Smart device, system, and method for diagnosing casing-casing annulus (CCA) behavior
A smart device located in a wellbore head during production operations in a well is disclosed. The smart device has a transceiver that exchanges signals with a wellhead sensor, the wellhead sensor monitoring a hydraulic line with T-connection for bleed-off. The transceiver communicates with the wellhead sensor through a first communication link established by the smart device. A localization system identifies pressure information relating to information of the well, including sizes of an inner casing and of an outer casing of the well, and a processor implements a combination of artificial intelligence and machine learning to pre-emptively provide warnings relating to possible estimated CCA behavior. Report information is generated that includes whether a source from a bleed-off is downhole or from trapped compressed fluid due to heat expansion, and provides a forward plan for a remedial job based on previous history of similar CCA behavior in the well.
1. A system comprising:
a plurality of casings corresponding to a plurality of casing annuli in a wellbore;
a wellhead that is installed at the wellbore and connected to the plurality of casings;
a side-outlet valve connected to the wellhead,
wherein the side-outlet valve comprises a surface gauge that determines an annulus pressure of at least one annulus among the plurality of casing annuli in the wellbore;
a hydraulic line connected to the plurality of casing annuli and a tank, wherein the hydraulic line sends influent fluid content with T-connection for bleed-off from the plurality of casing annuli to the tank; and
a smart device comprising a processor, a transceiver, and a memory, wherein the smart device is connected to the hydraulic line and is configured to:
determine a Casing-Casing Annulus (CCA) pressure build-up rate using the annulus pressure from the surface gauge, and
determine, using a machine learning (ML) model, predicted CCA behavior based on the CCA pressure build-up rate, annulus integrity data, and well condition data, and
pre-emptively provide one or more warnings relating to the predicted CCA behavior,
wherein the predicted CCA behavior identifies a source of a CCA leak in the plurality of casings.
2. The smart system of claim 1 , wherein the smart device is further configured to:
generate, based on the CCA pressure build-up rate, the annulus integrity data, and the well condition data, at least one workover report including rig workover solutions to be implemented in the wellbore, the at least one workover report being an output of implementing the ML model to pre-emptively provide the one or more warnings relating to the predicted CCA behavior.
3. The smart system of claim 2 , wherein the memory stores the CCA pressure build-up rate, the annulus integrity data, and the well condition data, the memory indexing the CCA pressure build-up rate, the annulus integrity data, and the well condition data based on bleed-off information and one or more casing condition statuses.
4. The smart system of claim 1 , wherein the smart device is further configured to:
establish a second communication link with a control system,
transmit operation information of the wellbore to the control system, the control system performing data evaluation to determine whether build-up is forming in the wellbore, and
receive one or more instruction signals from the control system, the one or more instruction signals including results from build-up testing based on the data evaluation.
5. The smart system of claim 1 , the smart device further comprising:
a cell group sensing element that stabilizes communications associated with the transceiver by preventing interferences between the transceiver and the rest of the smart device.
6. A method comprising:
obtaining, using a side-outlet valve connected to a wellhead, an annulus pressure,
wherein the side-outlet valve comprises a surface gauge that determines an annulus pressure of at least one annulus among the plurality of casing annuli in the wellbore,
wherein the wellhead is installed at a wellbore and connected to a plurality of casings, and
wherein the plurality of casings correspond to a plurality of casing annuli in the wellbore;
determine, using a smart device, a Casing-Casing Annulus (CCA) pressure build-up rate using the annulus pressure from the surface gauge,
wherein the smart device comprises a processor, a transceiver, and a memory and is connected to a hydraulic line,
wherein the hydraulic line is connected to the plurality of casing annuli and a tank,
wherein the hydraulic line sends influent fluid content with T-connection for bleed-off from the plurality of casing annuli to the tank;
determine, using the smart device and a machine learning (ML) model, predicted CCA behavior based on the CCA pressure build-up rate, annulus integrity data, and well condition data; and
pre-emptively, using the smart device, providing one or more warnings relating to the predicted CCA behavior,
wherein the predicted CCA behavior identifies a source of a CCA leak in the plurality of casings.
7. The method of claim 6 , further comprising:
generating, based on the CCA pressure build-up rate, the annulus integrity data, and the well condition data, at least one workover report including rig workover solutions to be implemented in the wellbore, the at least one workover report being an output of implementing the ML model to pre-emptively provide the one or more warnings relating to the predicted CCA behavior.
8. The method of claim 7 , further comprising:
storing, by the memory, the CCA pressure build-up rate, the annulus integrity data, and the well condition data, the memory indexing the CCA pressure build-up rate, the annulus integrity data, and the well condition data based on bleed-off information and one or more casing condition statuses.
9. The method of claim 6 , further comprising:
establishing a communication link with a control system,
transmitting operation information of the wellbore to the control system, the control system performing data evaluation to determine whether build-up is forming in the wellbore, and
receiving one or more instruction signals from the control system, the one or more instruction signals including results from build-up testing based on the data evaluation.