Global optimization of modular process flowsheets

This paper presents an approach for applying rigorous global optimization techniques to modular process design approaches. Modular flowsheeting systems are very popular in process engineering and some use local optimization methods. However, even very simple process engineering problems can give rise to nonlinear, nonconvex optimizations with multiple local optima. In these circumstances, local optimization approaches cannot guarantee that the global optima will be found. The paper introduces an approach to process simulation that allows construction of flowsheets in modular approaches that can then be optimized using interval global optimization methods. The modular flowsheets are constructed with generic unit modules that can provide interval bounds, linear bounds, derivatives, and derivative bounds using extended arithmetic types. Extended types are introduced to be used by the generic unit modules. Optimization is achieved by application of global optimization algorithms to the modular flowsheets built from these general models. Using interval analysis and automatic differentiation as the arithmetic types, lower bounding information is used in a branch and bound framework.