Data Mining Technology and Its Applications in Coal and Gas Outburst Prediction
Baiquan Lin
Round 1
Reviewer 1 Report
This paper is very well written, the statistical process control (SPC) method were used to assess and develop the critical value of outburst risk for single indicators, and logistic regression analyses was performed to explore the interrelation of the outburst warning with, and the prediction equation of the outburst risk was obtained on this basis. Finally, the SPC and logistic regression analysis methods were used for typical mines. The results showed that the SPC method accurately determined the sensitivity value of a single index for each borehole depth, and the accuracy of the logistic regression method was 94.7%. These methods are therefore useful for the timely detection of prominent hazards during the mining process.
There are some problems, which must be solved before it is considered for publication, if the following problems are well-addressed, this reviewer believes that the essential contribution of this paper are important for coal and gas outburst prediction.
1. In the article, K1 can be changed to K1, special meaning characters should be expressed normatively;
2. Figure 3 to Figure 18 are a bit blurry. Please consider replacing them with clearer ones.
3. Figure 2, Table 1 and Table 3, please pay attention to the content layout in the figure and tables, avoid the unnecessary transposition of a word to create a hyphen;
4. Line169, 191, 296, 299 and 302 should be set flush. Equation 4, 5 and 6 should be followed by a full stop. Please Note the language specification.
Author Response
Please see the attchment.
Author Response File: 
Author Response.pdf
Reviewer 2 Report
The article considers the problem of using data mining methods to predict the release of gas and coal into the atmosphere.
The risk of coal and gas blowouts is one of the main hazards that lead to serious injury and death in coal mines. Accurate prediction of coal and gas release can effectively prevent accidents. At present, most coal and gas blowout hazard prediction methods are single metric based methods that use a single metric such as the amount of cuttings, the gas or cuttings desorption rate, the initial rate of gas emission from the borehole, etc. or an empirical formula is used, obtained by summing these indicators in order to make a forecast. Due to the complex geological levels in coal mines, these indicators cannot comprehensively reflect the risk of coal and gas release; in addition, these indicators cannot provide a true integral forecast. Therefore, they cannot be used to accurately predict the danger of a coal and gas outburst, and coal and gas outburst accidents often occur, the probability of which has been underestimated, and they create a great hindrance to safe mining in coal mines. Based on the relevance and importance of carrying out research in this scientific direction, the results obtained in the work will be useful to specialists in the field under consideration.
However, the work has the following comments:
1. In the introduction, it would be better to dwell in more detail on the various emergency situations that take place in coal mines, in particular, methane emissions and aerological risks, which can be seen from the works:
https://doi.org/10.1016/j.atmosenv.2020.117471
https://doi.org/10.3390/fire6030095
2. The article should provide for the presence of a section "Materials and Methods", in which the materials and methods used should be consistently stated.
3. In section “2.1 Determination of the critical value of sensitive indicators”, the method used, on the basis of which Figure 1 was obtained, should be discussed in more detail. It should be more clear why μ ± 3σ was chosen as the control range.
4. Based on the analysis of what literature sources or operating experience is Table 1 compiled? Was the method of both expert assessments and cluster analysis used in the analysis? Is it possible to numerically study the data presented in Table 1?
5. In section "2.2.3 Establishment of logistic regression model" it was concluded that the probability of an accident is more than 50%. What is this value based on?
6. Figure 2 shows a functional diagram of the system software, but it should be discussed in more detail how exactly coal and gas emissions will be predicted.
7. According to the data presented in Figures 3, 5, 7, 9, 11, 13, 15, 17, specific regression models should be given, on the basis of which it was possible to predict the output values.
8. The conclusions should be expanded by adding the results obtained during the analysis of numerous figures and the given functional diagram of the system software (Figure 2).
9. The conclusions say about the good applied value of the results. It is necessary to dwell in more detail on the plan for further prospective research and approbation of the results obtained.
10. Is it planned to issue a patent for the developed research methodology for mines?
In general, in my opinion, the work can be published in the journal subject to the elimination of comments.
Author Response
Please see the attachment.
Author Response File: Author Response.pdf
Reviewer 3 Report
The manuscript "Data mining technology and its application in coal and gas outburst prediction" by Xianzhong Li, Shigang Hao, Tao Wu, Weilong Zhou and Jinhao Zhang was submitted for review.
I read this manuscript with great interest. The authors addressed a rather relevant topic of mine production safety.
The manuscript has some shortcomings. It needs to be corrected to improve the quality of the manuscript, enhance the comprehension of the material presented, and increase the interest of the reader.
1) If all authors represent one organization (School of Energy Science and Engineering), it is not necessary to indicate all authors with number 1.
It is necessary to correct.
2) From my point of view, very few keywords. In addition, keywords should be more direct and related to the content of the manuscript.
Keywords allow the reader to quickly search for the necessary material, and the author the opportunity to popularize his research, as well as to increase interest and citations.
But if this number of keywords satisfies the requirement of the journal, this observation is advisory.
3) Section Materials and Methods 2.1. Did the authors forget to delete this paragraph? Why is it in the text?
"The Materials and Methods should be described with sufficient detail to allow others to replicate and build on the published results. Please note that the publication of your manuscript implicates that you must make all materials, data, computer code, and protocols associated with the publication available to readers. Please disclose at the submission stage any restrictions on the availability of materials or information. New methods and protocols should be described in detail while well-established methods can be briefly described and appropriately cited.........".
Should be corrected.
4) It is not clear why Sihe Mine in Jincheng City was chosen for the study. What are the mining and geological conditions, the angles of occurrence, etc...?
5) It is not clear how the authors built the database architecture. What data were obtained. What queries were performed?
Need to be explained.
6) The manuscript has an insufficient list of references (only 21 references). There is no complete coverage of research in terms of geography of citations. Only references to the works of Chinese scientists are presented. There are no references to the world experience in the given field or related fields, especially to the works of Eastern European, Ukrainian or Russian scientists, for example:
- Gabov, V. V., Zadkov, D. A., Babyr, N. V., & Xie, F. (2021). Nonimpact rock pressure regulation with energy recovery into the hydraulic system of the longwall powered support. Eurasian Mining, 36(2), 55-59. doi:10.17580/em.2021.02.12. This paper Examined the advisability of increasing the adaptability of the powered support within advanced high-powered mechanized longwall face complexes to mining-geological conditions that change as the blocks are extracted.
- Gendler, S. G., Gabov, V. V., Babyr, N. V., & Prokhorova, E. A. (2022). Justification of engineering solutions on reduction of occupational traumatism in coal longwalls. Mining Informational and Analytical Bulletin, (1), 5-19. doi:10.25018/0236_1493_2022_1_0_5This study aims to justify engineering solutions in reduction of occupational traumatism in case of roof caving and rock falls in coal longwalls.
As it follows from the submitted papers, the authors of the manuscript submitted for review missed quite a large layer of research.
If the authors of the manuscript submitted for reviewing are acquainted with the submitted works, they can form the introduction properly, enrich their manuscript by international research of scientists from Poland, Czech Republic, Slovenia, Slovakia, Russia and Germany and demonstrate the depth of the material and also they can eliminate the remarks and increase the geography of citing. This is very important.
From my point of view, this study would do well to concretize the statements made by the authors in lines 24-39, which would allow them to increase the geography of citations.
Be sure to supplement the list of references with studies by scientists from different countries in the last 3-5 years to show geographical (general/global) interest and relevance.
7) Conclusion - this is the outcome of the study, carried out by the authors, without repetition. Such a presentation reduces the ease of the reader's perception of the information presented. The error of incorrect formation of conclusions is a consequence of incorrect presentation of the introduction, noted by me in the remark due to the fact that they did not formulate the goals and objectives when writing the introduction.
The conclusions should briefly characterize the result of the study, for example
As a result of the research
(1) the dependence..... was obtained
(2) it was found that......
(3) and so on.
The conclusion needs to be further elaborated.
8) Additional comments:
- Figure 1 -10 and Figure 11-18 need to be combined
Summary: The manuscript is not a complete research paper. Corrections are needed. The chosen research topic is indeed relevant. In my opinion, the authors were not able to present their research clearly and competently, which greatly reduced its value and readability of the material presented.
From my point of view, the manuscript cannot be published in the open press, taking into account the corrections of the shortcomings indicated in my recommendation.
Extensive editing of English language required
Author Response
Please see the attachment.
Author Response File: Author Response.pdf
Reviewer 4 Report
In this study, the researchers utilized statistical process control (SPC) and logistic regression analyses to evaluate and establish the critical value of outburst risk for specific indicators, such as the S value of drill cuttings and the K1 value of the desorption index. They conducted a multivariate information coupling analysis to investigate the interrelation of outburst warning, which led to the development of an equation to predict outburst risk. The SPC and logistic regression analysis methods were then applied to typical mines. The findings demonstrated that the SPC method accurately determined the sensitivity value of each borehole depth for a single indicator, and the logistic regression method achieved an accuracy of 94.7%. These methods can be valuable for promptly identifying significant hazards during the mining process.
Based on my analysis of this manuscript, I find it to be comprehensive and inclusive of all the essential elements. The overall structure is sound and coherent, and the design principle is effectively and sufficiently explained. In order to enhance the quality of this paper, I would like to propose the following recommendations:
1. The manuscript research focuses on the application of the developed system software to the prediction of coal and gas outburst. Therefore, the author also needs to focus on the application of mine and coal seam actual situation, whether it is coal and gas outburst mine and outburst coal seam.
2. Please ensure that the terminology used throughout the article is consistent. For instance, the phrase "single indicator" in line 13 and "single index" in line 18 should be consistently referred to as "single index". Pay attention to the correct usage of singular and plural forms. For instance, the term "indicators" in line 13 should be singular. Similarly, the term "phenomenon" in line 83 should be plural.
3. Is 6402transportation lane Sanhui No. 1 Mine or Sanhui No. 3 Mine? Please explain.
4. All abbreviations should be defined when first mentioned in both the abstract and main text, and consistently used thereafter. For instance, the abbreviation "XGBoost" in line 62 should be written in its full name.
5. Please ensure that the reference format adheres to the journal's formatting requirements.
6. The content within tables should follow a standardized format. For example, the first letter of each entry in the table should be capitalized.
7. Sanhuiyi Mine or Sanhui No. 1 Mine?
Minor editing of English language required.
Author Response
Please see the attachment.
Author Response File: Author Response.pdf
Round 2
Reviewer 2 Report
The authors finalized the article and responded to all my comments. The article can be published in my opinion.
Reviewer 3 Report
The authors have taken into account all recommendations. I believe that the manuscript represents a completed scientific work. From my point of view, the manuscript can be published in the open access.
Minor editing of English language required
