Systems and methods for monitoring and diagnosing power system assets

Patent metadata

Field	Value
Publication number	US-11835568-B2
Application number	US-202016951998-A
Country	US
Kind code	B2
Filing date	Nov 18, 2020
Priority date	Nov 18, 2020
Publication date	Dec 5, 2023
Grant date	Dec 5, 2023

Abstract

Systems, methods, and computer-readable media are disclosed for monitoring and diagnosing power system assets. An example method may include triggering, by a gateway device and at a first time, a capture of a first waveform from a first intelligent electronic device (IED) associated with a first asset in a power system. The method may also include transmitting, by the gateway device, the capture of the waveform to a remote device. The method may also include extracting fault features from the first waveform corresponding to different failure modes associated with the asset of the power system. The method may also include determining, based on the features extracted from first waveform, that a fault of a first fault mode has occurred in the asset. The method may also include providing an alert that the fault has been identified, wherein the alert initiates or otherwise facilitates a control action in the power system.

First claim

That which is claimed is:

1. A method comprising:
triggering, by a gateway device and at a first time, based on at least one of a first sampling frequency or a first data length of a first intelligent electronic device (IED), a capture of a first waveform from the first IED, the first IED associated with a first asset in a power system;
transmitting, by the gateway device, the first waveform to a remote device;
creating a first cluster of assets including the first asset and a second asset;
triggering, by the gateway device, based on at least one of a second sampling frequency or a second data length of a second IED, a capture of a second waveform from the second IED, the second IED associated with the second asset in the power system;
sending, by the gateway device and to the remote device, the second waveform;
establishing an operational baseline for the first cluster of assets based on the first waveform and the second waveform;
extracting fault features from the first waveform corresponding to different failure modes associated with the first asset of the power system;
determining, based on the features extracted from first waveform, that a fault of a first fault mode has occurred in the first asset; and
providing an alert that the fault has been identified, wherein the alert initiates or facilitates a control action in the power system.

2. The method of claim 1 , wherein the first waveform is associated with a first failure mode of the first asset, and wherein triggering the capture of the first waveform is based on a determination that the sampling frequency or the data length of the first IED for the first failure mode satisfies a first threshold sampling frequency or first threshold data length for the first failure mode.

3. The method of claim 1 , further comprising:
determining that the sampling frequency or the data length of the first IED for a second failure mode fails to satisfy a second threshold sampling frequency or a second threshold data length for the second failure mode, wherein second threshold sampling frequency or a second threshold data length are different than a first threshold sampling frequency or a first threshold data length associated with a first failure mode; and
blocking, based on the determination that the sampling frequency or the data length associated with the first IED for the second failure mode fails to satisfy the second threshold sampling frequency or the second threshold data length of the second failure mode, feature extraction and fault detections associated with the second failure mode for the first TED.

4. The method of claim 1 , further comprising:
determining that a fault feature of the second waveform deviates from the operational baseline for the first cluster of assets; and
determining, based on the determination that a fault feature of the second waveform deviates from the operational baseline for the first cluster of assets, that a fault of a first fault mode has occurred in a first asset associated with the first IED.

5. The method of claim 1 , wherein the second waveform is captured at a second time corresponding to a start-up of the first IED.

6. The method of claim 1 , wherein establishing the operational baseline for the first cluster further comprises establishing an operational baseline for a first data bin comprising a first range of operating conditions for the first cluster, and wherein the method further comprises establishing a second operational baseline for the first cluster for a second data bin comprising a second range of operating conditions for the first cluster, wherein the first data bin comprises a first fault index different than a second fault index of the second bin.

7. The method of claim 1 , wherein the method further comprises:
reducing, subsequent to triggering the capture of the first waveform from the first TED, a first triggering rate for capturing subsequent waveforms to a second triggering rate; and
increasing, based on the determination that the first fault mode has occurred in the first asset, the first triggering rate to a third triggering rate that is higher than the second triggering rate.

8. The method of claim 1 , further comprising:
performing, by the gateway device, at least one of a first data quality check or a second data quality check, wherein transmitting the capture of the first waveform to the remote device is further based on the first waveform passing the first data quality check or the second data quality check,
wherein the first data quality check involves comparing low frequency data to one or more threshold values, the low frequency data including at least one of: root mean square (RMS) voltage, RMS current, or frequency,
wherein the second data quality check involves a high frequency data analysis including at least one of: a phase-locked loop (PLL) or envelope extraction of voltage and current signals in the first waveform to make a transient stability determination.

9. The method of claim 1 , further comprising:
forming a baseline of extracted fault indices in a multidimensional bin, wherein the operational baseline is based on the baseline of the extracted fault indices; and
identifying a deviation of a fault index from the baseline corresponding to the multidimensional bin, wherein determining that the fault has occurred in the first asset is based on identifying the deviation of the fault index.

10. A system comprising:
at least one processor; and
at least one memory storing computer-executable instructions, that when executed by the at least one processor, cause the at least one processor to:
trigger, by a gateway device and at a first time, based on at least one of a first sampling frequency or a first data length of a first intelligent electronic device (IED), a capture of a first waveform from the first TED, the first TED associated with a first asset in a power system;
transmit, by the gateway device, the capture of the first waveform to a remote device;
create a first cluster of assets including the first asset and a second asset;
trigger, by the gateway device, based on at least one of a second sampling frequency or a second data length of a second TED, a capture of a second waveform from the second TED, the second TED associated with the second asset in the power system;
send, by the gateway device and to the remote device, the second waveform;
establish an operational baseline for the first cluster of assets based on the first waveform and the second waveform;
extract fault features from the first waveform corresponding to different failure modes associated with the first asset of the power system;
determine, based on the features extracted from first waveform, that a fault of a first fault mode has occurred in the first asset; and
provide an alert that the fault has been identified, wherein the alert initiates or facilitates a control action in the power system.

11. The system of claim 10 , wherein the first waveform is associated with a first failure mode of the first asset, and wherein triggering the capture of the first waveform is based on a determination that the sampling frequency or the data length of the first IED for the first failure mode satisfies a first threshold sampling frequency or first threshold data length for the first failure mode.

12. The system of claim 10 , wherein the computer-executable instructions further cause the at least one processor to:
determine that the sampling frequency or the data length of the first IED for a second failure mode fails to satisfy a second threshold sampling frequency or a second threshold data length for the second failure mode, wherein second threshold sampli

Assignees

• Gen Electric

Inventors

• Pamulaparthy Balakrishna
• Shahid Ali
• Mohan Sumitha
• Kommu Rajagopal
• Gurrapu Raju
• Dominguez Ruiz Sergio

Classifications

• G01R31/00 Primary

  Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere ({measuring superconductive properties G01R33/1238;} testing line transmission systems H04B3/46; testing or measuring semiconductors or solid state devices during manufacture {H10P74/00}) · CPC title

• G01R13/00

  Arrangements for displaying electric variables or waveforms · CPC title

• G01R31/34

  Testing dynamo-electric machines · CPC title

• G05B23/0205

  by means of a monitoring system capable of detecting and responding to faults · CPC title

• G06F1/28

  Supervision thereof, e.g. detecting power-supply failure by out of limits supervision · CPC title