Methods, systems, and apparatus for resource allocation in a manufacturing environment

Patent metadata

Field	Value
Publication number	US-10088836-B2
Application number	US-201514812760-A
Country	US
Kind code	B2
Filing date	Jul 29, 2015
Priority date	Jul 29, 2015
Publication date	Oct 2, 2018
Grant date	Oct 2, 2018

Abstract

Methods, systems, computer program products, and articles of manufacture for managing a manufacturing environment are described. An optimized schedule for operators is generated based on an optimization data structure, the optimization data structure comprising one or more manufacturing objectives and one or more resource constraints. The manufacturing activity is simulated based on the generated optimized schedule and an initial state data structure, the initial state data structure comprising a representation of an initial state of the manufacturing environment. The simulation results are analyzed to, for example, determine if the manufacturing objectives are satisfied.

First claim

What is claimed is:

1. A method for managing a manufacturing environment, the method comprising:
obtaining first sensor data from one or more sensors deployed in a manufacturing environment, the first sensor data indicating an initial state of the manufacturing environment;
obtaining second sensor data from the one or more sensors deployed in the manufacturing environment, the second sensor data indicating a current state of the manufacturing environment;
storing the first sensor data in an initial state data structure;
revising estimates of production metrics based upon the second sensor data;
translating an optimization model to a mixed integer program;
solving the mixed integer program;
translating, using an optimizer comprising at least one of one or more hardware devices, a solution to the mixed integer program using the optimization model to generate an optimized schedule for operators of the manufacturing environment based on an optimization data structure, the optimization data structure comprising one or more manufacturing objectives and one or more resource constraints;
simulating, using a simulator comprising at least one of the one or more hardware devices, manufacturing activity based on the generated optimized schedule, the revised estimates of production metrics, and the initial state data structure;
storing simulation results in a simulation data structure; and
analyzing the simulation results in the simulation data structure to determine a satisfaction of the manufacturing objectives.

2. The method of claim 1 , further comprising repeating the generating, simulating, storing, and analyzing operations based on one or more revised manufacturing objectives.

3. The method of claim 1 , wherein the generating operation generates an optimized schedule for one or more machines of the manufacturing environment.

4. The method of claim 1 , wherein the manufacturing objectives comprise one or more of total throughput of the manufacturing environment, target machine throughput, target buffer levels, and target operator movement.

5. The method of claim 1 , wherein the generating operation is based on the initial state of the manufacturing environment.

6. The method of claim 1 , wherein the initial state of the manufacturing environment is obtained from sensors located in the manufacturing environment.

7. The method of claim 1 , further comprising generating predictions of one or more of machine throughput and buffer inventory levels.

8. The method of claim 1 , further comprising generating a report based on the analysis of the simulation results, the report indicating an issue with one or more of the optimizer, the simulator, and the manufacturing environment.

9. The method of claim 1 , further comprising revising estimates of one or more manufacturing metrics, regenerating the optimized schedule and simulating manufacturing activity based on the regenerated optimized schedule and a manufacturing state data structure.

10. The method of claim 1 , wherein the simulator is a discrete event simulator.

11. A system for processing events, the system comprising:
one or more sensors deployed in a manufacturing environment that are configured to obtain first sensor data and second sensor data, the first sensor data indicating an initial state of the manufacturing environment, the second sensor data indicating a current state of the manufacturing environment;
one or more hardware processors;
memory to store instructions that, when executed by the one or more hardware processors perform operations comprising:
storing the first sensor data in an initial state data structure;
revising estimates of production metrics based upon the second sensor data;
generating one or more probability distributions characterizing one or more manufacturing metrics based upon historic data;
translating an optimization model to a mixed integer program, solving the mixed integer program; translating a solution to the mixed integer program using the optimization model to generate an optimized schedule for operators of a manufacturing environment based on an optimization data structure, the optimization data structure comprising one or more manufacturing objectives and one or more resource constraints;
simulating manufacturing activity based on the generated optimized schedule, the revised estimates of production metrics, and the initial state data structure; and
analyzing the simulation results in the simulation data structure to determine a satisfaction of the manufacturing objectives.

12. The system of claim 11 , further comprising repeating the generating, simulating, storing, and analyzing operations based on one or more revised manufacturing objectives.

13. The system of claim 11 , wherein the generating operation generates an optimized schedule for one or more machines of the manufacturing environment.

14. The system of claim 11 , wherein the manufacturing objectives comprise one or more of total throughput of the manufacturing environment, target machine throughput, target buffer levels, and target operator movement.

15. The system of claim 11 , wherein the generating operation is based on the initial state of the manufacturing environment.

16. The system of claim 11 , wherein the initial state of the manufacturing environment is obtained from sensors located in the manufacturing environment.

17. The system of claim 11 , further comprising generating predictions of one or more of machine throughput and buffer inventory levels.

18. The system of claim 11 , further comprising generating a report based on the analysis of the simulation results, the report indicating an issue with one or more of the optimization processing module, the simulation processing module, and the manufacturing environment.

19. A non-transitory machine-readable storage medium comprising instructions that, when executed by one or more processors of a machine, cause the machine to perform operations comprising:
obtaining first sensor data from one or more sensors deployed in a manufacturing environment, the first sensor data indicating an initial state of the manufacturing environment;
obtaining second sensor data from the one or more sensors deployed in the manufacturing environment, the second sensor data indicating a current state of the manufacturing environment;
storing the first sensor data in an initial state data structure;
revising estimates of production metrics based upon the second sensor data;
translating an optimization model to a mixed integer program;
solving the mixed integer program;
translating, using an optimizer, a solution to the mixed integer program using the optimization model to generate an optimized schedule for operators of a manufacturing environment based on an optimization data structure, the optimization data structure comprising one or more manufacturing objectives and one or more resource constraints;
simulating, using a simulator, manufacturing activity based on the generated optimized schedule, the revised estimates of production metrics, and the initial state data structure;
storing simulation results in a simulation data structure; and
analyzing the simulation results in the simulation data structure to determine a satisfaction of the manufacturing objectives.

20. The non-transitory machine-readable storage medium of claim 19 , further comprising instructions that, when executed by the one or more processors of the machine, cause the machine to perform operations comprising repeating the generating, simu

Assignees

• Gen Electric

Inventors

• Tyber Steven Jay
• Wang Shanshan
• Katlic Peter Leigh

Classifications

• Y02P90/18

  Cross-Sectional Technologies · mapped topic

• G05B19/41865 Primary

  characterised by job scheduling, process planning, material flow · CPC title

• Y02P90/26

  Cross-Sectional Technologies · mapped topic

• G05B2219/32301

  Simulate production, process stages, determine optimum scheduling rules · CPC title

• Y02P90/20

  Cross-Sectional Technologies · mapped topic