Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
The amendment filed 05/04/2026 has been entered. Claims 1, 5, 6, 8, 9, 12-14, 26, and 19 have been amended.
Response to Arguments
Applicant’s arguments, see page 15 lines 17, filed 05/04/2026, with respect to the specification have been fully considered and are persuasive. The objection of 02/05/2026 has been withdrawn.
Applicant’s arguments, see page 16 lines 4-7, with respect to claim 8 have been fully considered and are persuasive. The objection has been withdrawn.
Applicant’s arguments, see pages 16-17, with respect to the rejection(s) of claim(s) 1-20 under 35 U.S.C. 101 have been fully considered and are persuasive. The rejections have been withdrawn.
Applicant’s arguments, see pages 18-19, with respect to the rejection of claim 1 under 35 U.S.C. 103 are not persuasive. Applicant argues that Querales relates to the production phase of a well, whereas Coates relates to the drilling phase of a well; one of ordinary skill in the art would not be expected to combine experience from these phases as they pose distinct challenges. In response to applicant’s argument that there is no teaching, suggestion, or motivation to combine the references, the examiner recognizes that obviousness may be established by combining or modifying the teachings of the prior art to produce the claimed invention where there is some teaching, suggestion, or motivation to do so found either in the references themselves or in the knowledge generally available to one of ordinary skill in the art. See In re Fine, 837 F.2d 1071, 5 USPQ2d 1596 (Fed. Cir. 1988), In re Jones, 958 F.2d 347, 21 USPQ2d 1941 (Fed. Cir. 1992), and KSR International Co. v. Teleflex, Inc., 550 U.S. 398, 82 USPQ2d 1385 (2007). In this case, page) describe the advantages of Coates, primarily providing “a reliable indication that gas has been introduced” and thus allowing an operator to quickly take suitable corrective action.Furthermore, both Querales and Coates are directed to the safe and optimal operation of a well. With regards to Querales, page 7 lines 3-12 (“Mismatches between measured values…resolve said conditions”) and lines 23-25 (“Once a condition has been diagnosed…may also be used to improve the erformance of a system”) describe resolving problems that could decrease performance and generally optimizing performance. With regards to Coates, page 2 lines 3-7 (“Since the gas “kick” expands…a blow-out can occur”) and page 4 lines 24-32 as well as page 5 lines 1-4 (“The addition of gas to a fluid… prevent a blow-out from occurring”) describes the potential consequences of failing to detect a gas migration which could decrease performance or cause damage and how Coates’ method of detecting a gas migration allows for prevention of these consequences. As such, it would be obvious to one of ordinary skill in the art to combine them.
Applicant’s arguments, see pages 19-25, with respect to the rejection(s) of claim(s) 1-20 under 35 U.S.C. 103 have been fully considered and are persuasive. Therefore, the rejections have been withdrawn. However, upon further consideration, a new ground(s) of rejection is made in view of US 20190353016 A1 to Sandidge (herein "Sandidge").
Applicant’s arguments, see page 23, with respect to the rejection(s) of claim(s) 3, 6-7, 11, 14-15, and 18-20 under 35 U.S.C. 103 are not persuasive. Applicant argues that a person of ordinary skill in the art would have no motivation to supply the missing elements without the benefit of Applicant’s own disclosure as a guide. In response to applicant's argument that the examiner's conclusion of obviousness is based upon improper hindsight reasoning, it must be recognized that any judgment on obviousness is in a sense necessarily a reconstruction based upon hindsight reasoning. But so long as it takes into account only knowledge which was within the level of ordinary skill at the time the claimed invention was made, and does not include knowledge gleaned only from the applicant's disclosure, such a reconstruction is proper. See In re McLaughlin, 443 F.2d 1392, 170 USPQ 209 (CCPA 1971).
Applicant’s arguments, see page 25, with respect to the rejection(s) of claim(s) 4 under 35 U.S.C. 103 are not persuasive. Applicant argues that a person of ordinary skill in the art would have no motivation to supply the missing elements without the benefit of Applicant’s own disclosure as a guide. In response to applicant's argument that the examiner's conclusion of obviousness is based upon improper hindsight reasoning, it must be recognized that any judgment on obviousness is in a sense necessarily a reconstruction based upon hindsight reasoning. But so long as it takes into account only knowledge which was within the level of ordinary skill at the time the claimed invention was made, and does not include knowledge gleaned only from the applicant's disclosure, such a reconstruction is proper. See In re McLaughlin, 443 F.2d 1392, 170 USPQ 209 (CCPA 1971).
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claim(s) 1-2, 4-5, 9-10, 12-13, and 16 is/are rejected under 35 U.S.C. 103 as being unpatentable over WO 2014022320 A2 to Querales et al. (herein "Querales") in light of CA 2837193 A to Coates et al. (herein "Coates"), further in light of US 20190353016 A1 to Sandidge (herein “Sandidge”), further in light of WO 2021155272 A1 to Boguslawski et al. (herein “Boguslawski”), further in light of US 20230186218 A1 to Bestman et al. (herein “Bestman”).
Regarding claim 1, Querales teaches a method, comprising:
obtaining process data (abstract “collecting measured data”) pertaining to a gas-lifted, hydrocarbon production well (page 1, lines 17-25, 29) comprising a gas-lift system, using a plurality of sensors disposed on the production well (page 3 lines 27-33, page 4 lines 1-2), wherein:
the production well is controlled by a set of operation parameters (page 7 line 27, “control settings”) comprising one or more of a gas injection rate or a gas injection pressure of the gas-lift system (page 7 lines 31-32 “target values and control settings 238 (e.g., gas injection flow and choke setting)”);
detectingan anomaly using a computational model based on the process data (page 7 lines 3-10), wherein:
the computation model comprises
determining, using the computational model, adjustments to be made to one or more operation parameters in the set of operation parameters to mitigate the anomaly based on the anomaly and the process data (page 7 lines 10-12)
determining a maintenance action based on the anomaly (page 7 lines 10-12, page 9 lines 8-11)
generating an alert for the detected anomaly (page 8 line 34, page 9 lines 1-3); and
performing the maintenance action on the production well (page 9 lines 8-10).
While Querales teaches controlling a well by adjusting operation parameters to mitigate anomalies, Querales does not explicitly teach that these anomalies are specifically a “gas migration event”. Querales also does not specifically teach:
the process data comprise a downhole liquid production rate, and
the plurality of sensors comprises a liquid production rate sensor configured to measure the downhole liquid production rate,
the computation model comprises an artificial intelligence model comprising a classification model configured to receive the process data as input and return a gas migration status as output, the gas migration status comprising a binary indicator indicating whether gas migration is occurring, and
detecting the gas migration event comprises inputting the process data to the classification model;
wherein the adjustments comprise an adjustment of the gas injection rate or the gas injection pressure;
automatically adjusting the one or more operation parameters in accordance with the adjustments, using a computer;
However, Coates teaches detecting abnormalities (anomalies) indicative of a gas influx (gas migration event) (page 1 Line 30 – Page 2, Line 7, wherein a “gas kick” is equivalent to the claimed gas migration event).
Both Querales and Coates are analogous to the claimed invention because both are in the field of hydrocarbon extraction. It would have been obvious to a person of ordinary skill before the effective filing date of the claimed invention to incorporate the specific detecting a gas migration event of Coates as part of the broad anomaly detection and mitigation system of Querales to maintain operational efficiency or prevent potential damage caused by the gas migration (page 2, lines 3-7).
Therefore, the combination of Querales and Coates teaches specifically detecting and responding to a gas migration event using a computational model as opposed to detecting an anomaly in general.
The combination of Querales and Coates does not explicitly teach:
the process data comprise a downhole liquid production rate, and
the plurality of sensors comprises a liquid production rate sensor configured to measure the downhole liquid production rate,
the computation model comprises an artificial intelligence model comprising a classification model configured to receive the process data as input and return a gas migration status as output, the gas migration status comprising a binary indicator indicating whether gas migration is occurring, and
detecting the gas migration event comprises inputting the process data to the classification model;
wherein the adjustments comprise an adjustment of the gas injection rate or the gas injection pressure;
automatically adjusting the one or more operation parameters in accordance with the adjustments, using a computer;
However, Sandidge teaches the process data comprise a downhole liquid production rate, and
the plurality of sensors comprises a liquid production rate sensor configured to measure the downhole liquid production rate (Paragraph 7 “production rate sensor”, “total fluid production rate”),
wherein the adjustments comprise an adjustment of the gas injection rate or the gas injection pressure (Paragraph 7 “utilizes inputs associated a bottom hole pressure to subsequently adjust the gas injection rate”),
automatically adjusting the one or more operation parameters in accordance with the adjustments, using a computer (Paragraph 43 “continuing adjustment of the gas injection setpoint in an automated process”);
Both Querales and Sandidge are analogous to the claimed invention because both are in the field of controlling a gas-lift well. It would be obvious to a person of ordinary skill in the art to incorporate the method of Querales with the automated adjustment of gas injection of Sandidge to maximize production (Paragraph 28).
The combination of Querales, Coates, and Sandidge does not teach:
the computation model comprises an artificial intelligence model comprising a classification model configured to receive the process data as input and return a gas migration status as output, the gas migration status comprising a binary indicator indicating whether gas migration is occurring, and
detecting the gas migration event comprises inputting the process data to the classification model;
However, Boguslawski teaches an artificial intelligence model (page 3, paragraph 6 lines 2-3 “machine learning”) comprising a classification model configured to receive the process data as input and return a gas migration status as output (page 9 lines 1-4), and
detecting the gas migration event comprises inputting the process data to the classification model (page 9 line 2).
In particular, while Boguslawski does not specifically use “classification model”, the examiner interpretation is that a classification model is merely a kind of machine learning model that categorizes data, such as by applying labels. Since Boguslawski identifies abnormal performance patterns it necessarily categorizes performance as “normal” or “abnormal” (also see Paragraph 16) and thereby performs the functions of a classification model.
Querales and Boguslawski are analogous to the claimed invention because all are in the field of hydrocarbon extraction. It would have been obvious to a person of ordinary skill before the effective filing date of the claimed invention to incorporate the AI model and the preventative maintenance model of Boguslawski with the method of Querales because detecting anomalies reduces risk of damage (page 3, paragraph 6 lines 8-11).
The combination of Querales, Coates, Sandidge, and Boguslawski does not teach the gas migration status comprising a binary indicator indicating whether gas migration is occurring.
However, Bestman teaches the gas migration status comprising a binary indicator indicating whether gas migration is occurring (abstract, “performance deviation”, “threshold”).
In particular, while Bestman does not specifically use “a binary indicator”, a threshold serves to create a binary division between two groups. Bestman must necessarily perform the functions of a binary indicator where the binary indicator is whether or not the performance deviation exceeds the set threshold.
Querales and Bestman are analogous to the claimed invention because all are in the field of hydrocarbon extraction. It would have been obvious to a person of ordinary skill before the effective filing date of the claimed invention to incorporate the threshold of Bestman with the method of Querales because a threshold is potentially variable and can be altered by an operator depending on conditions (pages 6-7, paragraph 70 “performance deviation”).
Regarding claim 2, the combination of Querales, Coates, Sandidge, Boguslawski, and Bestman teaches the method of claim 1. Querales also teaches the method of claim 1, further comprising:
determining, with the computational model, a gas lift efficiency of the production well based on the process data (page 8 line 15 “GL system performance curves”); and
adjusting one or more operation parameters in the set of operation parameters to optimize a production rate of the production well based on the gas lift efficiency (page 7 lines 5-17).
Regarding claim 4, the combination of Querales, Coates, Sandidge, Boguslawski, and Bestman teaches the method of claim 1.
Coates also teaches detecting abnormalities (anomalies) indicative of a gas influx (gas migration event) (page 1 Line 30 – Page 2, Line 7, wherein a “gas kick” is equivalent to the claimed gas migration event).
Boguslawski also teaches adjusting one or more operation parameters in the set of operation parameters, using the computational model, in order to prevent a future anomaly (page 9, lines 2-4 “predict abnormal events”, lines 13-14 “corrective action”). While Boguslawski does not teach adjusting parameters to specifically prevent a future gas migration event, the combination of Querales and Coates already teaches using the computational model to detect and respond to a gas migration event instead of anomalies generally (see claim 1 analysis).
Querales and Boguslawski are analogous to the claimed invention because they are all in the field of hydrocarbon extraction. It would have been obvious to a person of ordinary skill before the effective filing date of the claimed invention to incorporate the adjusting one or more parameters to prevent a future anomaly of Boguslawski with the generic anomaly detection and mitigation of Querales to reduce damage from a future event (page 3, paragraph 6 lines 8-11).
Regarding claim 5, the combination of Querales, Coates, Sandidge, Boguslawski, and Bestman teaches the method of claim 1. Querales also teaches the method of claim 1, wherein the process data comprises downhole data and surface data (page 3 line 33, page 4 lines 1-2), the downhole data comprising one of: a downhole gas flow rate, a downhole gas injection rate, the downhole liquid production rate, a downhole pressure (page 10 line 4, “bottom hole pressure”), a downhole temperature (page 10 line 6, “bottom hole temperature”), a downhole gas concentration, and a subsurface equipment failure and maintenance report; and the surface data comprising one of: a surface pressure, a surface temperature, a gas injection pressure (page 10 line 6, “injected gas pressure”), a gas injection temperature (page 10 line 6, “injected gas temperature”), and a surface equipment failure and maintenance report.
Regarding claim 9, Querales teaches a system (abstract), comprising:
a plurality of sensors disposed on a gas-lifted, hydrocarbon production well comprising a gas-lift system (page 1, lines 17-25, 29), the plurality of sensors configured to acquire process data pertaining to the production well, wherein: (page 3 lines 27-33, page 4 lines 1-2)
the production well is controlled by a set of operation parameters comprising one or more of a gas injection rate or a gas injection pressure of the gas-lift system; (page 7 lines 31-32 “target values and control settings 238 (e.g., gas injection flow and choke setting)”)
and
a computer comprising one or more computer processors and a user interface (page 4 lines 27-29), the computer communicatively connected to the plurality of sensors and configured to:
receive the process data from the plurality of sensors (page 4 lines 20-29);
detect a an anomaly using a computational model based on the process data (page 7 lines 3-10), wherein:
the computation model comprises
determine, using the computational model, adjustments to be made to one or more operation parameters in the set of operation parameters to mitigate the anomaly based on the anomaly and the process data (page 7 lines 10-12)
determine a maintenance action based on the anomaly (page 7 lines 10-12); and
generate an alert for the anomaly (page 8 line 34, page 9 lines 1-3);
wherein the maintenance action is performed on the production well,
wherein the user interface is configured to communicate, to a user, the anomaly, one or more adjusted operation parameters, and the determined maintenance action (page 7 lines 5-12, page 9 lines 6-16).
While Querales teaches controlling a well by adjusting operation parameters to mitigate anomalies, Querales does not explicitly teach that these anomalies are specifically a “gas migration event”.
However, Coates teaches detecting abnormalities (anomalies) indicative of a gas influx (gas migration event) (page 1 Line 30 – Page 2, Line 7, wherein a “gas kick” is equivalent to the claimed gas migration event).
Both Querales and Coates are analogous to the claimed invention because both are in the field of hydrocarbon extraction. It would have been obvious to a person of ordinary skill before the effective filing date of the claimed invention to incorporate the specific detecting a gas migration event of Coates as part of the broad anomaly detection and mitigation system of Querales to maintain operational efficiency or prevent potential damage caused by the gas migration (page 2, lines 3-7).
Therefore, the combination of Querales and Coates teaches specifically detecting and responding to a gas migration event using a computational model as opposed to detecting an anomaly in general.
The combination of Querales and Coates does not explicitly teach:
the process data comprise a downhole liquid production rate, and
the plurality of sensors comprises a liquid production rate sensor configured to measure the downhole liquid production rate,
the computation model comprises an artificial intelligence model comprising a classification model configured to receive the process data as input and return a gas migration status as output, the gas migration status comprising a binary indicator indicating whether gas migration is occurring, and
detecting the gas migration event comprises inputting the process data to the classification model;
wherein the adjustments comprise an adjustment of the gas injection rate or the gas injection pressure;
adjust the one or more operation parameters in accordance with the adjustments;
However, Sandidge teaches the process data comprise a downhole liquid production rate, and
the plurality of sensors comprises a liquid production rate sensor configured to measure the downhole liquid production rate (Paragraph 7 “production rate sensor”, “total fluid production rate”),
wherein the adjustments comprise an adjustment of the gas injection rate or the gas injection pressure (Paragraph 7 “utilizes inputs associated a bottom hole pressure to subsequently adjust the gas injection rate”),
adjust the one or more operation parameters in accordance with the adjustments (Paragraph 43 “continuing adjustment of the gas injection setpoint in an automated process”);
Both Querales and Sandidge are analogous to the claimed invention because both are in the field of controlling a gas-lift well. It would be obvious to a person of ordinary skill in the art to incorporate the system of Querales with the automated adjustment of gas injection of Sandidge to maximize production (Paragraph 28).
The combination of Querales, Coates, and Sandidge does not teach:
the computation model comprises an artificial intelligence model comprising a classification model configured to receive the process data as input and return a gas migration status as output, the gas migration status comprising a binary indicator indicating whether gas migration is occurring, and
detecting the gas migration event comprises inputting the process data to the classification model;
However, Boguslawski teaches an artificial intelligence model (page 3, paragraph 6 lines 2-3 “machine learning”) comprising a classification model configured to receive the process data as input and return a gas migration status as output (page 9 lines 1-4), and
detecting the gas migration event comprises inputting the process data to the classification model (page 9 line 2).
In particular, while Boguslawski does not specifically use “classification model”, the examiner interpretation is that a classification model is merely a kind of machine learning model that categorizes data, such as by applying labels. Since Boguslawski identifies abnormal performance patterns it necessarily categorizes performance as “normal” or “abnormal” (also see Paragraph 16) and thereby performs the functions of a classification model.
Querales and Boguslawski are analogous to the claimed invention because all are in the field of hydrocarbon extraction. It would have been obvious to a person of ordinary skill before the effective filing date of the claimed invention to incorporate the AI model and the preventative maintenance model of Boguslawski with the system of Querales because detecting anomalies reduces risk of damage (page 3, paragraph 6 lines 8-11).
The combination of Querales, Coates, Sandidge, and Boguslawski does not teach the gas migration status comprising a binary indicator indicating whether gas migration is occurring.
However, Bestman teaches the gas migration status comprising a binary indicator indicating whether gas migration is occurring (abstract, “performance deviation”, “threshold”).
In particular, while Bestman does not specifically use “a binary indicator”, a threshold serves to create a binary division between two groups. Bestman must necessarily perform the functions of a binary indicator where the binary indicator is whether or not the performance deviation exceeds the set threshold.
Querales and Bestman are analogous to the claimed invention because all are in the field of hydrocarbon extraction. It would have been obvious to a person of ordinary skill before the effective filing date of the claimed invention to incorporate the threshold of Bestman with the system of Querales because a threshold is potentially variable and can be altered by an operator depending on conditions (pages 6-7, paragraph 70 “performance deviation”).
Regarding claim 10, the combination of Querales, Coates, Sandidge, Boguslawski, and Bestman teaches the system of claim 9. Querales also teaches the system of claim 9, wherein the computer is further configured to:
determine, with the computational model, a gas lift efficiency of the production well based on the process data (page 8 line 15 “GL system performance curves”); and
adjust one or more operation parameters in the set of operation parameters to optimize a production rate of the production well based on the gas lift efficiency (page 7 lines 5-17, page 8 lines 1-2).
Regarding claim 12, the combination of Querales, Coates, Sandidge, Boguslawski, and Bestman teaches the system of claim 9. Querales also teaches the system, of claim 9, wherein the plurality of sensors (page 3 lines 27-33, page 4 lines 1-2) comprise: at least one downhole sensor, comprising one or more of:
a downhole gas flow rate sensor,
a downhole gas injection rate sensor,
the downhole liquid production rate sensor,
a downhole pressure sensor (page 10 line 4, “bottom hole pressure”),
a downhole temperature sensor (page 10 line 6, “bottom hole temperature”), and
a downhole gas concentration sensor, and
at least one surface sensor, comprising one or more of:
a surface pressure sensor,
a surface temperature sensor,
a gas injection pressure sensor (page 10 line 6, “injected gas pressure”), and
a injection temperature sensor (page 10 line 6, “injected gas temperature”).
Regarding claim 13, the combination of Querales, Coates, Sandidge, Boguslawski, and Bestman teaches the system of claim 10.
Querales also teaches the system of claim 10, wherein the process data comprises:
downhole data comprising one or more of:
a downhole gas flow rate,
a downhole gas injection rate,
the downhole liquid production rate,
a downhole pressure (page 10 line 4, “bottom hole pressure”),
a downhole temperature (page 10 line 6, “bottom hole temperature”),
a downhole gas concentration, and
a subsurface equipment failures or maintenance report, and
surface data, comprising one or more of:
a surface pressure,
a surface temperature,
a gas injection pressure (page 10 line 6, “injected gas pressure”),
a gas injection temperature (page 10 line 6, “injected gas temperature”), and
surface equipment failures or a maintenance report.
Regarding claim 16, Querales teaches a non-transitory computer-readable memory comprising computer-executable instructions stored thereon that, when executed on a processor, cause the processor to perform steps comprising (page 10, lines 21-23):
obtaining process data (abstract “collecting measured data”) pertaining to a gas-lifted, hydrocarbon production well (page 1, lines 17-25, 29) comprising a gas-lift system, using at least one sensor disposed on the production well (page 3 lines 27-33, page 4 lines 1-2), wherein:
the production well is controlled by a set of operation parameters (page 7 line 27, “control settings”) comprising one or more of a gas injection rate or a gas injection pressure of the gas-lift system (page 7 lines 31-32 “target values and control settings 238 (e.g., gas injection flow and choke setting)”);
detecting a an anomaly using a computational model based on the process data (page 7 lines 3-10), wherein:
the computation model comprises
determine, using the computational model, adjustments to be made to one or more operation parameters in the set of operation parameters to mitigate the anomaly based on the anomaly and the process data (page 7 lines 10-12)
determining a maintenance action based on the anomaly (page 7 lines 10-12, page 9 lines 8-11); and
generating an alert for the detected anomaly (page 8 line 34, page 9 lines 1-3),
wherein the maintenance action is performed on the production well (page 9 lines 8-10).
While Querales teaches controlling a well by adjusting operation parameters to mitigate anomalies, Querales does not explicitly teach that these anomalies are specifically a “gas migration event”.
However, Coates teaches detecting abnormalities (anomalies) indicative of a gas influx (gas migration event) (page 1 Line 30 – Page 2, Line 7, wherein a “gas kick” is equivalent to the claimed gas migration event).
Therefore, the combination of Querales and Coates teaches specifically detecting and responding to a gas migration event using a computational model as opposed to detecting an anomaly in general.
Both Querales and Coates are analogous to the claimed invention because both are in the field of hydrocarbon extraction. It would have been obvious to a person of ordinary skill before the effective filing date of the claimed invention to incorporate the specific detecting a gas migration event of Coates as part of the broad anomaly detection and mitigation system of Querales to maintain operational efficiency or prevent potential damage caused by the gas migration (page 2, lines 3-7).
The combination of Querales and Coates does not explicitly teach:
the process data comprise a downhole liquid production rate, and
the at least one sensor comprise a liquid production rate sensor configured to measure the downhole liquid production rate,
the computation model comprises an artificial intelligence model comprising a classification model configured to receive the process data as input and return a gas migration status as output, the gas migration status comprising a binary indicator indicating whether gas migration is occurring, and
detecting the gas migration event comprises inputting the process data to the classification model;
wherein the adjustments comprise an adjustment of the gas injection rate or the gas injection pressure;
adjusting the one or more operation parameters in accordance with the adjustments;
However, Sandidge teaches the process data comprise a downhole liquid production rate, and
the at least one sensor comprise a liquid production rate sensor configured to measure the downhole liquid production rate (Paragraph 7 “production rate sensor”, “total fluid production rate”),
wherein the adjustments comprise an adjustment of the gas injection rate or the gas injection pressure (Paragraph 7 “utilizes inputs associated a bottom hole pressure to subsequently adjust the gas injection rate”),
adjusting the one or more operation parameters in accordance with the adjustments (Paragraph 43 “continuing adjustment of the gas injection setpoint in an automated process”);
Both Querales and Sandidge are analogous to the claimed invention because both are in the field of controlling a gas-lift well. It would be obvious to a person of ordinary skill in the art to incorporate the method of Querales with the automated adjustment of gas injection of Sandidge to maximize production (Paragraph 28).
The combination of Querales, Coates, and Sandidge does not teach:
the computation model comprises an artificial intelligence model comprising a classification model configured to receive the process data as input and return a gas migration status as output, the gas migration status comprising a binary indicator indicating whether gas migration is occurring, and
detecting the gas migration event comprises inputting the process data to the classification model;
However, Boguslawski teaches an artificial intelligence model (page 3, paragraph 6 lines 2-3 “machine learning”) comprising a classification model configured to receive the process data as input and return a gas migration status as output (page 9 lines 1-4), and
detecting the gas migration event comprises inputting the process data to the classification model (page 9 line 2).
In particular, while Boguslawski does not specifically use “classification model”, the examiner interpretation is that a classification model is merely a kind of machine learning model that categorizes data, such as by applying labels. Since Boguslawski identifies abnormal performance patterns it necessarily categorizes performance as “normal” or “abnormal” (also see Paragraph 16) and thereby performs the functions of a classification model.
Querales and Boguslawski are analogous to the claimed invention because all are in the field of hydrocarbon extraction. It would have been obvious to a person of ordinary skill before the effective filing date of the claimed invention to incorporate the AI model and the preventative maintenance model of Boguslawski with the method of Querales because detecting anomalies reduces risk of damage (page 3, paragraph 6 lines 8-11).
The combination of Querales, Coates, Sandidge, and Boguslawski does not teach the gas migration status comprising a binary indicator indicating whether gas migration is occurring.
However, Bestman teaches the gas migration status comprising a binary indicator indicating whether gas migration is occurring (abstract, “performance deviation”, “threshold”).
In particular, while Bestman does not specifically use “a binary indicator”, a threshold serves to create a binary division between two groups. Bestman must necessarily perform the functions of a binary indicator where the binary indicator is whether or not the performance deviation exceeds the set threshold.
Querales and Bestman are analogous to the claimed invention because all are in the field of hydrocarbon extraction. It would have been obvious to a person of ordinary skill before the effective filing date of the claimed invention to incorporate the threshold of Bestman with the method of Querales because a threshold is potentially variable and can be altered by an operator depending on conditions (pages 6-7, paragraph 70 “performance deviation”).
Regarding claim 17, the combination of Querales, Coates, Sandidge, Boguslawski, and Bestman teaches the non-transitory computer-readable memory of claim 16.
Querales also teaches the non-transitory computer-readable memory of claim 16, the steps further comprising:
determining, with the computational model, a gas lift efficiency of the production well based on the process data (page 8 line 15 “GL system performance curves”); and
adjusting one or more operation parameters in the set of operation parameters to optimize a production rate of the production well based on the gas lift efficiency (page 7 lines 5-17).
Claim(s) 3, 6-7, 11, 14-15, and 18-20 is/are rejected under 35 U.S.C. 103 as being unpatentable over Querales in light of Coates, further in light of Sandidge, further in light of Bestman, further in light of US 6999829 B2 to Bazzocchi et al. (herein "Bazzocchi"), further in light of Boguslawski.
Regarding claim 3, the combination of Querales, Coates, Sandidge, Boguslawski, and Bestman teaches the method of claim 2.
Coates also teaches detecting abnormalities (anomalies) indicative of a gas influx (gas migration event) (page 1 Line 30 – Page 2, Line 7, wherein a “gas kick” is equivalent to the claimed gas migration event).
Bestman also teaches obtaining environmental data related to the hydrocarbon production well, the environmental data comprising at least one of: weather forecast data, and seismic activity data (Paragraph 28).
Querales and Bestman are analogous to the claimed invention because both are in the field of hydrocarbon extraction. It would have been obvious to a person of ordinary skill before the effective filing date of the claimed invention to incorporate the obtaining environmental data of Bestman and predicting a future anomaly with the method of Querales and Coates, as adding the seismic data contributes to models which can predict well behavior and raise alarms similar to Querales (Paragraphs 5-6).
Bazzocchi also teaches determining a first expected economic cost from a predicted anomaly (col. 5 line 65-67, col. 6 lines 1-3); determining a preventative maintenance action based on the predicted anomaly (col. 3 line 60 “maintenance triggers”, lines 64-65), making a first determination of whether a second expected economic cost of performing the preventative maintenance action is less than the first expected economic cost (col. 5 line 65-67, col. 6 lines 1-3); and performing the preventative maintenance action on the production well based on the first determination that the second expected economic cost is less than the first expected economic cost (col. 6 lines 38-41, 47-48).
While Bazzocchi does not teach determining a first expected economic cost specifically from a gas migration event and determining a preventative maintenance action based specifically on the predicted gas migration event, the combination of Querales and Coates already teaches using the computational model to detect and respond to a gas migration event instead of anomalies generally (see claim 1 analysis).
Bazzocchi and Querales are analogous to the claimed invention because both are in the field of operating an industrial plant. It would have been obvious to a person of ordinary skill before the effective filing date of the claimed invention to incorporate the determining a first expected economic cost of Bazzocchi with the method of Querales, Coates, and Bestman since determining an expected economic cost and performing the preventative maintenance action when the cost of maintenance is lower than the cost of failure minimizes the cost in general (col. 6 lines 38-41, 47-48).
Boguslawski also teaches predicting a anomaly by processing the process data and the environmental data (page 8, paragraph 38 “provide early indication”) and generating an alert for a predictedanomaly (page 7, paragraph 35 line 15).
While Boguslawski does not teach specifically predicting a future gas migration event and generating an alert specifically for a predicted gas migration event, the combination of Querales and Coates already teaches using the computational model to detect and respond to a gas migration event instead of anomalies generally (see claim 1 analysis).
Boguslawski and Querales are analogous art because both are in the field of hydrocarbon production. It would have been obvious to a person of ordinary skill before the effective filing date of the claimed invention to incorporate the predicting a future anomaly and generating an alert of Boguslawski with the method of Querales, Coates, Bestman, and Bazzocchi, as predicting a future anomaly helps improve production and reduce downtime (page 8, paragraph 38 lines 3-4) and an alert reduces risk to field personnel (page 3, paragraph 6 “reduce health and safety risks”).
Regarding claim 6, the combination of Querales, Coates, Sandidge, Bestman, Bazzocchi, and Boguslawski teaches the method of claim 3.
Coates also teaches detecting abnormalities (anomalies) indicative of a gas influx (gas migration event) (page 1 Line 30 – Page 2, Line 7, wherein a “gas kick” is equivalent to the claimed gas migration event).
Boguslawski also teaches a preventative maintenance model that predicts a future anomaly (page 9, lines 2-4).
While Boguslawski does not teach a preventative maintenance model that specifically predicts a future gas migration event, the combination of Querales and Coates already teaches using the computational model to detect and respond to a gas migration event instead of anomalies generally (see claim 1 analysis).
Querales and Boguslawski are analogous to the claimed invention because all are in the field of hydrocarbon extraction. It would have been obvious to a person of ordinary skill before the effective filing date of the claimed invention to incorporate the preventative maintenance model of Boguslawski with the method of Querales because detecting future anomalies reduces risk of damage (page 3, paragraph 6 lines 8-11).
Bestman also teaches wherein the anomaly status is either positive if an anomaly is detected, or negative if an anomaly is not detected (abstract, “performance deviation”, “threshold”).
While Bestman does not specifically teach a gas migration status, the combination of Querales and Coates already teaches using the computational model to detect and respond to a gas migration event instead of anomalies generally (see claim 1 analysis).
Querales and Bestman are analogous to the claimed invention because all are in the field of hydrocarbon extraction. It would have been obvious to a person of ordinary skill before the effective filing date of the claimed invention to incorporate the threshold of Bestman with the method of Querales because a threshold is potentially variable and can be altered by an operator depending on conditions (pages 6-7, paragraph 70 “performance deviation”).
Regarding claim 7, the combination of Querales, Coates, Sandidge, Bestman, Bazzocchi, and Boguslawski teaches the method of claim 6.
Bestman also teaches the method of claim 6, wherein the AI model is an anomaly detection model (“prediction & machine learning module 225”, abstract “performance deviation”). In particular, the combination of Querales, Coates, Sandidge, and Boguslawski already teaches wherein the computational model comprises an artificial intelligence (AI) model (see claim 1 analysis).
Regarding claim 11, the combination of Querales, Coates, Sandidge, Bestman, and Boguslawski teaches the system of claim 9.
Coates also teaches detecting abnormalities (anomalies) indicative of a gas influx (gas migration event) (page 1 Line 30 – Page 2, Line 7, wherein a “gas kick” is equivalent to the claimed gas migration event).
Bestman also teaches obtaining environmental data related to the hydrocarbon production well, the environmental data comprising at least one of: weather forecast data, and seismic activity data (Paragraph 28).
Querales and Bestman are analogous to the claimed invention because both are in the field of hydrocarbon extraction. It would have been obvious to a person of ordinary skill before the effective filing date of the claimed invention to incorporate the obtaining environmental data of Bestman with the system of Querales, as adding the seismic data contributes to models which can predict well behavior (Paragraphs 5-6).
Bazzocchi also teaches determining a preventative maintenance action based on the predicted anomaly (col. 3 line 60 “maintenance triggers”, lines 64-65); and performing the preventative maintenance action on the production (col. 6 lines 38-41, 47-48).
While Bazzocchi does not teach determining a preventative maintenance action specifically based on the predicted gas migration event, the combination of Querales and Coates already teaches using the computational model to detect and respond to a gas migration event instead of anomalies generally (see claim 9 analysis).
Bazzocchi and Querales are analogous to the claimed invention because both are in the field of operating an industrial plant. It would have been obvious to a person of ordinary skill before the effective filing date of the claimed invention to incorporate the determining a first expected economic cost of Bazzocchi with the system of Querales since determining an expected economic cost and performing the preventative maintenance action when the cost of maintenance is lower than the cost of failure minimizes the cost in general (col. 6 lines 38-41, 47-48).
Boguslawski also teaches predicting a future anomaly by processing the process data and the environmental data (page 8, paragraph 38 “provide early indication”) and generating an alert for a predicted anomaly (page 7, paragraph 35 line 15).
While Boguslawski does not teach specifically predicting a future gas migration event and generating an alert specifically for a predicted gas migration event, the combination of Querales and Coates already teaches using the computational model to detect and respond to a gas migration event instead of anomalies generally (see claim 9 analysis).
Boguslawski and Querales are analogous art because both are in the field of hydrocarbon production. It would have been obvious to a person of ordinary skill before the effective filing date of the claimed invention to incorporate the predicting a future anomaly and generating an alert of Boguslawski with the system of Querales, as predicting a future anomaly helps improve production and reduce downtime (page 8, paragraph 38 lines 3-4) and an alert reduces risk to field personnel (page 3, paragraph 6 “reduce health and safety risks”).
Regarding claim 14, the combination of Querales, Coates, Sandidge, Bestman, Bazzocchi, and Boguslawski teaches the system of claim 11.
Coates also teaches detecting abnormalities (anomalies) indicative of a gas influx (gas migration event) (page 1 Line 30 – Page 2, Line 7, wherein a “gas kick” is equivalent to the claimed gas migration event).
Boguslawski also teaches a preventative maintenance model that predicts a future anomaly (page 9, lines 2-4).
While Boguslawski does not teach a preventative maintenance model that specifically predicts a future gas migration event, the combination of Querales and Coates already teaches using the computational model to detect and respond to a gas migration event instead of anomalies generally (see claim 9 analysis).
Querales and Boguslawski are analogous to the claimed invention because all are in the field of hydrocarbon extraction. It would have been obvious to a person of ordinary skill before the effective filing date of the claimed invention to incorporate the AI model and the preventative maintenance model of Boguslawski with the system of Querales because detecting presently occurring and future anomalies reduces risk of damage (page 3, paragraph 6 lines 8-11).
Bestman also teaches wherein the anomaly status is either positive if an anomaly is detected, or negative if an anomaly is not detected (abstract, “performance deviation”, “threshold”).
While Bestman does not specifically teach a gas migration status, the combination of Querales and Coates already teaches using the computational model to detect and respond to a gas migration event instead of anomalies generally (see claim 9 analysis).Querales and Bestman are analogous to the claimed invention because all are in the field of hydrocarbon extraction. It would have been obvious to a person of ordinary skill before the effective filing date of the claimed invention to incorporate the threshold of Bestman with the system of Querales because a threshold is potentially variable and can be altered by an operator depending on conditions (pages 6-7, paragraph 70 “performance deviation”).
Regarding claim 15, the combination of Querales, Coates, Sandidge, Bestman, Bazzocchi, and Boguslawski teaches the system of claim 14.
Bestman also teaches the system of claim 14, wherein the AI model is an anomaly detection model (“prediction & machine learning module 225”, abstract “performance deviation”). In particular, the combination of Querales, Coates, Sandidge, and Boguslawski already teaches wherein the computational model comprises an artificial intelligence (AI) model (see claim 9 analysis).
Regarding claim 18, the combination of Querales, Coates, Sandidge, Boguslawski, and Bestman teaches the non-transitory computer-readable memory of claim 17.
Coates also teaches detecting abnormalities (anomalies) indicative of a gas influx (gas migration event) (page 1 Line 30 – Page 2, Line 7, wherein a “gas kick” is equivalent to the claimed gas migration event).
The combination of Querales and Coates does not teach the non-transitory computer-readable memory of claim 17, the steps further comprising: obtaining environmental data related to the hydrocarbon production well, the environmental data comprising one or more of: weather forecast data, and seismic activity data; predicting a future gas migration event by processing the process data and the environmental data with the computational model; determining a preventative maintenance action based on the predicted future gas migration event; and generating an alert for the detected gas migration event, wherein the preventative maintenance action is performed on the production well.
However, Bestman teaches obtaining environmental data related to the hydrocarbon production well, the environmental data comprising at least one of: weather forecast data, and seismic activity data (Paragraph 28).
Querales and Bestman are analogous to the claimed invention because both are in the field of hydrocarbon extraction. It would have been obvious to a person of ordinary skill before the effective filing date of the claimed invention to incorporate the obtaining environmental data of Bestman with the non-transitory computer-readable memory of Querales, as adding the seismic data contributes to models which can predict well behavior (Paragraphs 5-6).
The combination of Querales, Coates, and Bestman does not teach the non-transitory computer-readable memory of claim 17, the steps further comprising: predicting a future gas migration event by processing the process data and the environmental data with the computational model; determining a preventative maintenance action based on the predicted future gas migration event; and generating an alert for the detected gas migration event, wherein the preventative maintenance action is performed on the production well.
However, Bazzocchi teaches determining a preventative maintenance action based on the predicted anomaly (col. 3 line 60 “maintenance triggers”, lines 64-65); and performing the preventative maintenance action on the production (col. 6 lines 38-41, 47-48).
While Bazzocchi does not teach determining a preventative maintenance action specifically based on the predicted gas migration event, the combination of Querales and Coates already teaches using the computational model to detect and respond to a gas migration event instead of anomalies generally (see claim 16 analysis).
Bazzocchi and Querales are analogous to the claimed invention because both are in the field of operating an industrial plant. It would have been obvious to a person of ordinary skill before the effective filing date of the claimed invention to incorporate the determining a first expected economic cost of Bazzocchi with the non-transitory computer-readable memory of Querales since determining an expected economic cost and performing the preventative maintenance action when the cost of maintenance is lower than the cost of failure minimizes the cost in general (col. 6 lines 38-41, 47-48).
The combination of Querales, Coates, Bestman, and Bazzocchi does not specifically teach the system of claim 9, wherein the computer is further configured to: predict a future gas migration event by processing the process data and the environmental data with the computational model; and generate an alert for the predicted gas migration event; wherein the preventative maintenance action is performed on the production well.
However, Boguslawski teaches predicting a anomaly by processing the process data and the environmental data (page 8, paragraph 38 “provide early indication”) and generating an alert for a predicted anomaly (page 7, paragraph 35 line 15).
While Boguslawski does not teach specifically predicting a future gas migration event and generating an alert specifically for a predicted gas migration event, the combination of Querales and Coates already teaches using the computational model to detect and respond to a gas migration event instead of anomalies generally (see claim 16 analysis).
Boguslawski and Querales are analogous art because both are in the field of hydrocarbon production. It would have been obvious to a person of ordinary skill before the effective filing date of the claimed invention to incorporate the predicting a future anomaly and generating an alert of Boguslawski with the non-transitory computer-readable memory of Querales, as predicting a future anomaly helps improve production and reduce downtime (page 8, paragraph 38 lines 3-4) and an alert reduces risk to field personnel (page 3, paragraph 6 “reduce health and safety risks”).
Regarding claim 19, the combination of Querales, Coates, Sandidge, Bestman, Bazzocchi, and Boguslawski teaches the non-transitory computer-readable memory of claim 18.
Coates also teaches detecting abnormalities (anomalies) indicative of a gas influx (gas migration event) (page 1 Line 30 – Page 2, Line 7, wherein a “gas kick” is equivalent to the claimed gas migration event).
Boguslawski also teaches a preventative maintenance model that predicts a future anomaly (page 9, lines 2-4).
While Boguslawski does not teach a preventative maintenance model that specifically predicts a future gas migration event, the combination of Querales and Coates already teaches using the computational model to detect and respond to a gas migration event instead of anomalies generally (see claim 16 analysis).
Querales and Boguslawski are analogous to the claimed invention because all are in the field of hydrocarbon extraction. It would have been obvious to a person of ordinary skill before the effective filing date of the claimed invention to incorporate the AI model and the preventative maintenance model of Boguslawski with the non-transitory computer-readable memory of Querales because detecting presently occurring and future anomalies reduces risk of damage (page 3, paragraph 6 lines 8-11).
Bestman also teaches wherein theanomaly status is either positive if an anomaly is detected, or negative if an anomaly is not detected (abstract, “performance deviation”, “threshold”).
While Bestman does not specifically teach a gas migration status, the combination of Querales and Coates already teaches using the computational model to detect and respond to a gas migration event instead of anomalies generally (see claim 16 analysis).
Querales and Bestman are analogous to the claimed invention because all are in the field of hydrocarbon extraction. It would have been obvious to a person of ordinary skill before the effective filing date of the claimed invention to incorporate the threshold of Bestman with the non-transitory computer-readable memory of Querales because a threshold is potentially variable and can be altered by an operator depending on conditions (pages 6-7, paragraph 70 “performance deviation”).
Regarding claim 20, the combination of Querales, Coates, Sandidge, Bestman, Bazzocchi, and Boguslawski teaches the non-transitory computer-readable memory of claim 19.
Bestman also teaches the non-transitory computer-readable memory of claim 19, wherein the AI model is an anomaly detection model (“prediction & machine learning module 225”, abstract “performance deviation”). In particular, the combination of Querales, Coates, Sandidge, and Boguslawski already teaches wherein the computational model comprises an artificial intelligence (AI) model (see claim 16 analysis).
Claim(s) 8 is/are rejected under 35 U.S.C. 103 as being unpatentable over Querales in light of Coates, further in light of Sandidge, further in light of Bestman, further in light of Bazzocchi, further in light of Boguslawski, further in light of US 3601191 A to McMurry et al. (herein “McMurry”).
Regarding claim 8, the combination of Querales, Coates, Sandidge, Bestman, Bazzocchi, and Boguslawski teaches the method of claim 3.
Bazzocchi also teaches the repair or replacement of components (col. 4 lines 39-44).
Querales and Bazzocchi are analogous to the claimed invention because all are in the field of operating an industrial plant. It would have been obvious to a person of ordinary skill before the effective filing date of the claimed invention to incorporate the incorporate the repairing and replacement of components of Bazzocchi with the method of Querales, since gas-lift well (plant) assets need maintenance/replacement (col. 1, lines 20-26)
The combination of Querales, Coates, Sandidge, Bestman, Bazzocchi, and Boguslawski does not specifically teach the method of claim 3, wherein the maintenance action is one of: repairing cement, repairing valves, and replacing valves, wherein the predictive maintenance action is one of: improving cement condition, replacing valves, and updating hydrocarbon production equipment.
However, McMurry teaches the replacing of defective valves (col. 1 lines 17-21).
Querales and McMurry are analogous to the claimed invention because all are in the field of hydrocarbon extraction. It would have been obvious to a person of ordinary skill before the effective filing date of the replacing of defective valves of McMurry with the method of Querales, since gas-lift valves are known to be an important component in gas-lift wells (col 1. lines 9-16) respectively.
Conclusion
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to WILLIAM XIANG ZHANG whose telephone number is (571)272-1276. The examiner can normally be reached M-F (8:30 AM - 5 PM).
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Robert Fennema can be reached at 5712722748. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/W.X.Z./Examiner, Art Unit 2117
/DARRIN D DUNN/Patent Examiner, Art Unit 2117
