Automated cement quality evaluation
A method for determining and classifying a quality of cement in a wellbore includes receiving input data. The input data is captured by one or more acoustic logging tools in the wellbore. The method also includes generating an image or a curve based upon the input data. The method also includes preprocessing the input data and the image or the curve to produce preprocessed data. The method also includes selecting portions of the preprocessed data for determining and classifying the quality of the cement in the wellbore. The method also includes determining and classifying the quality of the cement in the wellbore based upon the selected portions of the preprocessed data.
1 . A method for determining and classifying a quality of cement in a wellbore, the method comprising:
receiving input data, wherein the input data is captured by one or more acoustic logging tools in the wellbore, and wherein the input data comprises a plurality of measurements including acoustic impedance measurements, flexural attenuation measurements, sonic wave amplitude measurements, casing collar locator measurements, or a combination thereof;
generating an image or a curve based upon the input data;
preprocessing the input data and the image or the curve to produce preprocessed data;
selecting portions of the preprocessed data for determining and classifying the quality of the cement in the wellbore; and
determining and classifying the quality of the cement in the wellbore based upon the selected portions of the preprocessed data,
wherein:
the image or the curve comprises a solid-liquid-gas (SLG) image that is based upon the acoustic impedance measurements and/or the flexural attenuation measurements, and the preprocessed data comprises a modified SLG image;
the image or the curve comprises a micro-debonding image that is based upon the acoustic impedance measurements, and the preprocessed data comprises a modified micro-debonding image; or
the image or the curve comprises a bond index (BI) curve that is based upon the sonic wave amplitude measurements, and the preprocessed data comprises a modified BI curve.
2 . The method of claim 1 , wherein the image or the curve comprises the solid-liquid-gas (SLG) image that is based upon the acoustic impedance measurements and/or the flexural attenuation measurements, and wherein the preprocessed data comprises the modified SLG image.
3 . The method of claim 2 , wherein the one or more acoustic logging tools comprises an ultrasonic logging tool, wherein the ultrasonic logging tool comprises an isolation scanner tool, and wherein the selected portions comprise the modified SLG image in response to at least a portion of the input data being captured by the isolation scanner tool.
4 . The method of claim 1 , wherein the image or the curve comprises the micro-debonding image that is based upon the acoustic impedance measurements, and wherein the preprocessed data comprises the modified micro-debonding image.
5 . The method of claim 4 , wherein the one or more acoustic logging tools comprises an ultrasonic logging tool, wherein the ultrasonic logging tool comprises an ultrasonic transmitter tool, and wherein the selected portions comprise the modified micro-debonding image in response to at least a portion of the input data being captured by the ultrasonic transmitter tool.
6 . The method of claim 1 , wherein the image or the curve comprises the bond index (BI) curve that is based upon the sonic wave amplitude measurements, and wherein the preprocessed data comprises the modified BI curve.
7 . The method of claim 6 , wherein the one or more acoustic logging tools comprises a sonic logging tool, and wherein the selected portions comprise the modified BI curve in response to at least a portion of the input data being captured by the sonic logging tool.
8 . The method of claim 1 , further comprising displaying the quality of the cement.
9 . The method of claim 1 , further comprising performing a wellsite action in response to the quality of the cement being below a predetermined threshold.
10 . A computing system, comprising:
one or more processors; and
a memory system comprising one or more non-transitory computer-readable media storing instructions that, when executed by at least one of the one or more processors, cause the computing system to perform operations, the operations comprising:
receiving input data, wherein the input data is captured by one or more logging tools in a wellbore, wherein the one or more logging tools comprise one or more acoustic logging tools, wherein the one or more acoustic logging tools comprises a sonic logging tool and/or an ultrasonic logging tool, wherein the ultrasonic logging tool comprises an isolation scanner tool and/or an ultrasonic transmitter tool, and wherein the input data comprises a plurality of measurements including:
acoustic impedance measurements;
flexural attenuation measurements;
sonic wave amplitude measurements that are part of a cement bond log;
and/or
casing collar locator measurements;
generating an image or a curve based upon the input data, wherein the image or the curve comprises:
a solid-liquid-gas (SLG) image that is based upon the acoustic impedance measurements and/or the flexural attenuation measurements;
a micro-debonding image that is based upon the acoustic impedance measurements; and/or
a bond index (BI) curve that is based upon the sonic wave amplitude measurements;
preprocessing the input data and the image or the curve to produce preprocessed data, wherein the preprocessed data comprises a modified SLG image, a modified micro-debonding image, and/or a modified BI curve;
selecting portions of the preprocessed data for determining and classifying a quality of cement in the wellbore, wherein the selected portions comprise:
the modified SLG image in response to at least a portion of the input data being captured by the isolation scanner tool;
the modified micro-debonding image in response to at least a portion of the input data being captured by the ultrasonic transmitter tool; and/or
the modified BI curve in response to at least a portion of the input data being captured by the sonic logging tool; and
determining and classifying the quality of the cement in the wellbore based upon the selected portions of the preprocessed data.
11 . The computing system of claim 10 , wherein preprocessing comprises detecting positions of one or more casing collars and/or one or more centralizers in the wellbore, and wherein the positions are detected based upon the acoustic impedance measurements and/or the casing collar locator measurements.
12 . The computing system of claim 11 , wherein preprocessing also comprises identifying anomalous data in the input data and/or the image based upon the positions of the one or more casing collars and the one or more centralizers, wherein the anomalous data represents materials that cannot be identified with a predetermined confidence level caused by defects of the one or more acoustic logging tools and/or wellbore conditions, and wherein the anomalous data is identified in the SLG image and/or the micro-debonding image.
13 . The computing system of claim 12 , wherein preprocessing also comprises calibrating portions of the input data and/or the image that include or represent the one or more casing collars, the one or more centralizers, and/or the anomalous data to produce the modified SLG image and/or the modified micro-debonding image, which reduces an influence of the one or more casing collars, the one or more centralizers, and/or the anomalous data that are, thereby representing a more accurate condition of the wellbore.
14 . The computing system of claim 10 , wherein preprocessing comprises calibrating the sonic wave amplitude measurements and producing the modified BI curve based on the calibrated sonic wave amplitude measurements, which serves as an indicator for evaluating the quality of the cement based on sonic logging.
15 . A non-transitory computer-readable medium storing instructions that, when executed by one or more processors of a computing system, cause the computing system to perform operations, the operations comprising:
receiving input data, wherein the input data is captured by one or more logging tools in a wellbore, wherein the one or more logging tools comprise one or more acoustic logging tools, wherein the one or more acoustic logging tools comprises a sonic logging tool and/or an ultrasonic logging tool, wherein the ultrasonic logging tool comprises an isolation scanner tool and/or an ultrasonic transmitter tool, and wherein the input data comprises a plurality of measurements including:
acoustic impedance measurements;
flexural attenuation measurements;
sonic wave amplitude measurements that are part of a cement bond log; and
casing collar locator measurements;
generating an image or a curve based upon the input data, wherein the image or the curve comprises:
a solid-liquid-gas (SLG) image that is based upon the acoustic impedance measurements and/or the flexural attenuation measurements;
a micro-debonding image that is based upon the acoustic impedance measurements; and/or
a bond index (BI) curve that is based upon the sonic wave amplitude measurements;
preprocessing the input data and the image or the curve to produce preprocessed data, wherein the preprocessed data comprises a modified SLG image, a modified micro-debonding image, and/or a modified BI curve, and wherein preprocessing comprises:
detecting positions of one or more casing collars and/or one or more centralizers in the wellbore, wherein the positions are detected based upon the acoustic impedance measurements and/or the casing collar locator measurements;
identifying anomalous data in the input data and/or the image based upon the positions of the one or more casing collars and the one or more centralizers, wherein the anomalous data represents materials that cannot be identified with a predetermined confidence level caused by defects of the one or more acoustic logging tools and/or wellbore conditions, and wherein the anomalous data is identified in the SLG image and/or the micro-debonding image; and
calibrating portions of the input data and/or the image that include or represent the one or more casing collars, the one or more centralizers, and/or the anomalous data to produce the modified SLG image and/or the modified micro-debonding image, which reduces an influence of the one or more casing collars, the one or more centralizers, and/or the anomalous data that are, thereby representing a more accurate condition of the wellbore; or
calibrating the sonic wave amplitude measurements and producing the modified BI curve based on the calibrated sonic wave amplitude measurements, which serves as an indicator for evaluating a quality of cement based on sonic logging;
selecting portions of the preprocessed data for determining and classifying the quality of the cement in the wellbore, wherein the selected portions comprise:
the modified SLG image in response to at least a portion of the input data being captured by the isolation scanner tool;
the modified micro-debonding image in response to at least a portion of the input data being captured by the ultrasonic transmitter tool; and/or
the modified BI curve in response to at least a portion of the input data being captured by the sonic logging tool; and
determining and classifying the quality of the cement in the wellbore based upon the selected portions of the preprocessed data;
displaying the quality of the cement; and
performing a wellsite action in response to the quality being below a predetermined threshold, wherein the wellsite action comprises generating and/or transmitting a signal that recommends, instructs, or causes a physical action to occur in or to the wellbore, and wherein the physical action comprises pumping additional cement into the wellbore to fill connected liquid and/or gas channels.
16 . The non-transitory computer-readable medium of claim 15 , wherein determining and classifying comprises dividing the selected portions of the preprocessed data into intervals that correspond to intervals in the wellbore.
17 . The non-transitory computer-readable medium of claim 16 , wherein determining and classifying further comprises:
identifying the connected liquid and/or gas channels in the intervals in the preprocessed data; and
classifying the intervals in the preprocessed data with different grades based upon the connected liquid and/or gas channels.
18 . The non-transitory computer-readable medium of claim 16 , wherein determining and classifying further comprises:
determining average solid, liquid, and gas composition proportions in the intervals in the preprocessed data; and
classifying the intervals in the preprocessed data with different grades based upon the average solid, liquid, and gas composition proportions.
19 . The non-transitory computer-readable medium of claim 16 , wherein determining and classifying comprises:
determining an average bond index in the intervals in the preprocessed data; and
classifying the intervals in the preprocessed data with different grades based upon the average bond index.