METHODS AND SYSTEMS FOR DATA COLLECTION, LEARNING, AND STREAMING OF MACHINE SIGNALS FOR ANALYTICS AND MAINTENANCE USING THE INDUSTRIAL INTERNET OF THINGS

Abstract

A system generally includes a sensor detecting a condition of an industrial machine, the sensor producing a signal that varies over time and substantially corresponds with the condition; an analog to digital converter that receives the signal and samples the signal at a streaming sample rate that is at least twice a dominant frequency of the signal, the sampled signal being output from the analog to digital converter as a sequence of data values; and at least one digital signal router that receives the sequence of data value and a sub-sampling rate, wherein the sub-sampling rate is lower than the streaming sample rate, and produces at least one sub-sampled output sequence of data comprising select samples from the sequence of samples based on at least one of the sub-sampling rate and a ratio of the streaming sample rate and the sub-sampling rate.

Claims

1. A system comprising: a sensor detecting a condition of an industrial machine, the sensor producing a signal that varies over time and substantially corresponds with the condition; an analog to digital converter that receives the signal and samples the signal at a streaming sample rate that is at least twice a dominant frequency of the signal, the sampled signal being output from the analog to digital converter as a sequence of data values; and at least one digital signal router that receives the sequence of data value and a sub-sampling rate, wherein the sub-sampling rate is lower than the streaming sample rate, and produces at least one sub-sampled output sequence of data comprising select samples from the sequence of samples based on at least one of the sub-sampling rate and a ratio of the streaming sample rate and the sub-sampling rate.

2. The system of claim 1, further comprising a data storage facility that receives the sequence of data values and an analyzed set of data values derived from the sub-sampled output sequence, wherein the analyzed set of data values are stored in association with the sequence of data values such that data values in the sequence of data values that correspond to the sub-sampled output sequence are tagged with indicia that references the corresponding analyzed set of data values.

3. The system of claim 1, wherein producing the at least one sub-sampled output sequence comprises integrating a plurality of samples in the sequence of data values based on a ratio of the sub-sampling rate and the streaming sample rate.

4. The system of claim 1, wherein producing the at least one sub-sampled output sequence comprises selecting samples of the signal based on a ratio of the sub-sampling rate and the streaming sample rate.

5. The system of claim 1, wherein the streaming sample rate is at least twice as fast as a dominant frequency of the signal.

6. The system of claim 1, wherein the ratio of the sub-sampling rate to the streaming sample rate determines a number of supplemental binary bits in the sub-sampled output sequence.

7. The system of claim 6, wherein the number of supplemental binary bits comprises one when the streaming sample rate is at least twice and less than four times the sub-sampling rate.

8. The system of claim 6, wherein the number of supplemental binary bits comprise two when the streaming sample rate is at least four times and less than eight times the sub-sampling rate.

9. A method of predicting maintenance events for industrial machines comprising: generating streams of industrial machine health monitoring data by applying machine learning to data representative of conditions of portions of industrial machines, the condition representative data comprising vibration data for a least one moving part of the industrial machines and being received via a data collection network; accessing, from a data storage device disposed with the industrial machine, moving part-specific configuration information for the at least one moving part of the industrial machine; predicting industrial machine service recommendations responsive to the health monitoring data and the part-specific configuration information by applying machine fault detection and classification algorithms thereto; producing at least one of orders and requests for service and parts responsive to receiving the industrial machine service recommendations; and receiving and processing information regarding services performed on industrial machines responsive to the at least one of orders and requests for service and parts, thereby validating the services performed while producing a ledger of service activity and results for individual industrial machines.

10. The method of claim 9, wherein the industrial machine service recommendations are for an industrial machine.

11. The method of claim 9, wherein the industrial machine service recommendation is for the at least one moving part.

12. The method of claim 11, wherein the last least one moving part is a rotating part of a machine.

13. The method of claim 11, wherein the at least one moving part is disposed in a gear box of a machine.

14. The method of claim 11, wherein the at least one moving part is a gear of the industrial machine.

15. The method of claim 14, wherein applying machine fault detection algorithms comprises adapting reference data representing an industrial machine maintenance recommendation responsive to comparing a count of gear teeth of the gear of the industrial machine with a count of gear teeth of a corresponding gear in the reference data.

16. The method of claim 15, wherein the reference data being adapted is a timing of a maintenance event identified via the industrial machine maintenance recommendation.

17. The method of claim 14, wherein applying machine fault detection algorithms comprises adapting data representing an industrial machine maintenance recommendation for a similar industrial machine responsive to comparing a count of gear teeth of the gear of the industrial machine with a count of gear of a corresponding gear of the similar machine.

18. The method of claim 17, wherein the similar industrial machine data being adapted is a timing of a maintenance event identified via the industrial machine maintenance recommendation.