DETAILED ACTION
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 .
Response to Amendment
This Office Action is in response to applicant’s communication filed 22 May 2026, in response to the Office Action mailed 20 March 2026. The applicant’s remarks and any amendments to the claims or specification have been considered, with the results that follow.
Continued Examination Under 37 CFR 1.114
A request for continued examination under 37 CFR 1.114, including the fee set forth in 37 CFR 1.17(e), was filed in this application after final rejection. Since this application is eligible for continued examination under 37 CFR 1.114, and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114. Applicant's submission filed on 22 May 2026 has been entered.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
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.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
Claim(s) 16, 17, 20, 24-26, and 29-34 is/are rejected under 35 U.S.C. 103 as being unpatentable over Henry (US 9,513,149) in view of Potyrailo (US 2019/0156600).
As per claim 16, Henry teaches a method for determining a fluid density of a fluid in an encapsulated electrical device [sensor signals are used to determine the mass flow rate and density of fluid in a flowtube of an electronic system (figs. 2-4; col. 4, line 54 to col. 5, line 40; col. 10, lines 56-64; etc.)], the method comprising: acquiring measurement data by a sensor unit at the electrical device and deriving from the measurement data measurement values for the fluid density [sensor signals (measurement data) are used to determine the mass flow rate and density of fluid (measurement values) in a flowtube of an electronic system (figs. 2-4; col. 4, line 54 to col. 5, line 40; col. 10, lines 56-64; etc.)]; collecting weather data relating to weather conditions of the electrical device [the system can use additional information, including pressure and temperature measurements from pressure and temperature sensors and other sensors (col. 12, lines 35-61; fig. 11; etc.); where the temperature and pressure sensor measurements are weather data relating to weather conditions of the device]; using machine learning to generate a digital model for an influence of the weather conditions on a measurement deviation of a measurement value from a true fluid density [the system can use additional information, including pressure and temperature measurements (weather conditions) from pressure and temperature sensors and other sensors, as inputs to a neural network (machine learning model) to determine corrections to be made to the mass flow rate and density measurements (col. 12, lines 35-61; etc.); where the neural network (NN) is the digital model generated using machine learning and the corrections determined by the NN are the deviation influenced by the weather conditions]; using, via a control unit external to the electrical device and/or a data cloud, the digital model to calculate a correction value for the measurement values as a function of the weather data [the system can use additional information, including pressure and temperature measurements (weather conditions) from pressure and temperature sensors and other sensors, as inputs to a neural network (machine learning model) to determine corrections to be made to the mass flow rate and density measurements (col. 12, lines 35-61; etc.), where the output measurement and diagnostic information are sent to a distributed (external) control system (col. 5, lines 19-30; etc.)]; and correcting a measurement value with the correction value [the measurement system uses the determined corrections to correct the measured mass flow rate and density values (col. 12, lines 35-61; etc.)].
While Henry teaches inputting temperature and pressure sensor data (weather conditions) to the neural network to determine the correction (see above), it has not been relied upon for teaching collecting, from at least one weather data source external to the electrical device, weather data relating to weather conditions in an environment of the electrical device.
Potyrailo teaches collecting, from at least one weather data source external to the electrical device, weather data relating to weather conditions in an environment of the electrical device [in addition to internal fluid data, the system may collect supplemental data from remote data sources including meteorological/weather data such as wind patterns, etc. (paras. 0601-603; fig. 72; etc.)]; and using a control unit external to the electrical device [the control system may be based on inputs from the operator or locomotive sensors or remote inputs to a control device, tower, facility, etc. (paras. 0489, 0569, etc.)].
Henry and Potyrailo are analogous art, as they are within the same field of endeavor, namely utilizing machine learning algorithms to analyze the behavior of measured sensor data, including fluids.
It would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to utilize the supplemental data from remote data sources, including external weather data, alongside the internal fluid measurement data, as taught by Potyrailo, for the correcting/adjusting of the internal fluid measurement data from sensor data in the system taught by Henry.
Potyrailo provides motivation as [adding the remote supplemental data to the internal sensor data allows improved sophistication of the model, improved accuracy, and improved utility compared to using the sensor data alone (para. 0602, etc.)].
As per claim 17, Henry/Potyrailo teaches wherein the digital model comprises an artificial neural network having a plurality of layers of networked artificial neurons [the system can use additional sensor information as inputs to a neural network to determine corrections to be made to the mass flow rate and density measurements (Henry: col. 12, lines 35-61; etc.); where a neural network has a plurality of layers of networked artificial neurons].
As per claim 20, Henry/Potyrailo teaches the method according to claim 16, as described above, and transferring at least one of the measurement data or the measurement values to a data cloud and/or calculating the correction value with the digital model in a data cloud [the sensor data may be transmitted to a remote system, server, cloud or other source of remote data storage and processing (Potyrailo: paras. 0536, 0551, 0598-604, etc.)].
As per claim 24, Henry/Potyrailo teaches specifying a calculation period and calculating with the digital model the correction value for the measurement values that are acquired within the calculation period is calculated [calculating the measurement values includes producing predictions for a specified time period of collected data (Henry: col. 7, lines 13-50; etc.)].
As per claim 25, Henry/Potyrailo teaches specifying a period of time for the calculation period [calculating the measurement values includes producing predictions for a specified time period of collected data (Henry: col. 7, lines 13-50; etc.)].
While Henry/Potyrailo teaches specifying a time period for calculation (see above), it has not been relied upon for teaching specifying a 24 hour period.
However, it has been held that discovering an optimum value of a result effective variable (the time period) involves only routine skill in the art. In re Boesch, 617 F.2d 272, 205 USPQ 215 (CCPA 1980). It has also been held that where the general conditions of a claim are disclosed in the prior art, discovering the optimum or working ranges (the time period) involves only routine skill in the art. In re Aller, 105 USPQ 233. Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to specify a 24 hour period for the calculation period determined in the system taught by Henry/Potyrailo, to achieve the predictable result of calculating values for a common day-long time period.
As per claim 26, Henry/Potyrailo teaches wherein the weather data are selected from the group consisting of a temperature, a wind speed, precipitation, an air humidity, and an air pressure in the environment of the electrical device [the weather condition data can include temperature (Henry: col. 12, lines 35-61; fig. 11; etc.); and in addition to internal fluid data, the system may collect supplemental data from remote data sources including meteorological/weather data such as wind patterns, (Potyrailo: paras. 0601-603; fig. 72; etc.), temperature, humidity, pressure, and other known effects (Potyrailo: paras. 0147, 0159, 0169, 0298, 0559, 0666, etc.)].
As per claim 29, Henry/Potyrailo teaches feeding only measurement values and weather data as input variables to the digital model [the system can use pressure and temperature measurements as inputs to a neural network (machine learning model) to determine corrections to be made to the mass flow rate and density measurements (Henry: col. 12, lines 35-61; etc.); and in addition to internal fluid data, the system may collect supplemental data from remote data sources including meteorological/weather data such as wind patterns, (Potyrailo: paras. 0601-603; fig. 72; etc.), temperature, humidity, pressure, and other known effects (Potyrailo: paras. 0147, 0159, 0169, 0298, 0559, 0666, etc.)].
As per claim 30, Henry/Potyrailo teaches feeding measurement values, weather data, and additional data, generated from measurement values and the weather data, as input variables to the digital model [the system can use additional information, including pressure and temperature measurements (weather conditions) from pressure and temperature sensors and other sensors (additional data), as inputs to a neural network (machine learning model) to determine corrections to be made to the mass flow rate and density measurements (Henry: col. 12, lines 35-61; etc.); and in addition to internal fluid data, the system may collect supplemental data from remote data sources including meteorological/weather data such as wind patterns, (Potyrailo: paras. 0601-603; fig. 72; etc.), temperature, humidity, pressure, and other known effects (Potyrailo: paras. 0147, 0159, 0169, 0298, 0559, 0666, etc.)].
As per claim 31, Henry/Potyrailo teaches a non-transitory computer-readable medium storing computer-executable instructions which, when executed by at least one processor of a control unit or a computing system of a data cloud, cause the processor to implement the method according to claim 16 [the system may be implemented as software code executed by one or more processors (Henry: col. 5, lines 31-57; Potyrailo: paras. 0152, 0296; etc.)].
As per claim 32, see the rejection of claim 16, above, wherein Henry/Potyrailo also teaches an electrical device with encapsulated fluid [sensor signals are used to determine the mass flow rate and density of fluid in a flowtube of an electronic system (Henry: figs. 2-4; col. 4, line 54 to col. 5, line 40; col. 10, lines 56-64; etc.) and in addition to internal fluid data, the system may collect supplemental data from remote data sources including meteorological/weather data such as wind patterns, (Potyrailo: paras. 0601-603; fig. 72; etc.)], the electrical device comprising: a sensor unit for acquiring measurement data relating to a fluid density of the fluid [sensor signals are used to determine the mass flow rate and density of fluid in a flowtube of an electronic system (Henry: figs. 2-4; col. 4, line 54 to col. 5, line 40; col. 10, lines 56-64; etc.) and in addition to internal fluid data, the system may collect supplemental data from remote data sources including meteorological/weather data such as wind patterns, (Potyrailo: paras. 0601-603; fig. 72; etc.)]; a control unit or a connection to a data cloud [the system may be implemented as software code executed by one or more processors (a control unit) (Henry: col. 5, lines 31-57; Potyrailo: paras. 0152, 0296; etc.)]; a computer program residing in the control unit or in the data cloud, the computer program being configured to: [perform the method] [the system may be implemented as software code executed by one or more processors (a control unit) (Henry: col. 5, lines 31-57; Potyrailo: paras. 0152, 0296; etc.)].
As per claim 33, Henry/Potyrailo teaches wherein the at least one weather data source is a weather database in a data cloud and/or a weather station that collects weather data [in addition to internal fluid data, the system may collect supplemental data from remote data sources including meteorological/weather data such as wind patterns, etc., where the remote data source can include industrial cloud-based platforms (Potyrailo: paras. 0601-603; fig. 72; etc.) and/or a remote weather station(s) (paras. 0534, 0546, etc.)].
As per claim 34, Henry/Potyrailo teaches wherein the weather data includes at least two of a temperature, wind speed, precipitation, air humidity, and air pressure in an environment of the electrical device [in addition to internal fluid data, the system may collect supplemental data from remote data sources including meteorological/weather data such as wind patterns, (Potyrailo: paras. 0601-603; fig. 72; etc.), temperature, humidity, pressure, and other known effects (Potyrailo: paras. 0147, 0159, 0169, 0298, 0559, 0666, etc.)].
Claim(s) 18, 19, 21, and 22 is/are rejected under 35 U.S.C. 103 as being unpatentable over Henry (US 9,513,149), in view of Potyrailo (US 2019/0156600), and further in view of Roy (US 2020/0088897).
As per claim 18, Henry/Potyrailo teaches the method according to claim 17, as described above.
While Henry/Potyrailo teaches using an artificial neural network (see above), it has not been relied upon for teaching wherein the artificial neural network is a recurrent artificial neural network.
Roy teaches wherein the artificial neural network is a recurrent artificial neural network [a deep learning model is used to predict fluid attributes of a reservoir from received attribute data, where the deep learning model can include Long Short-Term Memory networks (LSTM) and/or a type of Recurrent Neural Networks (RNN) (para. 0013, etc.)].
Henry/Potyrailo and Roy are analogous art, as they are within the same field of endeavor, namely using a neural network to determine properties of encapsulated/reservoir fluids.
It would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to utilize an LSTM/RNN as the model for predicting fluid properties, as taught by Roy, for the NN model predicting fluid density correction properties in the system taught by Henry/Potyrailo.
Roy provides motivation as [the LSTM/RNN models can provide more effective and accurate predictions (para. 0013, etc.)].
As per claim 19, Henry/Potyrailo/Roy teaches wherein the artificial neural network comprises at least one memory-enabled cell [a deep learning model is used to predict fluid attributes of a reservoir from received attribute data, where the deep learning model can include Long Short-Term Memory networks (LSTM) and/or a type of Recurrent Neural Networks (RNN) (Roy: para. 0013, etc.); where an LSTM comprises memory-enabled cells].
Examiner’s Note: the reasoning and motivation for the combination of these references is the same as that provided, above, in the rejection of claim 18.
As per claim 21, Henry/Potyrailo teaches the method according to claim 17, as described above.
While Henry/Potyrailo teaches using an artificial neural network (see above), it has not been relied upon for teaching training the digital model by generating further training values for measurement values and/or weather data from measurement values and/or weather data.
Roy teaches training the digital model by generating further training values for measurement values and/or weather data from measurement values and/or weather data [training the machine learning model can include generating simulated fluid property measurements (paras. 0010-12, 0052-53, etc.)].
Henry/Potyrailo and Roy are analogous art, as they are within the same field of endeavor, namely using a neural network to determine properties of encapsulated/reservoir fluids.
It would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to generate simulated measurement data as training samples to train the neural network, as taught by Roy, for training the neural network in the system taught by Henry/Potyrailo.
Roy provides motivation as [using simulated training data provides for more accurate trained models without having to use large amounts of physical reservoir data, allowing training with less data while providing more data for specific types/wells as desired (paras. 0010-12, etc.)].
As per claim 22, Henry/Potyrailo/Roy teaches generating the training values by at least one of: temporally shifting weather data relative to measurement values, scaling measurement values and/or weather data, or shifting a value range of the measurement values [training the machine learning model can include generating simulated fluid property measurements based upon actual measurements and ranges (Roy: paras. 0010-12, 0052-53, etc.), including shifting seismic attribute data over time (Roy: paras. 0048, 0065, etc.); and in addition to internal fluid data, the system may collect supplemental data from remote data sources including meteorological/weather data such as wind patterns, (Potyrailo: paras. 0601-603; fig. 72; etc.)].
Claim(s) 23 is/are rejected under 35 U.S.C. 103 as being unpatentable over Henry (US 9,513,149), in view of Potyrailo (US 2019/0156600), and further in view of Hauge (US 2019/0169982).
As per claim 23, Henry/Potyrailo teaches the method according to claim 16, as described above.
While Henry/Potyrailo teaches using an artificial neural network (see above), it has not been relied upon for teaching training the digital model by generating training values for simulated fluid losses.
Hauge teaches training the digital model by generating training values for simulated fluid losses [a neural network can be used to perform the data analysis (para. 0204, etc.) and can be trained using simulated data including fluid leak data (paras. 0301-303, etc.)].
Henry/Potyrailo and Hauge are analogous art, as they are within the same field of endeavor, namely fluid property predictions using a neural network.
It would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to generate simulated fluid leaks (losses) for training the neural network, as taught by Hauge, for training the neural network in the system taught by Henry/Potyrailo.
Hauge provides motivation as [additional properties are used to create a more accurate characterization of the fluid (paras. 0051-54, etc.)].
Claim(s) 27-28 is/are rejected under 35 U.S.C. 103 as being unpatentable over Henry (US 9,513,149), in view of Potyrailo (US 2019/0156600), and further in view of well-known practices in the art.
As per claim 27, Henry/Potyrailo teaches the method according to claim 16, as described above.
While Henry/Potyrailo teaches generating a digital model on an electrical device (see above), it has not been relied upon for teaching generating the digital model specifically for a given electrical device.
However, the examiner takes official notice that generating (machine learning) models for a specific device is old and well-known within the art. Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to generate the digital model taught by Henry/Potyrailo by generating the digital model specifically for a given electrical device, to achieve the predictable result of generating a model that makes better use of the particular resources and limitations of the particular device.
As per claim 28, Henry/Potyrailo teaches the method according to claim 16, as described above.
While Henry/Potyrailo teaches generating a digital model on an electrical device (see above), it has not been relied upon for teaching generating the digital model specifically for mutually different electrical devices.
However, the examiner takes official notice that generating (machine learning) models for specific devices is old and well-known within the art. Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to generate the digital model taught by Henry/Potyrailo by generating the digital model specifically for mutually different electrical devices, to achieve the predictable result of generating a model that makes better use of the particular resources and limitations of the particular devices.
Response to Arguments
Applicant’s arguments, see the remarks, filed 22 May 2026, with respect to the rejection(s) of claim(s) 16-31 under 35 U.S.C. 103 have been fully considered and are persuasive in view of the amendments made to the independent claims. Therefore, the rejection has been withdrawn. However, upon further consideration, a new ground(s) of rejection is made in view of Potyrailo, which has been relied upon for teaching using internal fluid sensor data alongside supplement data collected from remote data sources, where the remote data sources can include weather station data, etc.
Examiner also notes that the applicant has not traversed examiner’s assertion of official notice. Therefore, the common knowledge or well-known in the art statement is taken to be admitted prior art. See MPEP § 2144.03(C).
Conclusion
The following is a summary of the treatment and status of all claims in the application as recommended by M.P.E.P. 707.07(i): claims 1-15 are cancelled; claims 16-34 are rejected.
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Liu (US 2017/0316121) – discloses a system for simulating effects of rupture on fluid expansion in sealed/open annuli, including predicting fluid density.
Nazari (US 2018/0306693) – discloses a neural network predicting fluid density from sensor data, including determining a correction factor.
Chen (US 2017/0270225) – discloses a neural network using fluid attributes as inputs to determine integrated computational element (ICE) optimization.
Elyas (US 2020/0285216) – discloses real time fluid analysis for drilling/reservoir control using machine learning model(s) and fluid attribute values.
Thuries (US 5,693,873 – cited in an IDS) – discloses correction of pressure sensor data based upon temperature/external conditions.
Alkadi (US 2018/0095032) – discloses using supplemental remote data sources such as meteorological/weather station data, similar to Potyrailo, above.
Davis (US 2011/0259322) – discloses using internal fluid temperature and external temperature data for temperature and other controls.
The examiner requests, in response to this Office action, that support be shown for language added to any original claims on amendment and any new claims. That is, indicate support for newly added claim language by specifically pointing to page(s) and line number(s) in the specification and/or drawing figure(s). This will assist the examiner in prosecuting the application.
When responding to this office action, Applicant is advised to clearly point out the patentable novelty which he or she thinks the claims present, in view of the state of the art disclosed by the references cited or the objections made. He or she must also show how the amendments avoid such references or objections. See 37 CFR 1.111(c).
Any inquiry concerning this communication or earlier communications from the examiner should be directed to GEORGE GIROUX whose telephone number is (571)272-9769. The examiner can normally be reached M-F 10am-6pm.
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, Omar Fernandez Rivas can be reached at 571-272-2589. 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.
/GEORGE GIROUX/Primary Examiner, Art Unit 2128
Prosecution Insights