US 11,953,862 B2
Optimal control configuration engine in a material processing system
John Thomas Clark, Jr., North Salt Lake, UT (US); Joakim Kalvenes, Glencoe, IL (US); Jason Thomas Stewart, Venice, IL (US); and Rohin Wood, Perth (AU)
Assigned to THE BOSTON CONSULTING GROUP, INC., Boston, MA (US)
Filed by The Boston Consulting Group, Inc., Boston, MA (US)
Filed on Nov. 5, 2021, as Appl. No. 17/520,551.
Claims priority of provisional application 63/229,931, filed on Aug. 5, 2021.
Prior Publication US 2023/0039441 A1, Feb. 9, 2023
Int. Cl. G05B 13/02 (2006.01); G05B 13/04 (2006.01)
CPC G05B 13/0265 (2013.01) [G05B 13/042 (2013.01); G05B 13/048 (2013.01)] 15 Claims
OG exemplary drawing
 
1. A computerized system comprising:
one or more computer processors; and
computer memory storing computer-useable instructions that, when used by the one or more computer processors, cause the one or more computer processors to perform operations comprising:
accessing, at a material processing engine implemented using the one or more computer processors, causal graph input data from one or more hardware storage devices, the causal graph input data comprising input materials associated with a continuous flow process;
based on the causal graph input data, generating a causal graph that aligns with do-calculus manipulations associated with determining identifiable causal relationships corresponding to the input materials of the continuous flow process;
parsing the causal graph based on the do-calculus manipulations to determine valid conditioning sets associated with estimating a causal impact on an optimization target;
based on parsing the causal graph, partitioning a set of control variables of the causal graph input data into a plurality of regimes comprising a first regime and a second regime, wherein for the first regime and a first control variable of the first regime, a shortest valid conditioning set is identified for training a machine learning model that predicts a quadratic causal impact of the first control variable on the optimization target; and
based on the valid conditioning sets, generating an optimal control configuration comprising optimal control variable values associated with the continuous flow process; and
controlling the continuous flow process in accordance with the optimal control configuration.