PREDICTIVE ANALYSIS FOR REMOTE MACHINE MONITORING

• US 20120092180A1
• Filed: 05/12/2011
• Published: 04/19/2012
• Est. Priority Date: 05/14/2010
• Status: Active Grant

• Current Assignee: Joy Global Surface Mining Inc. (Mitsui & Company Limited)
• Original Assignee: Harnischfeger Technologies Inc. (Mitsui & Company Limited)
• Inventors: Rikkola, Michael, Bhushan, Anubhaw, Gudur, Shashikiran, Raba, Brian
• Granted Patent: US 9,372,482 B2
• Time in Patent Office: Days
• US Class Current: 340/679
• CPC Class Codes: G05B 23/02 Electric testing or monitoring
• CPC Class Codes: G05B 23/0232 based on qualitative trend analysis, e.g. system evolution
• CPC Class Codes: G06F 21/554 involving event detection and direct action
• CPC Class Codes: G06V 20/695 Preprocessing, e.g. image segmentation

Abstract

Methods for predicting a machine event are described. In one aspect, a method includes receiving data for current events for the machine, and determining whether the data for the current events is within operational limits. The method also includes, when the data for the current events is within operational limits, determining, using a predetermined model, whether an anomaly exists, and generating an alert including information on the anomaly when the anomaly exists. Systems and machine-readable media are also described.

Claims

1. A method for predicting a machine event for a mining machine comprising:

receiving data for current events for the mining machine;

determining whether the data for the current events is within operational limits;

when the data for the current events is not within operational limits, discarding the data for the current events;

when the data for the current events is within operational limits, determining, using a predetermined model, whether an anomaly exists; and

generating an alert comprising information on the anomaly when the anomaly exists.

2. The method of claim 1, wherein determining whether an anomaly exists using a predetermined model comprises comparing a standard deviation of at least one of an incoming voltage for the mining machine or an equivalent voltage for the mining machine to a predetermined voltage threshold level.

3. The method of claim 2, wherein the predetermined voltage threshold level is based upon voltage information regarding past events for the mining machine.

4. The method of claim 1, wherein determining whether an anomaly exists using a predetermined model comprises identifying a dip in a voltage applied to a drive system of the mining machine.

5. The method of claim 1, wherein determining whether an anomaly exists using a predetermined model comprises comparing current events for the mining machine with past events for the mining machine to determine whether the anomaly exists.

6. The method of claim 1, wherein determining whether an anomaly exists using a predetermined model comprises comparing current event data for one portion of the mining machine with current event data for a related portion of the mining machine to determine whether the anomaly exists.

7. The method of claim 6, wherein the comparing current event data for the one portion of the mining machine with the current event data for the related portion of the mining machine takes into account an ambient temperature of the field environment of the mining machine.

8. The method of claim 1,

wherein the current event data comprises at least one of temperature information, voltage information, speed information, and count information for at least one portion of the mining machine, and

wherein determining whether an anomaly exists using a predetermined model comprises comparing the at least one of temperature information, voltage information, speed information, and count information for the at least one portion with a predetermined range of at least one of temperature information, voltage information, speed information, and count information for the at least one portion to determine whether the anomaly exists for another portion of the mining machine.

9. The method of claim 1, further comprising determining whether data for current events for the mining machine is available before receiving the data.

10. The method of claim 1, wherein determining whether an anomaly exists using a predetermined model comprises analyzing the number of faults for a particular component of the mining machine.

11. The method of claim 10, wherein the analyzing the number of faults for a particular component of a mining machine comprises considering a number of over voltage events.

12. The method of claim 10, wherein the processor analyzing the number of faults for a particular component of a mining machine comprises the processor considering a number of over voltage events.

13. The method of claim 1, wherein determining whether the data for the current events is within operational limits comprises comparing the data for the current events with a predetermined physical range for the operation of the mining machine.

14. The method of claim 1, further comprising transmitting the alert to a user.

15. The method of claim 1, wherein the alert is transmitted by at least one of a telephone call, voice notification, electronic message, text message, or instant message.

16. The method of claim 1, wherein the mining machine is at least one of a drill, conveyor, dragline, shovel, surface or underground mining machine, haulage vehicle or mining crusher.

32. The method of claim 2, wherein the incoming voltage powers a plurality of motor drive units of the mining machine.

17. A system for predicting a machine event for a mining machine having a drive system with a plurality of motor drive units comprising:

a memory comprising data for current events for the mining machine;

a processor configured to;

determine whether the data for the current events is within operational limits;

when the data for the current events is not within operational limits, discard the data for the current events;

when the data for the current events is within operational limits, determine, using a predetermined model, whether an anomaly exists; and

generate an alert when the anomaly exists.

18. The system of claim 17, wherein the processor determining whether an anomaly exists using a predetermined model comprises the processor comparing a standard deviation of at least one of an incoming voltage for the mining machine or an equivalent voltage for the mining machine to a predetermined voltage threshold level.

19. The system of claim 18, wherein the predetermined voltage threshold level is based upon information regarding past events for the mining machine.

20. The system of claim 17, wherein the processor determining whether an anomaly exists using a predetermined model comprises the processor identifying a dip in a voltage applied to a drive system of the mining machine.

21. The system of claim 17, wherein the processor determining whether an anomaly exists using a predetermined model comprises the processor comparing current events for the mining machine with past events for the mining machine to determine whether the anomaly exists.

22. The system of claim 17, wherein the processor determining whether an anomaly exists using a predetermined model comprises the processor comparing current event data for one portion of the mining machine with current event data for a related portion of the mining machine to determine whether the anomaly exists.

23. The system of claim 17, wherein the processor determining whether an anomaly exists using a predetermined model comprises the processor identifying at least one of a dip in a voltage applied to a drive system of the mining machine.

24. The system of claim 17,

wherein the current event data comprises at least one of temperature information, voltage information, speed information, and count information for at least one portion of the mining machine, and

wherein the processor determining whether an anomaly exists using a predetermined model comprises the processor comparing the at least one of temperature information, voltage information, speed information, and count information for the at least one portion with a predetermined range of at least one of temperature information, voltage information, speed information, and count information for the at least one portion to determine whether the anomaly exists for another portion of the mining machine.

25. The system of claim 17, wherein the processor is further configured to determine whether data for current events for the mining machine is available before receiving the data.

26. The system of claim 17, wherein the processor determining whether an anomaly exists using a predetermined model comprises the processor analyzing the number of faults for a particular component of the mining machine.

27. The system of claim 17, wherein the processor determining whether the data for the current events is within operational limits comprises the processor comparing the data for the current events with a predetermined physical range for the operation of the mining machine.

28. The system of claim 17, wherein the processor is further configured to transmit the alert to a user.

29. The system of claim 17, wherein the alert is transmitted by at least one of a telephone call, voice notification, electronic message, text message, or instant message.

30. The system of claim 17, wherein the mining machine is at least one of a drill, conveyor, dragline, shovel, surface or underground mining machine, haulage vehicle or mining crusher.

31. A machine-readable storage medium comprising machine-readable instructions for causing a processor to execute a method for predicting a machine event for a mining machine, comprising:

receiving data for current events for the mining machine;

determining whether the data for the current events is within operational limits;

when the data for the current events is not within operational limits, discarding the data for the current events;

when the data for the current events is within operational limits, determining, using a predetermined model, whether an anomaly exists; and

generating an alert when the anomaly exists.

33. A method for predicting a machine event for a mining machine comprising:

receiving voltage data for the mining machine corresponding to a voltage level of power supplied to the mining machine;

comparing the voltage data to a voltage model;

determining, based on the comparison, whether an anomaly exists, wherein the anomaly is a prediction of a future fault of the mining machine; and

generating an alert including information on the anomaly when the anomaly exists.

34. The method of claim 33, wherein comparing the voltage data to a voltage model includes comparing a standard deviation of the voltage level, or an equivalent thereof, to a predetermined voltage threshold level.

35. The method of claim 34, wherein the predetermined voltage threshold level is based upon voltage information regarding past events for the mining machine.

36. The method of claim 33, wherein determining whether an anomaly exists includes identifying a dip in the voltage level of power supplied to the mining machine.

37. The method of claim 33, wherein comparing the voltage data to a voltage model includes comparing the voltage data to previous voltage data corresponding to previous voltage levels of power supplied to the mining machine.