Journal of Quality Technology · 1996 · 372 citations · 11 references
ArchitectureIndustrial EngineeringManufacturing EngineeringDesign OptimizationMulti-criteria Decision MakingOptimizationDerivative-free OptimizationMulti-objective Design OptimizationMulti-objective OptimizationParameter OptimizationProcess OptimizationSurrogate-based OptimizationBondingDesirability FunctionsGradient Method OptimizationIndustrial Process OptimizationManufacturingMulti-response OptimizationResponse OptimizationWire Bonding
Desirability functions are widely used to simultaneously optimize multiple responses, but their original formulation contains non‑differentiable points and treats all responses equally, limiting efficient optimization. The study proposes modified desirability functions that are everywhere differentiable, enabling the use of gradient‑based optimization methods. The authors apply these modified functions to a wire bonding process in semiconductor manufacturing. The functions allow analysts to assign different priorities to responses, providing greater flexibility.
Desirability functions have been used extensively to simultaneously optimize several responses. Since the original formulation of these functions contains non-differentiable points, only search methods can be used to optimize the overall desirability response. Furthermore, all responses are treated as equally important. We present modified desirability functions that are everywhere differentiable so that more efficient gradient-based optimization methods can be used instead. The proposed functions have the extra flexibility of allowing the analyst to assign different priorities among the responses. The methodology is applied to a wire bonding process that occurs in semiconductor manufacturing, an industrial process where multiple responses are common.
11
Response Surfaces: Designs and Analyses
Eric R. Ziegel, André I. Khuri, John A. Cornell · Technometrics · 1997 · 1.5K citations