Process for the monitoring and diagnostics of data from a remote asset

• US 6,480,810 B1
• Filed: 10/30/2000
• Issued: 11/12/2002
• Est. Priority Date: 10/28/1999
• Status: Expired due to Fees

• Current Assignee: General Electric Company
• Original Assignee: General Electric Company
• Inventors: Cardella, Aidan Thomas, Varner, Evelyn
• Primary Examiner(s): Hoff, Marc S.
• Assistant Examiner(s): SUAREZ, FELIX E
• Application Number:
  US09/702,182
• Time in Patent Office: 743 Days
• Field of Search: 702/188, 702/183, 702/182, 702/186, 340/539
• US Class Current: 702/188
• CPC Class Codes: G05B 17/02 electric
• CPC Class Codes: G05B 2223/06 Remote monitoring
• CPC Class Codes: G05B 23/0232 based on qualitative trend analysis, e.g. system evolution
• CPC Class Codes: G05B 23/0283 Predictive maintenance, e.g. involving the monitoring of a system and, based on the monitoring results, taking decisions on the maintenance schedule of the monitored system; Estimating remaining useful life [RUL] preventive maintenance, i.e. planning maintenance according to the available resources without monitoring the system G06Q10/06
• 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: G07C 3/00 Registering or indicating the condition or the working of machines or other apparatus, other than vehicles

Abstract

A method for processing monitored data from a remote asset to optimize maintenance and operation schedules, the method comprising the steps of collecting data from the remote asset, building a data set based on the data collected, applying statistical scripts to the data set to create a statistical model, comparing the statistical model to the data set, creating a standardization model from the compared statistical model and the data set, applying a trending algorithm to the data, deriving statistical based control limits, and applying the control limits to a new set of collected data.

Claims

1. A method for processing monitored data from a remote asset to optimize maintenance and operation schedules, the method comprising:

collecting data from the remote asset;

building a data set based on the data collected;

applying statistical scripts to the data set to create a statistical model;

comparing the statistical model to the data set;

creating a standardization model from the compared statistical model and the data set;

applying a trending algorithm to the data;

deriving statistical based control limits;

applying the control limits to a new set of collected data;

trending information using a time series modeling optimization technique for determining the remote asset'"'"'s maintenance and operation schedules;

developing optimized maintenance and operation schedules based on the trended information;

reporting the schedules to a user.

2. The method of claim 1 wherein the building a data set further comprises using a series of algorithms to build the data set.

3. The method of claim 2 wherein using a series of algorithms further comprises:

creating an anomaly definition; and

identifying variables to monitor.

4. The method of claim 1 wherein the applying statistical scripts further comprises:

using a statistical script for centering the data at a predetermined variable;

using a statistical script for running a stepwise regression script on the centered data;

using a statistical script for un-centering the data.

5. The method of claim 1 further comprising eliminating extraneous variables discovered during comparing the statistical model to the data set.

6. The method of claim 1 wherein applying a trending algorithm to the data further comprises determining control chart type limits.

7. The method of claim 6 wherein determining control chart type limits comprises applying a time series modeling optimization technique to determine control chart type limits.

8. The method of claim 1 wherein applying the control limits to a new set of data further comprising the steps of:

recording the standardization model and data thresholds for implementation in an automated monitoring and diagnostic system; and

determining a remote asset'"'"'s maintenance and operation schedule.

9. The method of claim 8 further comprising the step of notifying a user of results after determining a remote asset'"'"'s maintenance and operation schedule.

10. A system for processing monitored data from a remote asset to evaluate and determine a status of the remote asset with minimum user interface, the system comprising:

a remote asset;

a data gathering module located at the remote asset to collect data about the remote asset;

a monitoring and diagnostic service center;

respective network interfaces located at the remote asset and the monitoring and diagnostic service center;

a processor to manage sending, evaluating, and receiving the data;

a process residing in the processor which uses algorithms to build a data set based on the data gathered uses statistical scripts on the data to determine a statistical model, and uses a time series modeling optimization technique to trend information to determine the remote asset'"'"'s maintenance and operation schedules.

11. The system of claim 10 wherein the remote asset transmits data collected by the data collection module to the process located at the monitoring and diagnostic service center.

12. The system of claim 10 further comprising:

a customer facility;

a repair depot;

respective network interfaces located at said customer facility and repair depot;

wherein the remote asset'"'"'s maintenance and operation schedules determined by the process are communicated from the monitoring and diagnostic service center to the customer facility and repair depot.

13. The system of claim 10 wherein the process comprises a sub-process to compare the statistical model to the collected data.

14. The system of claim 10 wherein the time series modeling optimization technique used in the process is an Exponentially Weighted Moving Average technique.

15. The system of claim 14 wherein an Auto-Regressive Integrated Moving Average technique is used to calculate a value in the Exponentially Weighted Moving Average technique.

16. The system of claim 10 wherein the processor further comprises a diagnostic compute engine to determine whether the data is within a specified operating range as determined by the process.

17. The system of claim 10 wherein the results determined by the process are communicated to a user.

18. A method for processing monitored data from a remote asset to determine whether the data is within a predetermined operating threshold, the method comprising:

collecting monitored data from the remote asset;

providing a processor;

supplying the monitored data to the processor;

creating an anomaly definition which comprises acceptable parameters;

identifying a first variable;

identifying a second set of variables which are used to monitor the first variable;

deleting data that is outside of a specified parameter;

centering data about a specified variable;

running a stepwise regression algorithm;

determining whether data is within acceptable parameters;

un-centering data if data are within acceptable parameters;

running the stepwise regression algorithm on the un-centered data;

calculating residuals based on a calculated first variable compared to a predicted first variable;

building a standardized variable based on calculated residuals;

assessing data before and after standardization to determine whether results are within a predetermined limit;

trending the data to determine whether the assessed data is within the predetermined operating threshold;

developing optimized maintenance and operation schedules based on the trended data;

reporting the schedules to a user.

19. The method of claim 18 wherein trending the data further comprises optimizing an Exponentially Weighted Moving Average technique and applying the optimized Exponentially Weighted Moving Average technique to the standardized variable and the monitored data.

20. The method of claim 18 wherein reporting results to a user further comprises formatting an algorithm to facilitate implementation with a diagnostic compute engine and implementing the diagnostic compute engine.

21. The method of claim 18 further comprising determining whether the data is within acceptable parameters.

22. The method of claim 21 further comprising re-running the first stepwise regression if the data is not within acceptable parameters.

23. The method of claim 18 further comprising identifying a new second set of variables which are used to monitor the first variable and continuing through a build standardization model when assessed data is not within an acceptable limit.