638.APPLICATION OF NON-STANDARD DOE AND ITS VALIDATION IN DETERMINING NOMINAL PARAMETERS IN PRODUCTION PROCESS
Keywords:design of experiments, non-standard fraction-factorial design, injection molding, model validation
AbstractA structured approach is fundamental in designing a complex multivariable process, while achiev-ing specified product quality. Nominal values of process parameters of an injection molding process are defined by implementing DOE methodology. Optimisation of experimental phase is achieved by progressive information acquir-ing concerning influential input factors and DOE design. Hence, most influential machine process parameters are varied using a non-standard fraction-factorial design. A linear regression model with included elements of second order inter-action is defined based on obtained data. Additional testing of its validation is in order before reaching a final conclu-sion. Firstly, model significance is tested by conducting an ANOVA analysis. Only significant models prove that DOE has been adequately planned and factors which affect the controlled output have been chosen. Finally, DOE is com-pleted by adequacy analysis of the regression model. Lack-of-fit test is chosen to test whether the model is a proper representation of the real process.
MKS Instruments Inc.: The Optimization of Injection Molding Processes Using Design of Experiments, 2012 [Online]. Available: https://www.mksinst.com/mam/celu m/celum_assets/resources/SenselinkQMDOE-ppNote.pdf
Andrisano, A. O., Gherardini, F., Leali, F., Pellicciari, M., Vergnano, A.: Design of simulation experiments method for injection molding process optimization, International Conference Innov. Meth. Prod. Des., Venice, Italy, 2011, pp. 476–486.
Rajalingam, S., Bono, A., Sulaiman, J.: Determining optimal moulding process parameters by two level factorial design with center points, J. B. Sri Lankan Journal of Applied Statistics, 11 (1), 63–88 (2012). DOI: 10.4038/sljastats. v12i0.4968
Abohashima, H. S., Aly, M. F., Mohib, A., Attia, H. A.: Minimization of defects percentage in injection molding process using design of experiment and Тaguchi approach, Journal of Industrial Engineering and Management, 4 (5), 1–6 (2015). DOI: 10.4172/2169-0316.1000179
García, V., Sánchez, J. S., Rodríguez-Picón, L. A., Méndez-González, L. C., Ochoa-Domínguez, H. J.: Using regression models for predicting the product quality in a tubing extrusion process. J. Intell. Manuf., 30, 2535–2544 (2019). DOI: 10.1007/s10845-018-1418-7
Pan, J. J., Mahmoudi, M. R., Baleanu, D., Maleki, M.: On comparing and classifying several independent linear and non-linear regression models with symmetric errors. J.Symmetry, 11 (6), 820–830 (2019), DOI: 10.3390/sym11060820
Kulkarni, S.: Robust Process Development and Scientific Molding, 2nd edition. Theory and Practice. Kanser Publications, Cincinnati, 2017.
Faraway, J. J.: Practical Regression and Anova using R, Chapman and Hall/CRC, 2002.
Montgomery D. C.: Design and Analysis of Experiment, 8th edition, New York, John Wiley & Sons Inc., 2013. ISBN: 978-1118-14692-7
Kanji, G. K.: 100 Statistical Tests, 3rd Edition, SAGE Publications, London, 2006.
Kenyon, G. N.: The Perception of Quality. Springer-Verlag, London, 2015.
Montgomery, D. C.: Introduction to Statistical Quality Control, 6th edition. John Wiley & Sons Inc., Arizona State University, 2009.
Attia, U. M., Alcock, J. R.: Optimizing process conditions for multiple quality criteria in micro-injection moulding, The International Journal of Advanced Manufacturing Technology, 50 (5–8), 533–542 (2010). DOI: 10.1007/s00170-010-2547-0
Mitra, A.: Fundamentals of Quality Control and Improvement, 3rd edition, New York, John Wiley & Sons Inc., Chapter 3: “Statistical Process Control”, 2008, pp. 263–288. DOI: 10.1002/9781118491645