System and method for improved accuracy of detecting meter removal or physical tampering

Patent metadata

Field	Value
Publication number	US-11709074-B2
Application number	US-202117143410-A
Country	US
Kind code	B2
Filing date	Jan 7, 2021
Priority date	Jan 7, 2021
Publication date	Jul 25, 2023
Grant date	Jul 25, 2023

Abstract

Methods and system for detecting tampering of a meter. A continuous stream of raw sensor values can be received from one or more meters among a group of meters. In response to receiving the continuous stream of raw sensor values from the meter(s), a model of normal sensor values can be automatically constructed for each meter among the group of meters based on the raw sensor values obtained from the meter(s) and based on data obtained through an ongoing development of the meter(s) or through automated machine learning by the meter(s). The model of normal sensor values can be used to detect abnormal conditions with respect to the meter(s). The abnormal conditions detected with respect to the meter(s) are potentially indicative of a removal of the meter(s) or of an attempt to physically tamper with the meter(s).

First claim

What is claimed is:

1. A method for detecting tampering of a meter, comprising:
receiving a continuous stream of raw sensor values from at least one meter among a plurality of meters;
in response to receiving the continuous stream of raw sensor values from the at least one meter, automatically constructing a model of normal sensor values for each meter among the plurality of meters based on the raw sensor values obtained from the at least one meter among the plurality of meters and based on data obtained through an ongoing development of the at least one meter or through automated machine learning by the at least one meter; and
using the model of normal sensor values to detect abnormal conditions with respect to the at least one meter, wherein at least some of the abnormal conditions detected with respect to the at least one meter are potentially indicative of a removal of the at least one meter or of an attempt to physically tamper with the at least one meter.

2. The method of claim 1 further comprising detecting the abnormal conditions with respect to the at least one meter by comparing abnormal conditions against the model of normal sensor values.

3. The method of claim 1 wherein the at least one meter comprises an electrical meter.

4. The method of claim 1 wherein the at least one meter comprises a gas meter.

5. The method of claim 1 wherein the at least one meter comprises at least one of: an electrical meter; and
a gas meter.

6. The method of claim 1 wherein the model of normal sensor values is further constructed based on data obtained external to the at least one meter.

7. The method of claim 6 wherein the data obtained external to the at least one meter comprises at least one of:
temperature data;
weather data; and
outage data associated with meters located near the at least one meter.

8. A system for detecting tampering of a meter, comprising:
at least one processor; and
a non-transitory computer-usable medium embodying computer program code, the computer-usable medium capable of communicating with the at least one processor, the computer program code comprising instructions executable by the at least one processor and operable for:
receiving a continuous stream of raw sensor values from at least one meter among a plurality of meters;
in response to receiving the continuous stream of raw sensor values from the at least one meter, automatically constructing a model of normal sensor values for each meter among the plurality of meters based on the raw sensor values obtained from the at least one meter among the plurality of meters and based on data obtained through an ongoing development of the at least one meter or through automated machine learning by the at least one meter; and
using the model of normal sensor values to detect abnormal conditions with respect to the at least one meter, wherein at least some of the abnormal conditions detected with respect to the at least one meter are potentially indicative of a removal of the at least one meter or of an attempt to physically tamper with the at least one meter.

9. The system of claim 8 wherein the instructions are further operable for detecting the abnormal conditions with respect to the at least one meter by comparing abnormal conditions against the model of normal sensor values.

10. The system of claim 8 wherein the at least one meter comprises an electrical meter.

11. The system of claim 8 wherein the at least one meter comprises a gas meter.

12. The system of claim 8 wherein the at least one meter comprises at least one of: an electrical meter; and
a gas meter.

13. The system of claim 8 wherein the model of normal sensor values is further constructed based on data obtained external to the at least one meter.

14. The system of claim 13 wherein the data obtained external to the at least one meter comprises at least one of:
temperature data;
weather data; and
outage data associated with meters located near the at least one meter.

15. A utility meter system for detecting tampering of a meter, comprising:
at least one meter among a plurality of meters, wherein a continuous stream of raw sensor values is received from the at least one meter among the plurality of meters;
a model of normal sensor values,
wherein in response to receiving the continuous stream of raw sensor values from the at least one meter, the model of normal sensor values is automatically constructed for each meter among the plurality of meters based on the raw sensor values obtained from the at least one meter among the plurality of meters and based on data obtained through an ongoing development of the at least one meter or through automated machine learning by the at least one meter;
wherein the model of normal sensor values is used to detect abnormal conditions with respect to the at least one meter; and
wherein at least some of the abnormal conditions detected with respect to the at least one meter are potentially indicative of a removal of the at least one meter or of an attempt to physically tamper with the at least one meter.

16. The utility meter system of claim 15 wherein the abnormal conditions with respect to the at least one meter are detected by comparing abnormal conditions against the model of normal sensor values.

17. The utility meter system of claim 16 wherein the model of normal sensor values is further constructed based on data obtained external to the at least one meter.

18. The utility meter system of claim 15 wherein the at least one meter comprises at least one of: an electrical meter; and
a gas meter.

19. The utility meter system of claim 15 wherein the model of normal sensor values is further constructed based on data obtained external to the at least one meter.

20. The utility meter system of claim 19 wherein the data obtained external to the at least one meter comprises at least one of:
temperature data;
weather data; and
outage data associated with meters located near the at least one meter.

Assignees

• Honeywell Int Inc

Inventors

• Scoggins Sean

Classifications

• G01D3/08 Primary

  with provision for safeguarding the apparatus, e.g. against abnormal operation, against breakdown · CPC title

• G01D4/002

  Remote reading of utility meters · CPC title

• G01R11/24

  Arrangements for avoiding or indicating fraudulent use · CPC title

• G06N20/00

  Machine learning · CPC title

• G01R22/066 Primary

  Arrangements for avoiding or indicating fraudulent use · CPC title