Methods and systems for data collection, learning, and streaming of machine signals for analytics and maintenance using the industrial Internet of Things
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 may perform a method of predicting a service event from vibration data captured data from at least one vibration sensor disposed to capture vibration of a portion of an industrial machine. A signal in a predictive maintenance circuit for executing a maintenance action on the portion of the industrial machine can be generated based on a severity unit calculated for the captured vibration.
1. A method of predicting a service event from vibration data, comprising:
capturing vibration data from at least one vibration sensor disposed to capture vibration of a portion of an industrial machine;
determining at least one of a velocity, and amplitude, or an acceleration level indicative of the captured vibration;
determining a segment of a multi-segment vibration frequency spectrum that bounds the captured vibration based on a frequency of the captured vibration;
calculating a vibration severity unit for the captured vibration based on the determined segment and at least one of the velocity, the amplitude or the acceleration level;
generating a signal in a predictive maintenance circuit for executing a maintenance action on the portion of the industrial machine based on the severity unit; and
when the severity unit indicates immediate action, triggering an automatic action for the industrial machine, wherein the automatic action comprises one or more of stopping use of the industrial machine, reducing a duty cycle of the industrial machine, or reducing an operating cycle rate of the industrial machine,
wherein calculating a vibration severity unit comprises producing a severity value by multiplying one of a plurality of severity normalizing values by a mid-range severity limit and mapping the severity value to one of a plurality of severity unit ranges of the determined segment, and
wherein a first severity normalizing value of the plurality of normalizing values is calculated by dividing the frequency of the captured vibration by a low-end frequency value of a mid-segment of the multi-segment vibration frequency spectrum.
2. The method of claim 1 , wherein the segment is determined based on comparing the frequency of the captured vibration to an upper limit and a lower limit of a mid-segment of the multi-segment vibration frequency spectrum.
3. The method of claim 1 , wherein a first segment of the multi-segment vibration frequency spectrum comprises determined frequency values below a lower limit of a mid-segment of the multi-segment vibration frequency spectrum.
4. The method of claim 3 , wherein the lower limit of the mid-segment of the multi-segment vibration frequency spectrum is 1200 kHz.
5. The method of claim 1 , wherein a second segment of the multi-segment vibration frequency spectrum comprises determined frequency values above an upper limit of a mid-segment of the multi-segment vibration frequency spectrum.
6. The method of claim 5 , wherein the upper limit of the mid-segment of the multi-segment vibration frequency spectrum is 18000 kHz.
7. The method of claim 1 , wherein the one of the plurality of severity normalizing values comprises the first severity normalizing value when the frequency of the captured vibration is less than the low-end frequency value.
8. The method of claim 1 , wherein a first segment of the multi-segment vibration frequency spectrum is divided into a plurality of severity units based on the amplitude of the captured vibration.
9. The method of claim 1 , wherein a second segment of the multi-segment vibration frequency spectrum is divided into a plurality of severity units based on the acceleration level of the captured vibration.
10. The method of claim 1 , wherein the vibration severity unit is determined based on a peak displacement of the amplitude of the captured vibration for determined vibration frequencies within a first segment of the multi-segment vibration frequency spectrum.
11. The method of claim 1 , wherein the vibration severity unit is determined based on the velocity of the captured vibration for determined vibration frequencies within a second segment of the multi-segment vibration frequency spectrum.
12. The method of claim 1 , wherein the portion of the industrial machine is a moving part.
13. The method of claim 1 , wherein the portion of the industrial machine is a structural member supporting a moving part.
14. The method of claim 1 , wherein the portion of the industrial machine is a motor.
15. The method of claim 1 , wherein the portion of the industrial machine is a drive shaft.
16. The method of claim 1 , wherein a second severity normalizing value of the plurality of normalizing values is calculated by dividing a high-end frequency value of a mid-segment of the multi-segment vibration frequency spectrum by the frequency of the captured vibration.
17. The method of claim 16 , wherein the one of the plurality of severity normalizing values comprises the second severity normalizing value when the frequency of the captured vibration is greater than the high-end frequency value.
18. A method of predicting a service event from vibration data, comprising:
capturing vibration data from at least one vibration sensor disposed to capture vibration of a portion of an industrial machine;
determining at least one of an amplitude, a velocity, or an acceleration level of the captured vibration;
determining a segment of a multi-segment vibration frequency spectrum that bounds the captured vibration based on a frequency of the captured vibration;
calculating a vibration severity unit for the captured vibration based on the determined segment and at least one value of the amplitude or the acceleration level;
generating a signal in a predictive maintenance circuit for executing a maintenance action on the portion of the industrial machine based on the severity unit; and
when the severity unit indicates immediate action, triggering an automatic action for the industrial machine, wherein the automatic action comprises one or more of stopping use of the industrial machine, reducing a duty cycle of the industrial machine, or reducing an operating cycle rate of the industrial machine,
wherein calculating a vibration severity unit comprises producing a severity value by multiplying one of a plurality of severity normalizing values by a mid-range severity limit and mapping the severity value to one of a plurality of severity unit ranges of the determined segment, and
wherein a second severity normalizing value of the plurality of normalizing values is calculated by dividing a high-end frequency value of a mid-segment of the multi-segment vibration frequency spectrum by the frequency of the captured vibration.
19. The method of claim 18 , wherein the one of the plurality of severity normalizing values comprises the second severity normalizing value when the frequency of the captured vibration is greater than the high-end frequency value.
20. The method of claim 18 , wherein the segment is determined based on comparing the frequency of the captured vibration to an upper limit and a lower limit of a mid-segment of the multi-segment vibration frequency spectrum.
21. The method of claim 18 , wherein a first segment of the multi-segment vibration frequency spectrum comprises determined frequency values below a lower limit of a mid-segment of the multi-segment vibration frequency spectrum.
22. The method of claim 21 , wherein the lower limit of the mid-segment of the multi-segment vibration frequency spectrum is 1200 kHz.
23. The method of claim 18 , wherein a second segment of the multi-segment vibration frequency spectrum comprises determined frequency values above an upper limit of a mid-segment of the multi-segment vibration frequency spectrum.
24. The method of claim 23 , wherein the upper limit of the mid-segment of the multi-segment vibration frequency spectrum is 18000 kHz.
25. The method of claim 18 , wherein a first segment of the multi-segment vibration frequency spectrum is divided into a plurality of severity units based on the amplitude of the captured vibration.
26. The method of claim 18 , wherein a second segment of the multi-segment vibration frequency spectrum is divided into a plurality of severity units based on the velocity of the captured vibration.
27. The method of claim 18 , wherein the vibration severity unit is determined based on a peak displacement of the amplitude of the captured vibration for determined vibration frequencies within a first segment of the multi-segment vibration frequency spectrum.
28. The method of claim 18 , wherein the vibration severity unit is determined based on the velocity of the captured vibration for determined vibration frequencies within a second segment of the multi-segment vibration frequency spectrum.
29. The method of claim 18 , wherein the portion of the industrial machine is a moving part.
30. The method of claim 18 , wherein the portion of the industrial machine is a structural member supporting a moving part.
31. The method of claim 18 , wherein the portion of the industrial machine is a motor.
32. The method of claim 18 , wherein the portion of the industrial machine is a drive shaft.