Technique for self learning motor load profile

• US 10,353,005 B2
• Filed: 07/13/2017
• Issued: 07/16/2019
• Est. Priority Date: 07/13/2017
• Status: Active Grant

• Current Assignee: ITT Manufacturing Enterprises LLC (ITT, Inc.)
• Original Assignee: ITT Manufacturing Enterprises LLC (ITT, Inc.)
• Inventors: Williams, Dean Patrick, George, Naveen Regi, Hauenstein, Kenneth Lee
• Primary Examiner(s): LaBalle, Clayton E.
• Assistant Examiner(s): Sanghera, Jas A
• Application Number:
  US15/648,838
• Publication Number:
  US 20190018066A1
• Time in Patent Office: 733 Days
• Field of Search: None
• CPC Class Codes: G01R 31/34 Testing dynamo-electric machines
• CPC Class Codes: G01R 31/343 in operation
• CPC Class Codes: G01R 33/02 Measuring direction or magnitude of magnetic fields or magnetic flux G01R33/20 takes precedence
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: H02H 7/08 for dynamo-electric motors
• CPC Class Codes: H02P 23/0031 implementing a off line learning phase to determine and store useful data for on-line control
• CPC Class Codes: H02P 29/024 Detecting a fault condition, e.g. short circuit, locked rotor, open circuit or loss of load
• CPC Class Codes: H02P 29/0241 the fault being an overvoltage

Abstract

Apparatus featuring a signal processor or signal processing module configured to: receive signaling containing information about a sampled leakage magnetic flux sensed from a motor, a motor load profile containing a learned leakage magnetic flux sensed from the motor and stored during a learning stage, and a user selectable band of tolerance related to the motor load profile to trigger an alarm condition for the motor; and determine corresponding signaling containing information about whether to trigger the alarm condition for the motor if the sampled leakage magnetic flux is outside the user selectable band of tolerance of the motor load profile, based upon the signaling received. The leakage magnetic flux may be sensed by, and/or received from, a motor flux leakage sensor arranged on an external surface of a frame of the motor.

Claims

1. Apparatus comprising:

a motor leakage flux detector arranged in relation to a motor, configured to detect a sample leakage magnetic flux sensed from the motor, and provide sensed signaling containing information about the sampled leakage magnetic flux sensed; and

a signal processor or signal processing module configured to;

receive the sensed signaling, and signaling containing information about a motor load profile containing a learned leakage magnetic flux sensed from the motor and stored during a learning stage, and a user selectable band of tolerance related to the motor load profile to trigger an alarm condition for the motor; and

determine corresponding signaling containing information about whether to trigger the alarm condition for the motor if the sampled leakage magnetic flux is outside the user selectable band of tolerance of the motor load profile, based upon the sensed signaling and the signaling received.

2. Apparatus according to claim 1, wherein the motor flux leakage sensor is arranged on an external surface of a frame of the motor or the motor'"'"'s shaft within a magnetic field generated by the motor.

3. Apparatus according to claim 1, wherein the motor flux leakage sensor is configured to connect to the signal processor or signal processing module having memory storage.

4. Apparatus according to claim 1, wherein the motor flux leakage sensor is attached to the external surface of the frame of the motor or the motor'"'"'s shaft using an adhesive, magnetic structure or mechanical fastener.

5. Apparatus according to claim 1, wherein the motor flux leakage sensor is configured to sense the sample leakage magnetic flux that produces a representative signal to a torque required to turn a shaft of the motor.

6. Apparatus according to claim 5, wherein the representative signal sensed includes an amplitude or a frequency, including where the amplitude is proportional to a load of the motor is driving or experiencing, and the frequency is proportional to the rotational speed of the motor.

7. Apparatus according to claim 1, wherein the user selectable band of tolerance is a percentage threshold of the motor load profile to trigger the alarm condition, including where the percentage threshold is user selectable of the motor load profile.

8. Apparatus according to claim 1, wherein the alarm condition contains an indication that the motor is starting to fail or that there is a change in the motor that should be investigated, including where the corresponding signaling contains information to issue an alarm.

9. Apparatus according to claim 1, wherein the user selectable band of tolerance is based off a calibrated load curve versus speed.

10. Apparatus according to claim 1, wherein the signal processor or signal processing module is configured to provide the corresponding signaling containing information about the alarm condition, including where the corresponding signaling includes wireless signaling transmitted for further processing.

11. Apparatus according to claim 1, wherein the signal processor or signal processing module is configured to implement a load curve calibration procedure during commissioning of a Variable Frequency Drive system for the motor.

12. Apparatus according to claim 1, wherein the signal processor or signal processing module is configured, during the learning stage, to store a flux magnitude as a value each time a transition is made in frequency increments.

13. Apparatus according to claim 12, wherein the signal processor or signal processing module is configured, after a predetermined number of transitions, to establish or determine the motor load profile containing the learned leakage magnetic flux sensed from the motor during the learning stage.

14. Apparatus according to claim 13, wherein the signal processor or signal processing module is configured to either average the learned leakage magnetic flux sensed and measured from the motor during the learning stage, or affix minimum and maximum values multiplied by a percentage margin, to establish or determine a motor load profile “

bandwidth”

.

15. Apparatus according to claim 14, wherein the signal processor or signal processing module is configured to compare future leakage magnetic flux values against the motor load profile established, determined or learned.

16. Apparatus according to claim 12, wherein the signal processor or signal processing module is configured to store the value in a memory storage for compiling a set of data of the sampled leakage magnetic flux sensed to form a statistical function, such as a Probability Density Function (PDF), including to build an aggregate of values in the motor load profile.

17. Apparatus according to claim 16, wherein the signal processor or signal processing module is configured to compare input signaling containing information about the sampled leakage magnetic flux sensed in relation to a standard deviation of the statistical function, including the PDF.

18. Apparatus according to claim 16, wherein the signal processor or signal processing module is configured to determine an impact of the statistical function, including the PDF, to processing depending on a bin size of a histogram that makes up the statistical function in order to determine anomalies, as well as process changes depending on the user selectable band of tolerance.

19. Apparatus according to claim 16, wherein the signal processor or signal processing module is configured to build the motor load profile having at least one leakage magnetic flux spectrum.

20. Apparatus according to claim 19, wherein the signal processor or signal processing module is configured to implement a technique to break down the at least one leakage magnetic spectrum using a spectral shape analysis into representations of vectors and numbers, including where the technique includes using a variation of spectral detectors.

21. Apparatus according to claim 19, wherein the signal processor or signal processing module is configured to implement a Fast Fourier Transform (FFT) analysis technique during the learning stage, including by receiving sampled leakage magnetic flux signaling sensed, performing the FFT analysis technique on the sampled leakage magnetic flux signaling, storing FFT sampled leakage magnetic flux signaling in a memory storage as the motor load profile for comparing to a current magnet flux spectrum later determined in the future.

22. Apparatus according to claim 21, wherein the signal processor or signal processing module is configured to determine the current magnetic flux spectrum, compare the current magnetic flux spectrum to the motor load profile, and determine the alarm condition if the current magnetic flux spectrum varies more than a predetermined percentage from the motor load profile.

23. Apparatus according to claim 22, wherein the current magnet flux spectrum includes FFT leakage magnetic flux sensed, frequency bins and associated amplitudes at individual frequencies.

24. Apparatus according to claim 21, wherein the signal processor or signal processing module is configured, after populating the motor load profile, to compare the motor load profile to actual or sampled leakage magnetic flux values sensed, and determine the alarm condition if the actual or sampled leakage magnetic flux values sensed are outside the user selectable band of tolerance, including where the user selectable band of tolerance takes the form of an established bandwidth for a user defined period of time.

25. Apparatus according to claim 12, wherein the signal processor or signal processing module is configured to determine the alarm condition using a minimum, maximum and time based technique, including by recording and assigning a respective weight to each leakage magnetic flux data point.

26. Apparatus according to claim 12, wherein the signal processor or signal processing module is configured to determine the alarm condition using a percentage of average and time based technique, including by recording each leakage magnetic flux data point at regular intervals over a fixed period of self learning time and assigning an averaged weight.

27. A method comprising:

arranging a motor leakage flux detector in relation to a motor to detect a sampled leakage magnetic flux sensed from the motor, and provide sensed signaling containing information about the sampled leakage magnetic flux sensed; and

receiving in a signal processor or signal processing module the sensed signaling, and signaling containing information about a motor load profile containing a learned leakage magnetic flux sensed from the motor and stored during a learning stage, and a user selectable band of tolerance related to the motor load profile to trigger an alarm condition for the motor; and

determining in the signal processor or signal processing module corresponding signaling containing information about whether to trigger the alarm condition for the motor if the sampled leakage magnetic flux is outside the user selectable band of tolerance of the motor load profile, based upon the signaling received.

28. A method according to claim 27, wherein the method comprises sensing the leakage magnetic flux with a motor flux leakage sensor arranged on an external surface of a frame of the motor or the motor'"'"'s shaft.