Process and system for multi-objective global optimization of maintenance schedules

• US 8,396,571 B2
• Filed: 03/19/2007
• Issued: 03/12/2013
• Est. Priority Date: 03/19/2007
• Status: Expired due to Fees

• Current Assignee: Raytheon Technologies Corporation d/b/a RTX (Rtx Corporation)
• Original Assignee: United Technologies Corporation (Rtx Corporation)
• Inventors: Costiner, Sorin, Winston, Howard A., Wang, Jihua, Khibnik, Alexander I., Rajamani, Ravi, Matthis, Thomas R., Benitez, Ricardo A., Ireland, Julie A., Cohen, Robert M.
• Primary Examiner(s): Robertson, Dave
• Assistant Examiner(s): Norton, Jennifer L
• Application Number:
  US11/725,934
• Publication Number:
  US 20080234979A1
• Time in Patent Office: 2,185 Days
• Field of Search: 700/28, 700/175, 700/100, 701/29, 702/34, 702/184, 702/182, 703/2, 703/7, 703/13, 703/22, 705/7.12, 705/7.24, 705/7.28, 706/14, 706/50
• US Class Current: 700/28
• CPC Class Codes: G06Q 10/04 Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem" market predictions or forecasting for commercial activities G06Q30/0202
• CPC Class Codes: G06Q 10/06 Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling

Abstract

A process for optimizing maintenance work schedules for at least one engine includes the steps of retrieving at least one set of data for an engine from a computer readable storage medium; selecting at least one scheduling parameter for the engine; selecting a set of maintenance rules for the engine; selecting at least one maintenance work decision; selecting at least one objective for the engine; optimizing the at least one objective to generate at least one optimal maintenance work decision; and generating at least one optimal maintenance work schedule for the engine.

Claims

1. A process for optimizing maintenance work schedules for at least one engine, comprising:

retrieving at least one set of data for an engine from a computer readable storage medium;

selecting at least one scheduling parameter for said engine;

selecting a set of maintenance rules for said engine;

selecting at least one maintenance work decision;

selecting at least one objective for said engine;

optimizing said at least one objective to generate at least one optimal maintenance work decision,

said optimizing step comprising

using a hierarchical multi-objective global optimization which integrates hierarchical searches with elimination criteria and with handling of constraints to evaluate said at least one objective by simulation of life realizations of said engine as time sequences of scheduled or random shop visits of said engine;

evaluating said at least one objective, said at least one set of data

and said at least one maintenance work decision based upon a set of engine life realizations;

constructing a scheduled maintenance plan based upon the evaluation step; and

generating a projected cost of at least one maintenance work decision based upon the construction step; and

generating at least one optimal maintenance work schedule for said engine.

2. The process of claim 1, further comprising the evaluation step comprising using any one of the following approaches:

deterministic approach and stochastic approach.

3. The process of claim 1, further comprising the selection step of said at least one scheduling parameter comprising selecting said at least one scheduling parameter based upon said at least one set of data.

4. The process of claim 1, further comprising the selection step of said set of maintenance rules comprising selecting said set of maintenance rules based upon the selection of said at least one scheduling parameter.

5. The process of claim 1, further comprising the selection step of said at least one maintenance work decision comprising the following steps:

accepting said at least one scheduling parameter;

incorporating said set of maintenance rules; and

determining said at least one maintenance work decision based upon said at least one scheduling parameter and said set of maintenance rules.

6. The process of claim 5, further comprising the determination step comprising processing said at least one scheduling parameter and said set of maintenance rules using any one of the following approaches:

deterministic approach and stochastic approach.

7. The process of claim 1, further comprising the selection step of said at least one objective comprising generating said at least one objective based upon said at least one set of data and said at least one maintenance work decision.

8. The process of claim 1, further comprising the generation step comprising generating at least one optimal maintenance work schedule based upon said at least one optimal maintenance work decision.

9. A system comprising a computer readable storage device readable by the system, tangibly embodying a program having a set of instructions executable by the system to perform the following steps for optimizing maintenance work schedules for at least one engine, the system comprising:

means for retrieving at least one set of data for an engine from a computer readable storage device;

means for selecting at least one scheduling parameter for said engine;

means for selecting a set of maintenance rules for said engine;

means for selecting at least one maintenance work decision;

means for selecting at least one objective for said engine;

means for optimizing said at least one objective to generate at least one optimal maintenance work decision,

said optimizing means comprising

means for using a hierarchical multi-objective global optimization which integrates hierarchical searches with elimination criteria and with handling of constraints to evaluate said at least one objective by simulation of life realizations of said engine as time sequences of scheduled or random shop visits for said engine;

means for evaluating said at least one objective, said at least one set of data and said at least one maintenance work decision based upon a set of engine life realizations;

means for constructing a scheduled maintenance plan based upon the evaluation step;

means for generating a projected cost of at least one maintenance work decision based upon the construction step;

means for selecting at least one cost effective maintenance work decision; and

means for optimizing said at least one objective based upon said at least one cost effective maintenance work decision; and

means for generating at least one optimal maintenance work schedule for said at least one engine.

10. The system of claim 9, further comprising said means for evaluating comprising means for using any one of the following approaches:

deterministic approach and stochastic approach.

11. The system of claim 9, further comprising means for selecting said at least one scheduling parameter comprises means for selecting said at least one scheduling parameter based upon said at least one set of data.

12. The system of claim 9, further comprising means for selecting said set of maintenance rules comprising means for selecting said set of maintenance rules based upon the selection of said at least one scheduling parameter.

13. The system of claim 9, further comprising means for selecting said at least one maintenance work decision comprising:

means for accepting said at least one scheduling parameter;

means for incorporating said set of maintenance rules; and

means for determining said at least one maintenance work decision based upon said at least one scheduling parameter and said set of maintenance rules.

14. The system of claim 13, further comprising said means for determining comprising means for processing said at least one scheduling parameter and said set of maintenance rules and to use any one of the following approaches:

deterministic approach and stochastic approach.

15. The system of claim 9, further comprising said means for selecting said at least one objective comprising means for generating said at least one objective based upon said at least one set of data and said at least one maintenance work decision.

16. The system of claim 9, further comprising means for generating comprising means for generating at least one optimal maintenance work schedule based upon said at least one optimal maintenance work decision.

17. A process for optimizing maintenance work schedules for at least one industrial system, comprising:

retrieving at least one set of data for at least one industrial system from a computer readable storage medium;

selecting at least one scheduling parameter for said at least one industrial system;

selecting a set of maintenance rules for said at least one industrial system;

selecting at least one maintenance work decision for said at least one industrial system;

selecting at least one objective for said at least one industrial system;

optimizing said at least one objective to generate at least one optimal maintenance work decision for said at least one industrial system,

said optimizing step comprising

using a hierarchical multi-objective global optimization which integrates hierarchical searches with elimination criteria and with handling of constraints to evaluate said at least one objective by simulation of life realizations of said industrial system as time sequences of scheduled or random shop visits of said industrial system;

evaluating said at least one objective, said at least one set of data and said at least one maintenance work decision based upon a set of engine life realizations;

constructing a scheduled maintenance plan based upon the evaluation step;

generating a projected cost of at least one maintenance work decision based upon the construction step;

selecting at least one cost effective maintenance work decision; and

optimizing said at least one objective based upon said at least one cost effective maintenance work decision; and

generating at least one optimal maintenance work schedule for said at least one industrial system.

18. The process of claim 17, further comprising the evaluation step comprising using any one of the following approaches:

deterministic approach and stochastic approach.

19. The process of claim 17, further comprising the selection step of said at least one scheduling parameter comprising selecting said at least one scheduling parameter based upon said at least one set of data.

20. The process of claim 17, further comprising the selection step of said set of maintenance rules comprising selecting said set of maintenance rules based upon the selection of said at least one scheduling parameter.

21. The process of claim 17, further comprising the selection step of said at least one maintenance work decision comprising the following steps:

accepting said at least one scheduling parameter;

incorporating said set of maintenance rules; and

determining said at least one maintenance work decision based upon said at least one scheduling parameter and said set of maintenance rules.

22. The process of claim 21, further comprising the determination step comprising processing said at least one scheduling parameter and said set of maintenance rules using any one of the following approaches:

deterministic approach and stochastic approach.

23. The process of claim 17, further comprising the selection step of said at least one objective comprising generating said at least one objective based upon said at least one set of data and said at least one simulated maintenance work decision.

24. The process of claim 17, further comprising the generation step comprising generating at least one optimal maintenance work schedule based upon said at least one optimal maintenance work decision.

25. A system for optimizing a maintenance schedule for an aircraft engine comprising:

means for retrieving engine data describing part history data, component data, systems data, maintenance history, engine performance, failure probabilities, and costs;

means for storing engine maintenance parameters including time thresholds, engine operation thresholds, part life thresholds, and decision rules parameters;

means for automatically executing said maintenance schedule;

said maintenance schedule executing means receiving said engine data and said engine maintenance parameters as inputs and outputting maintenance work decisions and costs;

means for simulating engine life realizations as time sequences of scheduled or random shop visits of said engine and at each said visit implementing said maintenance work decisions of said maintenance schedule using said engine maintenance parameters;

means for evaluating multiple objectives comprising costs of work, parts, and a contract for said parameters using said life realizations generated by said means for simulating engine life realizations;

means for executing a multitude of single level schedule optimizers of said maintenance schedule, each said single level schedule optimizer having means for searching for values of said parameters producing optimal multiple objectives; and

means for performing a hierarchical multi-objective global optimization of said maintenance schedule comprising means for executing said multitude of single level multi-objective global optimizations of said maintenance schedule;

means for transferring information between said single level multi-objective global optimizations;

means for searching a set using deterministic or stochastic techniques, means for defining constraints;

means for eliminating regions of poor solutions; and

means for performing hierarchical searches on said parameters.