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 Arguments
Applicant's arguments filed 4/10/2026 have been fully considered but they are not persuasive. Applicant argues that the amended claims include limitations to pre-processing the data, which Tuckett do not teach or do not elaborate on. The argument is unpersuasive since Azevedo (see below) is presently cited for teaching pre-processing of data using normalization, imputation, error removal, and standardization as a technique for improving machine learning models.
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.
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.
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.
Claim(s) 1-12 and 15 is/are rejected under 35 U.S.C. 103 as being unpatentable over Tuckett et al (US 4,106,916) and in further view of Rahmanpour et al (“Lean Amine Concentration Prediction Based on Computational Intelligences as Artificial Neural Networks (ANNs) in Gas Sweetening Processing Units”, Energy Sources, Part A, 36, (2014), pp. 2464-2473) and in further view of Azevedo (“Data Preprocessing Techniques: 6 Steps to Clean Data in Machine Learning” with citations from the version retrieved on October 1, 2022 by the Wayback Machine; https://web.archive.org/web/20221001145632/https://www.scalablepath.com/data-science/data-preprocessing-phase).
Regarding claim 1, Tuckett discloses a method for automatic control of an absorption/stripping process using for example a gas sweetening process (see Col 2, Ln 15-21), the method comprising:
obtaining data from signal lines for transmitting information to a computer from a gas sweetening system
the gas sweetening system comprising a pneumatic control valve for controlling the flow of a lean absorption medium such as diisopropanol amine capable of adsorbing acid gases from a feed gas to an adsorption column, a rich adsorption medium collecting at the bottom of the adsorption column and a pneumatic control valve controlling the rate of removal of the rich adsorption medium to a flash tank, the rich adsorption medium fed to a heat exchanger and a stripping column for separating the acid gases from the adsorption medium where the flow is controlled by a pneumatic control valve, the lean adsorption medium at the bottom of the stripping column is fed to a reboiler; and acid gas is condensed by using a cooling heat exchanger (see Col 2, Ln 34-50); wherein the system comprises a plurality of columns (see Col 5, Ln 46-48);
control of the total absorption process is accomplished by using a computer means to a dynamically simulate the absorption process based on certain process parameters input to the computer (see Col 4, Ln 37-40); where input signals to the computer including measured flow rates of the feed gas, measured concentration of acid gases in the feed gas, and measured flow rate of the rich adsorption medium into the stripping column are used to compute the required flow rate of the lean absorption medium (see Col 4, Ln 44 to Col 5, Ln 7);
discloses output signals form the computer is used to control the flow rate of the lean adsorption means by controlling the pneumatic control valves (see Col 5, Ln 7-19); the computer system using dynamic simulation of the absorption process to provide feed forward control of the two interacting and coupled columns using inputs and logic (see Col 5, Ln 59-65).
Tucker therefore discloses obtaining gas sweetening data from a gas sweetening system comprising an amine flow rate manager (i.e., the valves controlling the absorption medium), a plurality of sweetening units (i.e., the plurality of columns), and a plurality of sensors configured to determine one or more properties (i.e., sensors for sending input signals to the computer); wherein the plurality of sweetening units comprises at least one cooler (the cooling heat exchanger), an absorbing unit (the absorption column); and an amine regenerating unit (i.e., the stripper column); determining by a plant server computer processor a target amine circulation flow rate; transmitting by the plant server computer process, a target amine circulation flow rate to the control system of the gas sweetening unit based on optimization logic equations.
Tuckett does not teach determining by a computer processor an amine soft sensor prediction using a machine learning model and the gas sweetening data and transmitting the amine soft sensor prediction to the plant server where the target amine circulation flow rate to the control system is based on the amine soft sensor prediction and pre-processing the gas sweetening data, during a data cleaning stage, by performing normalization, imputation, error removal, and standardization of the gas sweetening data.
Rahmanpour discloses a method based on artificial neural network for prediction of lean amine concentration where inputs to the modeling system including CO2 concentration, H2S concentration , H2O concentration, and flow-rates in sour and sweet gases (i.e., determining by computer processor an amine soft sensor prediction using machine learning and gas sweetening data) (see Page 2467, Lean amine concentration prediction based on ANN). Rahmanpour further discloses the amine concentration prediction by artificial neural network can solve simplify absorber column controlling, help reach system equilibrium, and reduce reboiler duty (see Page 2468, Conclusions). It would have been obvious to one of ordinary skill in the art at the time of filing of the invention to perform the method for automating control of the absorption medium flow in a gas sweetening system as taught by Tuckett comprising using an artificial neural network is used as an amine soft sensor to predict a lean amine concentration and transmit the data to the computer as taught by Rahmanpour to simplify absorber column controlling with data about the absorbent medium amine concentration.
Regarding the data cleaning stage, Rahmanpour teaches that error free data available for prediction will improve modeling (see Page 2473, RECOMMENDATIONS).
Further regarding data cleaning by performing normalization, imputation, and standardization, Azevedo teaches a method for preprocessing data comprising missing data analysis/treatment by filling in missing data (i.e., imputation), fixing structural errors, data transformation by normalization and standardization for improving model performance (see Pages 5-6, 12-14, 17-18 and Figure 1). Azevedo teaches that data preprocessing is crucial for determining the correct input data for machine learning algorithms to prevent compromising the model(see Page 18-19). It would have been obvious to one of ordinary skill in the art at the time of filing of the invention to perform a method as suggested by Tuckett and Rahmanpour where the method further comprises preprocessing the data by normalization, imputation, error removal, and standardization, as taught by Azevedo, to improve the machine learning model.
Regarding claim 2, as applied above Rahmanpour discloses an artificial neural network.
Regarding claim 3, Rahmanpour discloses outputs in a linear fit (i.e., where the prepared gas sweetening data is transformed by normalizing by computer processor the gas sweetening data (see Figure 3).
Regarding claim 4, Tuckett discloses an automatic method where input signals to the computer including measured flow rates of the feed gas, measured concentration of acid gases in the feed gas, and measured flow rate of the rich adsorption medium into the stripping column are used to compute the required flow rate of the lean absorption medium (see Title and Col 4, Ln 44 to Col 5, Ln 7).
Therefore, Tuckett disclose a computer process which necessarily comprises determining actions based on decision boundaries in order for the process to be automatic.
Regarding claim 5, as applied above, Tuckett discloses using sensors to send signal to the computer (i.e., telemetry data) and computing the required flow rate of the lean absorption medium.
Regarding claim 6, Tuckett discloses a method where input signals to the computer including measured flow rates of the feed gas, measured concentration of acid gases in the feed gas, and measured flow rate of the rich adsorption medium into the stripping column are used to compute the required flow rate of the lean absorption medium (see Col 4, Ln 44 to Col 5, Ln 7). Tuckett further discloses flow sensors and analyzers providing the data to the computer (see Col 4, Ln 44-66). Regarding analyzers, the method according to Tuckett necessary comprises at least two analyzers since input signals from the plurality of gas sweetening units are translated to measured flow rates of the feed gas, measured concentration of acid gases in the feed gas, and measured flow rate of the rich adsorption medium.
Regarding claim 7, Rahmanpour discloses using 130 data sets and therefore discloses using at least a second amine circulation flow rate data.
Regarding claim 8, Tuckett discloses a method where input signals to the computer including measured flow rates of the feed gas, measured concentration of acid gases in the feed gas, and measured flow rate of the rich adsorption medium into the stripping column are used to compute the required flow rate of the lean absorption medium (see Col 4, Ln 44 to Col 5, Ln 7).
Regarding claim 9, Tuckett discloses a method where input signals to the computer including measured flow rates of the feed gas, measured concentration of acid gases in the feed gas, and measured flow rate of the rich adsorption medium into the stripping column are used to compute the required flow rate of the lean absorption medium (see Col 4, Ln 44 to Col 5, Ln 7).
Regarding claim 10, Tuckett discloses a method where input signals to the computer including measured flow rates of the feed gas, measured concentration of acid gases in the feed gas, and measured flow rate of the rich adsorption medium into the stripping column are used to compute the required flow rate of the lean absorption medium (see Col 4, Ln 44 to Col 5, Ln 7).
Regarding claim 11, besides the flash tank and reboiler, as applied above, Tuckett discloses a method comprising a cooling heat exchanger, pumps, and other conventional equipment associated with gas sweetening (see Col 3, Ln 41 and Col 5, Ln 52-55).
Regarding claim 12, Tuckett discloses a method where input signals to the computer including measured flow rates of the feed gas, measured concentration of acid gases in the feed gas, and measured flow rate of the rich adsorption medium into the stripping column are used to compute the required flow rate of the lean absorption medium (see Col 4, Ln XX to Col 5, Ln 7).
Regarding claim 15, Rahmanpour further discloses using 92 data sets to find the best artificial neural network structure as train data and using 19 data to check the generalization capability of the trained artificial neural network and 19 data to test an optimized network as train data (see Abstract). Therefore, Rahmanpour discloses a process comprising obtaining training data (i.e., the 92 data sets) and updating the artificial neural network using the training data based on a mismatch with the 19 data and where an artisan would recognize that optimizing the artificial neural network comprises adjusting parameters based on the test data.
Claim(s) 13-14 is/are rejected under 35 U.S.C. 103 as being unpatentable over Tuckett and Rahmanpour as applied to claim 1 and in further view of Abdulrahman et al (“Effect of Lean Amine Temperature on Amine Gas Sweetening: Case Study and Simulation”, Chem Tech Fuels Oils, Vol 49, No. 4 (2013) pp. 293-297).
As applied to claim 1, Tuckett and Rahmanpour disclose a method comprising obtain sweetening data from a gas sweetening system comprising a computer connected to receive from sensors and send signals to control valves, wherein the gas sweetening unit comprises at least one cooler, an absorbing column which removes acid gas by lean amine, and a stripping column which removes acid gas from the rich amine; determining and transmitting to the computer a lean amine concentration prediction using artificial neural network and the gas sweetening data; determining and transmitting to the control valves an optimum amine circulation flow rate using the computer’s logic and the lean amine concentration prediction.
Regarding claim 13, Abdulrahman discloses that lean amine temperature affects amine gas sweetening of natural gas with high acid content (see Abstract). Abdulrahman further discloses that the minimum possible amine circulation rate at an optimal lean amine temperature of 38°C (see Page 295, Top). It would have been obvious to one of ordinary skill in the art at the time of filing of the invention to perform the method for automating gas sweetening by controlling amine absorbent flow rates using machine learning and gas sweetening data as taught by Tuckett and Rahmanpour, where the gas sweetening data includes temperature data since the lean amine temperature has an effect on the optimal amine flow rate as taught by Abdulrahman.
Regarding claim 14, Tuckett discloses a method where signals for entering into the computer include a pressure transducer and flow rate sensors (see Col 7, Ln 25-50). Regarding temperature data, it would have been obvious to one of ordinary skill in the art at the time of filing of the invention to perform the method for automating gas sweetening by controlling amine absorbent flow rates using machine learning and gas sweetening data as taught by Tuckett and Rahmanpour, where the gas sweetening data includes temperature data since the lean amine temperature has an effect on the optimal amine flow rate as taught by Abdulrahman.
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 MICHAEL FORREST whose telephone number is (571)270-5833. The examiner can normally be reached Monday-Friday (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, Sally A Merkling can be reached at (571)272-6297. 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.
/MICHAEL FORREST/Primary Examiner, Art Unit 1738
Prosecution Insights