US 12,360,511 B2
Automated chemical formulation apparatus and method thereof
Seung Bum Hong, Daejeon (KR); Chi Hao Liow, Daejeon (KR); and Young Woo Choi, Daejeon (KR)
Assigned to KOREA ADVANCED INSTITUTE OF SCIENCE AND TECHNOLOGY, Daejeon (KR)
Filed by KOREA ADVANCED INSTITUTE OF SCIENCE AND TECHNOLOGY, Daejeon (KR)
Filed on Oct. 22, 2021, as Appl. No. 17/508,111.
Claims priority of application No. 10-2021-0072776 (KR), filed on Jun. 4, 2021.
Prior Publication US 2022/0397886 A1, Dec. 15, 2022
Int. Cl. G05B 19/4155 (2006.01); G06N 20/00 (2019.01)
CPC G05B 19/4155 (2013.01) [G06N 20/00 (2019.01); G05B 2219/32287 (2013.01)] 13 Claims
OG exemplary drawing
 
1. An automated chemical formulation apparatus comprising:
a computing device, comprising:
a data reception unit configured to receive an input chemical material dataset of a chemical material including chemical material information, chemical composition information, chemical formulation information and property information of the chemical material;
a predicting model generation unit configured to train a first machine learning model using the input chemical material dataset to generate a predicting model for predicting a chemical formulation based on target property information of a target material;
a formulation prediction unit configured to set a boundary condition based on the input chemical material dataset, generate a new input dataset including at least one of new chemical material information, new chemical composition information, and new chemical formulation information within the boundary condition, input the new input dataset to the predicting model, and set predetermined one or more pieces of target property information to perform prediction, thereby outputting a first group of chemical formulation data;
a validation model generation unit configured to train a second machine learning model different from the first machine learning model using the input chemical material dataset to generate a validation model;
a validation formulation prediction unit configured to input the new input dataset to the validation model, and set the predetermined one or more pieces of target property information to perform prediction, thereby outputting a second group of chemical formulation data; and
a validation unit configured to compare and verify the first group of chemical formulation data with the second group of chemical formulation data to derive matching data as a third group of chemical formulation data corresponding to the predetermined one or more pieces of target property information; and
a chemical dispensing device comprising a control unit, a dispensing pump and individual chemical repositories and the control unit of the chemical dispensing device configured to perform a control operation to supply component materials stored in individual chemical repositories through the dispensing pump based on the third group of chemical formulation data to synthesize a target chemical material.