods, but the introduction of experiments is inappropriate at the beginning of this chapter. The experimental section is better described later than in the Methodology section.

2. In Table 1, you give the health status, working status and related fault codes of the system control valve, but you do not give the technical manual of the device to supplement the details and support the credibility of the contents of this table.

3. Normally in Methodology we want to see rigorous mathematical reasoning to prove that your method has a satisfactory effect on the subject, rather than a lot of statements to describe your method.

4. In the section of Gage R&R Analysis, it is suggested to display the data collected under fault conditions at different pump speeds in a visual way, so that readers can see the effect more directly.

5. The size of Table 3 is a little out of proportion compared with the text and other diagrams and tables. Meanwhile, the layout of formulas and diagrams in this paper is not very standardized. I hope to improve the layout of the article and increase the reading experience of readers.

6. It is hoped that the description of the network structure can be expressed through the intuitive connection diagram between different functional layers.

 

C. Results & A potential IIoT instantiation section

1. The control algorithms listed in this chapter should enrich their evaluation indicators, make a horizontal index comparison table between the algorithm introduced in this paper and the control algorithm, and even show the advantages and disadvantages of these algorithms more directly through the performance indicator graph for further analysis.

2. The neural network appeared in the control group, and you can appropriately introduce some of the structure and layer number of the neural network you choose

Comments on the Quality of English Language

Minor editing of English language is required.

Author Response

Thank you very much for your feedback on our paper ‘Data Quality Assessment for Digital Twins targeting Multi-Component Degradation in Industrial Internet of Things (IIoT) enabled Smart Infrastructure Systems’. Kindly find our responses to the issues you raised in the table in the attached document and also in the revised manuscript

Author Response File: Author Response.pdf

Reviewer 4 Report

Comments and Suggestions for Authors

1- The results should be discussed in conclusion.

2- How the developed system in the study can be applied to the other Water Distribution System. It should be explained.

3- How the developed system can be expanded in order to enhance efficiency in Water Distribution Systems.

Comments on the Quality of English Language

the English level should be improved.

Author Response

Thank you very much for your feedback on our paper ‘Data Quality Assessment for Digital Twins targeting Multi-Component Degradation in Industrial Internet of Things (IIoT) enabled Smart Infrastructure Systems’. Kindly find our responses to the issues you raised in the table in the attached document and also in the revised manuscript

Author Response File: Author Response.pdf

Round 2

Reviewer 1 Report

Comments and Suggestions for Authors

The authors have improve the manuscript.

Comments on the Quality of English Language

The quality of English Language is acceptable.

Reviewer 3 Report

Comments and Suggestions for Authors

The authors have addressed all my comments.

Comments on the Quality of English Language

Minor editing of English language is required.

Reviewer 4 Report

Comments and Suggestions for Authors

The paper can be accepted.