Method and apparatus for planning a manufacturing schedule using an adaptive learning process

• US 7,818,082 B2
• Filed: 01/25/2008
• Issued: 10/19/2010
• Est. Priority Date: 10/16/2003
• Status: Expired due to Fees

• Current Assignee: E2E Processing Incorporated (Marathon Patent Group, Inc.)
• Original Assignee: TT IP LLC (IPNav)
• Inventors: Roumeliotis, George, Knight, Jonathan Louis
• Primary Examiner(s): Jarrett; Ryan A
• Application Number:
  US12/010,476
• Publication Number:
  US 20080140244A1
• Time in Patent Office: 998 Days
• Field of Search: 700/97, 700 99-107
• US Class Current: 700/101
• CPC Class Codes: G05B 13/0265 the criterion being a learning criterion
• CPC Class Codes: G05B 2219/31396 Business management, production, document, asset, regulatory management, high level
• CPC Class Codes: G06Q 10/06 Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
• CPC Class Codes: G06Q 50/04 Manufacturing
• CPC Class Codes: Y02P 90/30 Computing systems specially adapted for manufacturing

Abstract

An apparatus and method for a production planning system using a process of adaptive learning is disclosed. A production planning system receives, production objects wherein each production object has at least one attribute. In one embodiment, the production objects include information relating to product to be manufactured. After receipt of production objects, multiple preference scores according to the attributes of the production objects are calculated. In one embodiment, each preference score represents desirability of transition from manufacturing a first object to a second object. The system subsequently identifies a suggested production plan which includes a sequence order of two or more objects in response to the preference scores. In one embodiment, the planning preferences are updated or modified by an adaptive learning system in response to adjustments of the suggested production plant by a planner.

Claims

1. A computer-implemented method of creating and modifying manufacturing schedules comprising:

starting a production planner application using a computer;

accepting inputs, using the computer, regarding production requirements, including inputs of types and quantities of products to be manufactured, wherein the products each include one or more attributes;

obtaining data, using the computer, from an Adaptive Learning Unit, including product preference data that specifies manufacturing sequence preferences based on data including the product attributes and east manufacturing schedule data; and

creating a manufacturing schedule, using the data obtained from the Adaptive Learning Unit, wherein the manufacturing schedule specifies a sequence of production tasks for manufacturing the products and the manufacturing schedule is created using the computer.

2. The computer-implemented method of claim 1, further comprising:

outputting said manufacturing schedule in a machine-readable format, for use by a manufacturing system.

3. The computer-implemented method of claim 1, further comprising:

outputting said manufacturing schedule in a human-readable format.

4. The computer-implemented method of claim 3, further comprising:

retrieving past manufacturing schedules from a data storage; and

outputting a comparison of said human-readable manufacturing schedule and said past manufacturing schedules.

5. The computer-implemented method of claim 4 further comprising:

accepting inputs regarding changes to said manufacturing schedule.

6. The computer-implemented method of claim 5 further comprising:

modifying said manufacturing schedule based on said changes to said manufacturing schedule; and

storing said modified manufactured schedule in a data storage.

7. The computer-implemented method of claim 1, wherein the data obtained from the Adaptive Learning Unit comprises at least one preference score for a suggested production plan.

8. The computer-implemented method of claim 7, wherein the at least one preference score is based on a transition preference value obtained from a historical data storage.

9. The computer-implemented method of claim 1, wherein the data obtained from the Adaptive Learning Unit comprises preference scores for at least two adjacent production tasks.

10. The computer-implemented method of claim 1, wherein the data obtained from the Adaptive Learning Unit comprises preference scores for a sequence of production tasks.

11. A system for creating and modifying manufacturing schedules comprising:

providing a computer having;

a processor;

a memory; and

a computer-readable storage medium storing a plurality of instructions which, when executed by the processor, cause the processor to perform a method comprising;

starting a production planner application;

accepting inputs regarding production requirements, including inputs of types and quantities of products to be manufactured, wherein the products each include one or more attributes;

obtaining data from an Adaptive Learning Unit, including product preference data that specifies manufacturing sequence preferences based on data including the product attributes and past manufacturing schedule data; and

creating a manufacturing schedule, using the data obtained from the Adaptive Learning Unit, wherein the manufacturing schedule specifies a sequence of production tasks for manufacturing the products and the manufacturing schedule is created using the computer.

12. The system of claim 11, the method further comprising:

outputting the manufacturing schedule in a human-readable format;

retrieving past manufacturing schedules from a data storage; and

outputting a comparison of the human-readable manufacturing schedule and the past manufacturing schedules.

13. The system of claim 11, wherein the data obtained from the Adaptive Learning Unit comprises at least one preference score for a suggested production plan.

14. The system of claim 11, wherein the data obtained from the Adaptive Learning Unit comprises preference scores for at least two adjacent production tasks.

15. The system of claim 11, wherein the data obtained from the Adaptive Learning Unit comprises preference scores for a sequence of production tasks.

16. A computer-readable storage medium storing a plurality of instructions which, when executed by a processor, cause the processor to perform a method comprising:

starting a production planner application;

accepting inputs regarding production requirements, including inputs of types and quantities of products to be manufactured, wherein the products each include one or more attributes;

obtaining data from an Adaptive Learning Unit, including product preference data that specifies manufacturing sequence preferences based on data including the product attributes and past manufacturing schedule data; and

creating a manufacturing schedule, using the data obtained from the Adaptive Learning Unit wherein the manufacturing schedule specifies a sequence of production tasks for manufacturing the products and the manufacturing schedule is created using the computer.

17. The computer-readable storage medium of claim 16, the method further comprising:

outputting the manufacturing schedule in a human-readable format;

retrieving past manufacturing schedules from a data storage; and

outputting a comparison of the human-readable manufacturing schedule and the past manufacturing schedule.

18. The computer-readable storage medium of claim 16, wherein the data obtained from the Adaptive Learning Unit comprises at least one preference score for a suggested production plan.

19. The computer-readable storage medium of claim 16, wherein the data obtained from the Adaptive Learning Unit comprises preference scores for at least two adjacent production tasks.

20. The computer-readable storage medium of claim 16, wherein the data obtained from the Adaptive Learning Unit comprises preference scores for a sequence of production tasks.