Extracting overall equipment effectiveness by analysis of a vibro-acoustic signal
A method includes acquiring, by a vibro-acoustic sensor in a vicinity of a machine, vibro-acoustic signals due to an operation of the machine. The acquired vibro-acoustic signals are analyzed so as to estimate at least two operational parameters of the machine, selected from a group of the operational parameters consisting of an uptime factor, a production speed factor, and a production quality factor of the machine. An overall equipment effectiveness (OEE) of the machine is computed, the computed OEE including at least one of a minimum and a product of the at least two estimated operational parameters.
1. A method, comprising:
acquiring, by a vibro-acoustic sensor in a vicinity of a machine, vibro-acoustic signals due to an operation of the machine;
estimating, based on the acquired vibro-acoustic signals, an uptime factor, a production speed factor and a production quality factor of the machine, wherein estimating the production quality factor comprises:
comparing a vibro-acoustic signature of a production step against a baseline of prerecorded vibro-acoustic signatures for that step;
classifying machine production quality at each compared step as being high or low based on a confidence level derived from the baseline of prerecorded vibro-acoustic signatures; and
counting production events having a vibro-acoustic signature indicative of a low-quality production step; and
computing an overall equipment effectiveness (OEE) of the machine comprising at least one of a minimum and a product of the uptime factor, the production speed factor and the production quality factor, all estimated based on the acquired vibro-acoustic signals.
2. The method according to claim 1 , wherein estimating the uptime factor comprises classifying a root mean square (RMS) of the vibro-acoustic signal emitted by the machine as being above a given threshold.
3. The method according to claim 1 , wherein estimating the production speed factor comprises demodulating the acquired vibro-acoustic signals and analyzing the demodulated vibro-acoustic signals.
4. The method according to claim 1 , wherein estimating the production speed factor comprises iteratively estimating a median of the production speed and estimating a probability density function of the production speed using the iteratively estimated median.
5. The method according to claim 1 , wherein the derived confidence level is provided in a given number of standard deviations from to a median of a statistical distribution derived from the baseline of prerecorded vibro-acoustic signatures.
6. The method according to claim 1 , wherein estimating the OEE is performed in real time while acquiring the vibro-acoustic signals.
7. The method according to claim 1 , and comprising presenting the estimated OEE to a user.
8. The method according to claim 1 , and comprising identifying and indicating that the OEE is in a declining trend.
9. The method according to claim 1 , and comprising issuing an alert when the OEE is below a given minimum.
10. A system, comprising:
a vibro-acoustic sensor in a vicinity of a machine, the vibro-acoustic sensor configured to acquire vibro-acoustic signals due to an operation of the machine; and
a processor, which is configured to:
estimate, based on the acquired vibro-acoustic signals, an uptime factor, a production speed factor and a production quality factor of the machine, wherein the processor is configured to estimate the production quality factor by:
comparing a vibro-acoustic signature of a production step against a baseline of prerecorded vibro-acoustic signatures for that step;
classifying machine production quality at each compared step as being high or low based on a confidence level derived from the baseline of prerecorded vibro-acoustic signatures; and
counting production events having a vibro-acoustic signature indicative of a low-quality production step; and
compute an overall equipment effectiveness (OEE) of the machine comprising at least one of a minimum and a product of the uptime factor, the production speed factor and the production quality factor, all estimated based on the acquired vibro-acoustic signals.
11. The system according to claim 10 , wherein the processor is configured to estimate the uptime factor by classifying a root mean square (RMS) of the vibro-acoustic signal emitted by the machine as being above a given threshold.
12. The system according to claim 10 , wherein the processor is configured to estimate the production speed factor by demodulating the acquired vibro-acoustic signals and analyzing the demodulated acquired vibro-acoustic signals.
13. The system according to claim 10 , wherein the processor is configured to estimate the production speed factor by iteratively estimating a median of the production speed and estimating a probability density function of the production speed using the iteratively estimated median.
14. The system according to claim 10 , wherein the derived confidence level is provided in a given number of standard deviations from to a median of a statistical distribution derived from the baseline of prerecorded vibro-acoustic signatures.
15. The system according to claim 10 , wherein the processor is configured to estimate the OEE in real time while acquiring the vibro-acoustic signals.
16. The system according to claim 10 , wherein the processor is further configured to present the estimated OEE to a user.
17. The system according to claim 10 , wherein the processor is further configured to identify and indicate that the OEE is in a declining trend.
18. The system according to claim 10 , wherein the processor is further configured to alert when the OEE is below a given minimum.