中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

6 records (took 0.026 seconds)

    Supervisory Machine Intelligence Controls for Production of Meat Substitutes
    1.
    发明公开
    Supervisory Machine Intelligence Controls for Production of Meat Substitutes 审中-公开

    公开(公告)号：US20230225363A1

    公开(公告)日：2023-07-20

    申请号：US18005840

    申请日：2021-06-22

    Applicant: ABB Schweiz AG

    Inventor： Chau-Hon Ho ,  Vedrana Spudic ,  Kim Listmann ,  Sandro Schoenborn ,  Elsi-Mari Borrelli ,  Philipp Sommer ,  Mehmet Mercangoez ,  Erich J. Windhab ,  Eric Stirnemann ,  Lukas Böni ,  Patrick Rühs

    IPC: A23J3/26 ,  A23J3/22 ,  A23P30/20

    CPC classification number: A23J3/26 ,  A23J3/227 ,  A23P30/20

    Abstract: A system includes a wet extrusion process machine configured to receive, mix, and convey a plurality of ingredients to an extrusion die, the plurality of ingredients include a protein powder, an oil, and water. The system includes an electronic process control system (EPCS) configured to control the wet extrusion machine using a plurality of process settings effective to produce an extrusion die mixture which is forced into, passes through, and is output from the extrusion die. The system further includes a supervisory machine intelligence control system (SMICS) operatively coupled with at least one of a direct fibrosity measurement (DFM) subsystem configured to directly measure one or more physical fibrosity parameters of the extrusion die mixture, and an indirect fibrosity measurement (IFM) subsystem configured to measure one or more extrusion process parameters associated with the extrusion die mixture. The SMICS is configured to modify one or more of the plurality process settings in response to at least one of the one or more physical fibrosity parameters, and the one or more extrusion process parameters, effective to modify the extrusion die mixture.

    Predictions For A Process In An Industrial Plant
    2.
    发明申请
    Predictions For A Process In An Industrial Plant 有权

    公开(公告)号：US20220035346A1

    公开(公告)日：2022-02-03

    申请号：US17413020

    申请日：2019-11-25

    Applicant: ABB Schweiz AG

    Inventor： Mehmet Mercangoez ,  Andrea Cortinovis

    IPC: G05B19/418 ,  G05B13/02 ,  G06N3/08 ,  G06N3/04

    Abstract: To generate real-time or at least near real-time predictions for a process in an industrial plant, a set of neural networks are trained to create a set of trained models. The set of trained models is then used to output the predictions, by inputting online measurement results in an original space to two trained models whose outputs are fed, as reduced space inputs and reduced space initial states, to a third trained model. The third trained model processes the reduced space inputs to reduced space predictions. They are fed to a fourth trained model, which outputs the predictions in the original space.

Patent Agency Ranking