Study on Evaluation and Prediction for Shale Gas PDC Bit in Luzhou Block Sichuan Based on BP Neural Network and Bit Structure

Round 1

Reviewer 1 Report

Comments and Suggestions for Authors

This work presents a reverse modeling method for determining the structural characteristics of drill bits used in shale gas drilling operations. It also proposes a model based on neural networks as a tool for predicting drilling performance based on some characteristics of the drill bits. The work is interesting, and it has potential applications in the field of drilling, mainly in the analysis of tool performance.

The main drawback of this work is its inappropriate structure. I recommend that the authors rearrange the manuscript content into definite sections: Introduction, Theoretical Background, Materials and Methods, Results and Discussions, and Conclusions. In this sense, the significance of this research could be more evident.

 

Some recommendations are:

Although it could be obvious, please always specify acronyms and abbreviations. For example, the meaning of “PDC bits” and “BP neural network” is not declared in the abstract. Also, I recommend improving the title because it is not clear the relationship between the selection of bits, the structural characteristics (of what?), and the neural networks.

Could the authors please clarify the meaning of the term 'footage' as used in this paper? It appears frequently, but its specific application is unclear. In my understanding, 'drilling footage' typically refers to the measure of how much is drilled, often by a time unit (ROP). However, I’m uncertain if this definition applies to the term 'PDC bit footage' in this context.

In the Introduction, please specify what the WOB index represents.

In the Introduction, it is very reiterative that the drilling is a complex operation. The complexity of an operation or process is relative if adequate tools and methods are used.

The code in Appendix B must be explained in the text, and a Pseudocode representation should be used as a general expression of its functions and variables.

The code in Appendix C must be explained in the text, and a Pseudocode representation should be used as a general expression of its functions and variables.

I recommend including the function loss to evaluate the neural network training performance. Moreover, given the small number of samples, more information is required to understand how the neural network was trained and how the authors can be sure it was not overfitted.

On page 7, the authors explain the relevance of training accuracy, but insufficient details are given to understand how good this accuracy is.

 

Other minor comments are:

The English writing must be revised and improved thoroughly.

Improve the quality and resolution of Figure 4.

All figures utilize tiny text. Please use a more legible font size.

On page 7, line 202. Revise writing.

On page 7, line 216. Revise writing.

Almost all figures in Appendix A are illegible. Please improve.

Comments on the Quality of English Language

The English writing must be revised and improved thoroughly.

Author Response

Please see the attachment

Author Response File: Author Response.docx

Reviewer 2 Report

Comments and Suggestions for Authors

Please find my comments in the attachment

Comments for author File: Comments.docx

Comments on the Quality of English Language

Minor revision is recommended

Author Response

Please see the attachment

Author Response File: Author Response.docx

Round 2

Reviewer 1 Report

Comments and Suggestions for Authors

The authors have not correctly addressed all my observations. Please see attached file.

 

@font-face {font-family:"Cambria Math"; panose-1:2 4 5 3 5 4 6 3 2 4; mso-font-charset:0; mso-generic-font-family:roman; mso-font-pitch:variable; mso-font-signature:-536869121 1107305727 33554432 0 415 0;}@font-face {font-family:DengXian; panose-1:2 1 6 0 3 1 1 1 1 1; mso-font-alt:等线; mso-font-charset:134; mso-generic-font-family:auto; mso-font-pitch:variable; mso-font-signature:-1610612033 953122042 22 0 262159 0;}@font-face {font-family:"\@DengXian"; panose-1:2 1 6 0 3 1 1 1 1 1; mso-font-charset:134; mso-generic-font-family:auto; mso-font-pitch:variable; mso-font-signature:-1610612033 953122042 22 0 262159 0;}p.MsoNormal, li.MsoNormal, div.MsoNormal {mso-style-unhide:no; mso-style-qformat:yes; mso-style-parent:""; margin:0cm; text-align:justify; text-justify:inter-ideograph; mso-pagination:none; font-size:10.5pt; mso-bidi-font-size:11.0pt; font-family:DengXian; mso-ascii-font-family:DengXian; mso-ascii-theme-font:minor-latin; mso-fareast-font-family:DengXian; mso-fareast-theme-font:minor-fareast; mso-hansi-font-family:DengXian; mso-hansi-theme-font:minor-latin; mso-bidi-font-family:"Times New Roman"; mso-bidi-theme-font:minor-bidi; mso-font-kerning:1.0pt; mso-ansi-language:EN-US; mso-fareast-language:ZH-CN;}.MsoChpDefault {mso-style-type:export-only; mso-default-props:yes; font-size:10.5pt; mso-ansi-font-size:10.5pt; mso-bidi-font-size:11.0pt; mso-ascii-font-family:DengXian; mso-ascii-theme-font:minor-latin; mso-fareast-font-family:DengXian; mso-fareast-theme-font:minor-fareast; mso-hansi-font-family:DengXian; mso-hansi-theme-font:minor-latin; mso-bidi-font-family:"Times New Roman"; mso-bidi-theme-font:minor-bidi; mso-ligatures:none; mso-ansi-language:EN-US; mso-fareast-language:ZH-CN;}div.WordSection1 {page:WordSection1;}

Comments for author File: Comments.docx

Comments on the Quality of English Language

The writing has substantially improved in the revised version.

Author Response

Please see the attachment.

Author Response File: Author Response.docx

Reviewer 2 Report

Comments and Suggestions for Authors

The authors have incorporated all my suggestions. Thank you for the additional clarification.

Author Response

Dear reviewer, hello. Based on your professional suggestions, the manuscript has greatly improved. Thank you again for your hard work in reviewing the manuscript.

Round 3

Reviewer 1 Report

Comments and Suggestions for Authors

The authors have addressed all my concerns.