Automated analysis of non-stationary machine performance
A method for machine monitoring including causing a first sensor to acquire at least a first non-stationary signal from at least one machine operating in a non-stationary manner during at least one operational time frame, causing a second sensor to acquire at least a second non-stationary signal from the at least one machine during the operational time frame, fusing a first non-stationary output provided by the first sensor with a second non-stationary output provided by the second sensor, extracting at least one feature from the fused output, analyzing the at least one feature to ascertain a state of health of the at least one machine and performing at least one operation on the at least one machine based on the state of health as found by the analyzing.
1. A method for operating non-stationarily operating machinery, comprising:
acquiring at least a first non-stationary signal generated by at least one machine operating in a non-stationary manner during at least one operational time frame;
acquiring at least a second non-stationary signal different from said first non-stationary signal and generated by said at least one machine during said at least one operational time frame;
applying a wavelet transform to both of said at least first and second different non-stationary signals;
generating a mask of said wavelet transform of one of said first and second non-stationary signals;
multiplying said mask of said wavelet transform of said one of said first and second non-stationary signals by said wavelet transform of the other one of said first and second non-stationary signals;
extracting at least one feature of at least one of said first and second non-stationary signals based on said multiplying;
analyzing said at least one feature to ascertain a condition of said at least one machine; and
performing at least one of a repair operation, maintenance operation and modification of operating parameters of said at least one machine based on said condition.
2. A method according to claim 1 , wherein said first non-stationary signal is of a same type as said second non-stationary signal.
3. A method according to claim 1 , wherein said first non-stationary signal is of a different type to said second non-stationary signal.
4. A method according to claim 1 , wherein said mask comprises a binary wavelet matrix.
5. A method according to claim 1 , wherein said multiplying said wavelet transform of one of said first and second non-stationary signals by a mask of said wavelet transform of the other one of said first and second non-stationary signals comprises multiplying said wavelet transform of said one of said first and second non-stationary signals by an inverse of said mask of said wavelet transform of said other one of said first and second non-stationary signals.
6. A method according to claim 1 , wherein said extracting comprises summing said multiplied wavelet transforms.
7. A method according to claim 6 , wherein said extracting comprises extracting said at least one feature directly from said multiplied wavelet transforms.
8. A method according to claim 1 , wherein said performing is automatically implemented by a controller of said at least one machine.
9. A method according to claim 1 , and also comprising tracking, by feature tracking algorithms, said at least one feature, over time.
10. A method according to claim 1 , wherein said ascertaining a condition comprising ascertaining a condition of said at least one machine relating to at least one of machine performance and machine efficiency.
11. A system for operating non-stationarily operating machinery, comprising:
at least a first sensor operative to acquire at least a first non-stationary signal generated by at least one machine operating in a non-stationary manner during at least one operational time frame;
at least a second sensor operative to acquire at least a second non-stationary signal different from said first non-stationary signal and generated by said at least one machine during said at least one operational time frame;
a signal processor operative to:
apply a wavelet transform to both of said at least first and second different non-stationary signals;
generate a mask of said wavelet transform of one of said first and second non-stationary signals;
multiply said mask of said wavelet transform of said one of said first and second non-stationary signals by said wavelet transform of the other one of said first and second non-stationary signals;
extract at least one feature of at least one of said first and second non-stationary signals based on said multiplied wavelet transforms; and
analyze said at least one feature to ascertain a condition of said at least one machine, and
a machine control module operative to perform at least one of a repair operation, maintenance operation and modification of operating parameters of said at least one machine based on said condition.
12. A system according to claim 11 , wherein said first sensor is of a same type as said second sensor.
13. A system according to claim 11 , wherein said first sensor is of a different type to said second sensor.
14. A system according to claim 11 , wherein said mask comprises a binary wavelet matrix.
15. A system according to claim 11 , wherein said signal processor being operative to multiply said wavelet transform of one of said first and second non-stationary signals by a mask of said wavelet transform of the other one of said first and second non-stationary signals comprises multiplication of said wavelet transform of said one of said first and second non-stationary signals by an inverse of said mask of said wavelet transform of said other one of said first and second non-stationary signals.
16. A system according to claim 11 , wherein said signal processor being operative to extract at least one feature comprises summation of said multiplied wavelet transforms.
17. A system according to claim 16 , wherein said signal processor is operative to extract said at least one feature directly from said multiplied wavelet transforms.
18. A system according to claim 11 , wherein said machine control module is automatically operative to perform said at least one of a repair operation, maintenance operation and modification of operating parameters of said at least one machine based on said condition.
19. A system according to claim 11 , and also comprising feature tracking algorithms, operative to automatically track said at least one feature extracted by said signal processor over time.
20. A system according to claim 11 , wherein said signal processor being operative to ascertain a condition of said machine comprises said signal processor being operative to ascertain a condition of said at least one machine relating to at least one of machine performance and machine efficiency.