Internet-of-Things edge services for device fault detection based on current signals

Patent metadata

Field	Value
Publication number	US-11714738-B2
Application number	US-202117399170-A
Country	US
Kind code	B2
Filing date	Aug 11, 2021
Priority date	Aug 11, 2021
Publication date	Aug 1, 2023
Grant date	Aug 1, 2023

Abstract

Methods, systems, and computer-readable storage media for receiving, by an anomalous operation detection service, current signal data representing a driving current applied to a device over a time period, processing, by an anomalous operation detection service, the current signal data through a deep neural network (DNN) module, a frequency spectrum analysis (FSA) module, and a time series classifier (TSC) module to provide a set of indications, each indication in the set of indications indicating one of normal operation of the device and anomalous operation of the device, processing, by an anomalous operation detection service, the set of indications through a voting gate to provide an output indication, the output indication indicating one of normal operation of the device and anomalous operation of the device, and selectively transmitting one or more of an alert and a message based on the output indication.

First claim

What is claimed is:

1. A computer-implemented method for detecting anomalous operation of devices, the method being executed by one or more processors and comprising:
receiving, by an anomalous operation detection service, current signal data representing a driving current applied to a device over a time period;
processing, by an anomalous operation detection service, the current signal data through a deep neural network (DNN) module, a frequency spectrum analysis (FSA) module, and a time series classifier (TSC) module to provide a set of indications, each indication in the set of indications indicating one of normal operation of the device and anomalous operation of the device;
processing, by an anomalous operation detection service, the set of indications through a voting gate to provide an output indication, the output indication indicating one of normal operation of the device and anomalous operation of the device; and
selectively transmitting one or more of an alert and a message based on the output indication.

2. The method of claim 1 , wherein processing the current signal data through a DNN module comprises:
receiving, by the DNN module, the current signal data;
normalizing, by the DNN module, the current signal data to provide normalized data;
inputting, by the DNN module, the normalized data to a DNN, the DNN providing a prediction; and
providing an indication of the set of indications based on the prediction.

3. The method of claim 2 , wherein the DNN is specific to the device.

4. The method of claim 1 , wherein processing the current signal data through a FSA module comprises:
receiving, by the FSA module, the current signal data;
processing, by the FSA module, through each of a Hanning window sub-module, a Hamming window sub-module, and a Blackman sub-module, each processing the current signal data through a respective window function to provide an adjusted input, and processing the adjusted input through a fast Fourier transform (FFT) to provide a converted input; and
outputting, by the FSA module, a sub-set of indications based on converted outputs of the Hanning window sub-module, the Hamming window sub-module, and the Blackman sub-module.

5. The method of claim 4 , wherein the sub-set of indications comprises an indication based on converted outputs of the Hanning window sub-module and the Hamming window sub-module, and an indication based on the converted output of the Blackman window sub-module.

6. The method of claim 1 , wherein processing the current signal data through a TSC module comprises:
receiving, by the TSC module, the current signal data;
processing, by the TSC module, the current signal data using dynamic time warping (DTW) to provide a comparison between the current signal to a groundtruth current signal; and
providing an indication of the set of indications based on the comparison.

7. The method of claim 1 , wherein the device is an Internet-of-Things (IoT) device and the anomalous operation detection service is executed as an edge service remote from a cloud platform.

8. A non-transitory computer-readable storage medium coupled to one or more processors and having instructions stored thereon which, when executed by the one or more processors, cause the one or more processors to perform operations for detecting anomalous operation of devices, the operations comprising:
receiving, by an anomalous operation detection service, current signal data representing a driving current applied to a device over a time period;
processing, by an anomalous operation detection service, the current signal data through a deep neural network (DNN) module, a frequency spectrum analysis (FSA) module, and a time series classifier (TSC) module to provide a set of indications, each indication in the set of indications indicating one of normal operation of the device and anomalous operation of the device;
processing, by an anomalous operation detection service, the set of indications through a voting gate to provide an output indication, the output indication indicating one of normal operation of the device and anomalous operation of the device; and
selectively transmitting one or more of an alert and a message based on the output indication.

9. The non-transitory computer-readable storage medium of claim 8 , wherein processing the current signal data through a DNN module comprises:
receiving, by the DNN module, the current signal data;
normalizing, by the DNN module, the current signal data to provide normalized data;
inputting, by the DNN module, the normalized data to a DNN, the DNN providing a prediction; and
providing an indication of the set of indications based on the prediction.

10. The non-transitory computer-readable storage medium of claim 9 , wherein the DNN is specific to the device.

11. The non-transitory computer-readable storage medium of claim 8 , wherein processing the current signal data through a FSA module comprises:
receiving, by the FSA module, the current signal data;
processing, by the FSA module, through each of a Hanning window sub-module, a Hamming window sub-module, and a Blackman sub-module, each processing the current signal data through a respective window function to provide an adjusted input, and processing the adjusted input through a fast Fourier transform (FFT) to provide a converted input; and
outputting, by the FSA module, a sub-set of indications based on converted outputs of the Hanning window sub-module, the Hamming window sub-module, and the Blackman sub-module.

12. The non-transitory computer-readable storage medium of claim 11 , wherein the sub-set of indications comprises an indication based on converted outputs of the Hanning window sub-module and the Hamming window sub-module, and an indication based on the converted output of the Blackman window sub-module.

13. The non-transitory computer-readable storage medium of claim 8 , wherein processing the current signal data through a TSC module comprises:
receiving, by the TSC module, the current signal data;
processing, by the TSC module, the current signal data using dynamic time warping (DTW) to provide a comparison between the current signal to a groundtruth current signal; and
providing an indication of the set of indications based on the comparison.

14. The non-transitory computer-readable storage medium of claim 8 , wherein the device is an Internet-of-Things (IoT) device and the anomalous operation detection service is executed as an edge service remote from a cloud platform.

15. A system, comprising:
a computing device; and
a computer-readable storage device coupled to the computing device and having instructions stored thereon which, when executed by the computing device, cause the computing device to perform operations for detecting anomalous operation of devices, the operations comprising:
receiving, by an anomalous operation detection service, current signal data representing a driving current applied to a device over a time period;
processing, by an anomalous operation detection service, the current signal data through a deep neural network (DNN) module, a frequency spectrum analysis (FSA) module, and a time series classifier (TSC) module to provide a set of indications, each indication in the set of indications indicating one of normal operation of the device and anomalous operation of the device;
processing, by an anomalous operation detection service, the set of indications through a voting gate to provide an output indication, the output indication indicating one of normal operation of the device and anomalous operation of the device; and
selectively transmitt

Assignees

• Sap Se

Inventors

• He Jie
• Chen Jianwei
• Wang Xuemin

Classifications

• G06F11/3089 Primary

  Monitoring arrangements determined by the means or processing involved in sensing the monitored data, e.g. interfaces, connectors, sensors, probes, agents (software debugging using additional hardware using a specific debug interface G06F11/3656; performance evaluation by tracing or monitoring G06F11/3466) · CPC title

• G06F11/0772

  Means for error signaling, e.g. using interrupts, exception flags, dedicated error registers · CPC title

• G06F11/3075

  the data filtering being achieved in order to maintain consistency among the monitored data, e.g. ensuring that the monitored data belong to the same timeframe, to the same system or component · CPC title

• G06F17/142 Primary

  Fast Fourier transforms, e.g. using a Cooley-Tukey type algorithm · CPC title

• G06N3/04

  Architecture, e.g. interconnection topology · CPC title