US 12,299,623 B2
Smart manufacturing platform, smart manufacturing profiles and smart manufacturing marketplace
James F. Davis, Los Angeles, CA (US); John Dyck, Newbury, OH (US); Haresh Malkani, Pittsburgh, PA (US); Prakashan P. Korambath, Calabasas, CA (US); and Jonathan Wise, Chardon, OH (US)
Assigned to The Regents of the University of California, Oakland, CA (US)
Appl. No. 17/753,114
Filed by The Regents of the University of California, Oakland, CA (US)
PCT Filed Aug. 21, 2020, PCT No. PCT/US2020/047474
§ 371(c)(1), (2) Date Feb. 18, 2022,
PCT Pub. No. WO2021/035171, PCT Pub. Date Feb. 25, 2021.
Claims priority of provisional application 62/890,016, filed on Aug. 21, 2019.
Prior Publication US 2022/0245538 A1, Aug. 4, 2022
Int. Cl. G06Q 10/067 (2023.01); G06Q 50/04 (2012.01)
CPC G06Q 10/067 (2013.01) [G06Q 50/04 (2013.01)] 19 Claims
OG exemplary drawing
 
1. A data centric smart manufacturing system, comprising:
a plurality of machine systems each configured to provide raw data while performing a manufacturing process that applies transformations to raw inputs to produce a finished product using real time operations data, the systems having controllable operating parameters;
a plurality of reusable data model profiles as declarative templates that can be instantiated to ingest the raw data and contextualize the raw data, wherein a data model profile defines contextualized data as operating inputs and measured outputs, model configurations, controllable operating parameters, and data connectivity protocols for a particular type of machine system from the plurality of machine systems; and
a plurality of data transformation models integrated with the plurality of data model profiles and instantiated with contextualized data to provide higher level operational insights;
wherein at least one data model profile is a base data model profile;
wherein at least one data model profile is an extended data model profile that inherits the base data model profile and extends the base data model profile to define how to populate data points of the base data model profile from sensor data of environmental conditions output by an associated machine system of the plurality of machine systems and estimate data points of environmental conditions for locations within the associated machine system where sensor data was not collected;
wherein at least one data model profile is a model orchestration activity profile that calls at least one of the plurality of data transformation models to perform a computation against data identified and gathered as the base data model profile and the extended data model profile are executed, and where the computation is used to determine controllable operating parameters for one or more of the machine systems from the data points of the base data model profile including the estimated data points; and
another one of the plurality of data transformation models determines at least one optimal location within one of the machine systems for collection of sensor data to accurately measure an environmental condition and an optimal frequency of the data collection.