Robust optimisation of Nd: YLF laser beam micro-drilling process using Bayesian probabilistic approach

Nd: YLF laser beam machining (LBM) process has a great potential to manufacture intricate shaped microproducts with its unique characteristics. Continuous improvement (CI) effort for LBM process is usually realised by response surface methodology, which is an important tool in Design of Six Sigma. However, when determining the optimal machining parameters in CI for LBM process, model parameter uncertainty is typically neglected. Performing worst case analysis in CI, this paper presents a new loss function method that takes model parameter uncertainty into account via Bayesian credible region. Unlike existing CI methods in LBM process, the proposed Bayesian probabilistic approach is based on seemingly unrelated regression which can produce more precise estimations of the model parameters than ordinary least squares in correlated multiple responses problems. An Nd: YLF laser beam micro-drilling process is used to demonstrate the effectiveness of the proposed approach. The comparison results show that micro-holes produced by the proposed approach have better quality than those of existing approaches in terms of robustness and process capability.

[1]  Szu Hui Ng,et al.  Estimation of the mean and variance response surfaces when the means and variances of the noise variables are unknown , 2009 .

[2]  H. Jeffreys.  An invariant form for the prior probability in estimation problems , 1946, Proceedings of the Royal Society of London. Series A. Mathematical and Physical Sciences.

[3]  Byung Rae Cho,et al.  Robust parameter design in embedded high-variability production processes: an alternative approach to mitigating sources of variability , 2013 .

[4]  Chanseok Park,et al.  Determination of the joint confidence region of the optimal operating conditions in robust design by the bootstrap technique , 2012, International Journal of Production Research.

[5]  Douglas C. Montgomery,et al.  Response Surface Designs within a Split-Plot Structure , 2005 .

[6]  Di Xu,et al.  Optimizing settings by accounting for uncontrollable material and environmental variables , 2006 .

[7]  Vinod Yadava,et al.  Multi-objective optimization of Nd:YAG laser cutting of nickel-based superalloy sheet using orthogonal array with principal component analysis , 2008 .

[8]  R. Venkata Rao,et al.  Optimization of modern machining processes using advanced optimization techniques: a review , 2014 .

[9]  Byung Rae Cho,et al.  Development of a highly efficient and resistant robust design , 2007 .

[10]  Dennis K. J. Lin,et al.  Optimization of multiple responses considering both location and dispersion effects , 2006, Eur. J. Oper. Res..

[11]  Jai-Hyun Byun,et al.  An interval approach to robust design with parameter uncertainty , 2016 .

[12]  Joseph J. Pignatiello,et al.  STRATEGIES FOR ROBUST MULTIRESPONSE QUALITY ENGINEERING , 1993 .

[13]  T. Kim,et al.  Optimization of welding parameters for resistance spot welding of TRIP steel with response surface methodology , 2002 .

[14]  Edgar Santos-Fernández,et al.  MPCI: An R Package for Computing Multivariate Process Capability Indices , 2012 .

[15]  Saeed Maghsoodloo,et al.  Quadratic loss functions and signal-to-noise ratios for a bivariate response , 2001 .

[16]  Vinod Yadava,et al.  Laser beam machining—A review , 2008 .

[17]  G. Geoffrey Vining,et al.  A Compromise Approach to Multiresponse Optimization , 1998 .

[18]  H. K. Shah,et al.  Response Surface Modeling and Optimization in Multiresponse Experiments Using Seemingly Unrelated Regressions , 2004 .

[19]  Nadia Bhuiyan,et al.  An overview of continuous improvement: from the past to the present , 2005 .

[20]  Jeongbae Kim,et al.  A cautious approach to robust design with model parameter uncertainty , 2011 .

[21]  B. Bhattacharyya,et al.  Modelling and analysis of pulsed Nd:YAG laser machining characteristics during micro-drilling of zirconia (ZrO2) , 2006 .

[22]  Douglas C. Montgomery,et al.  Introduction to Linear Regression Analysis, Solutions Manual (Wiley Series in Probability and Statistics) , 2007 .

[23]  J. Brian Gray,et al.  Introduction to Linear Regression Analysis , 2002, Technometrics.

[24]  Arunanshu S. Kuar,et al.  A parametric study of pulsed Nd:YAG laser micro-drilling of gamma-titanium aluminide , 2010 .

[25]  C. Yang,et al.  Study of optimal laser parameters for cutting QFN packages by Taguchi's matrix method , 2007 .

[26]  Altab Hossain,et al.  A review of modeling and simulation of laser beam machining , 2014 .

[27]  Young-Hyun Ko,et al.  A New Loss Function-Based Method for Multiresponse Optimization , 2005 .

[28]  Darcy P. Mays.  Optimal Central Composite Designs in the Presence of Dispersion Effects , 1999 .

[29]  Arnold Zellner,et al.  A direct Monte Carlo approach for Bayesian analysis of the seemingly unrelated regression model , 2010 .

[30]  S. G. Deshmukh,et al.  A genetic algorithmic approach for optimization of surface roughness prediction model , 2002 .

[31]  Y. Tu,et al.  Closed-loop control in ultrafast laser milling process using laser triggered plasma , 2012 .

[32]  Fred A. Spiring,et al.  A multivariate measure of process capability , 1991 .

[33]  James W. Liddy,et al.  A note on multivariate capability indices , 1993 .

[34]  Arnold Zellner,et al.  BAYESIAN MODELING OF ECONOMIES AND DATA REQUIREMENTS , 2001, Macroeconomic Dynamics.

[35]  Jai-Hyun Byun,et al.  An Integrative Loss Function Approach to Multi‐Response Optimization , 2015, Qual. Reliab. Eng. Int..

[36]  Zhen He,et al.  A robust desirability function method for multi-response surface optimization considering model uncertainty , 2012, Eur. J. Oper. Res..