Intelligent Diagnosis Method of Data Center Precision Air Conditioning Fault Based on Knowledge Graph

Round 1

Reviewer 1 Report

Dear authors. The paper is very interesting because it catalogs the faults that occur in a precision air conditioning system. I recommend that Figures 8 and 9 be expanded: 9 horizontally, and with a page dedicated to both figures. Most importantly: the paper must include success and failure rates of the proposed deep learning strategy and be compared with case-based reasoning. The proposed deep learning strategy must be supported by a better analysis of the references used in the text. In the conclusions section, a detailed and quantitative analysis of the successes, failures, false positives and false results must be presented.Thank you

Author Response

Dear authors. The paper is very interesting because it catalogs the faults that occur in a precision air conditioning system. I recommend that Figures 8 and 9 be expanded: 9 horizontally, and with a page dedicated to both figures. Most importantly: the paper must include success and failure rates of the proposed deep learning strategy and be compared with case-based reasoning. The proposed deep learning strategy must be supported by a better analysis of the references used in the text. In the conclusions section, a detailed and quantitative analysis of the successes, failures, false positives and false results must be presented.Thank you

Response:Dear Reviewer, Thank you very much for your comments. Figure 8 has been expanded and Figure 9 has been expanded and horizontally extended. The paper has been supplemented with success and failure rates of deep learning strategies and compared with case-based reasoning. In the conclusion section, a detailed and quantitative analysis of successes, failures, false positives and false results has been added.

Reviewer 2 Report

Interesting article on Intelligent Diagnosis Method 

To improve the quality of this manuscript, some suggestions are listed as follows:

(1)The introduction should include relevant important references and related technical achievements.

(2)The manuscript does not indicate the corresponding figure and the table numbers are not easy to read.

(3)There are a lot of data explained in the manuscript, such as 12 million precision air conditioner historical monitoring data. The data type or classification method can be clearly explained, such as temperature and humidity, error signal, signal voltage, air conditioner performance curve, etc.

(4)How to import the Intelligent Diagnosis Method into the 1:1 digital twin of BIM tech (line 317)?

(5)The research results can reduce 70% of manual inspection work (342 lines). But, the results were not shown the comparison between cases and data.

Author Response

Interesting article on Intelligent Diagnosis Method 

To improve the quality of this manuscript, some suggestions are listed as follows:

(1)The introduction should include relevant important references and related technical achievements.

(2)The manuscript does not indicate the corresponding figure and the table numbers are not easy to read.

(3)There are a lot of data explained in the manuscript, such as 12 million precision air conditioner historical monitoring data. The data type or classification method can be clearly explained, such as temperature and humidity, error signal, signal voltage, air conditioner performance curve, etc.

(4)How to import the Intelligent Diagnosis Method into the 1:1 digital twin of BIM tech (line 317)?

(5)The research results can reduce 70% of manual inspection work (342 lines). But, the results were not shown the comparison between cases and data.

Response:Dear Reviewer, Thank you very much for your comments. We would like to respond to your comments as follows.

(1) The introduction have been supplemented with relevant important references and relevant technical results.

(2) The manuscript has been re-labeled with the corresponding figure and table numbers to make it easier to read.

(3) The manuscript has been supplemented with some data types of historical testing data.

(4) The manuscript has been supplemented with the steps for importing intelligent diagnostic methods into the 1:1 digital twin of BIM technology.

(5) The manuscript has been revised to describe another perspective.

Reviewer 3 Report

Dear author

In this paper, through the method of manual experience summary, historical operation and maintenance data structuring and analysis, we will build a knowledge map and fault diagnosis process, invoke real-time measurement point data of precision air conditioners, realize intelligent fault diagnosis, reason out the causes of fault formation and the scope of impact, and display them in 3D to achieve rapid elimination of safety hazards. The innovation of this method is good and has certain practical value. However, in the writing of the paper, the following improvements are needed:

1.In the Knowledge Reasoning section of the text, there are 182 lines, and the variable  writing format is not standardized;

2.The specific meaning of parameter  in line 193 of the text is not explained;

3.In the derivation of the formula from lines 206 to 209 in the text, the  and  parameters do not give detailed meanings;

4. The format of the reference needs to be revised 

Author Response

 

1.In the Knowledge Reasoning section of the text, there are 182 lines, and the variable  writing format is not standardized;

2.The specific meaning of parameter  in line 193 of the text is not explained;

3.In the derivation of the formula from lines 206 to 209 in the text, the  and  parameters do not give detailed meanings;

4. The format of the reference needs to be revised 

Response: Dear Reviewer, Thank you very much for your comments. We would like to respond to your comments as follows.

1, The problem of irregular format of writing variables in the knowledge inference part has been revised in the manuscript.

2, The specific meaning of the parameters has been added in the manuscript.

3, The meanings of the parameters of the derived equations have been given in the manuscript.

4, The format of the references has been revised in the manuscript.

Round 2

Reviewer 1 Report

changes adressed. paper has been improved

Reviewer 2 Report

Thank authors. The authors have responded to some comments. 

Reviewer 3 Report

In this paper, through the method of manual experience summary, historical operation and maintenance data structuring and analysis, we will build a knowledge map and fault diagnosis process, invoke real-time measurement point data of precision air conditioners, realize intelligent fault diagnosis, reason out the causes of fault formation and the scope of impact, and display them in 3D to achieve rapid elimination of safety hazards. The innovation of this method is good and has certain practical value.