IP Library Patent Application 18073925
Patent Application
App. No. 18/073,925

METHODS AND SYSTEMS FOR SENSOR FUSION IN A PRODUCTION LINE ENVIRONMENT

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 None
App. No.
18/073,925
Abstract

Systems and methods for data collection in an industrial production system including a plurality of components are disclosed. An example system may include a sensor communication circuit structured to interpret a plurality of data values from a sensed parameter group, the sensed parameter group including a plurality of sensors including a vibration sensor and a temperature sensor, and the plurality of sensors operatively coupled to at least one of the plurality of components; a data analysis circuit structured to detect an operating condition of the industrial production system based on detecting that the data values from the vibration sensor indicate a vibration pattern that matches a stored vibration fingerprint together with detecting that the data values from the temperature sensor indicate a change in a temperature; and a response circuit structured to modify a production-related operating parameter of the industrial production system in response to the detected operating condition.

Claims (47)

1 . A system for data collection in an industrial production system including a plurality of components, the system for data collection comprising:

a sensor communication circuit structured to interpret a plurality of data values from a sensed parameter group, wherein the sensed parameter group includes a plurality of sensors including a vibration sensor and a temperature sensor, and wherein the plurality of sensors are operatively coupled to at least one of the plurality of components;

a data analysis circuit structured to detect an operating condition of the industrial production system based on detecting that the data values from the vibration sensor indicate a vibration pattern that matches a stored vibration fingerprint together with detecting that the data values from the temperature sensor indicate a change in a temperature; and

a response circuit structured to modify a production-related operating parameter of the industrial production system in response to the detected operating condition.

2 . The system of claim 1 , wherein the sensed parameter group comprises a fused plurality of sensors including the vibration sensor and the temperature sensor.

3 . The system of claim 2 , further comprising:

a pattern recognition circuit structured to determine a recognized pattern value in response to the plurality of data values from the sensed parameter group comprising the fused plurality of sensors, wherein the recognized pattern value includes a secondary value comprising a component overtemperature value.

4 . The system of claim 1 , further comprising:

an input selection system that determines a fusion of the plurality of sensors including the vibration sensor and the temperature sensor based on learning from feedback to improve prediction of the operating condition.

5 . The system of claim 1 , wherein the data analysis circuit analyzes the data values including a variation in the temperature over time in fusion with the vibration pattern from the vibration sensor.

6 . The system of claim 1 , wherein the data analysis circuit omits an average temperature from a variation in the temperature over time to produce a resulting delta change in the temperature that is processed through a Fourier transform to produce a frequency spectrum, and wherein the data analysis circuit determines whether the frequency spectrum correlates to the operating condition.

7 . The system of claim 1 , further comprising:

a library, wherein the library stores a plurality of vibration fingerprints and associated operating conditions, and wherein the plurality of vibration fingerprints include the stored vibration fingerprint that matches the vibration pattern.

8 . The system of claim 7 , wherein each of the plurality of vibration fingerprints stored in the library includes at least one of a frequency, a spectra, a peak frequency location, a wave peak shape, a waveform shape, a wave envelope shape, phase information, or a phase shift.

9 . The system of claim 1 , wherein the data values from the temperature sensor and the data values from the vibration sensor are multiplexed into a data steam that combines the data values in a time series.

10 . The system of claim 1 , further comprising:

a peak detection circuit structured to verify consistency of timing of peak values between the data values from the vibration sensor and the data values from the temperature sensor.

11 . The system of claim 2 , wherein the fused plurality of sensors is self-organized.

12 . The system of claim 1 , further comprising:

an expert system seeded with the data values from the vibration sensor to determine if a change in a parameter of a machine of the industrial production system affects an intrinsic operation of the machine.

13 . A computer-implemented method for data collection in an industrial production system including a plurality of components, the method comprising:

interpreting a plurality of data values from a sensed parameter group, wherein the sensed parameter group includes a plurality of sensors including a vibration sensor and a temperature sensor, and wherein the plurality of sensors are operatively coupled to at least one of the plurality of components;

detecting an operating condition of the industrial production system based on detecting that the data values from the vibration sensor indicate a vibration pattern that matches a stored vibration fingerprint together with detecting that the data values from the temperature sensor indicate a change in a temperature; and

modifying a production-related operating parameter of the industrial production system in response to the detected operating condition.

14 . The computer-implemented method of claim 13 , wherein the sensed parameter group comprises a fused plurality of sensors including the vibration sensor and the temperature sensor.

15 . The computer-implemented method of claim 14 , further comprising:

determining a recognized pattern value in response to the plurality of data values from the sensed parameter group comprising the fused plurality of sensors, wherein the recognized pattern value includes a secondary value comprising a component overtemperature value.

16 . The computer-implemented method of claim 13 , further comprising:

determining a fusion of the plurality of sensors including the vibration sensor and the temperature sensor based on learning from feedback to improve prediction of the operating condition.

17 . The computer-implemented method of claim 13 , further comprising:

analyzing the data values including a variation in the temperature over time in fusion with the vibration pattern from the vibration sensor.

18 . The computer-implemented method of claim 13 , further comprising:

omitting an average temperature from a variation in the temperature over time to produce a resulting delta change in the temperature;

processing the resulting delta change in the temperature through a Fourier transform to produce a frequency spectrum; and

determining whether the frequency spectrum correlates to the operating condition.

19 . The computer-implemented method of claim 13 , wherein the stored vibration fingerprint is included in a library that stores a plurality of vibration fingerprints and associated operating conditions.

20 . The computer-implemented method of claim 19 , wherein each of the plurality of vibration fingerprints stored in the library includes at least one of a frequency, a spectra, a peak frequency location, a wave peak shape, a waveform shape, a wave envelope shape, phase information, or a phase shift.

21 . The computer-implemented method of claim 13 , further comprising:

multiplexing the data values from the temperature sensor and the data values from the vibration sensor into a data steam that combines the data values in a time series.

22 . The computer-implemented method of claim 13 , further comprising:

verifying consistency of timing of peak values between the data values from the vibration sensor and the data values from the temperature sensor.

23 . The computer-implemented method of claim 13 , further comprising:

detecting the operating condition further based on one or more additional parameters, wherein the one or more additional parameters includes at least one of a decreased flow rate, an increase in the temperature, a material in use, a duration of use, a power source, an installation, or an ambient sensed condition including at least one of an ambient noise or an ambient temperature.

24 . The computer-implemented method of claim 13 , further comprising:

seeding an expert system with the data values from the vibration sensor to determine if a change in a parameter of a machine of the industrial production system affects an intrinsic operation of the machine.

25 . The computer-implemented method of claim 24 , further comprising:

determining that the change in the parameter alters a vibration fingerprint of the machine such that a stored vibration fingerprint of the machine for a normal operation is no longer correct.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jan 13, 2023
From: CELLA, CHARLES HOWARD; DUFFY, GERALD WILLIAM, JR; MCGUCKIN, JEFFREY P.; DESAI, MEHUL
To: STRONG FORCE IOT PORTFOLIO 2016, LLC
Reel/Frame 062367/0471 →