Systems and methods for modeling a manufacturing assembly line

Patent metadata

Field	Value
Publication number	US-11790255-B2
Application number	US-202117216519-A
Country	US
Kind code	B2
Filing date	Mar 29, 2021
Priority date	Mar 31, 2020
Publication date	Oct 17, 2023
Grant date	Oct 17, 2023

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 faults, determine a priority level for each fault by applying the extracted feature data to a predictive model, determine at least one high priority fault, and generate at least one operator alert based on the at least one high priority fault.

First claim

We claim:

1. A method for assessing faults in a manufacturing assembly line, the manufacturing assembly line comprising a plurality of cells, each cell being configured to successively process a workpiece along the manufacturing assembly line, the method comprising operating a processor to:
receive cell data associated with at least one cell of the manufacturing assembly line, the cell data comprising, for each cell, at least one input state of that cell and a cell position of that cell within the manufacturing assembly line;
extract feature data from the cell data, the feature data comprising at least one input state and at least one a cell position of at least one cell;
determine a plurality of faults, each fault corresponding to one cell;
determine whether at least one fault of the plurality of faults comprises a defective workpiece fault;
for each defective workpiece fault,
generate a scrap workpiece cost associated with the defective workpiece fault;
determine whether the defective workpiece fault can be remedied with a cell within the plurality of cells configurable as a rework cell for remedying manufacturing faults; and
in response to determining the defective workpiece fault can be remedied with a rework cell, generate a rework workpiece cost associated with the defective workpiece fault;

apply the extracted feature data, the scrap workpiece cost, and the rework workpiece cost to a predictive model generated for predicting a production level of the manufacturing assembly line to determine a priority level for each fault and a recommendation for each defective workpiece fault, the recommendation comprising one of a rework recommendation to use the rework cell for remedying the defective workpiece fault and a scrap recommendation to discard the defective workpiece;
determine at least one high priority fault from the plurality of faults based on the priority level for each fault;
determine whether the at least one high priority fault comprises a defective workpiece fault; and
in response to determining that the at least one high priority fault comprises a defective workpiece fault, generate at least one operator alert based on the at least one high priority fault and the recommendation for the defective workpiece fault;
otherwise, generate at least one operator alert based on the at least one high priority fault.

2. The method of claim 1 , wherein:
determining the plurality of faults comprises determining a plurality of faults for one cell; and
determining the at least one high priority fault comprises determining one high priority fault for that one cell by selecting a fault with the highest priority level from the plurality of faults for that one cell.

3. The method of claim 1 , wherein:
determining the plurality of faults comprises determining a plurality of faults for at least two cells, each fault corresponding to one of the at least two cells;
determining the at least one high priority fault comprises determining one high priority fault for one of the at least two cells by selecting a fault with the highest priority level from the plurality of faults for the at least two cells.

4. The method of claim 1 , wherein determining the priority level for each fault comprises:
determining an input state of at least one cell upstream of a cell corresponding to that fault when that fault occurs at the corresponding cell; and
determining the priority level for that fault based on the input state.

5. The method of claim 1 , wherein determining the priority level for each fault comprises:
determining an input state of at least one cell downstream of a cell corresponding to that fault when that fault occurs at the corresponding cell; and
determining the priority level for that fault based on the input state.

6. The method of claim 1 , wherein determining the priority level for that fault is based on whether the production level meets a predetermined production quota.

7. The method of claim 1 , wherein determining the priority level for each fault comprises:
determining a defect level of the manufacturing assembly line when that fault occurs at a corresponding cell; and
determining the priority level for that fault based on the defect level.

8. The method of claim 7 , wherein determining the priority level for that fault is further based on whether the defect level meets a predetermined production quota.

9. The method of claim 1 , wherein:
each cell comprises at least one device configured to process the workpiece;
each fault comprises at least one device fault, each device fault corresponding to a device of a cell corresponding to that fault;
the at least one operator alert is generated further based on a device fault corresponding to the at least one high priority fault.

10. The method of claim 1 , wherein determining the plurality of faults comprises:
determining at least one input state of at least one cell; and
determining the plurality of faults based on the at least one input state.

11. A system for assessing faults in a manufacturing assembly line, the manufacturing assembly line comprising a plurality of cells, each cell being configured to successively process a workpiece along the manufacturing assembly line, the system comprising a processor configured to:
receive cell data associated with at least one cell of the manufacturing assembly line, the cell data comprising, for each cell, at least one input state of that cell and a cell position of that cell within the manufacturing assembly line;
extract feature data from the cell data, the feature data comprising at least one input state and at least one a cell position of at least one cell;
determine a plurality of faults, each fault corresponding to one cell;
determine whether at least one fault of the plurality of faults comprises a defective workpiece fault;
for each defective workpiece fault,
generate a scrap workpiece cost associated with the defective workpiece fault;
determine whether the defective workpiece fault can be remedied with a cell within the plurality of cells configurable as a rework cell for remedying manufacturing faults; and
in response to determining the defective workpiece fault can be remedied with a rework cell, generate a reworkable workpiece cost associated with the defective workpiece fault;

apply the extracted feature data, the scrap workpiece cost, and the reworkable workpiece cost to a predictive model generated for predicting a production level of the manufacturing assembly line to determine a priority level for each fault and a recommendation for each defective workpiece fault, the recommendation comprising one of a rework recommendation to use the rework cell for remedying the defective workpiece fault and a scrap recommendation to discard the defective workpiece;
determine at least one high priority fault from the plurality of faults based on the priority level for each fault;
determine whether the at least one high priority fault comprises a defective workpiece fault; and
in response to determining that the at least one high priority fault comprises a defective workpiece fault, generate at least one operator alert based on the at least one high priority fault and the recommendation for the defective workpiece fault;
otherwise, generate at least one operator alert based on the at least one high priority fault.

12. The system of claim 11 , wherein the processor is configured to:
determine a plurality of faults for one cell; and
determine one high priority fault for that one cell by selecting a fault with the highest priority level from the plurality of faults for that one cell.

13. The system of claim 1

Assignees

• Ats Automation Tooling Systems Inc
• Ats Corp

Inventors

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

Classifications

• G05B23/0267

  Fault communication, e.g. human machine interface [HMI] · CPC title

• G06N5/04 Primary

  Inference or reasoning models · 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

• G05B19/4183

  characterised by data acquisition, e.g. workpiece identification · CPC title

• G05B19/41805

  characterised by assembly · CPC title