A Systematic Literature Review of Cutting Tool Wear Monitoring in Turning by Using Artificial Intelligence Techniques

Round 1

Reviewer 1 Report

The submitted article contains valuable information on cutting tool wear in turning processes. 
The presented article is a review article, which contains a great amount of information on tool wear testing and the possibility of detecting the process of catastrophic wear. 
In the reviewer's opinion the article is described systematically. 
I would suggest changing the title from tool health to tool wear.
Why table 3 is at the end of the text. I suggest placing the table in the text and not as an attachment.

Author Response

Please see the attachment

Author Response File: Author Response.pdf

Reviewer 2 Report

The review deals with A systematic literature review of artificial intelligence techniques applied to cutting tool health monitoring in stable turning operations. 
According to the reviewer, the paper is not worth publishing at Machines Journal, 
but some corrections are needed and then the paper can be accepted for publication in the journal.
While the authors have made considerable research effort, 
the presentation of the paper and the results (comparison of the six methods) must be proved. 
Additionally make the following corrections to the manuscript:

Comment 1
Line 5
on artificial intelligence (AI) techniques
replace
on Artificial Intelligence (AI) techniques

Comment 2
Lines 8 - 9 
a systematic literature
review (SLR) methodology. This
replace
a Systematic Literature
Review (SLR) methodology. This

Comment 3
Lines 17 - 19
literature: artificial neural network (ANN),
fuzzy logic, support vector machine (SVM), self-organizing map (SOM), hidden Markov model
(HMM) and convolutional neural network (CNN). For 
replace
literature: Artificial Neural Network (ANN),
fuzzy logic, Support Vector Machine (SVM), Self-Organizing Map (SOM), Hidden Markov Model
(HMM) and Convolutional Neural Network (CNN). For 

Comment 4
Line 76
techniques in section 2. Then, in section 3, the standardized
replace
techniques in Section 2. Then, in Section 3, the standardized

Line 79
In section 4, a first bibliometric
replace
In Section 4, a first bibliometric

Line 80
proposed in section 5. The results are discussed in section
replace
proposed in Section 5. The results are discussed in Section

Line 81
in section 7. Finally,
replace
in Section 7. Finally,

Line 83
are identified in section 8.
replace
are identified in Section 8.

Comment 5
Line 91
of this articles (section
replace
of this articles (Section

Line 107
phrases (figure 1):
replace
phrases (Figure 1):

Line 120
presented in figure 2, and
replace
presented in Figure 2, and

Line 122
flank face (figure 2).
replace
flank face (Figure 2).

Comment 6
Figure 1
The text inside the Figure 
Initial wear
Steady-state wear
Accelerated wear

must be above the arroys.

Comment 7
The authors must increase the visibility of the Figure 2.

Comment 8
Line 155
comparison purposes, we have structured the
It is not so good to use the word "we". 
The authors must rephrase.

Comment 9
Line 176
section 5.
replace
Section 5.

Line 178
systematic literature review (SLR)
replace
Systematic Literature Review (SLR)

Line 199
of section 3.
replace
of Section 3.

Line 210
described in section 2.2.
replace
described in Section 2.2.

Comment 10
Line 199
According to the journal's instructions: 
Figures should be placed in the main text near to the first time they are cited. 
The authors must format (Figure 3) the review according to the Instructions for Authors.

Comment 11
Line 208
turning condition ?
replace (delete a space)
turning condition?

Comment 12
Line 220
in this context ?
replace (delete a space)
in this context?

Line 227
answered in section 7.
replace
answered in Section 7.

Line 243
are listed in table
replace
are listed in Table

Comment 13
Major Problem
Page 7 Table 1 
Page 13 Table 1

Two Tables 1
This is confusing for the readers.
The authors must renumber.

Comment 14
Line 250
For the "tool part" in table 1,
replace
For the "tool part" in Table 1,

Comment 15
Page 7
For all Tables
The authors must format the Table's title according to the journal's instructions

Table 1. This is a table. Tables should be placed in the main text near to the first time they are cited.

Table 1: List of keywords
replace
Table 1. List of keywords

Comment 16
Line 296
processes (figure 3).
replace
processes (Figure 3).

Line 309
about turning (figure 3).
replace
about turning (Figure 3).

Line 326
articles rejected (figure 3).
replace
articles rejected (Figure 3).

Line 329
in the SLR (figure 3).
replace
in the SLR (Figure 3).

Line 330
analysis (section 4).
replace
analysis (Section 4).

Line 334
techniques used (section 5). A
replace
techniques used (Section 5). A

Line 335
form of tables 3
replace
form of Tables 3

Line 351
presented in figure 4. It
replace
presented in Figure 4. It

Line 355
4.0. From figure 4,
replace
4.0. From Figure 4,

Lines 365 - 370
1. Artificial Neural Network (ANN) (section 9.1).
2. Fuzzy approach (FIS and ANFIS models) (section 9.2). 
3. Support Vector Machine (SVM) (section 9.3). 
4. Self Organizing Map (SOM) (section 9.4). 
5. Hidden Markov Model (HMM) (section 9.5). 
6. Convolutional Neural Network (CNN) (section 9.6).

replace
1. Artificial Neural Network (ANN) (Section 9.1).
2. Fuzzy approach (FIS and ANFIS models) (Section 9.2). 
3. Support Vector Machine (SVM) (Section 9.3). 
4. Self Organizing Map (SOM) (Section 9.4). 
5. Hidden Markov Model (HMM) (Section 9.5). 
6. Convolutional Neural Network (CNN) (Section 9.6).

Line 374
analysis in section 5,
replace
analysis in Section 5,

Line 379
is presented in figure
replace
is presented in Figure

Line 385
presented in figure 6.
replace
presented in Figure 6.

Line 387
by year in figure 4.
replace
by year in Figure 4.

Comment 17
Delete the space between the Figure 5 and the Figure 6. 
The authors must insert text

Line 408
is presented in table 1.
replace
is presented in Table 1.

Line 411
type in table 1):
replace
type in Table 1):

Line 423
literature (section 4.1),
replace
literature (Section 4.1),

Page 13
Table 1: Top 3 most cited articles by AI techniques, 3 globally most cited articles in boldface type.
replace
Table 2. Top 3 most cited articles by AI techniques, 3 globally most cited articles in boldface type.

What is the difference between the "No citation" and the "article" (Table 2 Page 13)?

Comment 18
Page 14: No numbering

Journal of intelligent Manufacturing
replace
Journal of Intelligent Manufacturing

presented in figure 7.
replace
presented in Figure 7.

this SLR. We observe that the
It is not so good to use the word "we". 
The authors must rephrase.

Comment 19
Delete the gap in the end of page 14.
Delete the gap in the front and the end of page 15.

Comment 20
Line 433
(tables 3 to 10).
replace
(Tables 3 to 10).

Line 437
(section 5.1 to 5.7).
replace
(Section 5.1 to 5.7).

Line 444
(section 2.2):
replace
(Section 2.2):

Line 482
is discussed in section 6.
replace
is discussed in Section 6.

Line 498
analysis (section 4),
replace
analysis (Section 4),

Line 500
presented in section 9.1, table 3
replace
presented in Section 9.1, Table 3

Line 508
presented in figure 8.
replace
presented in Figure 8.

Line 512
(figure 8). This
replace
(Figure 8). This

Line 520
presented in figure 9.
replace
presented in Figure 9.

Line 522
of the tool : cutting forces
replace (delete a space)
of the tool: cutting forces

Line 528
techniques are : None
replace (delete a space)
techniques are: None

Line 535
presented in section 9.1:
replace
presented in Section 9.1:

Line 538
presented in figure 11.
replace
presented in Figure 11.

Line 540
of VBB" in table 3 and figure 11).
replace
of VBB" in Table 3 and Figure 11).

Comment 21
Delete the gap in the end of page 19.
Delete the gap in the front and the end of page 20.

Comment 22
Line 568
presented in table 4 for the FIS and table 5 for the
replace
presented in Table 4 for the FIS and table 5 for the

Line 577
presented in figure 12.
replace
presented in Figure 12.

Line 579
We observe the
and 
Line 580
We can note that [93] uses the temperature
It is not so good to use the word "we". 
The authors must rephrase.

Line 583
presented in figure 13.
replace
presented in Figure 13.

Line 587
presented in figure 14.
replace
presented in Figure 14.

Line 596
We do not observe criteria
It is not so good to use the word "we". 
The authors must rephrase.

Delete the gap in the front and the end of page 22.

Line 605
As mentioned in section 4.2,
replace
As mentioned in Section 4.2,

Line 607
is provided in table 6.
replace
is provided in Table 6.

Line 609
presented in figure 15.
replace
presented in Figure 15.

Line 615
Indeed as figure 16
replace
Indeed as Figure 16

Line 620
presented in figure 17.
replace
presented in Figure 17.

Line 627
an autoregressive integrated moving average (ARIMA) model
replace
an AutoRegressive Integrated Moving Average (ARIMA) model

Lines 634 - 638
features are used as input of a gravitational search algorithm–least square support vector 
machine model (GSA-LSSVM). In this entry, the authors compare the results obtained 
with this technique with other related methods such as: K-nearest neighbour(k-NN), 
feed forward neural network (FFNN), classification and regression tree (CART) and 
linear discriminant analysis (LDA).

replace
features are used as input of a Gravitational Search Algorithm–Least Square Support Vector 
Machine model (GSA-LSSVM). In this entry, the authors compare the results obtained 
with this technique with other related methods such as: K-Nearest Neighbour(k-NN), 
Feed Forward Neural Network (FFNN), Classification And Regression Tree (CART) and 
Linear Discriminant Analysis (LDA).

Delete the gap in the end of page 24.

Line 654
presented in table 7.
replace
presented in Table 7.

Line 656
presented in figure 18.
replace
presented in Figure 18.

Line 661
presented in figure 19.
replace
presented in Figure 19.

Line 663
As presented in section 9.4,
replace
As presented in Section 9.4,

Line 668
observed in figure 20.
replace
observed in figure 20.

Delete the gap in the end of page 25.
Delete the gap in the front and the end of page 26.

Line 686
presented in table 8.
replace
presented in Table 8.

Line 718
presented in table 9.
replace
presented in Table 9.

Line 719
techniques (see section 4.2).
replace
techniques (see Section 4.2).

Delete the gap in the end of page 28.

Line 761
presented in the table 10.
replace
presented in the Table 10.

Line 766
section 6. However, it is possible to summarize the in depth analysis in the form of table
replace
Section 6. However, it is possible to summarize the in depth analysis in the form of Table

Line 771
by year (section 4.1),
replace
by year (Section 4.1),

Delete the gap in the end of page 29.

Comment 22
Table 2: General comparison of the different approaches
The authors must renumber and format according to the journal's instructions

Table 2. General comparison of the different approaches

For ANN
Nb of articles 44
The authors must explain how the sum for Estimation of VBB (34) and Classification (7) is 41 (= 34+7) less than 44.

Line 828
approaches than others. We
It is not so good to use the word "we". 
The authors must rephrase.

Line 832
performed in section 4.5:
replace
performed in Section 4.5:

Line 845
in the section
replace
in the Section

Line 852
and RQ2 to RQ 5.
replace
and RQ2 to RQ5.

Line 856
discussed in section 6,
replace
discussed in Section 6,

Line 862
In section 5 of this SLR,
replace
In Section 5 of this SLR,

Line 864
it appears in section 4.2
replace
it appears in Section 4.2

Line 883
discussed in section 6,
replace
discussed in Section 6,

Line 892
in figure 22.
replace
in Figure 22.

Line 901
in section
replace
in Section

Line 911
interest (section 3). The review
replace
interest (Section 3). The review

Line 918
approach (section 3.2.2).
replace
approach (Section 3.2.2).

Line 924
raters (section 3.3).

raters (Section 3.3).

Lines 927 - 931
The bibliometric analysis of the 102 articles was performed in section 4 and shows 
the trends in the literature over the last 20 years. Several aspects were discussed including 
the distribution of the number of articles per year (section 4.1), the number of articles 
citations (section 4.3), the identification of reference journals (section 4.4) and a discussion 
on the authors (section 4.5). Some general conclusions can be drawn:

replace

The bibliometric analysis of the 102 articles was performed in Section 4 and shows 
the trends in the literature over the last 20 years. Several aspects were discussed including 
the distribution of the number of articles per year (Section 4.1), the number of articles 
citations (Section 4.3), the identification of reference journals (section 4.4) and a discussion 
on the authors (Section 4.5). Some general conclusions can be drawn:

Line 934
domain (section 4.1).
replace
domain (Section 4.1).

Line 936
articles (section 4.2).
replace
articles (Section 4.2).

Line 941
form of tables 3 to 10.
replace
form of Tables 3 to 10.

Line 942
performed in section 5.
replace
performed in Section 5.

Comment 23
Table 3: General summary of ANN-related publications
replace
Table 3. General summary of ANN-related publications

Table 4: General summary of fuzzy logic related publications
replace
Table 4. General summary of fuzzy logic related publications

Table 5: General summary of neuro-fuzzy related publications
replace
Table 5. General summary of neuro-fuzzy related publications

Table 6: General summary of SVM-related publications
replace
Table 6. General summary of SVM-related publications

Page 126
Two times the:
[129] SVM

Table 7: General summary of SOM-related publications
replace
Table 7. General summary of SOM-related publications

Table 8: General summary of HMM-related publications
replace
Table 8. General summary of HMM-related publications

Table 9: General summary of CNN-related publications
replace
Table 9. General summary of CNN-related publications

Line 975
output layer (figure 24) [143].
replace
output layer (Figure 24) [143].

Line 992
defuzzification interface [145] (figure 25).
replace
defuzzification interface [145] (Figure 25).

Figure 25
Fuzzication
The authors must check the paper for spelling and typographical errors.

Delete the gap in the end of page 47.

Line 1012
(figure 26).
replace
(Figure 26).

Delete the gap in the end of page 48.
Delete the gap in the end of page 49.
Delete the gap in the end of page 50.

Line 1021
map (figure 27).
replace
map (Figure 27).

Line 1047
(figure 28).
replace
(Figure 28).

Figure 28
pooling Layer replace Pooling Layer
Convolutional layer replace Convolutional Layer

Comment 24
References
22. Oxford dictionnary.
112. Cambridge dictionnary.
The authors must check the paper for spelling and typographical errors.
The authors must give more details.

Something (data) missing:
23, 28, 52, 78, 79, 109, 110, 111

The authors must format the References: 26 and 150 (text out of limits) 

Comment 25
The authors must compare the results of artificial intelligence techniques
applied to cutting tool health monitoring in stable turning operations:
Artificial Neural Network (ANN),
Fuzzy Logic, 
Support Vector Machine (SVM), 
Self-Organizing Map (SOM), 
Ηidden Markov Μodel (HMM) 
and Convolutional Neural Network (CNN).

Author Response

Please see the attachment

Author Response File: Author Response.pdf

Reviewer 3 Report

Abstract:

The abstract summarizes clearly the purpose of the paper and designates the time frame of the review. This review is actual and the chosen selection method (SLR) is adequate for the purpose of the paper. The deeply analyzed AI methods are designated and they can be considered as the most frequent ones.

Introduction:

The past and present of cutting tool wear tendencies are approached briefly in this section. The cited works strengthen the need for the present review. A comprehensive review was published about 20 years ago, whish is exactly referred to in this paper. The repetition of a similarly deep review is needed now. In the last paragraph of the section the structure of the paper is introduced clearly. This helps the reader to follow and understand the logic of this relatively long article.

Background of turning process and AI:

In the first subsection the wear characteristics is introduced for single-point turning tools. The wear type which will be focused on in the work is defined properly.

The artificial intelligence and ML are defined clearly.

Recommended corrections:

• In figure 2 the time axis should be logarithmic (lgT [s]) because it reflects the real wear process more realistic.
• It should be mentioned here (not only in the discussion section) in explaining the end-of-life criterion that, although the referred standard designates, this criterion could vary depending on the actual machining purpose.

Review protocol:

The framework of the SLR is clear, its parts are detailed in a well-understandable manner. The process is considered as reproducible based on the information provided in this section. The quality of the method-description is increased because of the calculation of the inter-rater reliability. The scientific value of this kappa statistics should be increased a little more (see below in the recommendations part). The narrowing of papers is adequate, each step is described well and the result (102 paper applicable) can be considered reliable in this topic.

Recommended correction:

• The obtained P0 value and the Pe value should be provided.

Biometrics analysis:

The section is basically good. Some modifications are although recommended.

Recommended corrections:

• The method of citation analysis should be provided. Were the citations counted based only on the Scopus information?
• In Table 1 there are works cited 0-times. The reason of including them in the table should be explained, because the table is about the ‘most cited” works.

In-depth analysis and discussion:

The section is clear and logic. There can found no missing information the summarizing table at the end of the section increases the quality of the analysis. The discussion part is relatively short (supports the understanding) and well-structured. It includes critical statements, which increases the value of the paper.

Conclusion:

The conclusions are grouped (biometrical analysis, in-depth analysis. etc.), due to which the value of the paper is high. The statements are exact, and all pieces of information are founded by the analysis and discussion parts.

Overall notes:

The appendix includes summarizations about the analyzed AI methods. This supports the work and increase the quality. The summarization of the analyzed papers is useful, it helps the reproducibility of the study and provide additional information for the readers when looking for specific information.

Concerning the format of the paper, the next modification is recommended:

• Font type in the figures 1, 4-6, 8-28 should be the same as in the text. The font sizes should also be unified.

Author Response

Please see attachment 

Author Response File: Author Response.pdf

Round 2

Reviewer 2 Report

The authors must format the paper according to the journal's instructions.

Supplementary Materials: The following are available online at www.mdpi.com/xxx/s1, Figure S1: title, Table S1: title, Video S1: title.

Author Contributions: For research articles with several authors, a short paragraph specifying their individual contributions must be provided. The following statements should be used “Conceptualization, X.X. and Y.Y.; methodology, X.X.; software, X.X.; validation, X.X., Y.Y. and Z.Z.; formal analysis, X.X.; investigation, X.X.; resources, X.X.; data curation, X.X.; writing—original draft preparation, X.X.; writing—review and editing, X.X.; visualization, X.X.; supervision, X.X.; project administration, X.X.; funding acquisition, Y.Y. All authors have read and agreed to the published version of the manuscript.” Please turn to the CRediT taxonomy for the term explanation. Authorship must be limited to those who have contributed substantially to the work reported.

Funding: Please add: “This research received no external funding” or “This research was funded by NAME OF FUNDER, grant number XXX” and “The APC was funded by XXX”. Check carefully that the details given are accurate and use the standard spelling of funding agency names at https://search.crossref.org/funding. Any errors may affect your future funding.

Data Availability Statement: In this section, please provide details regarding where data supporting reported results can be found, including links to publicly archived datasets analyzed or generated during the study. Please refer to suggested Data Availability Statements in section “MDPI Research Data Policies” at https://www.mdpi.com/ethics. You might choose to exclude this statement if the study did not report any data.

Acknowledgments: In this section, you can acknowledge any support given which is not covered by the author contribution or funding sections. This may include administrative and technical support, or donations in kind (e.g., materials used for experiments).

Conflicts of Interest: Declare conflicts of interest or state “The authors declare no conflict of interest.” Authors must identify and declare any personal circumstances or interest that may be perceived as inappropriately influencing the representation or interpretation of reported research results. Any role of the funders in the design of the study; in the collection, analyses or interpretation of data; in the writing of the manuscript, or in the decision to publish the results must be declared in this section. If there is no role, please state “The funders had no role in the design of the study; in the collection, analyses, or interpretation of data; in the writing of the manuscript, or in the decision to publish the results”.