Patent application title: METHODS AND SYSTEMS FOR DATA COLLECTION, LEARNING, AND STREAMING OF MACHINE SIGNALS FOR ANALYTICS AND PREDICTED MAINTENANCE USING THE INDUSTRIAL INTERNET OF THINGS
Inventors:
IPC8 Class: AG05B2302FI
USPC Class:
1 1
Class name:
Publication date: 2020-05-28
Patent application number: 20200166922
Abstract:
An industrial machine predictive maintenance system may include an
industrial machine data analysis facility that generates streams of
industrial machine health monitoring data by applying machine learning to
data representative of conditions of portions of industrial machines
received via a data collection network. The system may include an
industrial machine predictive maintenance facility that produces
industrial machine service recommendations responsive to the health
monitoring data by applying machine fault detection and classification
algorithms thereto. The system detects an operating characteristic of an
industrial machine, such as vibration, using one or more sensors of a
mobile data collector and identify, as a condition of the industrial
machine, a characteristic for the industrial machine within the knowledge
base. The system can determine severity of the condition and predict and
execute a maintenance action to perform against the industrial machine
based on the severity of the condition.Claims:
1. A system comprising: an industrial machine comprising at least one
vibration sensor disposed to capture vibration of a portion of the
industrial machine; a mobile data collector that generates vibration data
by collecting the captured vibration from the at least one vibration
sensor; a multi-segment vibration frequency spectra structure that
facilitates mapping the captured vibration to one vibration frequency
segment of a multi-segment vibration frequency; a severity unit algorithm
that receives the frequency of the vibration and the corresponding
vibration frequency segment and produces a severity value which is then
mapped to one of a plurality of severity units defined for the
corresponding vibration frequency segment; and a signal generating
circuit that receives the one of the plurality of severity units, and
based thereon, signals a predictive maintenance server to execute a
corresponding maintenance action on the portion of the industrial
machine.
2. The system of claim 1, wherein the mobile data collector is a mobile robot.
3. The system of claim 1, wherein the mobile data collector is a mobile vehicle.
4. The system of claim 1, wherein the mobile data collector is a handheld device.
5. The system of claim 1, wherein the mobile data collector is a wearable device.
6. The system of claim 1, wherein the segment of a multi-segment vibration frequency spectra that bounds the vibrations is determined by mapping the vibrations to one of a number of severity units based on the determined segment, wherein each of the severity units corresponds to a different range of the multi-segment vibration frequency spectra.
7. The system of claim 6, wherein the severity unit algorithm maps the captured vibration to one vibration frequency segment of a multi-segment vibration frequency by: mapping the vibrations to a first severity unit when the frequency of the vibrations corresponds to a below a low-end knee threshold-range of the multi-segment vibration frequency spectra; mapping the vibrations to a second severity unit when the frequency of the vibrations corresponds to a mid-range of the multi-segment vibration frequency spectra; and mapping the vibrations to a third severity unit when the frequency of the vibrations corresponds to an above a high-end knee threshold-range of the multi-segment vibration frequency spectra.
8. A method, comprising: detecting an operating characteristic of an industrial machine using one or more sensors of a mobile data collector; transmitting data indicative of the operating characteristic to a server over a network; using intelligent systems associated with the server to process the operating characteristic against pre-recorded data for the industrial machine, wherein processing the operating characteristic against the pre-recorded data for the industrial machine includes identifying the pre-recorded data for the industrial machine within a knowledge base associated with an industrial environment that includes the industrial machine; identifying, as a condition of the industrial machine, a characteristic indicated by the pre-recorded data for the industrial machine within the knowledge base; determining a severity of the condition, the severity representing an impact of the condition on the industrial machine; predicting a maintenance action to perform against the industrial machine based on the severity of the condition; and storing a transaction record of the predicted maintenance action within a ledger of service activity associated with the industrial machine.
9. The method of claim 8, wherein the mobile data collector is a mobile robot.
10. The method of claim 8, wherein the mobile data collector is a mobile vehicle.
11. The method of claim 8, wherein the mobile data collector is a handheld device.
12. The method of claim 8, wherein the mobile data collector is a wearable device.
13. The method of claim 8, wherein the condition of the industrial machine relates to vibrations detected for at least a portion of the industrial machine, wherein determining the severity of the condition comprises: determining a frequency of the vibrations; determining a segment of a multi-segment vibration frequency spectra that bounds the vibrations; and calculating the severity for the detected vibrations based on the determined segment.
14. The method of claim 13, wherein the severity corresponds to a severity unit, wherein the segment of a multi-segment vibration frequency spectra that bounds the vibrations is determined by mapping the vibrations to one of a number of severity units based on the determined segment, wherein each of the severity units corresponds to a different range of the multi-segment vibration frequency spectra.
15. The method of claim 14, further comprising: mapping the vibrations to a first severity unit when the frequency of the vibrations corresponds to a below a low-end knee threshold-range of the multi-segment vibration frequency spectra; mapping the vibrations to a second severity unit when the frequency of the vibrations corresponds to a mid-range of the multi-segment vibration frequency spectra; and mapping the vibrations to a third severity unit when the frequency of the vibrations corresponds to an above a high-end knee threshold-range of the multi-segment vibration frequency spectra.
16. The method of claim 8, wherein the ledger uses a blockchain structure to track transaction records for predicted maintenance actions for the industrial machine, wherein each of the transaction records is stored as a block in the blockchain structure.
17. The method of claim 8, wherein the condition of the industrial machine relates to a temperature detected for at least a portion of the industrial machine.
18. The method of claim 8, wherein the condition of the industrial machine relates to an electrical output detected for at least a portion of the industrial machine.
19. The method of claim 8, wherein the condition of the industrial machine relates to a magnetic output detected for at least a portion of the industrial machine.
20. The method of claim 8, wherein the condition of the industrial machine relates to a sound output detected for at least a portion of the industrial machine.
Description:
User Contributions:
Comment about this patent or add new information about this topic: