US 11,953,433 B2
Method for analysing process streams
Marius Kirchmann, Heidelberg (DE); and Christoph Hauber, Heidelberg (DE)
Assigned to hte GmbH the high throughput experimentation company, Heidelberg (DE)
Appl. No. 16/978,333
Filed by hte GmbH the high throughput experimentation company, Heidelberg (DE)
PCT Filed Mar. 15, 2019, PCT No. PCT/EP2019/056537
§ 371(c)(1), (2) Date Sep. 4, 2020,
PCT Pub. No. WO2019/179887, PCT Pub. Date Sep. 26, 2019.
Claims priority of application No. 18162722 (EP), filed on Mar. 20, 2018.
Prior Publication US 2021/0003502 A1, Jan. 7, 2021
Int. Cl. G01N 21/61 (2006.01); G01N 21/3504 (2014.01); G01N 21/85 (2006.01); G01N 30/02 (2006.01); G01N 33/28 (2006.01); G06N 20/00 (2019.01); G01N 21/84 (2006.01); G01N 30/88 (2006.01)
CPC G01N 21/3504 (2013.01) [G01N 21/85 (2013.01); G01N 30/02 (2013.01); G01N 33/2829 (2013.01); G06N 20/00 (2019.01); G01N 2021/8411 (2013.01); G01N 2030/025 (2013.01); G01N 2030/8886 (2013.01)] 15 Claims
OG exemplary drawing
 
1. A method for investigating at least one process stream comprising at least five different hydrocarbon-containing components, wherein the method comprises at least the steps of:
a) providing at least one process stream conduit which is in operative connection with at least one online IR spectrometer and in operative connection with at least one online gas chromatograph;
b) passing at least one process stream through the at least one process stream conduit, wherein during this passing of the process stream through the process stream conduit an analytical characterization of the process stream using an online IR spectrometer and an online gas chromatograph is performed;
c) evaluating the spectral data obtained in the analytical characterization of the process stream using an online IR spectrometer as a function of the time at which this spectroscopic analysis of the process stream was carried out:
d) evaluating the chromatography data obtained during the analytical characterization of the process stream using the online gas chromatograph as a function of a sampling time for samples taken from the process stream;
e) machine learning-based training of a model that models a mathematical relationship between spectral data and corresponding chromatography data in respect of an identical process stream by using the evaluation results obtained in steps c) and d) in respect of the process stream passed through the process stream conduit in step b).