# MQL Strategies Applied in Ti-6Al-4V Alloy Milling—Comparative Analysis between Experimental Design and Artificial Neural Networks

^{1}

^{2}

^{3}

^{4}

^{5}

^{6}

^{7}

^{*}

## Abstract

**:**

## 1. Introduction

_{a}) average prediction, and that little attention was given to the efficiency of the training. Researchers point out the definition of the ideal network topology as the main problem in roughness modeling. Optimization efforts are detected in a small number of publications, and comparisons between topology definition approaches are hardly found. Moreover, with regard to validation, most publications neglect or make this ability unclear. The use of the third validation data set can be found in only a few studies. The use of statistical evaluation to compare trained networks can be found in only one fifth of the peer-reviewed papers, in addition to the lack of a statistical evaluation comparing ANN-based models and models obtained by other methods. According to authors, the ANNs models´ accuracy are points that require more attention and many papers are presented only in graphic forms, thus lacking information as to the results’ reproduction. There is no standard procedure for choosing more appropriate ANN settings, thus becoming a difficult task that depends on many variables. The trial and error method is the procedure most commonly used to identify the best settings [44]. Based on the peer-reviewed literature, some areas of improvement are suggested, such as the no need to transform or change data, that reveal non-regular periodic movement. In addition, papers focus on network characteristics in a specification phase, with tests being performed to determine errors and R oscillations, and to validate a performance optimization model [45].

## 2. Materials and Methods

#### 2.1. Experimental Design and Machining

^{3}) with two central points was used, as shown in Table 2. A replication was performed for each cutting condition, totaling 60 tests. From these, the respective averages were calculated. The data adopted for the cutting speed (v

_{c}), feed rate (f), and depth of cut (a

_{p}) were recommended by the insert manufacturer. The procedure for using each cutting insert was used up to a wear of 0.1 mm.

_{c}), feed force (F

_{f}), penetration force (F

_{p}), torque (M

_{z}), root mean square height of the surface (S

_{q}), Skewness of height distribution (S

_{sk}) and Kurtosis of height distribution (S

_{ku}) were considered. Response surfaces were generated, and the desirability function was used to optimize the results of each strategy employed. Three different conditions were stipulated for the trials: (a) using no lubrication, called Strategy 1, (b) applying the designed mixing valve and adopting the MQL approach with oil (Strategy 2), and (c) using the MQL approach with the addition of 30% commercial graphite (Strategy 3). The trials were carried out according to Table 3. For the MQL approach, the Superfluid 3 lubricating oil from Quimatic/Tapmatic was applied. Its characteristics are listed in Table 4. The fluid was driven by a Magneti Marelli MAM00103 electric automotive pump (Mauá, Brazil), with a working pressure of 3 bar and a flow rate of 110 L/h connected to a 20 L fuel tank, and with an oil return circuit to the tank. The flow regulation was performed by a manual control valve set to 110 mL/h. The compressed air pressure was maintained at 6 bar.

#### 2.2. Measurements

_{b}flank wear of up to 0.2 mm. Figure 8 shows the measurement of an insert.

_{q}(root mean square height of the surface), S

_{sk}(skewness of height distribution) and S

_{ku}(kurtosis of height distribution). The measuring area was 4.3mm

^{2}with used 0.8mm cut-off. Figure 9 illustrates the measurement procedure.

#### 2.3. Artificial Neural Networks

#### 2.4. Comparative Analysis

_{i}into a function d

_{i}, varying between 0 and 1. If the answer is the desired one, a value of d

_{i}= 1 is accepted, otherwise, d

_{i}= 0 [47]. In this way, the independent variables are chosen to maximize the global desirability function. In this work, d

_{i}= 1 was chosen as the lowest value for machining forces and roughness.

## 3. Results and Discussion

#### 3.1. Statistical Results of Surface Roughness Measurements

_{q}parameter corresponds to the standard deviation of the distribution curve [48]. The S

_{ku}parameter is always presented with the S

_{sk}parameter, describing the shape of a topographic surface and its roughness distribution. Mathematically, the parameters skewness and kurtosis measure the symmetry and histogram deviation of all peaks and valleys heights of a machined surface in relation to the Gaussian distribution. The skewness roughness parameter can monitor machined surfaces’ wear and tear in service. A surface with a Gaussian distribution, which is symmetrically distributed, has the S

_{sk}parameter equal to zero. Positive S

_{sk}values indicate the predominance of high peaks, and negative values indicate the prevalence of valleys. On the other hand, S

_{ku}parameter measures the degree of flattening or thinning of a topographic distribution of a peak´s roughness profile. On a surface with normal symmetric distribution, the S

_{ku}parameter is equal to three. In practical terms, S

_{ku}> 3 indicates the presence of acute peaks, while S

_{ku}< 3 indicates surface texture free of disproportionately sharp peaks [49,50]. In this work, the lowest S

_{q}value was obtained by the number 2 assay used in strategy 3 (0.39 µm). The maximum condition occurred in test 10 strategy 1 (1.57 µm). For the S

_{sk}parameter, the minimum value occurred in test 1 strategy 3 (−1.05), and the maximum condition occurred in test 1 strategy 2 (0.49). As for the S

_{ku}parameter, the minimum and maximum results are respectively found in test 2 strategy 1 (2.68) and test 1 strategy 3 (15.30). The statistical results are shown in Table 7. Based on statistical analysis results, the minimum and maximum topography surface values measured for each S

_{q}, S

_{sk}, S

_{ku}parameter are shown in Figure 11.

#### 3.2. Results and Analysis of Factorial Design

_{p}were the variables that most influenced roughness.

#### 3.2.1. Trial without Lubrication

_{p}.

_{c}, since it does not influence the torque in the studied confidence interval. The lowest values of cutting forces, feed rate force, penetration force, and torque occur in smaller feeds, smaller depths of cut, and lower cutting speeds. The contributions of a

_{p}and f are striking, indicating that they are possibly responsible for the mechanism regulating the machining forces of this test condition. The area of the section of cut that is defined by the product of the feed by the depth of cut increases with the increase of the feed and the depth of cut, causing an increase in the forces in question.

#### 3.2.2. Trial with Oil

_{p}, the advance f, and the interaction a

_{p}and f demonstrated an influence on the cutting force. The variables a

_{p}and f demonstrated an influence on the advance force for the 95% confidence interval.

_{q}was influenced by interaction ap and f. The S

_{sk}parameter was influenced by the cutting speed, the feed rate and the interactions between v

_{c}and f and v

_{c}and a

_{p}.

_{q}values also occur for lower f and higher a

_{p}.

#### 3.2.3. Trial with Graphite

_{p}and the feed rate showed an influence on the cutting force. The a

_{p}variable showed an influence on the feed rate force, and for a 95% confidence interval, the penetration force was not influenced by the independent variables. The depth of cut was the variable of greatest influence for the penetration force. The torque was influenced by the depth of penetration and the feed rate. For the confidence interval adopted, the S

_{q}roughness was influenced by the feed rate.

_{c}, F

_{f}, F

_{p}, M

_{z}, S

_{sk}, S

_{ku}and S

_{q}, obtained by the application of the factorial plan in this work.

_{c}, F

_{f}, F

_{p}) are not statistically influenced by the independent variables. Only torque was influenced by the parameters f and a

_{p}in the confidence interval studied. In the tests with lubrication, both with oil and graphite, it is apparent that machining forces and torque are significantly influenced by the parameters a

_{p}and f. The S

_{q}roughness was influenced by the interaction between a

_{p}and f in the oil assay, while in the graphite assay, only the f parameter showed significant influence.

#### 3.2.4. Machined Surface Roughness Analysis

_{p}and f. The variable v

_{c}is only noted in this work influencing S

_{sk}in Strategy 2. To verify the roughness parameters behavior studied, the study of the lowest and highest values of the cut-off conditions was adopted as a premise. Thus, tests 1 and 8 of each experimental planning strategy are analyzed. Figure 18 shows the isometric surfaces and contour maps of the tests for the dry strategy. An increase of S

_{q}in 99.8% was perceived due to the increase in a

_{p}and f causing greater irregularities of the roughness profile. The negative S

_{sk}parameter for both conditions indicates the prevalence of valleys. The positive S

_{ku}parameter indicates that the peaks of the machined surface are sharp.

_{sk}parameter, positive for the minimum cut-off condition, indicates the prevalence of peaks, which does not occur for the maximum values. The positive S

_{ku}parameter indicates that the peaks of the machined surface are sharp. It is observed that the increase in feed and cutting speed accentuated the milling marks.

_{q}of 27% is noted. The S

_{sk}parameter, negative for both cutting conditions, indicates the prevalence of valleys. The positive S

_{ku}parameter indicates that the peaks of the machined surface are sharp. It is observed that the increase of f accentuated the advance marks.

#### 3.2.5. Desirability Function

#### 3.3. Prediction of Results by Artificial Neural Networks

_{c}, f, and a

_{p}). As the target, the dependent samples F

_{f}, F

_{c}, F

_{p}, M

_{z}, and R

_{a}were selected.

#### 3.4. Comparative Analysis of Predictions

## 4. Conclusions

_{q}roughness was achieved by using the MQL practice with cutting fluid and graphite. The desirability function provided the optimized search for the lowest cutting forces and for a lower roughness value, aiming at the surface finish. In tests with no lubrication, it can be perceived that the machining forces (F

_{c}, F

_{f}, F

_{p}) are not statistically influenced by the independent variables. Only torque was influenced by the parameters f and a

_{p}in the confidence interval studied. In the tests with lubrication, both with oil and graphite, it is apparent that machining forces and torque are significantly influenced by the parameters a

_{p}and f. The S

_{q}roughness was influenced by the interaction between a

_{p}and f in the oil assay, while in the graphite assay, only the f parameter showed significant influence. Lower cutting forces and lower feed rates provided lower roughness values. The paper took into account surface finishing cutting conditions. In the lowest feed rate and depth cut, it can be perceived that statistically, for the confidence interval adopted, that the forces had lower statistical influences than variables a

_{p}and f. It has been observed that variables a

_{p}and f define the cutting geometry, ergo being responsible for the roughness. The S

_{sk}values showed values close to zero in most tests, indicating a symmetry between peaks and valleys. Negative values, however, indicate a trend of valley predominance and a concentration of material near the surface. All S

_{ku}parameters measured demonstrated positive values, showing that the tests presented centralized acute peaks. With sharp peaks, there is the possibility of premature wear and tear in contact with another surface. The statistical comparison between the experimental design adopted and the artificial neural networks provided similar responses.

## Author Contributions

## Funding

## Acknowledgments

## Conflicts of Interest

## Nomenclature

ANN | Artificial Neural Networks |

ANOVA | Analysis of variance |

a_{p} | Depth of cut (mm) |

BPNN | Backpropagation neural network |

CVD | Chemical vapor deposition |

CNC | Computer numeric controlled |

DOE | Design of experiments |

f | Feed rate (mm/rev) |

F_{c} | Cutting force (N) |

F_{f} | Feed force (N) |

F_{p} | Penetration force (N) |

GA | Genetic algorithm |

MQL | Minimum quantity lubrication |

M_{z} | Torque (Nm) |

MLP | Multi Layer Perceptron |

S_{ku} | Kurtosis of height distribution (dimensionless) |

SOS | Sum of squares error function (dimensionless) |

S_{sk} | Skewness of height distribution (dimensionless) |

S_{q} | Root mean square height of the surface (µm) |

v_{c} | Cutting speed (m/min) |

V_{b} | Flank wear (mm) |

2(**) | two levels |

## References

- Duc, T.M.; Tran, T.L.; Tran, Q.C. Performance evaluation of MQL parameters using Al
_{2}O_{3}and MoS_{2}nanofluids in hard turning 90CrSi steel. Lubricants**2019**, 7, 40. [Google Scholar] [CrossRef] [Green Version] - Rodríguez, J.M.; Larsson, S.; Carbonell, J.M.; Jonsén, P. Dislocation density based flow stress model applied to the PFEM simulation of orthogonal cutting processes of Ti-6Al-4V. Materials
**2020**, 13, 1979. [Google Scholar] [CrossRef] - Roy, S.; Kumar, R.; Sahoo, A.K.; Das, R.K. A brief review on effects of conventional and nano particle based machining fluid on machining performance of minimum quantity lubrication machining. Mater. Today Proc.
**2019**, 18, 5421–5431. [Google Scholar] [CrossRef] - Nagaraj, P.B.; Dinesh, P. Friction force during machining process—Part 1: Development of optimized neural network architecture. Mater. Today Proc.
**2020**, 27, 1407–1410. [Google Scholar] [CrossRef] - D’Addona, D.M.; Raykar, S.J. Thermal modeling of tool temperature distribution during high pressure coolant assisted turning of Inconel 718. Materials
**2019**, 12, 408. [Google Scholar] [CrossRef] [Green Version] - García-Martínez, E.; Miguel, V.; Martínez-Martínez, A.; Manjabacas, M.C.; Coello, J. Sustainable Lubrication Methods for the Machining of Titanium Alloys: An Overview. Materials
**2019**, 12, 3852. [Google Scholar] [CrossRef] [Green Version] - Shokrani, A.; Newman, S.T. A new cutting tool design for cryogenic machining of Ti–6Al–4V titanium alloy. Materials
**2019**, 12, 477. [Google Scholar] [CrossRef] [Green Version] - Shokrani, A.; Al-Samarrai, I.; Newman, S.T. Hybrid cryogenic MQL for improving tool life in machining of Ti-6Al-4V titanium alloy. J. Manuf. Process.
**2019**, 43, 229–243. [Google Scholar] [CrossRef] - Abbas, A.T.; Sharma, N.; Anwar, S.; Luqman, M.; Tomaz, I.; Hegab, H. Multi-response optimization in high-speed machining of Ti-6Al-4V using TOPSIS-fuzzy integrated approach. Materials
**2020**, 13, 1104. [Google Scholar] [CrossRef] [Green Version] - Abbas, A.T.; Sharma, N.; Anwar, S.; Hashmi, F.H.; Jamil, M.; Hegab, H. Towards optimization of surface roughness and productivity aspects during high-speed machining of Ti–6Al–4V. Materials
**2019**, 12, 3749. [Google Scholar] [CrossRef] [Green Version] - Sánchez Hernández, Y.; Trujillo Vilches, F.J.; Bermudo Gamboa, C.; Sevilla Hurtado, L. Experimental parametric relationships for chip geometry in dry machining of the Ti6Al4V alloy. Materials
**2018**, 11, 1260. [Google Scholar] [CrossRef] [Green Version] - Qin, S.; Li, Z.; Guo, G.; An, Q.; Chen, M.; Ming, W. Analysis of minimum quantity lubrication (MQL) for different coating tools during turning of TC11 titanium alloy. Materials
**2016**, 9, 804. [Google Scholar] [CrossRef] [PubMed] - Liu, D.; Zhang, Y.; Luo, M.; Zhang, D. Investigation of tool wear and chip morphology in dry trochoidal milling of titanium alloy Ti–6Al–4V. Materials
**2019**, 12, 1937. [Google Scholar] [CrossRef] [PubMed] [Green Version] - Matras, A.; Zębala, W.; Machno, M. Research and method of roughness prediction of a curvilinear surface after titanium alloy turning. Materials
**2019**, 12, 502. [Google Scholar] [CrossRef] [PubMed] [Green Version] - Fernández-Pérez, J.; Cantero, J.L.; Díaz-Álvarez, J.; Miguélez, M.H. Hybrid composite-metal stack drilling with different minimum quantity lubrication levels. Materials
**2019**, 12, 448. [Google Scholar] [CrossRef] [Green Version] - Słodki, B.; Zębala, W.; Struzikiewicz, G. Turning titanium alloy, grade 5 ELI, with the implementation of high pressure coolant. Materials
**2019**, 12, 768. [Google Scholar] [CrossRef] [Green Version] - Singh, G.; Pruncu, C.I.; Gupta, M.K.; Mia, M.; Khan, A.M.; Jamil, M.; Pimenov, D.Y.; Sen, B.; Sharma, V.S. Investigations of machining characteristics in the upgraded MQL-assisted turning of pure titanium alloys using evolutionary algorithms. Materials
**2019**, 12, 999. [Google Scholar] [CrossRef] [Green Version] - Gupta, M.K.; Jamil, M.; Wang, X.; Song, Q.; Liu, Z.; Mia, M.; Hegab, H.; Khan, A.M.; Collado, A.G.; Pruncu, C.I.; et al. Performance evaluation of vegetable oil-based nano-cutting fluids in environmentally friendly machining of Inconel-800 alloy. Materials
**2019**, 12, 2792. [Google Scholar] [CrossRef] [Green Version] - James, S.J.; Annamalai, A.R. Machinability study of developed composite AA6061-ZrO2 and analysis of influence of MQL. Metals
**2018**, 8, 472. [Google Scholar] [CrossRef] [Green Version] - Mia, M.; Morshed, M.; Kharshiduzzaman, M.; Razi, M.H.; Mostafa, M.R.; Rahman, S.M.; Ahmad, I.; Hafiz, M.T.; Kamal, A.M. Prediction and optimization of surface roughness in minimum quantity coolant lubrication applied turning of high hardness steel. Measurement
**2018**, 118, 43–51. [Google Scholar] [CrossRef] - Abbas, A.T.; Benyahia, F.; El Rayes, M.M.; Pruncu, C.; Taha, M.A.; Hegab, H. Towards optimization of machining performance and sustainability aspects when turning AISI 1045 steel under different cooling and lubrication strategies. Materials
**2019**, 12, 3023. [Google Scholar] [CrossRef] [PubMed] [Green Version] - Dong, P.Q.; Duc, T.M.; Long, T.T. Performance evaluation of MQCL hard milling of SKD 11 tool steel using MoS2 nanofluid. Metals
**2019**, 9, 658. [Google Scholar] [CrossRef] - Sousa, V.F.C.; Silva, F.J.G. Recent advances in turning processes using coated tools—A comprehensive review. Metals
**2020**, 10, 170. [Google Scholar] [CrossRef] [Green Version] - Sankar, M.R.; Saxena, S.; Banik, S.R.; Iqbal, I.M.; Nath, R.; Bora, L.J.; Gajrani, K.K. Experimental study and artificial neural network modeling of machining with minimum quantity cutting fluid. Mater. Today Proc.
**2019**, 18, 4921–4931. [Google Scholar] [CrossRef] - Swain, S.; Panigrahi, I.; Kumar Sahoo, A.; Panda, A. Study on machining performances during hard turning process using vibration signal under MQL environment: A review. Mater. Today Proc.
**2019**, 18, 3539–3545. [Google Scholar] [CrossRef] - Vishnu Vardhan, M.; Sankaraiah, G.; Yohan, M. Optimization of cutting parameters and prediction of Ra & MRR for machining of P20 Steel on CNC milling using Artificial Neural Networks. Mater. Today Proc.
**2018**, 5, 27058–27064. [Google Scholar] [CrossRef] - Vardhan, M.V.; Sankaraiah, G.; Yohan, M. Prediction of surface roughness & material removal rate for machining of P20 steel in CNC milling using artificial neural networks. Mater. Today Proc.
**2018**, 5, 18376–18382. [Google Scholar] [CrossRef] - Paturi, U.M.; Devarasetti, H.; Narala, S.K. Application of regression and artificial neural network analysis in modelling of surface roughness in hard turning of AISI 52100 steel. Mater. Today Proc.
**2018**, 5, 4766–4777. [Google Scholar] [CrossRef] - Prasad, M.D.; Malyadri, T.; Hari, S.S. Sensitivity analysis for process parameters influencing surface roughness of hardened steel in dry machining process. Mater. Today Proc.
**2020**, 26, 2521–2524. [Google Scholar] [CrossRef] - Arnold, F.; Hänel, A.; Nestler, A.; Brosius, A. New approaches for the determination of specific values for process models in machining using artificial neural networks. Procedia Manuf.
**2017**, 11, 1463–1470. [Google Scholar] [CrossRef] - Kant, G.; Sangwan, K.S. Predictive modelling and optimization of machining parameters to minimize surface roughness using artificial neural network coupled with genetic algorithm. Procedia CIRP
**2015**, 31, 453–458. [Google Scholar] [CrossRef] [Green Version] - Oneto, L.; Bunte, K.; Schleif, F.-M. Advances in artificial neural networks, machine learning and computational intelligence: Selected papers from the 26th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN 2018). Neurocomputing
**2019**, 342, 1–5. [Google Scholar] [CrossRef] - Pontes, F.J.; Amorim, G.F.; Balestrassi, P.P.; Paiva, A.P.; Ferreira, J.R. Design of experiments and focused grid search for neural network parameter optimization. Neurocomputing
**2016**, 186, 22–34. [Google Scholar] [CrossRef] - Lasheras, F.S.; Vilán, J.V.; Nieto, P.G.; del Coz Díaz, J.J. The use of design of experiments to improve a neural network model in order to predict the thickness of the chromium layer in a hard chromium plating process. Math. Comput. Model.
**2010**, 52, 1169–1176. [Google Scholar] [CrossRef] - Pontes, F.J.; Silva, M.B.; Ferreira, J.R.; Paiva, A.P.D.; Balestrassi, P.P.; Schönhorst, G.B. A DOE based approach for the design of RBF artificial neural networks applied to prediction of surface roughness in AISI 52100 hardened steel turning. J. Braz. Soc. Mech. Sci. Eng.
**2010**, 32, 503–510. [Google Scholar] [CrossRef] - Kumar, D.; Chandna, P.; Pal, M. Efficient Optimization of Neural Network using Taguchi-grey Relational Analysis with Signal-to-Noise Ratio Approach for 2.5 D End Milling Process. Am. J. Mech. Eng. Autom.
**2018**, 5, 30. [Google Scholar] - Morales Tamayo, Y.; Beltrán Reyna, R.F.; López Bustamante, R.J.; Zamora Hernández, Y.; López Cedeño, K.; Terán Herrera, H.C. Comparison of two methods for predicting surface roughness in turning stainless steel AISI 316L. Ingeniare Rev. Chil. Ing.
**2018**, 26, 97–105. [Google Scholar] [CrossRef] [Green Version] - Hanief, M.; Wani, M.F. Artificial neural network and regression-based models for prediction of surface roughness during turning of red brass (C23000). J. Mech. Eng. Sci.
**2016**, 10, 1835–1845. [Google Scholar] [CrossRef] - Hanief, M.; Wani, M.F.; Charoo, M.S. Modeling and prediction of cutting forces during the turning of red brass (C23000) using ANN and regression analysis. Eng. Sci. Technol. Int. J.
**2017**, 20, 1220–1226. [Google Scholar] [CrossRef] [Green Version] - Kalidass, S.; Palanisamy, P.; Muthukumaran, V. Prediction of tool wear using regression and artificial neural network models in end milling of AISI 304 austenitic stainless steel. Int. J. Eng. Innov. Technol.
**2012**, 1, 29–35. [Google Scholar] - Khorasani, A.M.; Yazdi, M.R.S.; Safizadeh, M.S. Tool Life Prediction in Face Milling Machining of 7075 Al by Using Artificial Neural Networks (ANN) and Taguchi Design of Experiment (DOE). Int. J. Eng. Technol.
**2011**, 3, 30. [Google Scholar] [CrossRef] [Green Version] - Sahoo, A.; Rout, A.; Das, D. Response surface and artificial neural network prediction model and optimization for surface roughness in machining. Int. J. Ind. Eng. Comput.
**2015**, 6, 229–240. [Google Scholar] [CrossRef] - Pontes, F.J.; Ferreira, J.R.; Silva, M.B.; Paiva, A.P.; Balestrassi, P.P. Artificial neural networks for machining processes surface roughness modeling. Int. J. Adv. Manuf. Technol.
**2010**, 49, 879–902. [Google Scholar] [CrossRef] - Kechagias, J.; Tsiolikas, A.; Asteris, P.; Vaxevanidis, N. Optimizing ANN performance using DOE: Application on turning of a titanium alloy. MATEC Web Conf.
**2018**, 178, 1017. [Google Scholar] [CrossRef] - Abiodun, O.I.; Jantan, A.; Omolara, A.E.; Dada, K.V.; Mohamed, N.A.; Arshad, H. State-of-the-art in artificial neural network applications: A survey. Heliyon
**2018**, 4, e938. [Google Scholar] [CrossRef] [Green Version] - Karkalos, N.E.; Galanis, N.I.; Markopoulos, A.P. Surface roughness prediction for the milling of Ti–6Al–4V ELI alloy with the use of statistical and soft computing techniques. Measurement
**2016**, 90, 25–35. [Google Scholar] [CrossRef] - Calado, V.; Montgomery, D.C. Planejamento de Experimentos Usando o Statistica; Editora E-papers: Rio de Janeiro, Brazil, 2003; ISBN 978-85-8792-283-0. [Google Scholar]
- Unda, A.G.R.; Lin, V.F.C.; De Godoy, G.C.D. Metodologia para a aplicação da análise topográfica ao estudo de processos de superfície. Matéria
**2007**, 12, 589–596. [Google Scholar] [CrossRef] [Green Version] - Dong, W.P.; Sullivan, P.J.; Stout, K.J. Comprehensive study of parameters for characterizing three-dimensional surface topography III: Parameters for characterizing amplitude and some functional properties. Wear
**1994**, 178, 29–43. [Google Scholar] [CrossRef] - Rodrigues, A.R.; Manarelli, F.H.; De Queiroz, M.C.G.P.; Matsumoto, H.; Yamakami, W.J. Rugosidade e microestrutura da peça no fresamento do aço vp100 para moldes. In Proceedings of the 7th Brazilian Congress on Manufacturing Engineering, Penedo, Itatiaia, RJ, Brazil, 15–19 April 2013. [Google Scholar]
- Oosthuizen, G.A.; Nunco, K.; Conradie, P.J.T.; Dimitrov, D.M. The effect of cutting parameters on surface integrity in milling Ti6Al4V. S. Afr. J. Ind. Eng.
**2016**, 27, 115–123. [Google Scholar] [CrossRef] [Green Version] - Polishetty, A.; Goldberg, M.; Littlefair, G.; Puttaraju, M.; Patil, P.; Kalra, A. A preliminary assessment of machinability of titanium alloy Ti6Al4V during thin wall machining using trochoidal milling. Procedia Eng.
**2014**, 97, 357–364. [Google Scholar] [CrossRef] [Green Version]

**Figure 4.**MQL valve circuit. (1) oil inlet; (2) return hose; (3) regulating valve; (4) check valve; (5) hydraulic equal cross coupling—air + oil mixture; (6) inlet compressed air; (7) control valve for compressed air.

**Figure 9.**Roughness measurement procedure. (

**a**) Taylor Hobson/Talysurf CCI Lite white light interferometer (

**b**) Position and application area. (

**c**) Measurement being performed. (

**d**) Milled 3D surface topography.

**Figure 11.**Sq, Ssk, Sku minimum and maximum milled surface topography parameter values measured. (

**a**) S

_{q}= 0.39 µm; (

**b**) S

_{q}= 1.57 µm; (

**c**) S

_{sk}= −1.05 and S

_{ku}= 15.30; (

**d**) S

_{sk}= 0.49 µm; (

**e**) S

_{sk}= 2.68 µm

**Figure 14.**Pareto charts for oil machining condition. (

**a**) Force F

_{c}. (

**b**) Force F

_{f}. (

**c**) Torque M

_{z}. (

**d**) Roughness S

_{q}. (

**e**) Skewness of height distribution.

**Figure 15.**Response surfaces for the oil lubricated condition. (

**a**) Cutting force F

_{c}(a

_{p}× f). (

**b**) Feed force F

_{f}(a

_{p}× f). (

**c**) Torque M

_{z}(a

_{p}× f). (

**d**) Skewness (f × v

_{c}).

**Figure 16.**Pareto graphs for machining condition with graphite. (

**a**) Cutting force F

_{c}. (

**b**) Feed force F

_{f}. (

**c**) Torque M

_{z}. (

**d**) Roughness S

_{q}.

**Figure 17.**Response surfaces for the lubrication condition with graphite. (

**a**) Cutting force F

_{c}(a

_{p}× f). (

**b**) Feed force F

_{f}(a

_{p}× f). (

**c**) Torque M

_{z}(a

_{p}× f). (

**d**) Roughness S

_{q}(a

_{p}× f).

**Figure 18.**Machined surface topography. Isometric views and contour maps—dry strategy. (

**a**)v

_{c}= 80 m/min, a

_{p}= 0.5 mm, f = 0.06 mm/rev.; (

**b**) v

_{c}= 100 m/min, a

_{p}= 1.0 mm, f = 0.1 mm/rev.

**Figure 19.**Machined surface topography. Isometric views and contour maps—oil strategy. (

**a**)v

_{c}= 80 m/min, a

_{p}= 0.5 mm, f = 0.06 mm/rev.; (

**b**) v

_{c}= 100 m/min, a

_{p}= 1.0 mm, f = 0.1 mm/rev

**Figure 20.**Machined surface topography. Isometric views and contour maps—oil + graphite strategy. (

**a**) v

_{c}= 80 m/min, a

_{p}= 0.5 mm, f = 0.06 mm/rev.; (

**b**) v

_{c}= 100 m/min, a

_{p}= 1.0 mm, f = 0.1 mm/rev.

**Figure 22.**Differences between pairs of averages. (

**a**) Cutting force F

_{c}(

**b**) Feed force F

_{f}. (

**c**) Penetration Force F

_{p}. (

**d**) Torque M

_{z}. (

**e**) Roughness S

_{q}. (

**f**) Skewness. (

**g**) Kurtosis.

**Table 1.**Chemical composition of Ti-6Al-4V (provided by VINER Brasil Tecnologia Ltda., Sao Paulo, Brazil).

Composition | Ti | Al | V | Fe | H | N | O | C | Y |
---|---|---|---|---|---|---|---|---|---|

Data (%) | Balance | 6.49–6.56 | 4.03–4.14 | 0.16–0.19 | 0.002–0.003 | 0.003–0.004 | 0.192–0.196 | 0.024–0.028 | <0.001 |

Tests | v_{c} (m/min) | f (mm/rev) | a_{p} (mm) |
---|---|---|---|

1 | 80 | 0.06 | 0.5 |

2 | 100 | 0.06 | 0.5 |

3 | 80 | 0.1 | 0.5 |

4 | 100 | 0.1 | 0.5 |

5 | 80 | 0.06 | 1.0 |

6 | 100 | 0.06 | 1.0 |

7 | 80 | 0.1 | 1.0 |

8 | 100 | 0.1 | 1.0 |

9 | 90 | 0.08 | 0.75 |

10 | 90 | 0.08 | 0.75 |

Strategy | Cooling and Lubrication Condition |
---|---|

1 | Dry (only compressed air) |

2 | Oil (minimum quantity lubrication (MQL)) |

3 | Oil + Graphite (MQL) |

Parameters | Properties |
---|---|

Aspect | Clear green viscous liquid |

Scent | Characteristic, light |

Density at 25 °C (g/mL) | 0.88–0.91 |

Corrosion test on iron chips | No corrosion after 2 h |

Viscosity centistokes, 25 °C | 20–35 |

Acidity index | 10–20 |

Train, Test and Validation—ANNs | Variables |
---|---|

Continuous inputs | v_{c}, f, a_{p} |

Continuous targets | F_{c}, F_{f}, F_{p}, M_{z}, S_{q}, S_{sk}, S_{ku} |

Train sample size (%) | 70 |

Test sample size (%) | 20 |

Validation sample size (%) | 10 |

Variable | Mean | Minimum | Maximum | Std. Dev. |
---|---|---|---|---|

S_{q} (µm) | 0.69 | 0.39 | 1.57 | 0.37 |

S_{sk} | −0.14 | −1.05 | 0.49 | 0.26 |

S_{ku} | 4.35 | 2.68 | 15.30 | 2.22 |

Dry | v_{c} (m/min) | f (mm/rev) | a_{p} (mm) | F_{c} (N) | F_{f} (N) | F_{p} (N) | M_{z} (Nm) | S_{q} (µm) | S_{sk} | S_{ku} |

1 | 80 | 0.06 | 0.5 | 258.97 | 71.00 | 52.04 | 0.62 | 0.57 | −0.13 | 3.95 |

2 | 100 | 0.06 | 0.5 | 228.50 | 108.00 | 60.96 | 0.68 | 0.80 | −0.17 | 2.68 |

3 | 80 | 0.1 | 0.5 | 364.12 | 112.99 | 93.74 | 1.03 | 0.82 | −0.20 | 3.06 |

4 | 100 | 0.1 | 0.5 | 427.50 | 109.00 | 113.53 | 0.97 | 1.01 | −0.29 | 3.34 |

5 | 80 | 0.06 | 1.0 | 371.80 | 94.73 | 63.35 | 1.01 | 1.13 | −0.06 | 3.18 |

6 | 100 | 0.06 | 1.0 | 396.81 | 100.50 | 70.97 | 0.98 | 1.31 | 0.09 | 3.65 |

7 | 80 | 0.1 | 1.0 | 510.50 | 172.62 | 119.37 | 1.44 | 1.46 | 0.04 | 3.07 |

8 | 100 | 0.1 | 1.0 | 531.50 | 139.40 | 103.14 | 1.45 | 1.14 | −0.05 | 3.60 |

9 | 90 | 0.08 | 0.75 | 570.50 | 164.42 | 203.95 | 1.14 | 1.51 | −0.09 | 4.30 |

10 | 90 | 0.08 | 0.75 | 617.50 | 207.94 | 207.94 | 1.31 | 1.57 | 0.36 | 5.39 |

Oil | v_{c} (m/min) | f (mm/rev) | a_{p} (mm) | F_{c} (N) | F_{f} (N) | F_{p} (N) | M_{z} (Nm) | S_{q} (µm) | S_{sk} | S_{ku} |

1 | 80 | 0.06 | 0.5 | 117.00 | 216.50 | 84.80 | 0.59 | 0.68 | 0.49 | 5.71 |

2 | 100 | 0.06 | 0.5 | 89.00 | 260.00 | 95.20 | 0.64 | 0.46 | −0.28 | 4.08 |

3 | 80 | 0.1 | 0.5 | 107.00 | 285.00 | 110.00 | 0.95 | 0.44 | −0.17 | 3.62 |

4 | 100 | 0.1 | 0.5 | 116.00 | 310.00 | 113.00 | 0.93 | 0.45 | −0.32 | 4.26 |

5 | 80 | 0.06 | 1.0 | 154.00 | 365.00 | 99.40 | 1.01 | 0.47 | −0.01 | 4.37 |

6 | 100 | 0.06 | 1.0 | 116.50 | 315.00 | 96.00 | 1.03 | 0.46 | −0.17 | 4.13 |

7 | 80 | 0.1 | 1.0 | 195.00 | 412.50 | 124.00 | 1.25 | 0.57 | −0.24 | 3.54 |

8 | 100 | 0.1 | 1.0 | 182.50 | 435.00 | 129.00 | 1.30 | 0.60 | −0.17 | 3.32 |

9 | 90 | 0.08 | 0.75 | 125.50 | 330.00 | 137.60 | 0.88 | 0.48 | −0.19 | 4.61 |

10 | 90 | 0.08 | 0.75 | 119.00 | 335.00 | 125.00 | 0.91 | 0.46 | −0.08 | 3.59 |

Oil + Graphite | v_{c} (m/min) | f (mm/rev) | a_{p} (mm) | F_{c} (N) | F_{f} (N) | F_{p} (N) | M_{z} (Nm) | S_{q} (µm) | S_{sk} | S_{ku} |

1 | 80 | 0.06 | 0.5 | 80.00 | 192.50 | 52.00 | 0.55 | 0.45 | −1.05 | 15.30 |

2 | 100 | 0.06 | 0.5 | 84.00 | 217.50 | 63.00 | 0.63 | 0.39 | 0.00 | 3.28 |

3 | 80 | 0.1 | 0.5 | 127.50 | 242.50 | 71.00 | 0.77 | 0.45 | 0.01 | 3.76 |

4 | 100 | 0.1 | 0.5 | 115.00 | 255.00 | 81.00 | 0.78 | 0.44 | −0.27 | 4.11 |

5 | 80 | 0.06 | 1.0 | 127.50 | 375.00 | 77.00 | 1.04 | 0.41 | −0.48 | 6.17 |

6 | 100 | 0.06 | 1.0 | 142.50 | 410.00 | 88.00 | 1.02 | 0.40 | −0.23 | 4.06 |

7 | 80 | 0.1 | 1.0 | 175.00 | 485.00 | 112.00 | 1.34 | 0.56 | −0.06 | 3.26 |

8 | 100 | 0.1 | 1.0 | 190.00 | 465.00 | 121.00 | 1.36 | 0.58 | −0.13 | 3.33 |

9 | 90 | 0.08 | 0.75 | 130.00 | 410.00 | 124.00 | 1.08 | 0.44 | −0.30 | 4.73 |

10 | 90 | 0.08 | 0.75 | 140.00 | 395.00 | 116.00 | 1.06 | 0.40 | −0.34 | 5.11 |

Dry | MathematicalFunction |

F_{c} | = 253.250 − 3.99675 × v_{c} − 867.125 × f + 56.15 × f × v_{c} + 0.655 × a_{p} × v_{c} 768.999 × a_{p} × f + 201.2475 |

F_{f} | = −451.195 + 6.336 × v_{c} + 4113.75 × f − 49.990 × f × v_{c} − 3.023 × a_{p} × v_{c} + 1845.0 × a_{p} × f + 133.2 |

F_{p} | = −212.050 + 2.299 × v_{c} + 1984.197 × f − 8.112 × f × v_{c} − 1.865 × a_{p} × v_{c} − 151.680 × a_{p} × f + 148.705 |

M_{z} | = −0.435 + 0.0045 × v_{c} + 10.75 × f − 0.05 × f × v_{c} − 0.0009 × a_{p} × v_{c} + 5.0 × a_{p} × f + 0.36 |

S_{q} | = −4.94 + 0.05 × v_{c} + 39.99 × f −0.34 × f × v_{c} − 0.028 × a_{p} × v_{c} − 7.4 × a_{p} × f + 3.01 |

S_{sk} | = −0.59 + 0.006 × v_{c} + 12.475 × f − 0.185 × f × v_{c} + 0.009 × a_{p} × v_{c} + 3.7 × a_{p} × f − 0.595 |

S_{ku} | = 17.67 − 0.15 × v_{c} − 93.925 × f + 1.00125 × v_{c} × f + 0.099 × a_{p} × v_{c} + 1.80 × a_{p} × f − 6.64 |

Oil | Mathematical Function |

F_{c} | = 375.025 − 2.8 × v_{c} − 4400 × f + 38.750 × f × v_{c} − 1.550 × a_{p} × v_{c} + 2250.0 × a_{p} × f + 51.75 |

F_{f} | = −41.225 + 1.412 × v_{c} − 2168.750 × f + 33.750 × f × v_{c} − 4.800 × a_{p} × v_{c} + 1225.0 × a_{p} × f + 421. |

F_{p} | = 13.775 + 0.580 × v_{c} + 298.750 × f + 0.625 × f × v_{c} − 0.590 × a_{p} × v_{c} + 365.0 × a_{p} × f + 34.95 |

M_{z} | = −0.554 + 0.0017 × v_{c} + 12.125 × f − 0.0250 × f × v_{c} + 0.002 × a_{p} × v_{c} − 3.5 × a_{p} × f + 0.63 |

S_{q} | = 3.48 − 0.025 × v_{c} − 24.69 × f + 0.168 × f × v_{c} + 0.012 × a_{p} × v_{c} + 12.625 × a_{p} × f − 1.55 |

S_{sk} | = 9.01 − 0.087 × v_{c} − 63.04 × f + 0.541 × f × v_{c} + 0.042 × a_{p} × v_{c} + 11.525 × a_{p} × f − 3.627 |

S_{ku} | =20.85 − 0.15 × v_{c} − 155.44 × f + 1.43 × f × v_{c} + 0.03 × a_{p} × v_{c} + 6.60 × a_{p} × f − 3.06 |

Oil + Graphite | Mathematical Function |

F_{c} | = 14.96 − 0.350 × v_{c} + 1703.125 × f − 10.312 × f × v_{c} + 1.925 × a_{p} × v_{c} + 412.50 × a_{p} × f − 69.0 |

F_{f} | = −414.31 + 4.875 × v_{c} + 3921.875 × f − 42.187 × f × v_{c} − 1.125 × a_{p} × v_{c} + 1937.5 × a_{p} × f + 270.0 |

F_{p} | = −27.625 + 0.7 × v_{c}+243.75 × f − 1.875 × f × v_{c} − 0.05 × a_{p} × v_{c} + 775.0× a_{p} × f + 6.0 |

M_{z} | = −0.438 + 0.006 × v_{c} + 2.937 × f − 0.019 × f × v_{c} − 0.004 × a_{p} × v_{c} + 6.75 × a_{p} × f + 0.66 |

S_{q} | = 1.191 − 0.006 × v_{c} − 6.425 × f + 0.036 × f × v_{c} + 0.0036 × a_{p} × v_{c} + 7.25 × a_{p} × f − 0.59475 |

S_{sk} | = −12.026 + 0.117 × v_{c} + 106.056×f − 1.03 × f × v_{c} − 0.03 × a_{p} × v_{c} − 6.67 × a_{p} × f + 2.589 |

S_{ku} | = 140.035 − 1.26 × v_{c} − 1039.62 × f + 9.081 × f × v_{c} + 0.48 × a_{p} × v_{c} + 176.87 × a_{p} × f − 46.74 |

Trial | v_{c} (m/min) | f (mm/rev) | a_{p} (mm) | %Confidence |
---|---|---|---|---|

Dry | 90.0 | 0.06 | 0.5 | 54.0 |

Oil | 100.0 | 0.07 | 0.5 | 66.0 |

Oil + Graphite | 100.0 | 0.06 | 0.5 | 69.0 |

Dry | v_{c} (m/min) | f (mm/rev) | a_{p} (mm) | F_{c} (N) | F_{f} (N) | F_{p} (N) | M_{z} (Nm) | S_{q}(µm) | S_{sk} | S_{ku} |

6 | 100 | 0.06 | 1.0 | 396.81 | 100.50 | 70.97 | 0.98 | 1.31 | 0.09 | 3.65 |

7 | 80 | 0.1 | 1.0 | 510.50 | 172.62 | 119.37 | 1.44 | 1.46 | 0.04 | 3.07 |

9 | 90 | 0.08 | 0.75 | 570.50 | 164.42 | 203.95 | 1.14 | 1.51 | −0.09 | 4.30 |

Oil | v_{c} (m/min) | f (mm/rev) | a_{p} (mm) | F_{c} (N) | F_{f} (N) | F_{p} (N) | M_{z} (Nm) | S_{q}(µm) | S_{sk} | S_{ku} |

1 | 80 | 0.06 | 0.5 | 117.00 | 216.50 | 84.80 | 0.59 | 0.68 | 0.49 | 5.71 |

4 | 100 | 0.1 | 0.5 | 116.00 | 310.00 | 113.00 | 0.93 | 0.45 | −0.32 | 4.26 |

9 | 90 | 0.08 | 0.75 | 125.50 | 330.00 | 137.60 | 0.88 | 0.48 | −0.19 | 4.61 |

Oil + Graphite | v_{c} (m/min) | f (mm/rev) | a_{p} (mm) | F_{c} (N) | F_{f} (N) | F_{p} (N) | M_{z} (Nm) | S_{q} (µm) | S_{sk} | S_{ku} |

2 | 100 | 0.06 | 0.5 | 84.00 | 217.50 | 63.00 | 0.63 | 0.40 | 0.00 | 3.28 |

7 | 80 | 0.1 | 1.0 | 175.00 | 485.00 | 112.00 | 1.34 | 0.56 | −0.06 | 3.26 |

9 | 90 | 0.08 | 0.75 | 130.00 | 410.00 | 124.00 | 1.08 | 0.44 | −0.30 | 4.73 |

Summary | Dry | Oil | Oil + Graphite |
---|---|---|---|

Index | 4 | 2 | 1 |

Network Name | MLP 3-8-7 | MLP 3-24-7 | MLP 3-16-7 |

Training | 1.0 | 1.0 | 1.0 |

Test | 1.0 | 1.0 | 1.0 |

Validation | 1.0 | 1.0 | 1.0 |

Training error | 0.0 | 0.0 | 0.0 |

Test error | 0.0 | 0.0 | 0.0 |

Validation error | 0.0 | 0.0 | 0.0 |

Training algorithm | BFGS 237 | BFGS 128 | BFGS 68 |

Error function | SOS | SOS | SOS |

Hidden activation | Tanh | Tanh | Exponential |

Output activation | Identity | Identity | Identity |

Dry | F_{c} | F_{c}_Output | F_{f} | F_{f}_Output | F_{p} | F_{p}_Output | M_{z} | M_{z}_Output |

1 | 396.81 | 385.77 | 100.50 | 130.93 | 70.97 | 91.13 | 0.98 | 0.98 |

2 | 510.50 | 500.35 | 172.62 | 95.27 | 119.37 | 81.32 | 1.44 | 1.36 |

3 | 570.50 | 617.46 | 164.42 | 207.93 | 203.95 | 207.95 | 1.14 | 1.31 |

Oil | F_{c} | F_{c}_Output | F_{f} | F_{f}_Output | F_{p} | F_{p}_Output | M_{z} | M_{z}_Output |

1 | 117.00 | 81.04 | 216.50 | 255.59 | 84.80 | 102.08 | 0.59 | 0.59 |

2 | 116.00 | 90.17 | 310.00 | 298.07 | 113.00 | 123.28 | 0.93 | 0.93 |

3 | 125.50 | 119.00 | 330.00 | 334.99 | 137.60 | 124.99 | 0.88 | 0.91 |

Oil + Graphite | F_{c} | F_{c}_Output | F_{f} | F_{f}_Output | F_{p} | F_{p}_Output | M_{z} | M_{z}_Output |

1 | 84.00 | 102.16 | 217.50 | 296.71 | 63.00 | 90.20 | 0.63 | 0.75 |

2 | 175.00 | 199.59 | 485.00 | 533.07 | 112.00 | 154.14 | 1.34 | 1.51 |

3 | 130.00 | 139.99 | 410.00 | 394.99 | 124.00 | 115.99 | 1.08 | 1.06 |

Dry | S_{q} | S_{q}_Output | S_{sk} | S_{sk}_Output | S_{ku} | S_{ku}_Output |

1 | 1.31 | 1.46 | 0.09 | −0.03 | 3.65 | 2.81 |

2 | 1.46 | 0.93 | 0.04 | −0.11 | 3.07 | 3.98 |

3 | 1.51 | 1.57 | −0.09 | 0.35 | 4.30 | 5.39 |

Oil | S_{q} | S_{q}_Output | S_{sk} | S_{sk}_Output | S_{ku} | S_{ku}_Output |

1 | 0.68 | 0.37 | 0.49 | −0.04 | 5.71 | 4.17 |

2 | 0.45 | 0.46 | −0.32 | −0.12 | 4.26 | 3.33 |

3 | 0.48 | 0.46 | −0.19 | −0.07 | 4.61 | 3.58 |

Oil + Graphite | S_{q} | S_{q}_Output | S_{sk} | S_{sk}_Output | S_{ku} | S_{ku}_Output |

1 | 0.40 | 0.35 | 0.00 | −0.55 | 3.28 | 7.20 |

2 | 0.56 | 0.52 | −0.06 | −0.01 | 3.26 | 2.14 |

3 | 0.44 | 0.41 | −0.30 | −0.33 | 4.73 | 5.10 |

© 2020 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 (http://creativecommons.org/licenses/by/4.0/).

## Share and Cite

**MDPI and ACS Style**

Paschoalinoto, N.W.; Batalha, G.F.; Bordinassi, E.C.; Ferrer, J.A.G.; Filho, A.F.d.L.; Ribeiro, G.d.L.X.; Cardoso, C.
MQL Strategies Applied in Ti-6Al-4V Alloy Milling—Comparative Analysis between Experimental Design and Artificial Neural Networks. *Materials* **2020**, *13*, 3828.
https://doi.org/10.3390/ma13173828

**AMA Style**

Paschoalinoto NW, Batalha GF, Bordinassi EC, Ferrer JAG, Filho AFdL, Ribeiro GdLX, Cardoso C.
MQL Strategies Applied in Ti-6Al-4V Alloy Milling—Comparative Analysis between Experimental Design and Artificial Neural Networks. *Materials*. 2020; 13(17):3828.
https://doi.org/10.3390/ma13173828

**Chicago/Turabian Style**

Paschoalinoto, Nelson Wilson, Gilmar Ferreira Batalha, Ed Claudio Bordinassi, Jorge Antonio Giles Ferrer, Aderval Ferreira de Lima Filho, Gleicy de L. X. Ribeiro, and Cristiano Cardoso.
2020. "MQL Strategies Applied in Ti-6Al-4V Alloy Milling—Comparative Analysis between Experimental Design and Artificial Neural Networks" *Materials* 13, no. 17: 3828.
https://doi.org/10.3390/ma13173828