Systems and methods for modeling a manufacturing assembly line

Patent metadata

Field	Value
Publication number	US-11514344-B2
Application number	US-202117216410-A
Country	US
Kind code	B2
Filing date	Mar 29, 2021
Priority date	Mar 31, 2020
Publication date	Nov 29, 2022
Grant date	Nov 29, 2022

Abstract

Various systems and methods for modeling a manufacturing assembly line are disclosed herein. Some embodiments relate to operating a processor to receive cell data, extract feature data from the cell data, determine a plurality of cell configurations, determine an efficiency score by applying the feature data to a predictive model generated for predicting a production level of the manufacturing assembly line, determine at least one target cell configuration from the cell configurations based on the efficiency score, and apply the at least one target cell configuration to at least one cell by implementing each target cell configuration to a corresponding cell.

First claim

We claim:

1. A method for optimizing a manufacturing assembly line, the manufacturing assembly line comprising a plurality of cells, each cell of the plurality of cells being configured to successively process a workpiece along the manufacturing assembly line, the method comprising operating a processor to:
receive cell data associated with a cell of the plurality of cells of the manufacturing assembly line, the cell data comprising an input state of the cell and a cell position of the cell within the manufacturing assembly line;
extract feature data from the cell data, the feature data comprising an input state of at least one cell of the plurality of cells and a cell position of the at least one cell of the plurality of cells;
determine a plurality of cell configurations, each cell configuration of the plurality of cell configurations corresponding to one or more cells of the plurality of cells and defining a different process for processing the workpiece by the one or more cells;
determine an efficiency score for one or more cell configurations of the plurality of cell configurations by applying the extracted feature data to a predictive model generated for predicting a production level of the manufacturing assembly line;
determine at least one target cell configuration from the plurality of cell configurations based on the efficiency score for the one or more cell configurations of the plurality of cell configurations; and
apply the at least one target cell configuration to the one or more cells of the plurality of cells by implementing each target cell configuration to the one or more cells of the plurality of cells.

2. The method of claim 1 , wherein:
determining the plurality of cell configurations comprises determining a plurality of cell configurations for the one or more cells of the plurality of cells; and
determining the at least one target cell configuration comprises determining one target cell configuration for the one or more cells by selecting a cell configuration with the highest efficiency score from the plurality of cell configurations for the one or more cells.

3. The method of claim 1 , wherein:
determining the plurality of cell configurations comprises determining at least one cell configuration from the plurality of cell configurations for the one or more cells of the plurality of cells; and
determining the at least one target cell configuration comprises determining a target cell configuration for the one or more cells of the plurality of cells.

4. The method of claim 3 , wherein determining the target cell configuration for the one or more cells of the plurality of cells comprises:
determining a plurality of sets of cell configurations, each set of cell configurations comprising one cell configuration from the plurality of cell configurations for the one or more cells of the plurality of cells;
determining an overall efficiency score for one or more sets of cell configurations based on the efficiency score of the one or more cell configurations in the one or more sets of cell configurations; and
selecting a set of cell configurations with the highest overall efficiency score as the target cell configuration for the one or more cells of the plurality of cells.

5. The method of claim 1 , wherein determining the efficiency score for each cell configuration of the plurality of cell configurations comprises:
determining an input state of at least one cell of the plurality of cells upstream of a cell corresponding to a cell configuration from the plurality of cell configurations; and
determining the efficiency score for the cell configuration based on the input state.

6. The method of claim 1 , wherein determining the efficiency score for the one or more cell configurations of the plurality of cell configurations comprises:
determining an input state of at least one cell downstream of a cell corresponding to the one or more cell configurations from the plurality of cell configurations; and
determining the efficiency score for the one or more cell configurations based on the input state.

7. The method of claim 1 , wherein determining the efficiency score for the one or more cell configurations of the plurality of cell configurations comprises:
determining a production level of the manufacturing assembly line when the one or more cell configurations from the plurality of cell configurations is applied to a corresponding cell from the plurality of cells; and
determining the efficiency score for the one or more cell configurations based on the production level.

8. The method of claim 7 , wherein determining the efficiency score for the one or more cell configurations is based on whether the production level meets a predetermined production quota.

9. The method of claim 1 , wherein determining the efficiency score for the one or more cell configurations of the plurality of cell configurations comprises:
determining a defect level of the manufacturing assembly line when the one or more cell configurations from the plurality of cell configurations is applied to a corresponding cell from the plurality of cells; and
determining the efficiency score for the one or more cell configurations based on the defect level.

10. The method of claim 9 , wherein determining the efficiency score for the one or more cell configurations of the plurality of cell configurations comprises:
determining at least one of a rework and a scrap cost based on the defect level; and
determining the efficiency score for the one or more cell configurations based on the at least one of the rework and the scrap cost.

11. The method of claim 9 , wherein determining the efficiency score for the one or more cell configurations is further based on whether the defect level meets a predetermined production quota.

12. The method of claim 1 , wherein:
each cell of the plurality of cells comprises at least one device configured to process the workpiece;
each cell configuration of the plurality of cell configurations comprises at least one device configuration corresponding to a device of a corresponding cell and defining a different process for processing the workpiece by that device;
applying the at least one target cell configuration comprises implementing each corresponding device configuration at a corresponding device.

13. A system for optimizing a manufacturing assembly line, the manufacturing assembly line comprising a plurality of cells, each cell of the plurality of cells being configured to successively process a workpiece along the manufacturing assembly line, the system comprising a processor configured to:
receive cell data associated with a cell from the plurality of cells of the manufacturing assembly line, the cell data comprising an input state of the cell and a cell position of the cell within the manufacturing assembly line;
extract feature data from the cell data, the feature data comprising an input state of at least one cell of the plurality of cells and a cell position of the at least one cell of the plurality of cells;
determine a plurality of cell configurations, each cell configuration of the plurality of cell configurations corresponding to one or more cells of the plurality of cells and defining a different process for processing the workpiece by the one or more cells;
determine an efficiency score for one or more cell configurations of the plurality of cell configurations by applying the extracted feature data to a predictive model generated for predicting a production level of the manufacturing assembly line;
determine at least one target cell configuration from the plurality of cell configurations based on the efficien

Assignees

• Ats Automation Tooling Systems Inc

Inventors

• Willison Nicholas
• Sadeghzadeh Mehdi
• Kheradmandi Masoud
• Chang Bo Yuan
• Bacso Stephen
• Wang Yang
• Foisy Nick
• Kleinikkink Stanley

Classifications

• G06N5/01

  Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound · CPC title

• G06N20/00

  Machine learning · CPC title

• G05B2219/32194

  Quality prediction · CPC title

• G01M99/005

  Testing of complete machines, e.g. washing-machines or mobile phones (testing of machine parts G01M13/00; testing of electric apparatus or components G01R31/50) · CPC title

• G05B2219/31438

  Priority, queue of alarms · CPC title