Optical manufacturing process sensing and status indication system
An optical manufacturing process sensing and status indication system is taught that is able to utilize optical emissions from a manufacturing process to infer the state of the process. In one case, it is able to use these optical emissions to distinguish thermal phenomena on two timescales and to perform feature extraction and classification so that nominal process conditions may be uniquely distinguished from off-nominal process conditions at a given instant in time or over a sequential series of instants in time occurring over the duration of the manufacturing process. In other case, it is able to utilize these optical emissions to derive corresponding spectra and identify features within those spectra so that nominal process conditions may be uniquely distinguished from off-nominal process conditions at a given instant in time or over a sequential series of instants in time occurring over the duration of the manufacturing process.
1. A manufacturing process sensing and status indication system comprising:
one or more optical sensors configured to:
measure optical emissions generated by a scanning heat source during an additive manufacturing process as the scanning heat source moves into and out of a field of view of the one or more optical sensors to produce a workpiece, and
produce time-domain data from the measured optical emissions;
an analysis system configured to provide:
a first feature extraction process that extracts, from the time domain data, features that are related to thermal excursions resulting from the scanning heat source moving into and out of the field of view of the one or more optical;
a second feature extraction process that extracts, from the time domain data, features that are related to a background temperature of the workpiece detected while the scanning heat source is outside of the field of view of the one or more optical sensors; and
a classification process that, from the features extracted by the first and second feature extraction processes, distinguishes features associated with a baseline or nominal operating condition from features associated with a deviant or off-nominal process condition; and
a status indicator that is configured to communicate the results of the classification process at a given instant in time to a human-machine interface.
2. The system as recited in claim 1 , wherein the status indicator is further configured to record the results of the classification process at a sequential series of times during the manufacturing process.
3. The system as recited in claim 1 , wherein machinery used to perform the manufacturing process includes a bed of powdered metals and the scanning heat source is a scanning laser that sinters or melts at least a portion of the bed of powdered metals.
4. The system as recited in claim 3 , wherein the manufacturing process is performed using one or more of: a bed of powdered metals that are sintered or melted by a scanning electron beam; a metal wire fed by a mechanical wire feeder and melted or sintered by a laser; a metal wire fed by a mechanical wire feeder and melted or sintered by an electron beam; a metal wire fed by a mechanical wire feeder and melted or sintered by an arc welding process comprising one or more of gas metal arc welding (GMAW), gas tungsten arc welding (GTAW), plasma arc welding (PAW); powder fed by a nozzle and fluidized, carried, or otherwise entrained in an inert gas stream and where the heat addition is by a laser.
5. The system as recited in claim 1 , wherein the classification process determines the Mahalanobis Distance between nominal and off-nominal process conditions in a vector space comprised of feature vectors produced by the first and second feature extraction processes.
6. The system as recited in claim 5 , where the classification process determines whether the Mahalanobis Distance associated with a specific feature vector is above or below a critical Chi-Squared critical cutoff value to distinguish between nominal and off-nominal conditions.
7. The system as recited in claim 1 , wherein the one or more optical sensors comprise a single or multiple wavelength pyrometer.
8. The system as recited in claim 1 , wherein the one or more optical sensors comprise a thermocouple.
9. The system as recited in claim 1 , wherein the one or more optical sensors comprise a Resistance Thermal Device.
10. The system as recited in claim 1 , where the classification system uses features from the first feature extraction process to determine if the heat addition and heat source characteristics associated with the two different process conditions are different or the same.
11. The system as recited in claim 1 , where the classification system uses features from the second feature extraction process to determine if a material response associated with the two different process conditions are different or the same.
12. A manufacturing process sensing and status indication system comprising:
one or more optical sensors measuring optical emissions generated by a scanning heat source during an additive manufacturing process as the scanning heat source moves into and out of a field of view of the one or more optical sensors to produce a workpiece
an analysis system configured to provide:
a first feature extraction process that extracts, from sensor data collected by the one or more optical sensors, features that are related to thermal excursions resulting from the scanning heat source moving into and out of the field of view of the one or more optical sensors;
a second feature extraction process that extracts, from sensor data collected by the one or more optical sensors, features that are related to a background temperature of the workpiece detected while the scanning heat source is outside of the field of view of the one or more optical sensors; and
a classification process that, from the features extracted by the first and second feature extraction processes, distinguishes features associated with a baseline or nominal operating condition from features associated with a deviant or off-nominal process condition; and
a status indicator that is configured to communicate the results of the classification process at a given instant in time to a human-machine interface.
13. The system as recited in claim 12 , wherein the status indicator is further configured to record the results of the classification process at a sequential series of times during the manufacturing process.
14. The system as recited in claim 12 , wherein the additive manufacturing process is performed using a bed of powdered metals that are sintered or melted by a scanning laser.
15. The system as recited in claim 12 , wherein the manufacturing process comprises one or more of a bed of powdered metals that are sintered or melted by a scanning electron beam; a metal wire fed by a mechanical wire feeder and melted or sintered by a laser; a metal wire fed by a mechanical wire feeder and melted or sintered by an electron beam; a metal wire fed by a mechanical wire feeder and melted or sintered by an arc welding process comprising one or more of gas metal arc welding (GMAW), gas tungsten arc welding (GTAW), plasma arc welding (PAW); powder fed by a nozzle and fluidized, carried, or otherwise entrained in an inert gas stream and where the heat addition is by a laser.
16. The system as recited in claim 12 , wherein the classification processes determines the Mahalanobis Distance between nominal and off-nominal process conditions in a vector space comprised of feature vectors produced by the first and second feature extraction processes.
17. The system as recited in claim 16 , where the classification system determines whether the Mahalanobis Distance associated with a specific feature vector is above or below the critical Chi-Squared critical cutoff value to distinguish between nominal and off-nominal conditions.