System and method for operational-data-based detection of anomaly of a machine tool
A self-aware machine platform is implemented through analyzing operational data of machining tools to achieve machine tool damage assessment, prediction and planning in manufacturing shop floor. Machining processes are first identified by matching similar processes through an ICP algorithm. Machining processes are further clustered by Hotelling's T-squared statistics. Degradation of the machining tool is detected through a trend of the operational data within a cluster of machining processes by a monotonicity test, and the remaining useful life of the machining tool is predicted through a particle filter by extrapolating the trend under a first-order Markov process. In addition, process anomalies across machines are detected through a combination of outlier detection methods including SOMs, multivariate regression, and robust Mahalanobis distance. Warnings and recommendations are flexibly provided to manufacturing shop floor based on policy choice.
1. A system for operational-data-based detection an anomaly of a machine tool, comprising:
a server comprising a processor and configured to execute code, comprising:
a stream module configured to collect a stream of operational data comprising positional parameters and movement parameters of machining processes performed by a machine tool;
a characterization module configured to characterize distribution patterns of the operational data using a plurality of analytical methods;
a collection module configured to collect further operational data comprising further positional parameters and further movement parameters of machining processes performed by the machine tool;
a comparison module configured to compare the further operational data against the distribution patterns of the operational data;
a determination module configured to determine a presence of one or more outliers against the distribution patterns based on the comparison;
a threshold module configured to compare a number of the outliers to a threshold;
a notification module configured to send a notification if the number of the outliers exceeds the threshold, wherein maintenance of the machine tool is performed based on the notification.
2. A system according to claim 1 , wherein the analytical methods comprise self-organizing maps (SOMs), multivariate regression, and robust Mahalanobis distance.
3. A system according to claim 1 , further comprising:
a machine module configured to compare at least some of the operational data to additional operational data associated with an additional machine tool,
wherein the maintenance of a machine in which the machine tool is comprised is performed based on the additional operational data comparison.
4. A system according to claim 3 , wherein the operational data being compared to the additional operational comprises spindle loads weighted by time spent at various spindle speeds and the additional operational data comprises additional spindle loads weighted by time spent at various additional spindle speeds, further comprising:
a histogram module configured to plot histograms of the spindle loads weighted by time spent at various spindle speeds and the additional spindle loads weighted by time spent at various additional spindle speeds; and
a histogram comparison module configured to compare the histograms.
5. A system according to claim 1 , wherein the operational data being compared to the additional operational comprises aggregate axes traverses, further comprising:
a threshold module configured to set a further threshold based on additional aggregate axis traverses of an additional machine tool;
compare the aggregate axis traverses to the threshold, wherein the maintenance of a machine in which the machine tool is comprised is performed based on the comparison.
6. A system according to claim 5 , wherein the further threshold is greater than twice of the additional aggregate axis traverses of the additional machine tool.
7. A system according to claim 5 , wherein the maintenance comprises switching of parts between the machine tool and the additional machine tool.
8. A system according to claim 5 , further comprising:
a position module configured to obtain a commanded position of the machine tool;
a position comparison module configured to compare the aggregate axes traverses to the commanded position; and
an error module configured to detect an error in the position based on the comparison.
9. A system according to claim 1 , wherein the stream of the operational data is provided to the server by a sensor installed on or proximately to a machine in which the machine tool is comprised.
10. A system according to claim 1 , wherein the server is a web-based server.
11. A method for operational-data-based detection of an anomaly of a machine tool, comprising:
collecting by a server a stream of operational data comprising positional parameters and movement parameters of machining processes performed by a machine tool;
characterizing by the server distribution patterns of the operational data using a plurality of analytical methods;
collecting by the server further operational data comprising further positional parameters and further movement parameters of machining processes performed by the machine tool;
comparing by the server the further operational data against the distribution patterns of the operational data;
determining by the server a presence of one or more outliers against the distribution patterns based on the comparison;
comparing by the server a number of the outliers to a threshold; and
sending by the server a notification if the number of the outliers exceeds the threshold, wherein maintenance of the machine tool is performed based on the notification.
12. A method according to claim 11 , wherein the analytical methods comprise self-organizing maps (SOMs), multivariate regression, and robust Mahalanobis distance.
13. A method according to claim 11 , further comprising:
comparing at least some of the operational data to additional operational data associated with an additional machine tool,
wherein the maintenance of a machine in which the machine tool is comprised is performed based on the additional operational data comparison.
14. A method according to claim 13 , wherein the operational data being compared to the additional operational comprises spindle loads weighted by time spent at various spindle speeds and the additional operational data comprises additional spindle loads weighted by time spent at various additional spindle speeds, further comprising:
plotting histograms of the spindle loads weighted by time spent at various spindle speeds and the additional spindle loads weighted by time spent at various additional spindle speeds; and
comparing the histograms.
15. A method according to claim 11 , wherein the operational data being compared to the additional operational comprises aggregate axes traverses, further comprising:
setting a further threshold based on additional aggregate axis traverses of an additional machine tool;
comparing the aggregate axis traverses to the threshold, wherein the maintenance of a machine in which the machine tool is comprised is performed based on the comparison.
16. A method according to claim 15 , wherein the further threshold is greater than twice of the additional aggregate axis traverses of the additional machine tool.
17. A method according to claim 15 , wherein the maintenance comprises switching of parts between the machine tool and the additional machine tool.
18. A method according to claim 15 , further comprising:
obtaining a commanded position of the machine tool;
comparing the aggregate axes traverses to the commanded position; and
detecting an error in the position based on the comparison.
19. A method according to claim 11 , wherein the stream of the operational data is provided to the server by a sensor installed on or proximately to a machine in which the machine tool is comprised.
20. A method according to claim 11 , wherein the server is a web-based server.