An integrated dimensionality reduction and surrogate optimization approach for plant‐wide chemical process operation

Abstract

With liquefied natural gas becoming increasingly prevalent as a flexible source of energy, the design and optimization of industrial refrigeration cycles becomes even more important. In this article, we propose an integrated surrogate modeling and optimization framework to model and optimize the complex CryoMan Cascade refrigeration cycle. Dimensionality reduction techniques are used to reduce the large number of process decision variables which are subsequently supplied to an array of Gaussian processes, modeling both the process objective as well as feasibility constraints. Through iterative resampling of the rigorous model, this data-driven surrogate is continually refined and subsequently optimized. This approach was not only able to improve on the results of directly optimizing the process flow sheet but also located the set of optimal operating conditions in only 2 h as opposed to the original 3 weeks, facilitating its use in the operational optimization and enhanced process design of large-scale industrial chemical systems.

Comparative design, thermodynamic and techno‐economic analysis of utilizing liquefied natural gas cold energy for hydrogen liquefaction processes

“…The mean function is often defined as a constant of zero for computational simplicity and functional flexibility. 39 The Gaussian distribution is expressed as follows:…”

Bayesian Symbolic Learning to Build Analytical Correlations from Rigorous Process Simulations: Application to CO2 Capture Technologies

“…In the latter, functions with an algebraic form or derivative information might be absent or too costly and noisy to evaluate . Stochastic algorithms, such as genetic algorithms, can be employed in these cases, requiring numerous samplings and iterations; alternatively, derivative-free algorithms can also be used . Here, process flowsheet optimization is treated as a black-box problem because process simulators commonly present intractable gradients .…”

“…This approach could find applications in refrigeration cycles, 87 natural gas liquefaction, 91 supply chain inventory control, 92 carbon capture, 93 process synthesis, 94 pharmaceutical processes, 95 semibatch bioprocesses, 27 and biorefineries, 96 to mention a few in chemical engineering and beyond. On the other hand, the applications are not limited to technology benchmarking, as discussed below.…”