Feasibility and flexibility analysis of black-box processes Part 1: Surrogate-based feasibility analysis

摘要: Abstract The flexibility index can be used to evaluate process robustness and incorporated into algorithms for optimal design under uncertainty. Traditional approaches evaluating the have focused on explicit enumeration or active set strategies. These necessitate closed form expressions constraints computationally expensive implement problems with a large numbers of constraints. In addition, these methods generally perform best involving convex 1-d quasi feasible regions respect uncertain variables. this article, method analysis systems black-box will introduced. This is second in series two articles related surrogate-based feasibility analysis. first article described strategy building surrogate models represent region processes work, functions are that lack closed-form proposed approach applied stochastic uncertainties by arbitrary distribution functions. Due low computational cost functions, also useful models. demonstrated test nonlinear, nonconvex disjoint regions. It pharmaceutical roller compaction both uniform normal distributions.