In-Process Tool Condition Forecasting of Drilling CFRP/Ti Stacks Based on ResNet and LSTM Network
Round 1
Reviewer 1 Report
The authors monitored and forecasted tool wear of drilling CFRP/Ti stack susing LSTM network. Using the cutting spindle power and vibration signals preprocessed by the proposed method, the LSTM network with ResNet based model integrated can forecast tool wear values of the next drilling holes. A case study demonstrated the effectiveness of TCF, where the results using raw measured signals and preprocessed datasets are tested for comparison. The mean absolute error (MAE) using raw signals are 45.01μm, which is 2.20 times than that using preprocess signals. With proposed method, the data preprocessing for drilling CFRP/Ti stacks can improve the tool wear forecasting accuracy to MAE 20.43μm level, which meets the demand for online TCF.
The paper will be ready for publication after major revision based on the attached pdf file.
Comments for author File: Comments.pdf
Author Response
Please see the attachment.
Author Response File: Author Response.docx
Reviewer 2 Report
Notes in the attachment.
Comments for author File: Comments.pdf
Author Response
Please see the attachment.
Author Response File: Author Response.docx
Reviewer 3 Report
Please find attached 2 files attached. The first one has my comments for improvement as well as some language correction suggestions. Please incorporate the suggested changes and improve the paper where I made comments.
The second one for similarity check result. Please note that similarity should be less than 10%
Comments for author File: Comments.zip
Author Response
Please see the attachment.
Author Response File: Author Response.docx
Reviewer 4 Report
The manuscript is aimed to monitor and forecast tool wear of drilling CFRP/Ti stacks, and then explored an in-process TCF 14 method based on residual neural network (ResNet) and LSTM network. I recommend the publication of this manuscript with the following minor questions and suggestions:
1) There are several minor grammar errors such as the tense and singular &plural errors. For example, on page 3 line 112 signals were... Please do a grammar check.
2) What is the advantage of using moving average root mean square to remove noise? Is that possible to use Fast Fourier Transform (FFT) to handle this? Please provide more details about this since this is the fundamental part of this research.
3) It would be better if the authors could provide more theoretical descriptions of the experimental results. For example, why the TCM errors become large when the hole number is large?
Author Response
Please see the attachment.
Author Response File: Author Response.docx
Round 2
Reviewer 1 Report
Accept.
Reviewer 2 Report
The authors responded to my comments.