METHOD AND SYSTEM FOR REAL TIME PRODUCTION OPTIMIZATION BASED ON EQUIPMENT LIFE

• US 20160314409A1
• Filed: 04/23/2015
• Published: 10/27/2016
• Est. Priority Date: 04/23/2015
• Status: Abandoned Application

• Current Assignee: General Electric Company
• Original Assignee: General Electric Company
• Inventors: Bittencourt, Jose Luiz, Gonzaga, Carlos
• Application Number:
  US14/694,701
• Publication Number:
  US 20160314409A1
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G05B 13/0265 the criterion being a learning criterion
• CPC Class Codes: G05B 2219/32216 If machining not optimized, simulate new parameters and correct machining
• CPC Class Codes: G05B 23/0294 Optimizing process, e.g. process efficiency, product quality
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 7/01 Probabilistic graphical models, e.g. probabilistic networks
• CPC Class Codes: Y02P 80/10 Efficient use of energy, e.g. using compressed air or pressurized fluid as energy carrier

Abstract

A system and method include a controlled mechanical system coupled to self-optimization of equipment life system. The method includes providing a controlled mechanical system; collecting and aggregating data in a time series related to the controlled mechanical system for processing with a monitoring module; calculating an estimated current level of degradation of the controlled mechanical system from the collected and aggregated data with a learning and prognostic module; determining, with the learning and prognostic module, trade-offs between degradation and performance of the controlled mechanical system for the next optimization period; and calculating an optimum operating point for the controlled mechanical system based on the forecast and economic data with an optimization module. Numerous other aspects are provided.

Claims

1. A method comprising:

providing a controlled mechanical system;

collecting and aggregating data in a time series related to the controlled mechanical system for processing with a monitoring module;

calculating an estimated current level of degradation of the controlled mechanical system from the collected and aggregated data with a learning and prognostic module;

determining, with the learning and prognostic module, trade-offs between degradation and performance of the controlled mechanical system for the next optimization period; and

calculating an optimum operating point for the controlled mechanical system based on the forecast and economic data with an optimization module.

2. The method of claim 1, further comprising:

collecting and aggregating data from the environment associated with the controlled mechanical system.

3. The method of claim 1, wherein processing the data with the monitoring module further comprises:

filtering the data to account for at least one of outliers, sensor drift and bias.

4. The method of claim 1, further comprising:

calculating an estimated current performance loss of the controlled mechanical system from the collected and aggregated data with the learning and prognostic module.

5. The method of claim 1, wherein calculating an estimated current level of degradation further comprises:

applying at least one of physics-based models and data-driven models to the collected and aggregated data.

6. The method of claim 1, further comprising:

calculating a remaining useful life for the controlled mechanical system from the collected and aggregated data with the learning and prognostic module.

7. The method of claim 1, wherein the determined tradeoffs are for at least one of short-term and long-term projections.

8. The method of claim 1, wherein the optimum operating point is calculated in real time.

9. The method of claim 1, further comprising:

correlating, with an economic objective function, a profit provided by the mechanical system with at least one of a degradation rate of the controlled mechanical system, energy efficiency used by the controlled mechanical system and production output of the controlled mechanical system, via the optimization module, to calculate the optimum operating point.

10. The method of claim 9, wherein the economic objective function is based on one of discounted payback, expected value added, return of investment or net present value.

11. The method of claim 1, further comprising:

operating the controlled mechanical system at the calculated optimum operating point, via an adaptive supervisor module.

12. The method of claim 1, further comprising:

performing a sensitivity analysis, via the learning and prognostic module, to identify one or more factors that contribute the most to the estimated current level of degradation and prognostic deviations compared to a baseline.

13. A system comprising:

a controlled mechanical system;

a monitoring module operative to collect and aggregate data in a time series related to the controlled mechanical system for processing;

a learning and prognostic module operative to;

calculate an estimated current level of degradation of the controlled mechanical system from the collected and aggregated data;

determine trade-offs between degradation and performance of the controlled mechanical system for the next optimization period; and

an optimization module operative to calculate an optimum operating point for the controlled mechanical system based on the forecast and economic data.

14. The system of claim 13, wherein the monitoring module is further operative to:

collect and aggregate data from the environment associated with the controlled mechanical system.

15. The system of claim 13 wherein collected and aggregated data is filtered to account for at least one of outliers, sensor drift and bias.

16. The system of claim 13 wherein the learning and prognostic module is further operative to calculate an estimated current performance loss of the controlled mechanical system from the collected and aggregated data.

17. The system of claim 13, wherein the learning and prognostic module is operative to apply at least one of physics-based models and data-driven models to the collected and aggregated data to calculate the estimated current level of degradation.

18. The system of claim 13, wherein the learning and prognostic module is further operative to calculate a remaining useful life for the mechanical system from the collected and aggregated data.

19. The system of claim 13, wherein the learning and prognostic module is further operative to perform a sensitivity analysis to identify one or more factors that contribute the most to the estimated current level of degradation and prognostic deviations compared to a baseline.

20. The system of claim 13, wherein the determined tradeoffs are for at least one of short-term and long term projections.

21. The system of claim 13, wherein the optimum operating point is calculated in real time.

22. The system of claim 13, wherein the optimization module is further operative to correlate, via an economic objective function, a profit provided by the controlled mechanical system with at least one of a degradation rate of the mechanical system, energy efficiency used by the controlled mechanical system and production output of the controlled mechanical system to calculate the optimum operating point.

23. The system of claim 22, wherein the economic objective function is based on one of discounted payback, expected value added, return of investment or net present value.

24. The system of claim 13, further comprising:

an adaptive supervisor module operative to operate the controlled mechanical system at the calculated optimum operating point.