Sensor time series data: functional segmentation for effective machine learning

Abstract

Feature engineering can be performed on time series data making the data easy to manipulate and accessible to business users for analysis according to existing best practices. A computer system can, after receiving time series data related to a device, contextualize the time series data based on business data related to the device from, for example, an enterprise resource planning database. The contextualized data can be windowed by a selected feature based on execution data related to the device from, for example, a manufacturing execution system database. The windowed data can be transformed into summary data using a time series transformation. The summary data can be easily manipulated by, for example, generating genetic maps of the segmented and transformed data for clustering or searching for anomalies and patterns in response to user requests or automatically.

What is claimed is: 
     
         1 . A non-transitory computer-readable medium comprising instructions that, when executed by one or more processors, cause the one or more processors to perform operations comprising:
 receiving time series data related to a device for a period of time, the time series data providing information about the device for the period of time;   contextualizing the time series data based on business data related to the device for the period of time to generate contextualized data;   feature windowing the contextualized data based on execution data related to the device for the period of time to generate a plurality of windows of data;   transforming each of the plurality of windows of data into summary data using a time series transformation to generate a plurality of summary data; and   storing each of the plurality of summary data.   
     
     
         2 . The non-transitory computer-readable medium of  claim 1 , wherein transforming each of the plurality of windows of data into summary data comprises:
 generating a plurality of strings by, for each window of data in the plurality of windows of data:
 normalizing the data in the window of data; 
 smoothing the data in the window of data using piecewise aggregate approximation; and 
 converting the data in the window of data into a string. 
   
     
     
         3 . The non-transitory computer-readable medium of  claim 2 , wherein the operations further comprise:
 converting each string of the plurality of strings into a genetic map of a plurality of genetic maps;   clustering the plurality of genetic maps to identify pattern similarities;   grouping the plurality of genetic maps based on the identified pattern similarities; and   displaying the grouped genetic maps to a user.   
     
     
         4 . The non-transitory computer-readable medium of  claim 2 , wherein the operations further comprise:
 identifying, by the computer system, a pattern that represents an indication of a device failure;   building, by the computer system, a predictive model based on the pattern; and   sending, by the computer system, an alert based on applying the predictive model to current data.   
     
     
         5 . The non-transitory computer-readable medium of  claim 1 , wherein the operations further comprise:
 receiving, by the computer system, a selection of a second time series data from a user, the second time series data related to the device for a second period of time;   transforming, by the computer system, the second time series data into selected summary data using the time series transformation;   searching, by the computer system, the plurality of summary data for a pattern matching at least a portion of the selected summary data; and   displaying, by the computer system, summary data from the plurality of summary data having the pattern to the user.   
     
     
         6 . The non-transitory computer-readable medium of  claim 5 , wherein the operations further comprise:
 predicting, by the computer system, a quality of a second product produced by the device during the second period of time based on a quality of a first product produced by the device during the period of time having the matching pattern.   
     
     
         7 . The non-transitory computer-readable medium of  claim 1 , wherein the time series transformation used is symbolic aggregate approximation (“SAX”) and each of the plurality of summary data is a string in a plurality of strings. 
     
     
         8 . The non-transitory computer-readable medium of  claim 1 , wherein the feature windowing is based on one of a time segment, a sliding window, or an event. 
     
     
         9 . The non-transitory computer-readable medium of  claim 1 , wherein the business data is data from an enterprise resource planning database and the execution data is from a manufacturing execution system database. 
     
     
         10 . The non-transitory computer-readable medium of  claim 1 , wherein the device comprises a manufacturing machine, and the time series data is received from a sensor measuring operating characteristics of the manufacturing machine during the period of time. 
     
     
         11 . The non-transitory computer-readable medium of  claim 1 , wherein contextualizing the time series data based on the business data comprises segmenting the time series data based on the business data related to the manufacturing machine. 
     
     
         12 . The non-transitory computer-readable medium of  claim 1 , wherein feature windowing the contextualized data comprises windowing the contextualized data into time windows of a time window type based on the contextualized data. 
     
     
         13 . The non-transitory computer-readable medium of  claim 12 , wherein feature windowing the contextualized data comprises windowing the contextualized data into time windows of a time window type based on execution data related to the device for the period of time to generate a plurality of windows of data, the execution data associated with execution of the device received from a database. 
     
     
         14 . The non-transitory computer-readable medium of  claim 1 , wherein the plurality of summary data comprises clustered anomalies. 
     
     
         15 . The non-transitory computer-readable medium of  claim 14 , wherein the plurality of summary data comprises a plurality of graphs, each representing one of the clustered anomalies. 
     
     
         16 . The non-transitory computer-readable medium of  claim 1 , wherein the time series data comprises temperature readings from a sensor associated with the device. 
     
     
         17 . The non-transitory computer-readable medium of  claim 1 , wherein the time series data comprises pressure readings from a sensor associated with the device. 
     
     
         18 . The non-transitory computer-readable medium of  claim 1 , wherein a context associated with the contextualized data includes a user of the device. 
     
     
         19 . A method comprising:
 receiving time series data related to a device for a period of time, the time series data providing information about the device for the period of time;   contextualizing the time series data based on business data related to the device for the period of time to generate contextualized data;   feature windowing the contextualized data based on execution data related to the device for the period of time to generate a plurality of windows of data;   transforming each of the plurality of windows of data into summary data using a time series transformation to generate a plurality of summary data; and   storing each of the plurality of summary data.   
     
     
         20 . A system comprising:
 one or more processors; and   one or more memory devices comprising instructions that, when executed by the one or more processors, cause the one or more processors to:
 receiving time series data related to a device for a period of time, the time series data providing information about the device for the period of time; 
 contextualizing the time series data based on business data related to the device for the period of time to generate contextualized data; 
 feature windowing the contextualized data based on execution data related to the device for the period of time to generate a plurality of windows of data; 
 transforming each of the plurality of windows of data into summary data using a time series transformation to generate a plurality of summary data; and 
 storing each of the plurality of summary data.