Systems and methods for modeling a manufacturing assembly line

Patent metadata

Field	Value
Publication number	US-11449778-B2
Application number	US-202117216290-A
Country	US
Kind code	B2
Filing date	Mar 29, 2021
Priority date	Mar 31, 2020
Publication date	Sep 20, 2022
Grant date	Sep 20, 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 and line production data, determine one or more production associations between the cell data and the line production data; evaluate the one or more production associations to identify one or more critical production associations; retrieve the cell data and the line production data associated with the one or more critical production associations; and train a predictive model with the retrieved cell data and the retrieved line production data to predict the production level of the manufacturing assembly line.

First claim

We claim:

1. A method for generating a predictive model for predicting a production level of a 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 during an operation of an active 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 active manufacturing assembly line;
receive line production data associated with the cell data, the line production data being representative of a production level of the active manufacturing assembly line in association with the respective cell data;
determine one or more production associations between the cell data of each cell and the production level of the active manufacturing assembly line;
evaluate the one or more production associations to identify one or more critical production associations to the operation of the active manufacturing assembly line;
retrieve the cell data and the line production data associated with the one or more critical production associations; and
train the predictive model with the retrieved cell data and the retrieved line production data to predict the production level of the manufacturing assembly line.

2. The method of claim 1 , wherein the line production data is representative of a defect level of the active manufacturing assembly line, the one or more production associations comprise one or more associations between the cell data of each cell and the defect level of the active manufacturing assembly line, and the predictive model is trained to predict the defect level of the manufacturing assembly line.

3. The method of claim 1 , wherein the one or more production associations comprises a cell input association between an input state of a cell and the production level of the active manufacturing assembly line, and a cell position association between a cell position of a cell and the production level of the active manufacturing assembly line.

4. The method of claim 1 , wherein evaluating the one or more production associations comprises identifying one or more one statistically significant production associations as the one or more critical production associations.

5. The method of claim 4 , wherein identifying the one or more statistically significant production associations comprises:
determining a probability value of each production association in the one or more production associations being unassociated; and
identifying a production association as the one of the one or more statistically significant associations if the probability value of that production association is less than or equal to a predetermined significance level.

6. The method of claim 1 , wherein:
the cell data comprises a cell position of a first cell relative to a second cell in the active manufacturing assembly line; and
the one or more production associations comprises a cell position association between the cell position of the first cell relative to the second cell and the production level of the active manufacturing assembly line.

7. The method of claim 6 , wherein the first cell is downstream of the second cell in the active manufacturing assembly line.

8. The method of claim 6 , wherein the first cell is upstream of the second cell in the active manufacturing assembly line.

9. The method of claim 1 , wherein:
at least some of the cell data corresponds to a first time;
at least some of the line production data corresponds to a second time later than the first time; and
the one or more production associations comprises a production association between cell data corresponding to the first time and a production level corresponding to the second time.

10. The method of claim 9 , wherein evaluating the one or more production associations comprises:
identifying the production association between the cell data corresponding to the first time and the production level corresponding to the second time as one of the one or more critical production associations if a difference between the first time and the second time is less than a pre-determined time limit.

11. The method of claim 1 , wherein the at least one input state comprises a starved state in which the corresponding cell received an undersupply of at least one input for processing the workpiece.

12. The method of claim 1 , wherein:
the predictive model comprises a decision tree, the decision tree comprising a plurality of nodes; and
training the predictive model comprises generating at least one node corresponding to the one or more critical production associations.

13. The method of claim 1 , wherein:
each cell comprises at least one device configured to process the workpiece;
the method further comprises operating the processor to receive device data associated with the at least one device during the operation of the active manufacturing assembly line, the device data comprising, for each device, at least one device state; and
the one or more production associations comprises an association between the device state and the production level of the active manufacturing assembly line.

14. A system for generating a predictive model for predicting a production level of a 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 during an operation of an active 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 active manufacturing assembly line;
receive line production data associated with the cell data, the line production data being representative of a production level of the active manufacturing assembly line in association with the respective cell data;
determine one or more production associations between the cell data of each cell and the production level of the active manufacturing assembly line;
evaluate the one or more production associations to identify one or more critical production associations to the operation of the active manufacturing assembly line;
retrieve the cell data and the line production data associated with the one or more critical production associations; and
train the predictive model with the retrieved cell data and the retrieved line production data to predict the production level of the manufacturing assembly line.

15. The system of claim 14 , wherein the line production data is representative of a defect level of the active manufacturing assembly line, the one or more production associations comprise one or more associations between the cell data of each cell and the defect level of the active manufacturing assembly line, and the predictive model is trained to predict the defect level of the manufacturing assembly line.

16. The system of claim 14 , wherein the one or more production associations comprises a cell input association between an input state of a cell and the production level of the active manufacturing assembly line, and a cell position association between a cell position of a cell and the production level of the active manufacturing assembly line.

17. The system of claim 14 , wherein the processor is configured to identify one or more statistically significant production associations as the one or more critic

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

• G05B23/0267

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

• G05B2219/2629

  Assembly line · CPC title

• G05B19/41805

  characterised by assembly · CPC title

• G05B2219/32371

  Predict failure time by analysing history fault logs of same machines in databases · CPC title