An Effective Tangent Stiffness of Train–Track–Bridge Systems Based on Artificial Neural Network

Round 1

Reviewer 1 Report

Very good manuscript presenting the response of a train-track-bridge system under wheel rail interaction.

Some comments made during reading are the following:

• Please revise the reference of figures and tables, not shown properly in the text of the manuscript.
• In section 3.4 a vehicle body and bogies are modelled using lumped mass points and rigid beams. However, the equations are not shown in an appendix.
• The conclusions should also discuss potential future research that can be done after this manuscript.

Author Response

Dear reviewer：

Thanks a lot for your suggestion, the responses have been submitted  in the attachment.

Best wishes!

Minhong Fu

Author Response File: Author Response.docx

Reviewer 2 Report

In this paper the Authors present a tangent stiffness calculation method based on back propagation neural network for a wheel rail interaction element.

The manuscript is interesting, fits well with the aim of the Special Issue "Design of Track System and Railway Vehicle Dynamics Analysis", and it is opinion of the reviewer that it can be published after the following minor revisions.

(1) The Authors should carefully proofread the manuscript because in the text many references to publications or figures have not been found.
See for example line 81.

(2) To improve reading, in Figures 9, 10, and 11 the BPTS graph could be drawn with red dots, as in the following figures.

According to what said above, the reviewer’s opinion is that the manuscript can be accepted for publication after the described minor revisions.

Author Response

Dear reviewer:

Thanks a lot for your suggestions, the responses have been submitted in the attachment.

Best wishes!

Minhong Fu

Author Response File: Author Response.docx

Reviewer 3 Report

This paper represent Back Propagation Neural Network for computing tangent stiffness rail/wheel interaction. The comparison of the proposed method shows that errors are so tiny which could be a used for other nonlinearities of the train/track interactions. A good effort could be made to implement this method for creep forces to see how accurate this method could be. Results show that for this specific assumption which is running train on straight bridge, neural network could be reliable.

Author Response

Dear reviewer:

Thanks a lot for your suggestions, the responses have been submitted in the attachment.

Best wishes!

Minhong Fu

Author Response File: Author Response.docx

Reviewer 4 Report

This is an interesting and well written paper. However, I have a few important questions with regard to methodology and the results interpretation, as the answers could clarify the paper for potential readers.

1. Why only lateral displacement?
2. What is physical interpretation of the results given in figures 12, 13 and 15?
3. What are initial conditions for moving train (wheels) system?
4. It would be good to see some results related to other dynamic properties of the system, if the method is supposed to be general.
5. What is the influence of nonlinearity, if any, for the investigated model?

Author Response

Dear reviewer:

Thanks a lot for your suggestions, the responses have been submitted in the attachment.

Best wishes!

Minhong Fu

Author Response File: Author Response.docx

Reviewer 5 Report

There are many errors that say: “Error! Reference source not found”. Authors should fix these errors.

Table 1 and Table 2 are not referenced in the text. Authors should check that all figures and tables are referenced in the text.

Many parameters relative to the OpenSees finite element model are missing, i.e.: convergence data, tolerances, analysis type, boundary conditions… Each OpenSees model should be explained more in detail.

The conclusions should be extended. There are just three lines of conclusions (352-354). The rest of this section is a summary of the performed work.

Author Response

Dear reviewer:

Thanks a lot for your suggestions, the responses have been submitted in the attachment.

Best wishes!

Minhong Fu

Author Response File: Author Response.docx

Round 2

Reviewer 5 Report

The authors have adressed the reviewer comments properly.