A Multiple Response Prediction Model for Dissimilar AA-5083 and AA-6061 Friction Stir Welding Using a Combination of AMIS and Machine Learning
, Chakat Chueadee 1,*, Ganokgarn Jirasirilerd 2, Worapot Sirirak 3 and Sarayut Gonwirat 4Round 1
Reviewer 1 Report
The procedure for creating the predictions is explained in detail, but the experimental side is also important. Please add detailed information about the welding and testing setup (tool geometry, temperature measurement method, testing devices etc.).
Author Response
Point 1: The procedure for creating the predictions is explained in detail, but the experimental side is also important. Please add detailed information about the welding and testing setup (tool geometry, temperature measurement method, testing devices etc.).
Response 1: We added information and figures 2–3 that explained the experimental methods and testing in Section 2.1.2.
Author Response File: 
Author Response.pdf
Reviewer 2 Report
1. Overall, the language is also a little uneven and can be improved. Please have the text edited by a native speaker or a professional service.
2. Pay attention to the format. For example, there is no space between of and AA-5083 in the 17th line.
3. The introduction and the conclusion should be brief and concise. For example, the authors repeated “Aluminum alloys are the primary material in many industries used for parts of products such as aviation, aircraft, automotive, railroad, and marine industries…” in 34th line and “wildly used in the automotive, shipbuilding, and aerospace industries are series 5XXX and 6XXX” in the 39th line. “Solid-state welding is used for ..” in 47th line and “Solid-state welding is used…” in the 59th line. They mean the same thing.
4. The plunge depth of the tool should also be the parameter.
5. What do you mean by the type of reinforcing particle? Why it is the category type? The reinforcement of AA5083 and AA6061 are Silicon Carbide and Aluminum Oxide?
6. The model is suitable for different thicknesses of plates?
Author Response
Point 1: Overall, the language is also a little uneven and can be improved. Please have the text edited by a native speaker or a professional service.
Response 1: Adjust by sending to edited English with professional service by mdpi.
Point 2: Pay attention to the format. For example, there is no space between of and AA-5083 in the 17th line.
Response 2: Adjust the format space between of AA-5083.
Point 3: The introduction and the conclusion should be brief and concise. For example, the authors repeated “Aluminum alloys are the primary material in many industries used for parts of products such as aviation, aircraft, automotive, railroad, and marine industries…” in 34th line and “wildly used in the automotive, shipbuilding, and aerospace industries are series 5XXX and 6XXX” in the 39th line. “Solid-state welding is used for ..” in 47th line and “Solid-state welding is used…” in the 59th line. They mean the same thing.
Response 3: We improved the succinct introduction and conclusion so that the number of words in the introduction decreased from 1,235 words to 1,004 words and the conclusion from 544 words to 324 words.
Point 4: The plunge depth of the tool should also be the parameter.
Response 4: The plunge depth of the tool in this research is a constant factor because relevant studies showed that it had very little effect on the response value (UTS, hardness, and heat input). In addition, it was found that the factors that most affected the welding heat generation were the rpm and the welding speed, followed by the size of the tool shoulder.
Point 5: What do you mean by the type of reinforcing particle? Why it is the category type? The reinforcement of AA5083 and AA6061 are Silicon Carbide and Aluminum Oxide?
Response 5: The type of reinforcing particle is a factor in the study of weld seam strength. There are two types of reinforcement particles: silicon carbide and aluminum oxide. The two types of reinforcement particles are determined by a fixed ratio in the filling in welding. Therefore, we defined factors of category type for this study, as shown in Table 4.
Point 6: The model is suitable for different thicknesses of plates?
Response 6: The thickness of plates is an interesting factor, but this model is not suitable for different thicknesses of plates because the thickness of plates is a fixed parameter. The change in thicknesses of plates may affect the tensile strength, hardness, and heat input accordingly.
Author Response File: Author Response.pdf
Reviewer 3 Report
1. Penetration depth is an important parameter, it controls the axial force and frictional heat, could you explain why it was not included in your study?
2. Rewrite line 117 to line 129 into one paragraph.
3. Delete line 130 to line 132.
4. What’s the meaning of the numbers in Table 2.
5. The conclusion is lengthy, please make it more concise.
6. Check for grammar and typing errors throughout the essay, e.g. Line 117, “this research will use to EML and AI for estimation of the UTS”;
Line 120, “; base on EML approach shows not to apply forecasting”;
Line 130, “The section remain consists; “;
Line 145, The UTS and MH properties of two materials show as Table 3”.
Line 146 “The workpiece dimension for the experiment is worksheet plates too wide”
Line 136, change “Section 2” to “This section”
Author Response
Point 1: Penetration depth is an important parameter, it controls the axial force and frictional heat, could you explain why it was not included in your study?
Response 1: Penetration depth is one of the variables that affects friction heat, but also affects weld quality because if the depth is too deep, the weld will be concave, leading to a reduction in strength. In addition, from the literature review, it was found that the factors that most affected the welding heat generation were the rpm and the welding speed, followed by the size of the tool shoulder. The penetration depth showed no difference in the heat generation . Therefore, we defined a factor of constant type for this study.
Point 2: Rewrite line 117 to line 129 into one paragraph.
Response 2: Adjust the paragraph into one paragraph in lines 101 to 112.
Point 3: Delete line 130 to line 132.
Response 3: Adjust by deleting lines 130 to 132.
Point 4: What’s the meaning of the numbers in Table 2.
Response 4: The meaning of the numbers in Table 2 is the training dataset (80%) and the testing dataset (20%).
Adjust the paragraph from line 123 to line 126. "The study dataset used in our experiment consisted of a training dataset (80%) and a testing dataset (20%), divided into two groups: 7PI-V1 and 7PI-V2. For example, 7PI-V1 had 57 datasets, divided into 45 training datasets and 12 testing datasets and this was used to test the performance of the proposed model as shown in Table 2. "
Point 5: The conclusion is lengthy, please make it more concise.
Response 5: We reduced the succinct conclusion from 544 words to 324 words.
Point 6: Check for grammar and typing errors throughout the essay, e.g. Line 117, “this research will use to EML and AI for estimation of the UTS”;
Line 120, “; base on EML approach shows not to apply forecasting”;
Line 130, “The section remain consists; “;
Line 145, The UTS and MH properties of two materials show as Table 3”.
Line 146 “The workpiece dimension for the experiment is worksheet plates too wide”
Line 136, change “Section 2” to “This section”
Response 6: 1) Adjust by checking for grammar by sending to edited English with professional service.
2) Adjust by checking for typing errors in the article.
Author Response File: Author Response.pdf
Round 2
Reviewer 1 Report
no comments
Reviewer 3 Report
The authors have corrected the paper according to my comments.
