Artificial Neural Network Modelling to Optimize Micro-Drilling Parameters of ECDM of Developed Novel Zn/(Ag+Fe)-MMC

[{“box”:0,”content”:”[user_role]

n

n

n

n

n

By

n

n

    n t

  1. n

      [foreach 286]n

      1. n

    n

    n

    Inderjeet Singh Sandhu

    n

    n

      n t

    1. n

    [/foreach]n

    n

    n

      [foreach 286] [if 1175 not_equal=””]n t

    1. Research Scholar,Punjab Engineering College,Punjab,India

      2. n[/if 1175][/foreach]

    n

    n

    n

    n

    n

    Abstract

    nSeveral engineering fields have increased their use of metal matrix composites (MMCs) in the past few years. Due to the increase in composites, the demand for accurate machining has also become important. Specifically, pertaining to biomaterial applications, accuracy factor with desired surface finish is critical. While the near-net shape manufacturing process has advanced, MMCs frequently require post-mould machining to achieve surface quality, and dimensional tolerances. In the present study, a zinc MMC (ZMMC) is fabricated and its mechanical properties are tested. Taguchi’s orthogonal array (L18) is used to determine the machineability of novel Zn/(Ag+Fe)-MMC. As part of the current work, an artificial neural network (ANN) is implemented to model and optimize materials removal rate (MRR), overcut (Oc), and tool wear (TW) during electrochemical discharge machining (ECDM) of novel Zn/(Ag+Fe)-MMC. In order to obtain the response/output values, ECDM microdrilling experiments were conducted under different input control factors such as pulse-on-time, current, pulse-off-time, and feed rate. It identified that 4-16-3-3 was the best architecture for the ANN model. The root mean square error (RMSE) from the optimization model was used to evaluate performance. Based on regression coefficients between experimental and model predictions and the correlation coefficient (R-value) between the ANN predictions and experimental results, the performance of the model was evaluated. The overall R-index was assessed as 0.98722. During the experiment it was found that training, validation and testing results are 98.782%, 98.122% and 98.505%, respectively. ANN modelling and prediction analysis succeeded in replacing conventional method of regression analysis in field of machining hybrid materials.

    n

    n

    n

    Keywords: Artificial neural network, micro-drilling, optimization, metal matrix composite, electrochemical discharge machining, correlation coefficient, prediction

    n[if 424 equals=”Regular Issue”][This article belongs to Journal of Polymer and Composites(jopc)]

    n

    [/if 424][if 424 equals=”Special Issue”][This article belongs to Special Issue under section in Journal of Polymer and Composites(jopc)][/if 424][if 424 equals=”Conference”]This article belongs to Conference Special Issue [/if 424]

    n

    n

    nn

    nn

    Full Text

    nn[if 992 equals=”open access”]https://storage.googleapis.com/journals-stmjournals-com-wp-media-to-gcp-offload/2023/06/772cbad2-s1-s13-artificial-neural-network_ed-1.pdfn[else]nnvar fieldValue = “[user_role]”;nif (fieldValue == ‘indexingbodies’) {ndocument.write(‘‘);ndocument.write(‘https://storage.googleapis.com/journals-stmjournals-com-wp-media-to-gcp-offload/2023/06/772cbad2-s1-s13-artificial-neural-network_ed-1.pdf’);n} else if (fieldValue === ‘administrator’) {ndocument.write(‘‘);ndocument.write(”);n}else if (fieldValue === ‘jopc’) {n document.write(‘‘);n} else {n document.write(‘ ‘);n}nn[/if 992]n

    n[if 379 not_equal=””]n

    Browse Figures

    n

    n

    [foreach 379]n

    n[/foreach]n

    nn

    n

    n[/if 379]n

    n

    References

    n[if 1104 equals=””]n

    1. Dubey AK, Yadava V. Laser beam machining—a review. Int J Machine Tools Manuf. 2008; 48: 609–628.

    2. Notton G, Voyant C, Fouilloy A, Duchaud JL, Nivet MN. Some applications of ANN to solar radiation estimation and forecasting for energy applications. Appl Sci. 2019; 9 (1): 209.

    3. Hassoun MH. Fundamentals of Artificial Neural Networks. Cambridge, MA: MIT Press; 1995.

    4. Gupta N. Artificial neural network. Netw Complex Syst. 2013; 3: 24–28.

    5. Haykin S. Kalman Filtering and Neural Networks. New York: John Wiley & Sons; 2004.

    6. Kechagias JD, Ninikas K, Petousis M, Vidakis N, Vaxevanidis N. An investigation of surface quality characteristics of 3D printed PLA plates cut by CO2 laser using experimental design. Mater Manuf Process. 2021; 36 (13): 1544–1553.

    7. Tamrin K, Nukman Y, Sheikh N. Laser spot welding of thermoplastic and ceramic: an experimental investigation. Mater Manuf Process. 2015; 30: 1138–1145.

    8. Manikandan N, Raju R, Palanisamy D, Binoj J. Optimisation of spark erosion machining process parameters using hybrid grey relational analysis and artificial neural network model. Int J Machining Machinabil Mater. 2020; 22: 1–23.

    9. Kechagias J, Tsiolikas A, Asteris P, Vaxevanidis N. Optimizing ANN performance using DOE: application on turning of a titanium alloy. MATEC Web of Conferences. 2018; 178: Article 01017.

    10. Vidakis N, Petousis M, Vaxevanidis N, Kechagias J. Surface roughness investigation of poly-jet 3D printing. Mathematics. 2020; 8 (10): 1758.

    11. Tsiolikas A, Tsiamitros D, Kitsakis K, Kechagias J, Mastorakis N, Kaminaris SD. Optimization of neural network parameters using Taguchi robust design: application in plasma arc cutting process. In: 2017 Fourth International Conference on Mathematics and Computers in Sciences and in Industry (MCSI), IEEE, Corfu, Greece. 2017, August 24–27. pp. 57–61.

    12. Jankovíc P, Madíc M, Radovanovíc M, Petkovíc D, Mladenovíc S. Optimization of surface roughness from different aspects in high-power CO2 laser cutting of AA5754 aluminum alloy. Arab J Sci Eng. 2019; 44: 10245–10256.

    13. Albugami N, Avrutin E. Dynamic modelling of electrooptically modulated vertical compound cavity surface emitting semiconductor lasers. Optic Quantum Electron. 2017; 49: Article 307.

    14. Yousef BF, Knopf GK, Bordatchev EV, Nikumb SK. Neural network modeling and analysis of the material removal process during laser machining. Int J Adv Manuf Technol. 2003; 22: 41–53.

    15. Fotovvati B, Balasubramanian M, Asadi E. Modeling and optimization approaches of laser-based powder-bed fusion process for Ti-6Al-4V alloy. Coatings. 2020; 10: 1104.

    16. McDonnell MD, Arnaldo D, Pelletier E, Grant-Jacob JA, Praeger M, Karnakis D, Eason RW, Mills B. Machine learning for multi-dimensional optimisation and predictive visualisation of laser machining. J Intell Manuf. 2021; 32: 1471–1483.

    17. Mills B, Grant-Jacob JA. Lasers that learn: the interface of laser machining and machine learning. IET Optoelectron. 2021; 15 (5): 207–224. 18. Zhang Q, Wang Z, Wang B, Ohsawa Y, Hayashi T. Feature extraction of laser machining data by using deep multi-task learning. Information. 2020; 11: 378.

    19. Madíc MJ, Radovanovíc MR. Optimal selection of ANN training and architectural parameters using Taguchi method: a case study. FME Trans. 2011; 39: 79–86.

    20. Kumar D, Gupta AK, Chandna P, Pal M. Optimization of neural network parameters using Grey–Taguchi methodology for manufacturing process applications. Proc Inst Mech Eng Part C: J Mech Eng Sci. 2015; 229: 2651–2664.

    21. Zhou P, Erning JW, Ogle K. Interactions between elemental components during the dealloying of Cu-Zn alloys. Electrochim Acta. 2019; 293: 290–298.

    22. Kecman V. Learning and Soft Computing. Cambridge, MA: MIT Press; 2000. 23. Das S, Bandyopadhyay PP, Chattopadhyay AB. Neural networks-based tool wear monitoring in turning medium carbon steel using a coated carbide tool. J Mater Process Technol. 1997; 63: 187–192.

    nn[/if 1104][if 1104 not_equal=””]n

      [foreach 1102]n t

    1. [if 1106 equals=””], [/if 1106][if 1106 not_equal=””],[/if 1106]

      2. n[/foreach]

    n[/if 1104]

    nn

    nn[if 1114 equals=”Yes”]n

    n[/if 1114]

    n

    n

    Conference Open Access Original Research

    n

    n

    n

    n

    n

    Journal of Polymer and Composites

    n

    [if 344 not_equal=””]ISSN: 2321–2810[/if 344]

    n

    n

    n

    n

    n

    n

    n

    n

    n

    n

    n

    n

    n

    n

    n

    n

    n

    n

    n

    n

    n

    n

    n

    n

    n

    n

    n

    n

    n

    Volume 11
    Issue 01
    Received December 21, 2022
    Accepted March 19, 2023
    Published June 19, 2023

    n

    n

    Views: 483
    n

    [if 1190 not_equal=””]n

    Editor

    n

    [foreach 1188]n

    n[/foreach]

    n[/if 1190] [if 1177 not_equal=””]n

    Reviewer

    n

    [foreach 1176]n

    n[/foreach]

    n[/if 1177]

    n

    nn .post-views{n text-align: center;n }n .ALLreveiwers img,.ALLeditors img{n width: 50px;n height: 50px;n border-radius: 50px;n margin: 10px;n }n .ALLreveiwers,.ALLeditors{n border-bottom:1px solid black;n }n .modaltext{color:white; padding: 0px 30px 0px 30px; text-decoration:none;}n .modaltext:hover{color:black background-color:rgb(255 221 204); color:black;}n .modal-content{ margin-top: 50%;}n Edit n function myfun() {n x=document.getElementById(“editor”);n y=document.getElementById(“down”);n z=document.getElementById(“up”);n if(x.style.display==”none”){n x.style.display=”block”;n }n else {n x.style.display=”none”;n }n if(y.style.display==”none”){n y.style.display=”block”;n }n else {n y.style.display=”none”;n }n if(z.style.display==”none”){n z.style.display=”block”;n }n else {n z.style.display=”none”;n }n }n function myfun2() {n x=document.getElementById(“reviewer”);n y=document.getElementById(“down2”);n z=document.getElementById(“up2″);n if(x.style.display==”none”){n x.style.display=”block”;n }n else {n x.style.display=”none”;n }n if(y.style.display==”none”){n y.style.display=”block”;n }n else {n y.style.display=”none”;n }n if(z.style.display==”none”){n z.style.display=”block”;n }n else {n z.style.display=”none”;n }n }n n table, tr, td{n padding: 10px;n border: none;n }n

    n

    n

    n h2{font-size:16px !important; font-family: ‘Roboto’, Slab !important; line-height: 1.4em;}n h3{font-size:18px !important;font-family: ‘Roboto’, Slab !important;}n h4{font-family: ‘Roboto’, Slab !important;}n a{color:blue; font-size:15px !important;font-family: ‘Roboto’, Slab !important;}n li, p{font-size: 15px !important; font-family: ‘Roboto’, Slab !important; text-align: justify;}n .authdiv img{max-width:17px; max-height:17px;}n .authdiv{display:flex; padding: 1px 2px;”}n n function myFunction2() {n var x = document.getElementById(“browsefigure”);n if (x.style.display === “block”) {n x.style.display = “none”;}n else {x.style.display = “Block”;}}n document.querySelector(“.prevBtn”).addEventListener(“click”, () => {n changeSlides(-1);});n document.querySelector(“.nextBtn”).addEventListener(“click”, () => {n changeSlides(1);});n var slideIndex = 1;n showSlides(slideIndex);n function changeSlides(n) {n showSlides((slideIndex += n));}n function currentSlide(n) {n showSlides((slideIndex = n));}n function showSlides(n) {n var i;n var slides = document.getElementsByClassName(“Slide”);n var dots = document.getElementsByClassName(“Navdot”);n if (n > slides.length) {slideIndex = 1;}n if (n (item.style.display = “none”));n Array.from(dots).forEach(n item => (item.className = item.className.replace(” selected”, “”))n );n slides[slideIndex – 1].style.display = “block”;n dots[slideIndex – 1].className += ” selected”;n }n

    “}]