ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE

Let me talk about my year and a half of experience.

Submitted on October 7, 2021.
Major revision on December 20, 2021, with three reviewers and 29 comments.
Revised on January 15, 2022.
Minor revision on March 1, 2022, with only one reviewer left, and no additional reviewers were added after submission.
Revised on March 6, 2022.
Reminder sent on June 7, 2022, with a template response.
Reminder sent on July 7, 2022, with a template response.
Reminder sent on August 7, 2022, with a template response.
Reminder sent on September 7, 2022, with a template response.
Reminder sent on October 7, 2022, with a template response.
Reminder sent on November 7, 2022, with a template response.
Reminder sent on December 7, 2022, stating to send emails to the handling editor and the editor-in-chief simultaneously.
Minor revision on December 13, 2022, explaining originality and checking references.
Accepted on January 19, 2023, explaining originality and checking references.
Based on the approximately 16-month submission period for this journal, some classmates in the same laboratory were accepted within 4 months, while others, like me, experienced significant delays. The speed of manuscript handling varies greatly depending on different editors. Generally, articles that undergo multiple changes with the editor are processed faster, while those with a consistent editor tend to be slower. In cases where the processing is slow, urging the system is ineffective, and only sending emails to the editor-in-chief or associate editor will be effective. I wish you all a happy new year and early publication of your papers!

Vomiting, the journal is a good journal, and the speed is fast, but some individual reviewers are really trash, directly negating the research direction! The reviewer's comments have no relevance to the content of the paper!

1) There is no clear explanation of the reasons for using deep learning methods to solve the research problem.

2) Undoubtedly, machine learning methods can provide enhanced accuracy on existing experimental data. However, besides the correlation between input and output parameters, machine learning methods cannot address any issues regarding the blasting effect. For engineers, making pure numerical estimates of the segmentation of blasting pile images without a clear understanding of the underlying mechanisms is dangerous.

3) In many cases, the fundamental purpose of designing equations is to ensure the safety of blasting while considering the economy of the project. The use of machine learning methods should focus on reducing safety factors to make the design more economical, rather than solely focusing on numerical accuracy.

4) At the current state, the English proficiency of the entire manuscript does not meet the journal's requirements.

5) More importantly, the reviewers believe that the results of this paper have little significance for practical engineering applications.