Abstract
Optimum process parameters combination showed photochemical machining (PCM) is one of the best micromachining process for machining of difficult-to-cut materials. For the machining of Stainless Steel-304, ferric chloride is utilized as an etchant. The aim of this study is to look into the possibilities of using Artificial Neural Networks (ANN) and Regression Analysis (RA) in the Photochemical Machining process and look into the possibilities of using Artificial Neural Networks (ANN) and Regression Analysis (RA) in PCM. A Full factorial (L27) Taguchi method is worked out with machining parameters (temperature, time of etching and etchant concentration) on the predominant micromachining criteria such as Material Removal Rate (MRR), Undercut (Uc) Surface roughness (Ra), and Etch Factor (EF). Based on the observations, Regression models are derived with an acceptable degree of correlation between experimental and regression values. In addition, the ANN model with three inputs and one output node, as well as a hidden layer, in architecture is employed. To predict response parameters, a Feed Forward Back Propagation Network (FFBPN) is used. The network training is carried out to validate the performance of experimental and predicted values of all sets of experiments with Coefficient of Performance (R2) and Mean Square Error (MSE). The findings of the research are critically reviewed and reported.
References
A. David; M. Ler; T. Leong; Increasing utilization efficiency of ferric chloride etchant in industrial photochemical machining, J.Environ. Monit, 1:103-108(1999).
A. M. Zain; H. Haron ;S.M. Qasim; S. Sharif; 2016. Regression and ANN models for estimating minimum value of machining performance. Applied Mathematical Modeling 36:1477–1492(2016).
A.M.David; A.J.A.Heather; Characterization of aqueous ferric chloride etchants used in industrial photochemical machining, Journal of Material Processing Technology, 149, 238-245 (2004). doi:10.1016 /j.jmatprotec. 2004 .0 2.44.
A. R. Saraf; M. Sadaiah; Application of artificial intelligence for the prediction of undercut in photochemical machining, International journal of Mechatronics and Manufacturing systems, 6(2)183-194(2013).https://doi.org/10.1504/IJMMS.2013 .053 829
A.Tehrani; A. Fadaei; E. Imanian; A new etchant chemical machining of St.304, Journal of Material Processing Technology, 149, 404-408 (2004). doi: 10. 1016 /jmatprotec . 2004.02.055.
D. Umbrello; G. Ambrogioa; L. Filice; R. Shivpuri; 2007. An ANN approach for predicting subsurface residual stresses and the desired cutting conditions during hard turning, Journal of Materials Processing Technology, 189:143–152(2007).
D.M.Allen; Photochemical Machining (PCM) of aluminum and its Alloys, Proc. of the 2nd Int. &23rd (AIMTDR) International conference Chennai, 37-44(2008).
D.P. Agrawal; D. N. Kamble; Multi–objective optimization of photochemical machining process based grey relational analysis method. Applied Mechanics and Materials, Transtech publications. Switzerland, 612:77–82 (2014).doi:10.4028/www. Scientific. Net/AMM. 612.77.
D.P.Agrawal; D.N.Kamble; Optimization of photochemical machining process parameters for manufacturing microfluidic channel, Materials and Manufacturing process, 34(1)1-7 (2018). https://doi. org/10. 1080/10426914.2018.1512115.
F. J. Pontes; G. F. Amorim ; P. P. Balestrassi; A. P. Paiva; J.R. Ferreira;2016. Design of experiments and focused grid search for neural network parameter optimization, Neurocomputing, 186:22–34(2016).
H. K. Dave; H.K. Raval; 2010. Modeling of cutting forces as a function of cutting parameters in milling process using regression analysis and artificial neural network. International journal of Machining and Machinability of Materials, 8:198-208(2010).
M. Shukla; P.B.Tambe; Predictive modeling of surface roughness and kerf widths in abrasive water jet cutting of Kevlar composites using neural network, International journal of Machining and Machinability of Materials, 8(1/2):226-244(2010).
N. D. Misal; A . R . Saraf; M. Sadaiah; Experimental investigation of surface topology in photochemical machining of Inconel 718, Materials and Manufacturing Process 32 (15) 1756-1763 (2017).
N. Mehdi; M. Hadzima-Nyarko; K.N. Emmanuel; N. Mohammad;Determination of Natural Frequency of Cantilever Beams Using ANN and Heuristic Search, An International Journal of Applied Artificial Intelligence (32):309-334 (2018), doi. dog/10.1080 / 08839514.2018.1448003.
O.Cakir; Chemical etching of aluminum, Journal of Material Processing Technology, 199:337-340 (2008). doi:10.1016/j.jmatprotec.2007.08.012.
O.Cakir; Chemical etching of Cu-ETP copper, Material Processing Technology, 275-279(2005).
P. Palanisamy; I. Rajendra; S. Shanmugasundaram; Investigations on end-milling process by artificial neural network, finite element analysis and experimental studies, International journal of Machining and Machinability of Materials,1 (2):233-257(2006).
S. Tiryaki; A. Malkoçog˘lu; S.Özs_ahin; S_ükrü; Using artificial neural networks for modeling surface roughness of wood in machining process. Construction and Building Materials (66):329–335(2014).
S.S.Wangikar; P.K. Potawari; M.R.Dev; Effect of process parameters and optimization for Photochemical Machining of Brass and German silver, Materials and Manufacturing Process, 32:1747-1455(2016). doi: 10.1 080/ 104 26914.2017. 1317786.
W.Wei; Z. Di; D.M. Allen; H.J.A.Almond; Non-traditional machining techniques for fabricating metal aerospace filters. Chinese Journal of Aeronautics 21:441-447(2008).
Trion Studio
