Detecting mud motor stalls

Abstract

Detecting a mud motor stall, using one or more computer processors, includes: receiving differential pressure data indicative of differential pressure measured over time during drilling of a wellbore; identifying, within the differential pressure data, one or more differential pressure peaks; for at least a first peak of the one or more differential pressure peaks, identifying one or more features of the first peak; and determining, based on each of the one or more features, that the first peak is indicative of a mud motor stall. Identifying the one of more features may include identifying at least a first feature including: determining an amplitude of the first peak; determining an amplitude of at least a second peak of the one or more differential pressure peaks; and comparing the amplitude of the first peak to the amplitude of the second peak.

1 . A method of detecting a mud motor stall, comprising using one or more computer processors to:
 receive differential pressure data indicative of differential pressure measured over time during drilling of a wellbore;   identify, within the differential pressure data, one or more differential pressure peaks;   for at least a first peak of the one or more differential pressure peaks, identify one or more features of the first peak; and   determine, based on each of the one or more features, that the first peak is indicative of a mud motor stall,   
       wherein identifying the one of more features comprises identifying at least a first feature comprising:
 determining an amplitude of the first peak; 
 determining an amplitude of at least a second peak of the one or more differential pressure peaks; and 
 comparing the amplitude of the first peak to the amplitude of the second peak. 
 
     
     
         2 . The method of  claim 1 , further comprising, in response to determining that the first peak is indicative of the mud motor stall, adjusting the drilling of the wellbore. 
     
     
         3 . The method of  claim 1 , wherein the amplitude of the first and second peaks comprises respective maximum differential pressures of the first and second peaks. 
     
     
         4 . The method of  claim 1 , wherein:
 determining the amplitude of at least the second peak comprises determining the amplitude of each peak in a pre-set number of the one or more differential pressure peaks that precede the first peak; and   comparing the amplitude of the first peak to the amplitude of the second peak comprises comparing the amplitude of the first peak to an average of the amplitude of each peak in the pre-set number of the one or more differential pressure peaks that precede the first peak.   
     
     
         5 . The method of  claim 4 , wherein comparing the amplitude of the first peak to the amplitude of each peak in the pre pre-set sent number of the one or more differential pressure peaks that precede the first peak comprises determining either:
 the absolute value of: the maximum differential pressure of the first peak minus an average of the maximum differential pressure values of each peak in the pre-set number of the one or more differential pressure peaks that precede the first peak; or   (the maximum differential pressure of the first peak minus an average of the maximum differential pressure values of each peak in the pre-set number of the one or more differential pressure peaks that precede the first peak) divided by the average of the maximum differential pressure values of each peak in the pre-set number of the one or more differential pressure peaks that precede the first peak.   
     
     
         6 . The method of  claim 1 , wherein identifying the one or more differential pressure peaks comprises:
 determining, based on the differential pressure data, a first moving average of the differential pressure data integrated over a first time window;   determining, based on the differential pressure data, a second moving average of the differential pressure data integrated over a second time window that is longer than the first time window;   determining that the first moving average has climbed above the second moving average and has then dropped below the first moving average; and   in response to determining that the first moving average has climbed and has then dropped below the first moving average, identifying the first peak.   
     
     
         7 . The method of  claim 1 , wherein identifying the one of more features further comprises identifying a further feature comprising:
 applying a threshold to divide the first peak into an upper portion and a lower portion; and   determining an amount of time the differential pressure of the first peak is greater than the threshold.   
     
     
         8 . The method of  claim 7 , wherein:
 the upper portion is the upper 50% of the magnitude of the first peak; and   the lower portion is the lower 50% of the magnitude of the first peak.   
     
     
         9 . The method of  claim 7 , wherein:
 determining the amount of time the differential pressure of the first peak is greater than the threshold comprises determining that the amount of time is less than an upper time limit; and   identifying the further feature further comprises, in response to determining that the amount of time is less than the upper time limit, determining (Max_Diff_P−End_Diff_P)/(Max_Diff_P−Start_Diff_P), wherein Max_Diff_P is the maximum differential pressure of the first peak, End_Diff_P is the differential pressure at the end of the first peak, and Start_Diff_P is the differential pressure at the start of the first peak.   
     
     
         10 . The method of  claim 1 , wherein identifying the one of more features further comprises identifying a further feature comprising:
 determining a ratio of the magnitude of the first peak to the differential pressure at the start of the first peak.   
     
     
         11 . The method of  claim 1 , wherein identifying the one or more differential pressure peaks comprises:
 identifying, within the differential pressure data, one or more initial differential pressure peaks; and   filtering the one or more initial differential pressure peaks by ignoring any initial differential pressure peak identified on the basis of differential pressure data not associated with rotary or slide drilling.   
     
     
         12 . The method of  claim 1 , wherein identifying the one of more features further comprises identifying a further feature comprising:
 determining a maximum differential pressure value of the first peak.   
     
     
         13 . The method of  claim 1 , wherein identifying the one of more features further comprises identifying a further feature comprising:
 determining (Max_Diff_P−End_Diff_P)/(Max_Diff_P−Start_Diff_P), wherein Max_Diff_P is the maximum differential pressure of the first peak, End_Diff_P is the differential pressure at the end of the first peak, and Start_Diff_P is the differential pressure at the start of the first peak.   
     
     
         14 . The method of  claim 1 , wherein identifying the one or more differential pressure peaks comprises:
 identifying, within the differential pressure data, at least a first potential differential pressure peak; and   identifying, within the differential pressure data associated with the first potential differential pressure peak, the first peak.   
     
     
         15 . The method of  claim 1 , wherein identifying the one of more features further comprises identifying a further feature comprising:
 determining a first amount of time from the start of the first peak to the peak of the first peak;   determining a second amount of time from the peak of the first peak to the end of the first peak; and   comparing each of the first and second amounts of time to a threshold.   
     
     
         16 . The method of  claim 1 , wherein identifying the one of more features further comprises identifying a further feature comprising:
 determining Max_Diff_P−(Upper_Percentile+α (Upper_Percentile−Lower_Percentile)), wherein Max_Diff_P is the maximum differential pressure of the first peak, Upper_Percentile and Lower_Percentile are percentiles of the differential pressure values of a number of the one or more differential pressure peaks that precede the first peak, and α is a constant.   
     
     
         17 . The method of  claim 16 , wherein Upper_Percentile is the 75 th  percentile and Lower_Percentile is the 25 th  percentile. 
     
     
         18 . The method of  claim 1 , wherein identifying the one of more features further comprises identifying a further feature comprising:
 determining a difference between the maximum differential pressure of the first peak and the maximum differential pressure from among a number of data points that precede the first peak.   
     
     
         19 . The method of  claim 1 , wherein identifying the one of more features further comprises identifying a further feature comprising:
 comparing the maximum differential pressure of the first peak to a differential pressure limit.   
     
     
         20 . The method of  claim 1 , wherein identifying the one of more features further comprises identifying a further feature comprising:
 comparing the magnitude of the first peak to a minimum magnitude.   
     
     
         21 . The method of  claim 1 , wherein identifying the one of more features further comprises identifying a further feature comprising:
 determining that the differential pressure at the start of the first peak is less than a differential pressure threshold; and   in response to determining that the differential pressure at the start of the first peak is less than the differential pressure threshold:
 determining a ratio of a magnitude of the first peak to a differential pressure at the start of the first peak; and 
 comparing the ratio to a threshold. 
   
     
     
         22 . The method of  claim 1 , wherein identifying the one of more features further comprises identifying a further feature comprising:
 determining that the differential pressure at the start of the first peak is less than a differential pressure threshold; and   in response to determining that the differential pressure at the start of the first peak is less than the differential pressure threshold, comparing the magnitude of the first peak to a threshold.   
     
     
         23 . A computer-readable medium having stored thereon computer program code configured when executed by one or more processors to cause the one or more processors to perform a method for detecting a mud motor stall during drilling of a wellbore, comprising:
 receiving differential pressure data indicative of differential pressure measured over time during the drilling operation;   identifying, within the differential pressure data, one or more differential pressure peaks;   for at least a first peak of the one or more differential pressure peaks, identifying one or more features of the first peak; and   determining, based on each of the one or more features, whether the first peak is indicative of a mud motor stall,   
       wherein identifying the one of more features comprises identifying at least a first feature comprising:
 determining an amplitude of the first peak; 
 determining an amplitude of at least a second peak of the one or more differential pressure peaks; and 
 comparing the amplitude of the first peak to the amplitude of the second peak. 
 
     
     
         24 . A drilling rig comprising:
 a drill string having a mud motor at an end of the drill string;   one or more sensors for measuring differential pressure; and   a stall detector comprising one or more processors configured to receive as inputs real-time measurements of the differential pressure obtained by the one or more sensors during drilling of a wellbore, and configured to:
 identify, based on the measurements of the differential pressure, one or more differential pressure peaks; 
 for at least a first peak of the one or more differential pressure peaks, identify one or more features of the first peak; and 
 determine, based on each of the one or more features, whether the first peak is indicative of a mud motor stall, 
   wherein identifying the one of more features comprises identifying at least a first feature comprising:
 determining an amplitude of the first peak; 
 determining an amplitude of at least a second peak of the one or more differential pressure peaks; and 
 comparing the amplitude of the first peak to the amplitude of the second peak.