Sensor data integration and event detection

Patent metadata

Field	Value
Publication number	US-12422283-B2
Application number	US-202017906567-A
Country	US
Kind code	B2
Filing date	Mar 17, 2020
Priority date	Mar 17, 2020
Publication date	Sep 23, 2025
Grant date	Sep 23, 2025

Abstract

A method for time alignment of sensor having a plurality of sensors for use in sensor data integration. A reference signal, with timestamp, is provided to each sensor. Output signals in response to the reference signal are identified and used to determine a time delay for response for the sensors. These time delays are stored applying time corrections to sensor data during sensor data integration used in event detection. An associated method of detecting events from sensor data from a plurality of sensors is disclosed. A threshold is determined for each of the sensors, such that a signal exceeding the threshold is identified as a potential sensor event. Potential sensor events from each sensor are detected and when potential events from at least two sensors fall within a predetermined time window this is identified to be a likely actual event.

First claim

The invention claimed is:

1. A method of detecting events from sensor data from a plurality of sensors, the method comprising:
determining a threshold for each of the sensors, whereby a signal exceeding the threshold is identified as a potential sensor event;
receiving the sensor data, and detecting potential sensor events from each of the sensors;
identifying when potential sensor events from two or more sensors fall within a predetermined time window;
performing time alignment of the sensor data for sensor data integration, wherein performing the time alignment comprises finding a preferred timing offset for each sensor, and wherein, for one or more of the sensors, the preferred timing offset is averaged over multiple readings;
based on the time-aligned sensor data, determining that the potential sensor events occur at a same point in time;
based on determining that the potential sensor events occur at the same point in time, determine that the potential sensor events correspond to an actual event; and
providing a representation of the actual event from the integrated sensor data.

2. The method of claim 1 , wherein the preferred timing offset is a windowed average over the last N readings.

3. The method of any of claim 1 , wherein time alignment comprises using time delays for the plurality of sensors established using a method having the steps of:
determining a plurality of sensors for use in sensor data integration;
providing a reference signal with timestamp to each of the sensors in the plurality of sensors;
detecting an output signal from each of the sensors in response to the reference signal, and determining a time delay for response for each of the sensors; and
storing the time delay for each sensor for applying time corrections for the plurality of sensors during sensor data integration.

4. The method of claim 1 , wherein the representation of the actual event comprises an identification of the sensors that have detected that actual event.

5. A computing apparatus comprising a processor and a memory, wherein the processor is programmed to perform the method of claim 1 , and wherein the computing apparatus is connected to receive sensor data from the plurality of sensors used in the method.

6. The computing apparatus of claim 5 , wherein the computing apparatus is adapted to provide the representation of the actual event to a remote computing system.

7. A control system comprising a programmed processor, wherein:
the control system is adapted to receive representations of actual events obtained according to claim 1 ; and
the programmed processor is adapted to analyse a system using the received representations of actual events, and to determine control operations or a control strategy therefrom.

8. The control system of claim 7 , where the control system is a power management system for an environment and the actual events are events associated with the environment.

9. The method of claim 1 , wherein performing the time alignment of sensor data comprises:
ranking the sensor data in time order;
selecting a first measurement as a time alignment point for the sensor data;
recovering a time stamp for each measurement of the sensor data; and
performing a delay correction on each measurement of the sensor data based the timing offset for each sensor.

10. The method of claim 9 , wherein the time order is oldest first.

11. The method of claim 10 , wherein the first measurement is an oldest measurement of the sensor data.

12. The method of claim 9 , wherein the delay correction on each measurement is performed by subtracting the preferred timing offset from the time stamp for each measurement of sensor data.

13. A system for detecting events, comprising:
a plurality of sensors, wherein each of the sensors has a stored time delay for response and a threshold for detection of a potential sensor event; and
a programmed processor, adapted to identify potential sensor events from the plurality of sensors and to use the stored time delays for relevant sensors from the plurality of sensors to determine whether identified potential sensor events corresponds to an actual event based on determining that the identified potential sensor events occurred at the same point in time, wherein determining that the identified potential sensor events occurred at the same point in time is based on performing time alignment of sensor data for sensor data integration, wherein performing the time alignment comprises finding a preferred timing offset for each sensor of the plurality of sensors, and wherein for one or more of the plurality of sensors the preferred timing offset is averaged over multiple readings.

14. The system of claim 13 , wherein the programmed processor is adapted to provide a representation of the event to a remote computing system.

15. The system of claim 13 , wherein the programmed processor is adapted to characterise a determined actual event from data received from relevant sensors of the plurality of sensors.

16. A method of detecting events from sensor data from a plurality of sensors, the method comprising:
determining a threshold for each of the sensors, whereby a signal exceeding the threshold is identified as a potential sensor event;
receiving the sensor data, and detecting potential sensor events from each of the sensors;
identifying when potential sensor events from two or more sensors fall within a predetermined time window;
performing time alignment of the sensor data for sensor data integration, wherein performing the time alignment comprises finding a preferred timing offset for each sensor;
based on the time-aligned sensor data, determining that the potential sensor events occur at a same point in time;
based on determining that the potential sensor events occur at the same point in time, determine that the potential sensor events correspond to an actual event; and
providing a representation of the actual event from the integrated sensor data,
wherein performing the time alignment of sensor data further comprises:
ranking the sensor data in time order;
selecting a first measurement as a time alignment point for the sensor data;
recovering a time stamp for each measurement of the sensor data; and
performing a delay correction on each measurement of the sensor data based the timing offset for each sensor.

17. The method of claim 16 , wherein the time order is oldest first.

18. The method of claim 17 , wherein the first measurement is an oldest measurement of the sensor data.

19. The method of claim 16 , wherein the delay correction on each measurement is performed by subtracting the preferred timing offset from the time stamp for each measurement of sensor data.

Assignees

• Eaton Intelligent Power Ltd

Inventors

• Nolan Keith
• Larkin Maebh
• Van De Belt Johannes
• Quinn Ruth

Classifications

• G01D7/02

  Indicating value of two or more variables simultaneously · CPC title

• G01D9/005 Primary

  Solid-state data loggers · CPC title

• G01D21/00 Primary

  Measuring or testing not otherwise provided for · CPC title