Optimal Molecular Design of Low-Temperature Organic Fluids under Uncertain Conditions

Abstract

Computer-aided molecular design as a mixed-integer nonlinear programming problem under uncertainty in group contribution parameters has been addressed. A set of new low-temperature organic compounds, for heat recovery purposes, was obtained by solving the mixed-integer nonlinear programming problem with nominal values from a previous work. Monte Carlo simulations with Latin hypercube sampling were carried out to asses the effect of uncertain group contributions on thermo-physical properties. Furthermore, a set-based robust counterpart was formulated by taking into account uncertainty only in linear constraints. The results show that even small uncertainty in group contribution parameters can lead to significant variations in thermo-physical properties of the compounds analyzed. Therefore, it is necessary to consider uncertainty in the Computer-aided molecular design formulation. Solutions of the robust counterpart became more conservative as the uncertainty set size increased, producing organic compounds different from the nominal case.

Process Systems Engineering Perspective on the Design of Materials and Molecules

“…For instance, it is known that for difficult separations, a small error in a separation factor can result in a 50% error in the sizing of a distillation column . There have been some efforts to embed design under uncertainty concepts in CAMPD, ,, but there remain numerous open questions on how uncertainty should be handled within the optimization formulation. Given that the outcome of a CAMPD study often includes a prioritized list of chemical entities which need to be investigated further experimentally, questions arise as to how one should balance generating experimental data to make the underpinning models more reliable with performing experiments on the most promising chemicals.…”

Reservoir Production Prediction Model Based on a Stacked LSTM Network and Transfer Learning

“…From the 10th month, the well was opened and maintained upto the 12th month, the flowing bottom-hole pressure of P1 is 27 000 kPa, and that of P2 is 11 000 kPa. To generate sufficient and diverse data as well as keep the difference between different working systems in the process of generating the database, that is, to make the parameter values of each well under each system evenly distributed, Latin hypercube sampling 21 is selected in this paper. Compared with the pure stratified sampling method, its biggest advantage is that any number of samples can be easily produced.…”