A multivariate normal boundary intersection PCA-based approach to reduce dimensionality in optimization problems for LBM process
- 29 Downloads
Laser beam machining (LBM) is a promising manufacturing process that exhibits several desirable quality characteristics. Given a large number of objective functions, the level of complexity increases in an optimization problem. Therefore, this study presents a multivariate application of the normal boundary intersection (NBI) method to reduce dimensionality in optimization problems of the LBM process. Such an approach is capable of exploring the entire solution space with only a small number of Pareto points, and generating equispaced frontiers based on the objective functions written in terms of principal component scores. Hence, a design of experiment with three input parameters and six quality characteristics was undertaken to appropriately model the process requirements applied to AISI 314S steel. The results indicate that the proposed methodology is capable of achieving optimal values for interest characteristics. In addition, this approach shows a reduction in computational effort of approximately 91.89% (from 259 to 21 subproblems) in obtaining the best solution for rough operation.
KeywordsLaser beam machining Principal component analysis Normal boundary intersection Material removal rate Roughness
The authors gratefully acknowledge the IDMEC/UL, Associated Laboratory for Energy, Transports and Aeronautics (LAETA), IST/University of Lisbon, the SMART2 program from ERASMUS MUNDUS, FAPEMIG, CAPES, CNPq and IFSULDEMINAS.
- 4.Saghatforoush A, Monjezi M, Shirani Faradonbeh R, Jahed Armaghani D (2016) Combination of neural network and ant colony optimization algorithms for prediction and optimization of flyrock and back-break induced by blasting. Eng Comput 32:255–266. https://doi.org/10.1007/s00366-015-0415-0 CrossRefGoogle Scholar
- 18.Mistry V, James S (2017) Finite element analysis and simulation of liquid-assisted laser beam machining process. Int J Adv Manuf Technol 2325–2331. https://doi.org/10.1007/s00170-017-1009-3
- 26.Almeida FA, Gomes GF, Sabioni RC, Gomes JHF, Paula VR, Paiva AP et al (2018) A gage study applied in shear test to indentify variation causes from a resistance spot welding measurement system. Stroj Vestnik/J Mech Eng 63:621–631Google Scholar
- 31.Prakash C, Kansal HK, Pabla BS, Puri S (2016) Multi-objective optimization of powder mixed electric discharge machining parame- ters for fabrication of biocompatible layer on β -Ti alloy using NSGA-II coupled with Taguchi based response surface methodology †. J Mech Sci Technol 30:4195–4204. https://doi.org/10.1007/s12206-016-0831-0 CrossRefGoogle Scholar
- 32.Costa DMD, Belinato G, Brito TG et al (2016) Weighted principal component analysis combined with Taguchi’s Signal-to-noise ratio to the multiobjective optimization of dry end milling process: a comparative study. J Brazilian Soc Mech Sci Eng. https://doi.org/10.1007/s40430-016-0614-7 CrossRefGoogle Scholar
- 34.Montgomery DC (2016) Design and analysis of experiments, 9th edn. Wiley, New YorkGoogle Scholar
- 41.Cukor G, Jurković Z, Sekulić M (2011) Rotatable central composite design of experiments versus Taguchi method in the optimization of turning. Metalurgija 50:17–20Google Scholar
- 46.Brito TG, Paiva AP, Ferreira JR et al (2014) A normal boundary intersection approach to multiresponse robust optimization of the surface roughness in end milling process with combined arrays. Precis Eng 38:628–638. https://doi.org/10.1016/j.precisioneng.2014.02.013 CrossRefGoogle Scholar