Auto-Detection And Classification Of Rig Activities From Trend Analysis Of Sensor Data

Abstract

Systems and methods for auto-detection and classification of rig activities from trend analysis of sensor data are provided. Sensor data from rig equipment may be obtained during wellsite operations. The sensor data may be analyzed to identify one or more index points where a trend in the sensor data changes. The sensor data may be segmented into a first set of time segments representing macro activities performed during the well site operations, based on the one or more identified index points. Statistical analysis may be performed on the sensor data within each first time segment to identify points where statistical properties of the sensor data change. Each first time segment may he segmented into a second set of time segments representing micro activities performed during the wellsite operations, based on the identified points of change in the statistical properties.

What is claimed is: 
     
         1 . A computer-implemented method for detecting rig activities during operations at a wellsite, the method comprising:
 obtaining, by a computer system, sensor data from rig equipment during wellsite operations;   generating time series data from the obtained sensor data;   to analyzing the generated time series data to identify one or more index points where a trend in the time series data changes;   segmenting the time series data into a first set of time segments representing macro activities performed during the weilsite operations, based on the one or more identified index points;   performing statistical analysis on the time series data within each time segment of the first set of time segments to identify points where statistical properties of the time series data change; and   segmenting each time segment of the first set of time segments into a second set of time segments representing micro activities performed during the wellsite operations, based on the identified points of change in the statistical properties of the corresponding time series data.   
     
     
         2 . The method of  claim 1 , wherein generating the time series data from the obtained sensor data comprises using a linear regression to determine a gradient transition of the obtained sensor data over time. 
     
     
         3 . The method of  claim 2 , wherein the one or more identified index points correspond to one or more changes in the gradient transition of the sensor data. 
     
     
         4 . The method of  claim 2 , wherein:
 positive slope values of a line representing the gradient transition of the sensor data between two identified index points correspond to a first macro activity of weilsite operations;   negative slope values of the line representing the gradient transition of the sensor data between two identified index points correspond to a second macro activity of wellsite operations; and   flat slope values of the line representing the gradient transition of the sensor data between two identified index points correspond to a third macro activity of wellsite operations.   
     
     
         5 . The method of  claim 1 . wherein the statistical analysis performed on the time series data identifies where the mean or variance of the time series data changes. 
     
     
         6 . The method of  claim 1 , wherein the sensor data obtained comprises bit depth, borehole depth, and hook load values measured by one or more sensors coupled to the rig equipment during the wellsite operations. 
     
     
         7 . The method of  claim 6 , wherein generating the time series data from the obtained sensor data comprises generating a time series curve indicating a difference between respective values of borehole depth and bit depth measured by the one or more sensors during the wellsite operations over a period of time. 
     
     
         8 . The method of  claim 7 . wherein generating the time series data of the obtained sensor data further comprises using a linear regression to determine a gradient for the time series curve with respect to borehole depth and the difference between borehole depth and bit depth. 
     
     
         9 . The method of  claim 1 , wherein the macro activities performed during wellsite operations include trip in, trip out, drilling, and making a connection. 
     
     
         10 . The method of  claim 9 , wherein the micro activities performed during wellsite operations include inslip, pre-connection, and post-connection activities of drilling operations. 
     
     
         11 . The method of  claim 1 , wherein segmenting each time segment of the first set of time segments into a second set of time segments comprises comparing average values of the operation data before and after the identified points of change. 
     
     
         12 . A system for detecting rig activities during operations at a wellsite, the system comprising:
 at least one processor; and   a memory coupled to the processor having instructions stored therein, which when executed by the processor, cause the processor to perform a plurality of functions, including functions to:
 obtain sensor data from rig equipment during wellsite operations; 
 generate time series data from the obtained sensor data; 
 analyze the generated time series data to identify one or more index points where a trend in the time series data changes; 
 segment the time series data into a first set of time segments representing macro activities performed during the wellsite operations, based on the one or more identified index points; 
 perform statistical analysis on the time series data within each time segment of the first set of time segments to identify points where statistical properties of the time series data change; and 
 segment each time segment of the first set of time segments into a second set of time segments representing micro activities performed during the wellsite operations, based on the identified points of change in the statistical properties of the corresponding time series data. 
   
     
     
         13 . The system of  claim 12 , wherein the plurality of functions comprises functions to calculate one or more operation efficiency descriptors by comparing the time segment duration of at least one macro activity or micro activity with a best practice target duration. 
     
     
         14 . The system of  claim 13 , wherein the calculated operation efficiency descriptors include invisible lost time (ILT) and non-productive time (NPT). 
     
     
         15 . The system of  claim 12 , wherein generating the time series data from the obtained sensor data comprises using a linear regression to determine a gradient transition of the obtained sensor data over time, wherein the one or more identified index points correspond to one or more changes in the gradient transition of the sensor data. 
     
     
         16 . The system of  claim 12 , wherein:
 the macro activities performed during wellsite operations include trip in, trip out, drilling, and making a connection; and   the micro activities performed during wellsite operations includes inslip, pre-connection, and post-connection activities of drilling operations.   
     
     
         17 . A computer-readable storage medium having instructions stored therein, which when executed by a computer cause the computer to perform a plurality of functions, including functions to:
 obtain, by a computer system, sensor data from rig equipment during wellsite operations;   generate time series data from the obtained sensor data;   analyze the generated time series data to identify one or more index points where a trend in the time series data changes;   segment the time series data into a first set of time segments representing macro activities performed during the wellsite operations, based on the one or more identified index points;   is perform statistical analysis on the time series data within each time segment of the first set of time segments to identify points where statistical properties of the time series data change; and   segment each time segment of the first set of time segments into a second set of time segments representing micro activities performed during the wellsite operations, based on the identified points of change in the statistical properties of the corresponding time series data.   
     
     
         18 . The computer-readable storage medium of  claim 17 , wherein the sensor data obtained comprises bit depth, borehole depth, and hook load values measured by one or more sensors coupled to the rig equipment during the wellsite operations. 
     
     
         19 . The computer-readable storage medium of  claim 18 , wherein performing statistical analysis on the time series data comprises applying a Pruned Exact Linear Time (PELT) algorithm to the time series data within each time segment of the first set of time segments to detect when a hook load value drops. 
     
     
         20 . The computer-readable storage medium of  claim 19 , wherein generating the time series data of the obtained sensor data comprises using a linear regression to determine a gradient for the time series curve with respect to borehole depth and the difference between borehole depth and bit depth.