Latin Hypercube Sampling Data for Surrogate Model-Based Optimisation of a Batch Distillation Process

Description

The data presented in the two Excel files were used in the paper "Laszlo Hegely, Ömer Faruk Karaman, Marton Tamas Szucs, Peter Lang: Surrogate Model-Based Optimisation of a Batch Distillation Process, 2023". They show the data points in which the simulation of batch distillation process was performed, as well as the simulation results. By the data points, we refer to points in the five-dimensional space of the optimisation variables, which were the reflux ratios of Steps 1-3 of the procedure (R1, R2, R3) and the stopping criteria of Steps 1 and 2 (Cr1 and Cr2). The stopping criteria are the values of tetrahydrofuran concentration in the (instantaneous) distillate when the given step is finished. Selected simulation results, the ones necessary to calculate the profit of the process, are also shown: duration of the process (t), mass of the Fore-cut 1 (mfc1) and of the main cut (mmc), the concentration of methanol, THF and toluene in Fore-cut 2 (xfc2,B, xfc2,C and xfc2,E, respectively), the final (xmc,B) and maximal (xmc,B,max) concentration of methanol in the main cut, as well as the profit (OF). The procedure was performed twice, first with the original ranges of the optimisation variables ("Original range.xlsx") and then with narrowed ranges ("Narrowed range.xlsx"). Each row is a data point, each column contains either an optimisation variable or a simulation result.

Steps to reproduce

The input data points (two times 500 points) were generated by Latin Hypercube Sampling within previously fixed intervals for each variables. The simulation results were obtained by performing a dynamic simulation using CHEMCAD in each point. More detailed information is given in the paper "Laszlo Hegely, Ömer Faruk Karaman, Marton Tamas Szucs, Peter Lang: Surrogate Model-Based Optimisation of a Batch Distillation Process, 2023".

Institutions

Categories

Funding

Licence