IP Library Granted Patent US 11,620,181
Granted Patent B2
US 11,620,181 · App. 17/654,988 · Granted Apr 4, 2023

Utility infrastructure fault detection and monitoring

Inventors: Timothy Jonathan Barat (Folsom, CA); Zhenhao Chen (Oakland, CA); Prabal Dutta (Ann Arbor, MI)
Assignee: Gridware Technologies Inc.
G06F11/079G05B23/0218
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 11,620,181
App. No.
17/654,988
Granted
Apr 4, 2023
Kind
B2
Abstract

A method may include obtaining, at a server or analysis device, sensor data comprising at least one of vibration data and impulse data from one or more sensor devices coupled to a first utility infrastructure; obtaining training sensor data associated with at least one of the first utility infrastructure from a previous time period and one or more second utility infrastructures; comparing the sensor data with the training sensor data associated with the at least one of the first utility infrastructure from the previous time period and the one or more second utility infrastructures; and identifying or predicting a fault occurrence associated with the first utility infrastructure based on the comparing the sensor data associated with the first utility infrastructure to the training sensor data associated with the at least one of the first utility infrastructure from the previous time period and the one or more second utility infrastructures.

Claims (18)

1. A system comprising:

one or more sensor devices coupled to a first utility infrastructure, the sensor devices comprising:

an enclosure;

one or more internal sensors positioned inside of the enclosure, one or more external sensors positioned at least partly outside of the enclosure, or a combination thereof;

one or more antennae; and

one or more energy-storage features;

one or more processors of a server or analysis device; and

one or more non-transitory computer-readable storage media of the server or analysis device configured to store instructions that, in response to being executed, cause the one or more processors to perform operations, the operations comprising:

obtaining sensor data comprising vibration data from one or more sensor devices coupled to a first utility infrastructure;

obtaining training sensor data associated with at least one of the first utility infrastructure from a previous time period and one or more second utility infrastructures;

comparing the sensor data with the training sensor data associated with the at least one of the first utility infrastructure from the previous time period and the one or more second utility infrastructures;

identifying or predicting a fault occurrence associated with the first utility infrastructure based on the comparing the sensor data associated with the first utility infrastructure to the training sensor data associated with the at least one of the first utility infrastructure from the previous time period and the one or more second utility infrastructures, wherein the fault occurrence comprises a deterioration of the first utility infrastructure, wherein the vibration data obtained from the one or more sensor devices comprises a present first oscillatory pattern of the first utility infrastructure due to current flowing through channels coupled to the first utility infrastructure, wherein the training sensor data comprises at least one of a previous first oscillatory pattern of the first utility infrastructure due to current flowing through the channels obtained during the previous time period, a present second oscillatory pattern of a second utility infrastructure due to current flowing through channels coupled to the second utility infrastructure, and a previous second oscillatory pattern of the second utility infrastructure due to current flowing through channels coupled to the second utility infrastructure and obtained during the previous time period, wherein at least one of the previous first oscillatory pattern, the present second oscillatory pattern, and the previous second oscillatory pattern is an oscillation at a frequency between 10 Hz and 50 Hz, and wherein the fault occurrence is identified or predicted when the present first oscillatory pattern is at a frequency below the at least one of the previous first oscillatory pattern, the present second oscillatory pattern, and the previous second oscillatory pattern, wherein the first utility infrastructure is made in part of wood and wherein the deterioration of the first utility infrastructure is caused by at least one of heart rot, rot caused by an insect or animal, and termite damage of the wood making up at least part of the first utility infrastructure; and

transmitting a message, to a computing device, describing the fault occurrence of the first utility infrastructure or summarizing a condition of the first utility infrastructure.

2. The system of claim 1 , wherein the sensor data further comprises at least one of structure-orientation data, gyration data, temperature data, humidity data, atmospheric pressure data, precipitation data, wind velocity data, smoke density data, particulate matter data, gas composition data, magnetic field data, electric field data, microwave radiation data, infrared radiation data, ultraviolet radiation data, visible luminosity data, electromagnetic spectroscopy data, mechanical spectroscopy data, audio data, image data, and video data relating to the utility infrastructure.

3. The system of claim 1 , wherein each of the one or more sensor devices comprises at least one of a vibrometer, an accelerometer, a gyroscope, an acoustic microphone, a video camera, an ambient temperature sensor, a barometer, a hygrometer, a magnetometer, a smoke detector, a visible light meter or photometer, an ultraviolet (UV) light detector, an infrared (IR) light detector, an anemometer or wind sensor, a particulate meter or counter, an electrometer, a multi-field electromagnetic field (EMF) meter, a radio frequency (RF) meter, and a spectrometer.

4. The system of claim 1 , wherein the fault occurrence of the first utility infrastructure is identified or predicted by feeding the sensor data to at least one of a supervised learning model and an unsupervised learning model and obtaining a prediction from the at least one of the supervised learning model and the unsupervised learning model concerning the fault occurrence, and wherein the supervised learning model and the unsupervised learning models are trained using the training sensor data.

5. The system of claim 1 , wherein each of the one or more sensor devices is coupled to the first utility infrastructure at a position at least 3.0 meters above ground level.

6. The system of claim 5 , wherein each of the one or more sensor devices is coupled to the first utility infrastructure via a bracket fixedly fastened to an exterior side of the first utility infrastructure, and wherein at least one of a vibration sustained by the first utility infrastructure or a channel coupled to the first utility infrastructure is passed through the first utility infrastructure via the bracket to each of the one or more sensor devices.

Assignments (2)
INTELLECTUAL PROPERTY SECURITY AGREEMENT Recorded Apr 30, 2025
From: GRIDWARE TECHNOLOGIES INC.
To: JPMORGAN CHASE BANK, N.A.
Reel/Frame 071133/0573 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Apr 22, 2022
From: BARAT, TIMOTHY JONATHAN; CHEN, ZHENHAO; DUTTA, PRABAL
To: GRIDWARE TECHNOLOGIES INC.
Reel/Frame 059685/0603 →
Continuity (2)
Provisional Application 63200653 · Mar 19, 2021
Related Publication 20220300363A1 · Sep 22, 2022