Predictive Modeling of Surface Roughness and Cutting Temperature Using Response Surface Methodology and Artificial Neural Network in Hard Turning of AISI 52100 Steel with Minimal Cutting Fluid Application
Abstract
1. Introduction
- To create predictive models for surface roughness and cutting temperature in the hard turning of AISI 52100 steel using the RSM and the ANN.
- To evaluate the performance of the MCFA technique in comparison to dry and MQL environments during hard turning processes.
- To compare both the accuracy and reliability of the RSM and ANN models in predicting surface roughness and cutting temperature with implications for their potential use in sustainable machining practices.
2. Materials and Methods
2.1. Test Specimen and Chemical Composition
2.2. Experimental Setup
2.3. Measurement of Surface Roughness and Cutting Temperature
2.4. ANN Modeling
2.4.1. Data Acquisition
2.4.2. Data Pre-Processing
2.4.3. ANN Architecture Design
- Input Layer: The input layer comprised 3 neurons, which corresponded to cutting speed, feed rate, and depth of cut.
- Hidden Layer: The optimal number of neurons was determined through trial and error, evaluating configurations with 2, 4, 5, 10, 15, and 20 neurons. A hyperbolic tangent sigmoid activation function (tansig) was used.
- Output Layer: A single neuron in the output layer represented the response, employing a purelin linear activation function for precise output estimation.
2.4.4. Network Training
- Training Algorithm: Levenberg–Marquardt (trainlm) due to its fast convergence properties.
- Training function: Tansig, transfer function was applied to incorporate non-linearity, enabling the network to capture intricate patterns effectively.
- Learning function: Learngdm, learning function was used to refine weight adjustments, promoting faster convergence and minimizing fluctuations during training.
- Performance Function: Mean Squared Error (MSE) function was utilized to evaluate model accuracy by calculating the average squared deviation between predicted and actual outcomes.
- Learning Rate: Initially set between 0.01 and 0.1 and fine-tuned based on validation results.
- Epochs: Maximum of 1000 epochs, with early stopping applied if validation error increased for consecutive iterations.
2.4.5. Model Validation and Performance Evaluation
3. Results and Discussion
3.1. Effect of Cutting Parameters on Cutting Temperature
3.2. Effect of Cutting Parameters on Surface Roughness
3.3. Cutting Temperature Prediction by RSM
3.3.1. Quadratic Regression Model for Cutting Temperature
3.3.2. Diagnostic Plots for Cutting Temperature
3.4. Surface Roughness Prediction by RSM
3.4.1. Quadratic Regression Model for Surface Roughness
3.4.2. Diagnostic Plots for Surface Roughness
3.5. Cutting Temperature Prediction by ANN
3.6. Surface Roughness Prediction by ANN
4. Comparative Study
5. Conclusions
Author Contributions
Funding
Data Availability Statement
Conflicts of Interest
Abbreviations and Symbols
AISI | American Iron and Steel Institute |
OHNS | Oil-Hardened Non-Shrinking |
AI | Artificial Intelligence |
ANNs | artificial neural networks |
ANFIS | Adaptive Neuro-Fuzzy Inference Systems |
ANOVA | Analysis of Variance |
CBN | Cubic Boron Nitride tool |
CC | Coated Ceramic |
EDM | Electric Discharge Machining |
GP | genetic programming |
HRC | Hardness Rockwell C (scale for hardness) |
HST | High-Speed Turning |
LM | Levenberg–Marquardt |
MAPE | Mean Absolute Percentage Error |
MRA | Multivariable Regression Analysis |
MCFA | minimal cutting fluid application |
MQL | minimum quantity lubrication |
QR | quadratic regression |
R | Correlation Coefficient Factor |
R2 | coefficient of determination |
RMSE | root mean square error |
RSM | response surface methodology |
VIF | Variance Inflation Factor |
Seq SS | Sequential Sum of Squares |
Adj MS | Adjusted Mean Square |
F-Value | F-Ratio (test statistic used to determine significance in ANOVA) |
cutting speed (m/min) | |
feed rate (mm/rev) | |
depth of cut (mm) | |
Arithmetic Average Roughness | |
Maximum peak-to-valley height | |
Average peak-to-valley height |
References
- Astakhov, V.P. Machining of Hard Materials—Definitions and Industrial Applications. In Machining of Hard Materials; Springer: Berlin/Heidelberg, Germany, 2011. [Google Scholar]
- Anand, A.; Behera, A.K.; Das, S.R. An Overview on Economic Machining of Hardened Steels by Hard Turning and Its Process Variables. Manuf. Rev. 2019, 6, 4. [Google Scholar] [CrossRef]
- Özel, T.; Karpat, Y. Prediction of Surface Roughness and Tool Wear in Finish Dry Hard Turning Using Back Propagation Neural Networks. In Proceedings of the 17th International Conference on Production Research, Blacksburg, VA, USA, 3–7 August 2003. [Google Scholar]
- Nalbant, M.; Gokkaya, H.; Toktaş, I. Comparison of Regression and Artificial Neural Network Models for Surface Roughness Prediction with the Cutting Parameters in CNC Turning. Model. Simul. Eng. 2007, 2007, 092717. [Google Scholar] [CrossRef]
- Quiza, R.; Figueira, L.; Davim, J.P. Comparing Statistical Models and Artificial Neural Networks on Predicting the Tool Wear in Hard Machining D2 AISI Steel. Int. J. Adv. Manuf. Technol. 2008, 37, 641–648. [Google Scholar] [CrossRef]
- Leo Dev Wins, K.; Varadarajan, A.S. Simulation of Surface Milling of Hardened AISI4340 Steel with Minimal Fluid Application Using Artificial Neural Network. Adv. Prod. Eng. Manag. 2012, 7, 51. [Google Scholar] [CrossRef]
- Chandrasekaran, M.; Muralidhar, M.; Krishna, C.M.; Dixit, U.S. Application of Soft Computing Techniques in Machining Performance Prediction and Optimization: A Literature Review. Int. J. Adv. Manuf. Technol. 2010, 46, 445–464. [Google Scholar] [CrossRef]
- Sethi, D.; Kumar, V. Modeling of Tool Wear in Turning En 31 Alloy Steel Using Coated Carbide Inserts. Int. J. Manuf. Mater. Mech. Eng. 2012, 2, 34–51. [Google Scholar] [CrossRef]
- Aouici, H.; Yallese, M.A.; Chaoui, K.; Mabrouki, T.; Rigal, J.F. Analysis of Surface Roughness and Cutting Force Components in Hard Turning with CBN Tool: Prediction Model and Cutting Conditions Optimization. Measurement 2012, 45, 344–353. [Google Scholar] [CrossRef]
- Bouacha, K.; Yallese, M.A.; Mabrouki, T.; Rigal, J.F. Statistical Analysis of Surface Roughness and Cutting Forces Using Response Surface Methodology in Hard Turning of AISI 52100 Bearing Steel with CBN Tool. Int. J. Refract. Met. Hard Mater. 2010, 28, 349–361. [Google Scholar] [CrossRef]
- Attanasio, A.; Ceretti, E.; Giardini, C.; Cappellini, C. Tool Wear in Cutting Operations: Experimental Analysis and Analytical Models. J. Manuf. Sci. Eng. 2013, 135, 051012. [Google Scholar] [CrossRef]
- Chinchanikar, S.; Choudhury, S.K. Machining of Hardened Steel—Experimental Investigations, Performance Modeling and Cooling Techniques: A Review. Int. J. Mach. Tools Manuf. 2015, 89, 95–109. [Google Scholar] [CrossRef]
- Cica, D.; Sredanovic, B.; Kramar, D. Modelling of Tool Life and Surface Roughness in Hard Turning Using Soft Computing Techniques: A Comparative Study. Int. J. Mater. Prod. Technol. 2015, 50, 49–64. [Google Scholar] [CrossRef]
- Mia, M.; Dhar, N.R. Response Surface and Neural Network Based Predictive Models of Cutting Temperature in Hard Turning. J. Adv. Res. 2016, 7, 1035–1044. [Google Scholar] [CrossRef] [PubMed]
- Panda, A.; Sahoo, A.K.; Panigrahi, I.; Rout, A.K. Investigating Machinability in Hard Turning of AISI 52100 Bearing Steel through Performance Measurement: QR, ANN and GRA Study. Int. J. Automot. Mech. Eng. 2018, 15, 4935–4961. [Google Scholar] [CrossRef]
- Labidi, A.; Tebassi, H.; Belhadi, S.; Khettabi, R.; Yallese, M.A. Cutting Conditions Modeling and Optimization in Hard Turning Using RSM, ANN and Desirability Function. J. Fail. Anal. Prev. 2018, 18, 1017–1033. [Google Scholar] [CrossRef]
- Zerti, A.; Yallese, M.A.; Zerti, O.; Nouioua, M.; Khettabi, R. Prediction of Machining Performance Using RSM and ANN Models in Hard Turning of Martensitic Stainless Steel AISI 420. Proc. Inst. Mech. Eng. C J. Mech. Eng. Sci. 2019, 233, 4439–4462. [Google Scholar] [CrossRef]
- Kumar, R.; Sahoo, A.K.; Das, R.K.; Panda, A.; Mishra, P.C. Modelling of Flank Wear, Surface Roughness and Cutting Temperature in Sustainable Hard Turning of AISI D2 Steel. Procedia Manuf. 2018, 20, 406–413. [Google Scholar] [CrossRef]
- Elsadek, A.A.; Gaafer, A.M.; Mohamed, S.S.; Mohamed, A.A. Prediction and Optimization of Cutting Temperature on Hard-Turning of AISI H13 Hot Work Steel. SN Appl. Sci. 2020, 2, 540. [Google Scholar] [CrossRef]
- Adizue, U.L.; Tura, A.D.; Isaya, E.O.; Farkas, B.Z.; Takács, M. Surface Quality Prediction by Machine Learning Methods and Process Parameter Optimization in Ultra-Precision Machining of AISI D2 Using CBN Tool. Int. J. Adv. Manuf. Technol. 2023, 129, 1375–1394. [Google Scholar] [CrossRef]
- Şahin, Y. Prediction of Surface Roughness When Maching Mild Steel Using Statistical Methods. Adv. Mater. Process. Technol. 2024, 10, 1593–1609. [Google Scholar] [CrossRef]
- Bañon, F.; Martin, S.; Vazquez-Martinez, J.M.; Salguero, J.; Trujillo, F.J. Predictive Models Based on RSM and ANN for Roughness and Wettability Achieved by Laser Texturing of S275 Carbon Steel Alloy. Opt. Laser Technol. 2024, 168, 109963. [Google Scholar] [CrossRef]
- Mebrek, H.; Mansouri, S.; Touggui, Y.; Ameddah, H.; Yallese, M.A.; Benia, H.M. Predictive modeling and optimization of cutting parameters in high speed hardened turning of aisi D2 steel using rsm, ann and desirability function. Surf. Rev. Lett. 2024, 31, 2450036. [Google Scholar] [CrossRef]
- Bien, D.X. Predictive Modeling of Surface Roughness in Hard Turning with Rotary Cutting Tool Based on Multiple Regression Analysis, Artificial Neural Network, and Genetic Programing Methods. Proc. Inst. Mech. Eng. B J. Eng. Manuf. 2024, 238, 137–150. [Google Scholar] [CrossRef]
- Hossain, S.; Abedin, M.Z.; Saha, R.K.; Touhiduzzaman, M.; Hossen, M.J. Optimization of Cutting Temperature and Surface Roughness in CNC Turning of Ti-6Al-4V Alloy Using Response Surface Methodology. Heliyon 2025, 11, e41051. [Google Scholar] [CrossRef] [PubMed]
- Vasconcelos, G.A.V.B.; Francisco, M.B.; da Costa, L.R.A.; Ribeiro Junior, R.F.; Melo, M.d.L.N.M. Prediction of Surface Roughness in Duplex Stainless Steel Face Milling Using Artificial Neural Network. Int. J. Adv. Manuf. Technol. 2024, 133, 2031–2048. [Google Scholar] [CrossRef]
- Ambhore, N.; Gaikwad, M.; Patil, A.; Sharma, Y.; Manikjade, A. Predictive Modeling and Optimization of Dry Turning of Hardened Steel. Int. J. Interact. Des. Manuf. 2023, 18, 6281–6287. [Google Scholar] [CrossRef]
- Kumar, R.; Rafighi, M.; Özdemir, M.; Şahinoğlu, A.; Kulshreshta, A.; Singh, J.; Singh, S.; Prakash, C.; Bhowmik, A. Modeling and Optimization of Hard Turning: Predictive Analysis of Surface Roughness and Cutting Forces in AISI 52100 Steel Using Machine Learning. Int. J. Interact. Des. Manuf. (IJIDeM) 2024. [Google Scholar] [CrossRef]
- Sukonna, R.T.; Zaman, P.B.; Dhar, N.R. Estimation of Machining Responses in Hard Turning under Dry and HPC Conditions Using Different AI Based and Statistical Techniques. Int. J. Interact. Des. Manuf. 2022, 16, 1705–1725. [Google Scholar] [CrossRef]
- Hoyne, A.C.; Nath, C.; Kapoor, S.G. On Cutting Temperature Measurement during Titanium Machining with an Atomization-Based Cutting Fluid Spray System. J. Manuf. Sci. Eng. Trans. ASME 2015, 137, 024502. [Google Scholar] [CrossRef]
C % | Si % | Mn % | P % | S % | Cr % | Ni % | Cu % | Fe % |
---|---|---|---|---|---|---|---|---|
0.98 | 0.277 | 0.391 | 0.026 | 0.022 | 1.410 | 0.060 | 0.058 | Balance |
Parameters 1 | Units | Levels | ||
---|---|---|---|---|
Cutting Speed | m/min | 80 | 110 | 140 |
Feed Rate | mm/rev | 0.05 | 0.075 | 0.10 |
Depth of Cut | mm | 0.1 | 0.2 | 0.3 |
Serial # | (m/min) | (mm/rev) | (mm) | (°C) | (μm) |
---|---|---|---|---|---|
1 | 80 | 0.05 | 0.1 | 535 | 0.289 |
2 | 80 | 0.05 | 0.3 | 539 | 0.226 |
3 | 80 | 0.05 | 0.5 | 561 | 0.314 |
4 | 110 | 0.05 | 0.1 | 521 | 0.243 |
5 | 110 | 0.05 | 0.3 | 558 | 0.209 |
6 | 110 | 0.05 | 0.5 | 587 | 0.319 |
7 | 140 | 0.05 | 0.1 | 563 | 0.189 |
8 | 140 | 0.05 | 0.3 | 584 | 0.303 |
9 | 140 | 0.05 | 0.5 | 607 | 0.404 |
10 | 80 | 0.10 | 0.1 | 531 | 0.469 |
11 | 80 | 0.10 | 0.3 | 557 | 0.406 |
12 | 80 | 0.10 | 0.5 | 581 | 0.478 |
13 | 110 | 0.10 | 0.1 | 554 | 0.415 |
14 | 110 | 0.10 | 0.3 | 578 | 0.389 |
15 | 110 | 0.10 | 0.5 | 603 | 0.446 |
16 | 140 | 0.10 | 0.1 | 591 | 0.287 |
17 | 140 | 0.10 | 0.3 | 613 | 0.252 |
18 | 140 | 0.10 | 0.5 | 632 | 0.429 |
19 | 80 | 0.15 | 0.1 | 556 | 0.671 |
20 | 80 | 0.15 | 0.3 | 579 | 0.613 |
21 | 80 | 0.15 | 0.5 | 601 | 0.670 |
22 | 110 | 0.15 | 0.1 | 572 | 0.558 |
23 | 110 | 0.15 | 0.3 | 595 | 0.459 |
24 | 110 | 0.15 | 0.5 | 618 | 0.543 |
25 | 140 | 0.15 | 0.1 | 621 | 0.396 |
26 | 140 | 0.15 | 0.3 | 644 | 0.334 |
27 | 140 | 0.15 | 0.5 | 663 | 0.406 |
Sequential Model Sum of Squares (Type I) | ||||||
---|---|---|---|---|---|---|
Source | Sum of Square | DF | Mean Square | F-Value | p-Value | |
Mean vs. Total | 8.518 × 106 | 1 | 8.518 × 106 | |||
Linear vs. Mean | 17,924.31 | 3 | 5974.77 | 12.95 | 0.0002 | |
2FI vs. Linear | 588.38 | 3 | 196.13 | 0.3753 | 0.7723 | |
Quadratic vs. 2FI | 6419.31 | 3 | 2139.77 | 57.09 | <0.0001 | Suggested |
Cubic vs. Quadratic | 251.19 | 4 | 62.80 | 3.05 | 0.1080 | Aliased |
Residual | 123.62 | 6 | 20.60 | |||
Total | 8.543 × 106 | 20 | 4.272 × 105 | |||
Lack of Fit Tests | ||||||
Source | Sum of Square | DF | Mean Square | F-Value | p-Value | |
Linear | 7303.65 | 11 | 663.97 | 42.11 | 0.0003 | |
2FI | 6715.28 | 8 | 839.41 | 53.24 | 0.0002 | |
Quadratic | 295.97 | 5 | 59.19 | 3.75 | 0.0864 | Suggested |
Cubic | 44.79 | 1 | 44.79 | 2.84 | 0.1527 | Aliased |
Pure Error | 78.83 | 5 | 15.77 | |||
Model Summary Statistics | ||||||
Source | Standard Deviation | R2 | Adjusted R2 | Predicted R2 | PRESS | |
Linear | 21.48 | 0.7083 | 0.6536 | 0.4957 | 12,761.71 | |
2FI | 22.86 | 0.7315 | 0.6076 | 0.4796 | 13,168.80 | |
Quadratic | 6.12 | 0.9852 | 0.9719 | 0.8966 | 2617.60 | Suggested |
Cubic | 4.54 | 0.9951 | 0.9845 | 0.5599 | 11,136.84 | Aliased |
Term | Coefficient Estimate | DF | Standard Error | 95% CI Low | 95% CI High | VIF |
---|---|---|---|---|---|---|
Constant | 639.31 | 1 | 2.45 | 633.85 | 644.78 | |
27.05 | 1 | 1.66 | 23.34 | 30.75 | 1.0000 | |
7.24 | 1 | 1.35 | 4.23 | 10.26 | 1.0000 | |
20.81 | 1 | 1.53 | 17.40 | 24.22 | 1.0000 | |
1.38 | 1 | 2.16 | −3.45 | 6.20 | 1.0000 | |
8.13 | 1 | 2.16 | 3.30 | 12.95 | 1.0000 | |
2.38 | 1 | 2.16 | −2.45 | 7.20 | 1.0000 | |
20.79 | 1 | 1.68 | 17.03 | 24.54 | 1.08 | |
0.9761 | 1 | 0.7955 | −0.7964 | 2.75 | 1.10 | |
−2.25 | 1 | 1.22 | −4.97 | 0.4664 | 1.08 |
Sequential Model Sum of Squares (Type I) | ||||||
---|---|---|---|---|---|---|
Source | Sum of Square | DF | Mean Square | F-Value | p-Value | |
Mean vs. Total | 12.31 | 1 | 12.31 | |||
Linear vs. Mean | 0.1141 | 3 | 0.0380 | 3.01 | 0.0611 | |
2FI vs. Linear | 0.0053 | 3 | 0.0018 | 0.1163 | 0.9490 | |
Quadratic vs. 2FI | 0.1847 | 3 | 0.0616 | 49.85 | <0.0001 | Suggested |
Cubic vs. Quadratic | 0.0037 | 4 | 0.0009 | 0.6353 | 0.6561 | Aliased |
Residual | 0.0087 | 6 | 0.0014 | |||
Total | 12.62 | 20 | 0.6311 | |||
Lack of Fit Tests | ||||||
Source | Sum of Square | DF | Mean Square | F-Value | p-Value | |
Linear | 0.1995 | 11 | 0.0181 | 31.49 | 0.0007 | |
2FI | 0.1942 | 8 | 0.0243 | 42.15 | 0.0004 | |
Quadratic | 0.0095 | 5 | 0.0019 | 3.29 | 0.1086 | Suggested |
Cubic | 0.0058 | 1 | 0.0058 | 10.07 | 0.0247 | Aliased |
Pure Error | 0.0029 | 5 | 0.0006 | |||
Model Summary Statistics | ||||||
Source | Standard Deviation | R2 | Adjusted R2 | Predicted R2 | PRESS | |
Linear | 0.1125 | 0.3606 | 0.2407 | −0.3438 | 0.4253 | |
2FI | 0.1231 | 0.3773 | 0.0899 | −0.4310 | 0.4529 | |
Quadratic | 0.0351 | 0.9610 | 0.9258 | 0.7591 | 0.0762 | Suggested |
Cubic | 0.0380 | 0.9726 | 0.9132 | −3.5225 | 1.43 | Aliased |
Term | Coefficient Estimate | DF | Standard Error | 95% CI Low | 95% CI High | VIF |
---|---|---|---|---|---|---|
Constant | 0.8457 | 1 | 0.0141 | 0.8144 | 0.8771 | |
0.0677 | 1 | 0.0095 | 0.0464 | 0.0890 | 1.0000 | |
0.0449 | 1 | 0.0078 | 0.0276 | 0.0622 | 1.0000 | |
0.0259 | 1 | 0.0088 | 0.0063 | 0.0455 | 1.0000 | |
0.0168 | 1 | 0.0124 | −0.0109 | 0.0444 | 1.0000 | |
0.0168 | 1 | 0.0124 | −0.0109 | 0.0444 | 1.0000 | |
−0.0100 | 1 | 0.0124 | −0.0377 | 0.0177 | 1.0000 | |
−0.0277 | 1 | 0.0097 | −0.0493 | −0.0062 | 1.08 | |
−0.0515 | 1 | 0.0046 | −0.0617 | −0.0414 | 1.10 | |
0.0129 | 1 | 0.0070 | −0.0027 | 0.0285 | 1.08 |
Configuration | Parameters |
---|---|
Entity model | Cutting Temperature |
Input neuron | Cutting speed (v), Feed (f), Depth of cut (d), |
Output neuron | Cutting Temperature |
Network type | Feedforward backpropagation |
Algorithm | Backpropagation with Levenberg–Marquardt (LM) |
Transfer function | Tansig |
Training function | Trainlm |
Learning function | Learngdm |
Performance Function | MSE |
Learning conditions | Supervised learning |
Number of hidden layers | 1 Hidden layer each 2 Neurons |
Learning rate, (α) | 0.1 |
Momentum constant, (β) | 0.5 |
Performance/goal/Error | 0.000001 |
Maximum epochs (cycles) set | 1000 |
Cutting Speed (m/min) | Feed (mm/rev) | Depth of Cut (mm) | Exp. Result | Prediction by ANN | ANN % Error |
---|---|---|---|---|---|
80 | 0.05 | 0.1 | 535 | 544 | 1.68 |
140 | 0.05 | 0.1 | 563 | 570 | 1.24 |
80 | 0.15 | 0.3 | 579 | 559 | −3.39 |
110 | 0.15 | 0.5 | 618 | 623 | 0.81 |
Average Error | 1.78 |
Configuration | Parameters |
---|---|
Entity model | Surface Roughness |
Input neuron | Cutting speed (v), Feed (f), Depth of cut (d) |
Output neuron | Output neuron Surface Roughness |
Network type | Feedforward backpropagation |
Algorithm | Backpropagation with Levenberg–Marquardt (LM) |
Transfer function | Tansig |
Training function | Trainlm |
Learning function | MSE |
Performance Function | Learngdm |
Learning conditions | Supervised learning |
Number of hidden layers | 1 Hidden layer each 20 Neurons |
Learning rate, (α) | 0.1 |
Momentum constant, (β) | 0.5 |
Performance/goal/Error | 0.000001 |
Maximum epochs (cycles) set | 1000 |
Testing Data | Surface Roughness | |||||
---|---|---|---|---|---|---|
v (m/min) | f (mm/rev) | d (mm/rev) | Exp. Result | Prediction by ANN | ANN % Error | Average Error |
100 | 0.05 | 0.5 | 0.319 | 0.322 | 0.10 | |
140 | 0.10 | 0.3 | 0.252 | 0.245 | −2.70 | 1.42 |
110 | 0.15 | 0.3 | 0.459 | 0.446 | −2.67 | |
140 | 0.05 | 0.5 | 0.403 | 0.404 | 0.21 |
Testing Data | Cutting Temperature | % Error | |||||
---|---|---|---|---|---|---|---|
v (m/min) | F (mm/rev) | d (mm) | Exp. Result | Prediction by RSM | Prediction by ANN | RSM % Error | ANN % Error |
110 | 0.10 | 0.5 | 603 | 574 | 620 | −4.80 | 2.82 |
140 | 0.15 | 0.3 | 644 | 677 | 639 | 5.12 | −0.78 |
110 | 0.05 | 0.5 | 587 | 593 | 608 | 1.02 | 3.57 |
140 | 0.10 | 0.3 | 613 | 662 | 617 | 7.99 | 0.65 |
Average % Error | 4.73 | 1.95 |
Testing Data | Surface Roughness | % Error | |||||
---|---|---|---|---|---|---|---|
v (m/min) | f (mm/rev) | d (mm) | Exp. Result | Prediction by RSM | Prediction by ANN | RSM % Error | ANN % Error |
110 | 0.10 | 0.5 | 0.319 | 0.294 | 0.322 | −7.83 | 0.10 |
140 | 0.15 | 0.3 | 0.252 | 0.260 | 0.245 | 3.17 | 2.70 |
110 | 0.05 | 0.5 | 0.459 | 0.499 | 0.446 | 8.71 | 2.67 |
140 | 0.10 | 0.3 | 0.404 | 0.418 | 0.403 | 3.46 | 0.21 |
Average % Error | 5.79 | 1.42 |
Run. No | v (m/min) | f (mm/rev) | d (mm) | Average Value of (Ra) at Three Experimental Runs (µm) | % Reduction of (Ra) When Compared to | |||
---|---|---|---|---|---|---|---|---|
Dry | MQL | MCFA | Dry | MQL | ||||
1 | 80 | 0.05 | 0.1 | 0.537 | 0.381 | 0.289 | 46.182 | 24.147 |
4 | 110 | 0.05 | 0.1 | 0.401 | 0.307 | 0.243 | 39.401 | 20.847 |
7 | 140 | 0.05 | 0.1 | 0.334 | 0.246 | 0.189 | 43.413 | 23.171 |
11 | 80 | 0.1 | 0.3 | 0.701 | 0.523 | 0.406 | 42.083 | 22.371 |
14 | 110 | 0.1 | 0.3 | 0.521 | 0.461 | 0.389 | 25.336 | 15.618 |
17 | 140 | 0.1 | 0.3 | 0.446 | 0.334 | 0.252 | 43.498 | 24.551 |
21 | 80 | 0.15 | 0.5 | 0.871 | 0.772 | 0.670 | 23.077 | 13.212 |
24 | 110 | 0.15 | 0.5 | 0.667 | 0.605 | 0.543 | 18.591 | 10.248 |
27 | 140 | 0.15 | 0.5 | 0.575 | 0.492 | 0.406 | 29.391 | 17.480 |
Run. No | v (m/min) | f (mm/rev) | d (mm) | Average Value of Cutting Temperature at Three Experimental Runs (°C) | % Reduction in Cutting Temperature When Compared to | |||
---|---|---|---|---|---|---|---|---|
Dry | MQL | MCFA | Dry | MQL | ||||
1 | 80 | 0.05 | 0.1 | 583 | 554 | 521 | 10.63 | 5.96 |
4 | 110 | 0.05 | 0.1 | 611 | 586 | 535 | 12.44 | 8.70 |
7 | 140 | 0.05 | 0.1 | 678 | 591 | 563 | 16.96 | 4.74 |
11 | 80 | 0.1 | 0.3 | 635 | 603 | 557 | 12.28 | 7.63 |
14 | 110 | 0.1 | 0.3 | 651 | 612 | 578 | 11.21 | 5.56 |
17 | 140 | 0.1 | 0.3 | 732 | 675 | 613 | 16.26 | 9.19 |
21 | 80 | 0.15 | 0.5 | 662 | 630 | 601 | 9.21 | 4.60 |
24 | 110 | 0.15 | 0.5 | 697 | 654 | 618 | 11.33 | 5.50 |
27 | 140 | 0.15 | 0.5 | 784 | 723 | 663 | 15.43 | 8.30 |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2025 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Mane, S.; Patil, R.B.; Al-Dahidi, S. Predictive Modeling of Surface Roughness and Cutting Temperature Using Response Surface Methodology and Artificial Neural Network in Hard Turning of AISI 52100 Steel with Minimal Cutting Fluid Application. Machines 2025, 13, 266. https://doi.org/10.3390/machines13040266
Mane S, Patil RB, Al-Dahidi S. Predictive Modeling of Surface Roughness and Cutting Temperature Using Response Surface Methodology and Artificial Neural Network in Hard Turning of AISI 52100 Steel with Minimal Cutting Fluid Application. Machines. 2025; 13(4):266. https://doi.org/10.3390/machines13040266
Chicago/Turabian StyleMane, Sandip, Rajkumar Bhimgonda Patil, and Sameer Al-Dahidi. 2025. "Predictive Modeling of Surface Roughness and Cutting Temperature Using Response Surface Methodology and Artificial Neural Network in Hard Turning of AISI 52100 Steel with Minimal Cutting Fluid Application" Machines 13, no. 4: 266. https://doi.org/10.3390/machines13040266
APA StyleMane, S., Patil, R. B., & Al-Dahidi, S. (2025). Predictive Modeling of Surface Roughness and Cutting Temperature Using Response Surface Methodology and Artificial Neural Network in Hard Turning of AISI 52100 Steel with Minimal Cutting Fluid Application. Machines, 13(4), 266. https://doi.org/10.3390/machines13040266