Methods and systems for pervasive diagnostics

• US 7,937,175 B2
• Filed: 07/10/2008
• Issued: 05/03/2011
• Est. Priority Date: 07/10/2008
• Status: Active Grant

• Current Assignee: Xerox Corporation (Xerox Holdings Corp.)
• Original Assignee: Palo Alto Research Center, Inc. (Xerox Holdings Corp.)
• Inventors: Do, Minh, Price, Robert, Zhou, Rong, Kuhn, Lukas D., de Kleer, Johan
• Primary Examiner(s): Decady; Albert
• Assistant Examiner(s): ROBERTSON, DAVID
• Application Number:
  US12/170,542
• Publication Number:
  US 20100010654A1
• Time in Patent Office: 1,027 Days
• Field of Search: 700/96, 700/97, 700/99, 700/100, 700/103, 700/79, 700/105, 705/7, 705/8, 714/26
• US Class Current: 700/99
• CPC Class Codes: G05B 19/41865 characterised by job scheduling, process planning, material flow
• CPC Class Codes: G05B 2219/32083 Alternative, variant operation planning, revision specification of product
• CPC Class Codes: G05B 2219/33299 Real time, online diagnostic, integrated in normal control system
• CPC Class Codes: G05B 23/021 adopting a different treatment of each operating region or a different mode of the monitored system, e.g. transient modes; different operating configurations of monitored system
• CPC Class Codes: G05B 23/0243 model based detection method, e.g. first-principles knowledge model
• CPC Class Codes: Y02P 90/02 Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
• CPC Class Codes: Y02P 90/80 Management or planning

Abstract

Model-based production control systems and methods are presented for constructing plans for controlling operation of a production system with a plant having a plurality of resources to achieve one or more production goals, in which a planner constructs plans for execution in the plant based on production goals while balancing both production objectives (e.g., production cost, production time) and diagnostic objectives (e.g., diagnostic cost, information gained, repair cost), and a diagnosis engine determines a current plant condition based on a previously executed plan and corresponding observations from the plant, and provides expected information gain data to the planner, with the planner generating a plan that will achieve a given production goal and is improved for one or more diagnostic objectives and the expected information gain data.

Claims

1. A production control system for controlling operation of a production system with a plant that can achieve one or more production goals, the control system comprising:

a planner operatively coupled with the production system to provide one or more plans for execution in the plant based on at least one production goal;

a plant model operatively coupled with the planner and including a model of the plant; and

a diagnosis engine operatively coupled with the planner, the production system, and the model, the diagnosis engine operative to determine a current plant condition based at least partially on a previously executed plan, at least one corresponding observation from the plant, and the plant model, and to determine expected information gain data representing diagnostic value for one or more possible plans or partial plans based on the current plant condition and the model;

wherein the planner is operative to construct or select at least one production plan for the plant that concurrently achieves at least one production goal and at least one diagnostic objective relating to identifying resources causing intermittent or persistent faults based at least partially on the current plant condition, the plant model, and the expected information gain data from the diagnosis engine.

2. The control system of claim 1, wherein the planner is operative to selectively provide a dedicated diagnostic plan for execution in the plant at least partially based on at least one diagnostic objective and the current plant condition.

3. The control system of claim 2, further comprising an operator interface operatively coupled with the diagnosis engine to allow an operator to define a diagnostic job using a diagnosis job description language.

4. The control system of claim 2, wherein the planner is operative to selectively provide interleaved dedicated diagnostic plans and production plans for execution in the plant at least partially based on at least one production objective and at least one diagnostic objective.

5. The control system of claim 4, wherein the planner is operative to use the current plant condition in providing the interleaved dedicated diagnostic plans and production plans for execution in the plant.

6. The control system of claim 1, wherein the diagnosis engine formulates a heuristic associated with the plan construction, and wherein the planner employs a partial-plan search using the heuristic to construct the plans for execution in the plant.

7. The control system of claim 1, further comprising a plan data store including a plurality of whole or partial plans selectable by the planner for execution in the plant to facilitate one or more production or diagnostic objectives.

8. The control system of claim 1, further comprising an operator interface operatively coupled with the diagnosis engine to provide operator observations to the diagnosis engine, wherein the diagnosis engine is operative to determine the current plant condition based at least partially on the operator observations.

9. The control system of claim 1, wherein the planner is operative to use the current plant condition in making a tradeoff between production objectives and diagnostic objectives in constructing or selecting plans for execution in the plant.

10. The control system of claim 1, wherein the planner is operative to use the current plant condition in constructing or selecting plans for execution to perform diagnosis in isolating faulty resources in the plant.

11. The control system of claim 1, wherein the planner is operative to use the current plant condition in constructing or selecting plans for execution to perform prognosis about a remaining useful life of plant components or resources.

12. A method of generating plans for execution in a production system with a plant to achieve one or more production goals, the method comprising:

determining a current plant condition based at least partially on a previously executed plan, at least one corresponding observation from the plant, and a plant model;

determining expected information gain data representing diagnostic value for a plurality of possible plans or partial plans based on the current plant condition and the model; and

using a processor, constructing or selecting a production plan that will concurrently achieve a given production goal and a diagnostic objective relating to identifying resources causing intermittent or persistent faults based at least partially on the current plant condition and the expected information gain data.

13. The method of claim 12, wherein constructing or selecting the plan includes making a tradeoff between production objectives and diagnostic objectives based at least partially on the current plant condition.

14. The method of claim 12, wherein constructing or selecting the plan includes performing diagnosis to isolate faulty resources in the plant based at least partially on the current plant condition.

15. The method of claim 12, further comprising constructing or selecting a dedicated diagnostic plan for execution in the plant based at least partially on at least one diagnostic objective and the current plant condition.

16. The method of claim 15, further comprising selectively interleaving dedicated diagnostic plans and production plans based on at least one production objective and at least one diagnostic objective.

17. The method of claim 15, further comprising allowing an operator to define a diagnostic plan using a diagnosis job description language.

18. The method of claim 12, further comprising receiving operator observations, wherein constructing or selecting the plan is based at least partially on the operator observations.

19. A non-transitory computer readable medium having computer executable instructions for performing the steps of:

determining a current plant condition in a production system plant based at least partially on a previously executed plan, at least one corresponding observation from the plant, and a plant model;

determining expected information gain data representing diagnostic value for a plurality of possible plans or partial plans based on the current plant condition and the model; and

constructing or selecting a production plan that will concurrently achieve a given production goal and a diagnostic objective relating to identifying resources causing intermittent or persistent faults based at least partially on the current plant condition and the expected information gain data.