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 .
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1-21 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more.
Claim 1 is a method which recites processing the plurality of parameters and respective values to obtain a training dataset and testing dataset; training a neural network using the plurality of parameters and respective values of the training dataset to create a gas hydrate formation model; and using the trained gas hydrate formation model to determine a gas hydrate formation probability for the pipeline from a second plurality of parameters and respective values associated with the pipeline.
In the context of the claim, the limitation of processing the plurality of parameters encompasses performing normalization which is using mathematical calculations. Given the broadest reasonable interpretation in light of the specification, the limitation of training a neural network may include adjusting weights and biases of the connections in the layers ([0025]) which is using mathematical relationships or formulas. Given the broadest reasonable interpretation in light of the specification, the limitation of using the model to determine a gas hydrate formation probability encompasses using mathematical formulas or relationships ([0006], [0018], [0033]). Thus, these limitations fall within the mathematical concepts grouping of abstract ideas. See MPEP 2106.04(a)(2)I. The claim recites an abstract idea.
This judicial exception is not integrated into a practical application. The claim recites the additional claim limitation of obtaining a first plurality of parameters and respective values associated with a gas mixture, the first plurality of parameters comprising temperature, pressure, a composition of the gas mixture, and an indication of gas hydrate formation. The claim does not put any limits on how the first plurality of parameters are obtained, but the background supports the plain meaning of “obtaining” as encompassing obtaining the data remotely over a network. Thus, the limitation is mere data gathering and output recited at a high level of generality, and is insignificant extra-solution activity. See MPEP 2106.05(g). Additionally, the claim recites the additional claim element of a neural network, however, the element is recited at a high level of generality that it amounts to no more than a generic computer used as a tool to perform the abstract idea. As such, it amounts to no more than mere instructions to apply the exception using a generic computer. See MPEP 2106.05(f). The claim is directed to an abstract idea.
The claim(s) does/do not include additional elements that are sufficient to amount to significantly more than the judicial exception. As disclosed above, the additional claim limitations the additional claim elements recite mere instructions to apply the exception using a generic computer and insignificant extra-solution activity, which amounts to obtaining the data remotely over a network. Thus, the claim element amounts to receiving or transmitting data over a network and is well-understood, routine, conventional activity. See MPEP 2106.05(d)II. The claim is not patent eligible.
Claims 2-7 depend from claim 1 and recite the same abstract idea as claim 1. The additional claim limitations recited in claims 2-7 serve merely to additional steps to the abstract idea (claims 2-3 and 6-7) or additional limitations of a generic computer used as a tool to perform the abstract idea (claims 4-5). That is, the steps of normalizing, determine a temperature and pressure, calculating a metric and adjusting a temperature or pressure encompasses using mathematical formulas, equations or relationships. Thus, these limitations fall within the mathematical concepts grouping of abstract ideas. See MPEP 2106.04(a)(2)I. Additionally, the limitations of a feed-forward neural network and a multilayer perceptron are recited at a high level of generality such that they amount to no more than mere instructions to apply the exception using a generic computer. See MPEP 2106.05(f). The claim is directed to an abstract idea. The additional claim limitations neither integrated the abstract idea into a practical application or amount to significantly more than the abstract idea. The claims are not patent eligible.
Claim 8 is a product or manufacturer which recites processing the plurality of parameters and respective values to obtain a training dataset and testing dataset; training a neural network using the plurality of parameters and respective values of the training dataset to create a gas hydrate formation model; and using the trained gas hydrate formation model to determine a gas hydrate formation probability for the pipeline from a second plurality of parameters and respective values associated with the pipeline.
In the context of the claim, the limitation of processing the plurality of parameters encompasses performing normalization which is using mathematical calculations. Given the broadest reasonable interpretation in light of the specification, the limitation of training a neural network may include adjusting weights and biases of the connections in the layers ([0025]) which is using mathematical relationships or formulas. Given the broadest reasonable interpretation in light of the specification, the limitation of using the model to determine a gas hydrate formation probability encompasses using mathematical formulas or relationships ([0006], [0018], [0033]). Thus, these limitations fall within the mathematical concepts grouping of abstract ideas. See MPEP 2106.04(a)(2)I. The claim recites an abstract idea.
This judicial exception is not integrated into a practical application. The claim recites the additional claim limitation of obtaining a first plurality of parameters and respective values associated with a gas mixture, the first plurality of parameters comprising temperature, pressure, a composition of the gas mixture, and an indication of gas hydrate formation. The claim does not put any limits on how the first plurality of parameters are obtained, but the background supports the plain meaning of “obtaining” as encompassing obtaining the data remotely over a network. Thus, the limitation is mere data gathering and output recited at a high level of generality, and is insignificant extra-solution activity. See MPEP 2106.05(g). Additionally, the claim recites the additional claim elements of a neural network and a non-transitory computer readable storage medium comprising program instructions stored thereon, however, the elements are recited at a high level of generality that it amounts to no more than a generic computer used as a tool to perform the abstract idea. As such, they amount to no more than mere instructions to apply the exception using a generic computer. See MPEP 2106.05(f). The claim is directed to an abstract idea.
The claim(s) does/do not include additional elements that are sufficient to amount to significantly more than the judicial exception. As disclosed above, the additional claim elements recite mere instructions to apply the exception using a generic computer and limitations that are insignificant extra-solution activity, amounting to obtaining the data remotely over a network. Additionally, the claim element of obtaining amounts to receiving or transmitting data over a network and is well-understood, routine, conventional activity. See MPEP 2106.05(d)II. The claim is not patent eligible.
Claims 9-14 depend from claim 8 and recite the same abstract idea as claim 8. The additional claim limitations recited in claims 9-14 serve merely to additional steps to the abstract idea (claims 9-10 and 13-14) or additional limitations of a generic computer used as a tool to perform the abstract idea (claims 11-12). That is, the steps of normalizing, determine a temperature and pressure, calculating a metric and adjusting a temperature or pressure encompasses using mathematical formulas, equations or relationships. Thus, these limitations fall within the mathematical concepts grouping of abstract ideas. See MPEP 2106.04(a)(2)I. Additionally, the limitations of a feed-forward neural network and a multilayer perceptron are recited at a high level of generality such that they amount to no more than mere instructions to apply the exception using a generic computer. See MPEP 2106.05(f). The claim is directed to an abstract idea. The additional claim limitations neither integrated the abstract idea into a practical application or amount to significantly more than the abstract idea. The claims are not patent eligible.
Claim 15 is a machine which recites processing the plurality of parameters and respective values to obtain a training dataset and testing dataset; training a neural network using the plurality of parameters and respective values of the training dataset to create a gas hydrate formation model; and using the trained gas hydrate formation model to determine a gas hydrate formation probability for the pipeline from a second plurality of parameters and respective values associated with the pipeline.
In the context of the claim, the limitation of processing the plurality of parameters encompasses performing normalization which is using mathematical calculations. Given the broadest reasonable interpretation in light of the specification, the limitation of training a neural network may include adjusting weights and biases of the connections in the layers ([0025]) which is using mathematical relationships or formulas. Given the broadest reasonable interpretation in light of the specification, the limitation of using the model to determine a gas hydrate formation probability encompasses using mathematical formulas or relationships ([0006], [0018], [0033]). Thus, these limitations fall within the mathematical concepts grouping of abstract ideas. See MPEP 2106.04(a)(2)I. The claim recites an abstract idea.
This judicial exception is not integrated into a practical application. The claim recites the additional claim limitation of obtaining a first plurality of parameters and respective values associated with a gas mixture, the first plurality of parameters comprising temperature, pressure, a composition of the gas mixture, and an indication of gas hydrate formation. The claim does not put any limits on how the first plurality of parameters are obtained, but the background supports the plain meaning of “obtaining” as encompassing obtaining the data remotely over a network. Thus, the limitation is mere data gathering and output recited at a high level of generality, and is insignificant extra-solution activity. See MPEP 2106.05(g). Additionally, the claim recites the additional claim elements of a processor; a non-transitory computer-readable memory accessible by the processor and having executable code stored thereon, however, the elements are recited at a high level of generality that it amounts to no more than a generic computer used as a tool to perform the abstract idea. As such, they amounts to no more than mere instructions to apply the exception using a generic computer. See MPEP 2106.05(f). The claim is directed to an abstract idea.
The claim(s) does/do not include additional elements that are sufficient to amount to significantly more than the judicial exception. As disclosed above, the additional claim elements recite mere instructions to apply the exception using a generic computer and limitations that are insignificant extra-solution activity, amounting to obtaining the data remotely over a network. Additionally, the claim element of obtaining amounts to receiving or transmitting data over a network and is well-understood, routine, conventional activity. See MPEP 2106.05(d)II. The claim is not patent eligible.
Claims 16-21 depend from claim 15 and recite the same abstract idea as claim 15. The additional claim limitations recited in claims 16-21 serve merely to additional steps to the abstract idea (claims 16-17 and 20-21) or additional limitations of a generic computer used as a tool to perform the abstract idea (claims 18-19). That is, the steps of normalizing, determine a temperature and pressure, calculating a metric and adjusting a temperature or pressure encompasses using mathematical formulas, equations or relationships. Thus, these limitations fall within the mathematical concepts grouping of abstract ideas. See MPEP 2106.04(a)(2)I. Additionally, the limitations of a feed-forward neural network and a multilayer perceptron are recited at a high level of generality such that they amount to no more than mere instructions to apply the exception using a generic computer. See MPEP 2106.05(f). The claim is directed to an abstract idea. The additional claim limitations neither integrated the abstract idea into a practical application or amount to significantly more than the abstract idea. The claims are not patent eligible.
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 is/are rejected under 35 U.S.C. 102(a)(1) as anticipated by or, in the alternative, under 35 U.S.C. 103 as obvious over Sahith et al. in Non-Patent Literature “Application of Artificial Neural Networks on Measurement of Gas Hydrates in Pipelines” (see IDS filed 2024 Feb 26).
Regarding claim 1, Sahith et al. teaches:
A method for determining the probability of gas hydrate formation in a pipeline (see “application…ANN…in the prediction of gas hydrate formation in…pipelines”, Abstract), comprising:
obtaining a first plurality of parameters and respective values associated with a gas mixture (see “2. Base for development of modelling techniques”, p. 5770), the first plurality of parameters comprising temperature (see “…The Pressure and Temperature…”, p. 5770 section 2), pressure (see “…The Pressure and Temperature…”, p. 5770 section 2), a composition of the gas mixture (see “…chemical potential of every components in each phase”, p. 5770 section 2), and an indication of gas hydrate formation (see “…formation of gas hydrates calculations…”, p. 5770 section 2 );
processing the plurality of parameters and respective values to obtain a training dataset and testing dataset (see “…ANN…is trained by trial and error…”, p. 5772 col. 2 par. 2 it is understood that in order to train an ANN a training dataset and testing dataset are needed);
training a neural network using the plurality of parameters and respective values of the training dataset to create a gas hydrate formation model (see “…ANN…is trained by trial and error…”, p. 5772 col. 2 par. 2); and
using the trained gas hydrate formation model to determine a gas hydrate formation probability for the pipeline from a second plurality of parameters and respective values associated with the pipeline (see “The ANN model enables the user to accurately predict hydrate formation conditions…”, p. 5772 col. 2 par. 2; Abstract).
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:
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) 2 is/are rejected under 35 U.S.C. 103 as being unpatentable over Sahith et al. in Non-Patent Literature “Application of Artificial Neural Networks on Measurement of Gas Hydrates in Pipelines” (see IDS filed 2024 Feb 26) as applied to claim 1 above, and further in view of Wen-Long et al. in Foreign Patent Document CN-113326665-A (see Machine Translation).
Regarding claim 2, Sahith et al. teaches the limitations of claim 1 as indicated above. Sahith et al. differs from the claimed invention in that it does not expressly teach wherein processing the plurality of parameters and respective values comprising normalizing the plurality of respective values to a range.
Wen-Long et al. teaches “a prediction method for generating temperature of acidic natural gas hydrate based on genetic programming algorithm. the method comprises the following steps: obtaining the related data generated by the acid natural gas hydrate in the literature; setting the generation temperature as output variable, natural gas component, pressure, genetic programming algorithm basic frame of input variable; dividing the original data into a training set and a test set and normalizing the data; inputting data and using the genetic programming algorithm to model to obtain the optimal explicit expression; finally, inversely normalizing to obtain the prediction model” (Abstract a training dataset, a testing dataset, temperature and pressure data, normalizing the data to train). Wen-Long et al. teaches “step two…all data normalization processing” (page 2) wherein the normalization parameters for each variable include normalized temperature, normalized pressured and normalized composition of the gas mixture (pages 5-6, claims 1-4 normalizing the plurality of respective values to a range). Wen-Long et al. “solves the problem that the traditional prediction model has low prediction precision of the natural gas hydrate generation temperature” (pages 7-8).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have combined the teachings of Wen-Long et al. with Sahith et al. for monitoring the development of gas hydrates in pipelines, thereby improving the functionality and utility of the Sahith et al.
Claim(s) 3 is/are rejected under 35 U.S.C. 103 as being unpatentable over Sahith et al. in Non-Patent Literature “Application of Artificial Neural Networks on Measurement of Gas Hydrates in Pipelines” (see IDS filed 2024 Feb 26) as applied to claim 1 above, and further in view of Sayani et al. in Non-Patent Literature “Development of a Simple Statistical Model for the Prediction of Gas Hydrate Formation Conditions”.
Regarding claim 3, Sahith et al. teaches the limitations of claim 1 as indicated above. Sahith et al. differs from the claimed invention in that it does not expressly teach using the trained gas hydrate formation model to determine a temperature of gas hydrate formation and a pressure of gas hydrate formation.
Sayani et al. teaches “a simple statistical correlation is developed for the prediction of gas hydrate formation temperature” (Abstract, using the trained gas hydrate formation model to determine a temperature of gas hydrate formation). Further, Sayani et al. discloses “The thermodynamic models can predict the formation pressure of hydrate” (pg. 2 par 1, using the trained gas hydrate formation model to determine a pressure of gas hydrate formation) and “Nowadays, an Artificial Neural Network (ANN) is employed to predict the temperature of hydrate formation. Artificial neural networks can be trained to understand correlation patterns between variables and then used to predict outputs based on fresh inputs” (pg. 2 par. 5-6 using the trained gas hydrate formation model to determine a temperature of gas hydrate formation). Sayani et al. establishes that using the trained gas hydrate formation model to determine a temperature of gas hydrate formation and a pressure of gas hydrate formation is part of the knowledge of a person of ordinary skill in the art.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have combined the teachings of Sayani et al. as known in the art with Sahith et al. for monitoring the development of gas hydrates in pipelines, thereby improving the functionality and utility of the Sahith et al.
Claim(s) 4 is/are rejected under 35 U.S.C. 103 as being unpatentable over Sahith et al. in Non-Patent Literature “Application of Artificial Neural Networks on Measurement of Gas Hydrates in Pipelines” (see IDS filed 2024 Feb 26) as applied to claim 1 above, and further in view of Shaik et al. in Non-Patent Literature “Experimental investigation and ANN modelling on CO2 hydrate kinetics in multiphase pipeline systems”.
Regarding claim 4, Sahith et al. teaches the limitations of claim 1 as indicated above. Sahith et al. differs from the claimed invention in that it does not expressly teach wherein the neural network comprises a feed-forward neural network.
Shaik et al. teaches “Artificial Neural Networks (ANN) are developed to study and predict the effect of the multiphase system on the kinetics of gas hydrates formation… two ANN models with single layer perceptron are presented for the two combinations of gas hydrates” (Abstract). Further, Shaik et al. discloses “Mohammadi et al.26–28 provided a statistical model based on a feed-forward artificial neural network (ANN) algorithm that could predict the thermodynamic conditions of the hydrate systems: H2O + H2, H2O + H2 + THF, and H2 + H2O + tetra-n-butyl ammonium bromide. They showed that the projected and experimental results are in good agreement, proving the algorithm’s reliability as a predictive tool.” (pg. 3 par 2, neural network comprises a feed-forward neural network). Shaik et al. establishes that using a neural network that comprises a feed-forward neural network in determining gas hydrate is part of the knowledge of a person of ordinary skill in the art.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have combined the teachings of Shaik et al. as known in the art with Sahith et al. for monitoring the development of gas hydrates in pipelines, thereby improving the functionality and utility of the Sahith et al.
Claim(s) 5 is/are rejected under 35 U.S.C. 103 as being unpatentable over Sahith et al. in Non-Patent Literature “Application of Artificial Neural Networks on Measurement of Gas Hydrates in Pipelines” (see IDS filed 2024 Feb 26) as applied to claim 1 above, and further in view of Rosli et al. in Non-Patent Literature “Neural Network Architecture Selection for Efficient Prediction Model of Gas Metering System”.
Regarding claim 5, Sahith et al. teaches the limitations of claim 1 as indicated above. Sahith et al. differs from the claimed invention in that it does not expressly teach wherein the neural network comprises a multilayer perceptron.
Rosli et al. teaches “election of a suitable model architecture for the purpose of predicting accurate and reliable energy measurements. This is because the selection of the architecture is fundamental to neural network modeling and design. The proposed Artificial Neural Network (ANN) prediction model is optimized with particle swarm optimization (PSO). A very good structure of neural network model ensures improved performance of the model.” (p. 1 Introduction par. 4) and Rosli discloses “Neural systems are intense as nonlinear signal processors, however results are regularly a long way from satisfactory. The most essential criteria in building up a neural system model are the network architecture and parameter selection. There are various neural system structures which are generally depicted in the literature [1-4].. The most well known system engineering utilized was multilayer perceptron (MLP) system. MLP is one of the favored neural system topology of most analysts [5]” (p. 1 Network Architecture par. 1; Fig. 1 the neural network comprises a multilayer perceptron). Rosli establishes that using a multilayer perceptron neural network for modeling in the oil and gas industry is part of the knowledge of a person of ordinary skill in the art.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have combined the teachings of Rosli et al. as known in the art with Sahith et al. for monitoring the development of gas hydrates in pipelines, thereby improving the functionality and utility of the Sahith et al.
Claim(s) 6 is/are rejected under 35 U.S.C. 103 as being unpatentable over Sahith et al. in Non-Patent Literature “Application of Artificial Neural Networks on Measurement of Gas Hydrates in Pipelines” (see IDS filed 2024 Feb 26) as applied to claim 1 above, and further in view of Hossain et al. in U.S. Patent Publication 2013/0318016.
Regarding claim 6, Sahith et al. teaches the limitations of claim 1 as indicated above. Sahith et al. differs from the claimed invention in that it does not expressly teach calculating a metric between a gas hydrate formation probability produced by the gas hydrate formation model and an indication of gas hydrate formation in the training data, wherein the metric comprises a mean absolute error, a mean squared error, or a root mean squared error.
Hossain et al. “relates to predicting gas composition” ([0002]) and discloses “In recent years, computational intelligence techniques, such as artificial neural network (ANNs), have gained enormous popularity in predicting various petroleum reservoirs' properties” ([0004]). Further, Hossain et al. teaches “For such ANN methods, common techniques for performance evaluation include the correlation coefficient (CC) and the root mean squared error (RMSE). The CC measures the statistical correlation between the predicted and the actual values…The RMSE is one of the most commonly used measures of success for numeric prediction…The RMSE is simply the square root of the mean squared error. The RMSE gives the error value with the same dimensionality as the actual and predicted values” ([0014]-[0015] calculating a metric between actual and predicted values comprising a mean squared error or root mean squared error). Hossain et al. establishes metrics for measuring success for a numeric prediction as part of the knowledge of the ordinary skill in the art.
It would have been obvious to one of ordinary skill in the art to have applied the most commonly used measures of success for numeric prediction, mean squared error or root mean squared error, as taught in Hossain et al. for calculating a metric between a gas hydrate formation probability produced by the gas hydrate formation model and an indication of gas hydrate formation in the training data to improve Sahith et al. with a reasonable expectation that it would result in improving the model for determining the probability of gas hydrate formation, thereby improving the utility of Sahith et al.
Claim(s) 7 is/are rejected under 35 U.S.C. 103 as being unpatentable over Sahith et al. in Non-Patent Literature “Application of Artificial Neural Networks on Measurement of Gas Hydrates in Pipelines” (see IDS filed 2024 Feb 26) as applied to claim 1 above, and further in view of Otto in U.S. Patent Publication 2022/0154889.
Regarding claim 7, Sahith et al. teaches the limitations of claim 1 as indicated above. Sahith et al. differs from the claimed invention in that it does not expressly teach adjusting a temperature or pressure associated with the pipeline based on the gas hydrate formation probability.
Otto teaches “performing a real-time and closed loop control scheme using the sensor data and a material model of the gas to determine one or more control decisions. The method also includes operating one or more controllable pipeline elements to adjust a temperature, a pressure, a flow rate, or a composition of the gas according to the one or more control decisions” (Abstract, [0003] adjusting a temperature or pressure associated with the pipeline; [0009]). Otto teaches “one or more control decisions are determined to meet one or more control objectives. In some embodiments, the one or more control objectives include at least one of limiting a formation of hydrates in the gas…reducing a likelihood of a fracture of a pipeline of the pipeline system” ([0012]; [0041]). Otto further teaches “The controller 102 can use the sensor data obtained from the sensing unit 30 to determine one or more properties (e.g., a phase) of the fluid 16…The controllable pipeline elements 106 may be configured…to adjust/control one or more properties of the fluid 16 (or the fluid slug 18) that flows through the pipeline 12…temperature, pressure, flow rate and composition can be controlled” ([0047] adjusting a temperature or pressure associated with the pipeline based on the gas hydrate formation probability).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have combined the teachings of Otto as known in the art with Sahith et al. for monitoring and limiting the development of gas hydrates in pipelines, thereby improving the functionality and utility of the Sahith et al.
Claim(s) 8, 14-15 and 21 is/are rejected under 35 U.S.C. 103 as being unpatentable over Sahith et al. in Non-Patent Literature “Application of Artificial Neural Networks on Measurement of Gas Hydrates in Pipelines” (see IDS filed 2024 Feb 26) and further in view of Otto in U.S. Patent Publication 2022/0154889.
Regarding claim 8, Sahith et al. teaches:
obtaining a first plurality of parameters and respective values associated with a gas mixture (see “2. Base for development of modelling techniques”, p. 5770), the first plurality of parameters comprising temperature (see “…The Pressure and Temperature…”, p. 5770 section 2), pressure (see “…The Pressure and Temperature…”, p. 5770 section 2), a composition of the gas mixture (see “…chemical potential of every components in each phase”, p. 5770 section 2), and an indication of gas hydrate formation (see “…formation of gas hydrates calculations…”, p. 5770 section 2 );
processing the plurality of parameters and respective values to obtain a training dataset and testing dataset (see “…ANN…is trained by trial and error…”, p. 5772 col. 2 par. 2 it is understood that in order to train an ANN a training dataset and testing dataset are needed);
training a neural network using the plurality of parameters and respective values of the training dataset to create a gas hydrate formation model (see “…ANN…is trained by trial and error…”, p. 5772 col. 2 par. 2); and
using the trained gas hydrate formation model to determine a gas hydrate formation probability for the pipeline from a second plurality of parameters and respective values associated with the pipeline (see “The ANN model enables the user to accurately predict hydrate formation conditions…”, p. 5772 col. 2 par. 2; Abstract).
Sahith et al. differs from the claimed invention in that it does not expressly teach A non-transitory computer readable storage medium comprising program instructions stored thereon for determining the probability of gas hydrate formation in a pipeline, the program instructions executable by a processor.
Otto teaches “performing a real-time and closed loop control scheme using the sensor data and a material model of the gas to determine one or more control decisions. The method also includes operating one or more controllable pipeline elements to adjust a temperature, a pressure, a flow rate, or a composition of the gas according to the one or more control decisions” (Abstract, [0003]) and “one or more control decisions are determined to meet one or more control objectives. In some embodiments, the one or more control objectives include at least one of limiting a formation of hydrates in the gas…reducing a likelihood of a fracture of a pipeline of the pipeline system” ([0012]; [0041] determining the probability of gas hydrate formation in a pipeline). Further, Otto discloses “The controller 102 includes processing circuitry 108 including a processor 110 and a memory 112… The processor 110 may be configured to execute computer code and/or instructions stored in the memory 112 or received from other computer readable media” ([0052] A non-transitory computer readable storage medium comprising program instructions stored thereon for determining the probability of gas hydrate formation in a pipeline, the program instructions executable by a processor).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have combined the teachings of Otto as known in the art with Sahith et al. for monitoring and limiting the development of gas hydrates in pipelines, thereby improving the functionality and utility of the Sahith et al.
Regarding claim 14, Sahith et al. and Otto teach the limitations of claim 8 as indicated above. Further, Otto teaches “The controller 102 can use the sensor data obtained from the sensing unit 30 to determine one or more properties (e.g., a phase) of the fluid 16…The controllable pipeline elements 106 may be configured…to adjust/control one or more properties of the fluid 16 (or the fluid slug 18) that flows through the pipeline 12…temperature, pressure, flow rate and composition can be controlled” ([0047] adjusting a temperature or pressure associated with the pipeline based on the gas hydrate formation probability).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have combined the teachings of Otto as known in the art with Sahith et al. for monitoring and limiting the development of gas hydrates in pipelines, thereby improving the functionality and utility of the Sahith et al.
Regarding claim 15, Sahith et al. teaches:
obtaining a first plurality of parameters and respective values associated with a gas mixture (see “2. Base for development of modelling techniques”, p. 5770), the first plurality of parameters comprising temperature (see “…The Pressure and Temperature…”, p. 5770 section 2), pressure (see “…The Pressure and Temperature…”, p. 5770 section 2), a composition of the gas mixture (see “…chemical potential of every components in each phase”, p. 5770 section 2), and an indication of gas hydrate formation (see “…formation of gas hydrates calculations…”, p. 5770 section 2 );
processing the plurality of parameters and respective values to obtain a training dataset and testing dataset (see “…ANN…is trained by trial and error…”, p. 5772 col. 2 par. 2 it is understood that in order to train an ANN a training dataset and testing dataset are needed);
training a neural network using the plurality of parameters and respective values of the training dataset to create a gas hydrate formation model (see “…ANN…is trained by trial and error…”, p. 5772 col. 2 par. 2); and
using the trained gas hydrate formation model to determine a gas hydrate formation probability for the pipeline from a second plurality of parameters and respective values associated with the pipeline (see “The ANN model enables the user to accurately predict hydrate formation conditions…”, p. 5772 col. 2 par. 2; Abstract).
Sahith et al. differs from the claimed invention in that it does not expressly teach a processor; a non-transitory computer-readable memory accessible by the processor and having executable code stored thereon.
Otto teaches “performing a real-time and closed loop control scheme using the sensor data and a material model of the gas to determine one or more control decisions. The method also includes operating one or more controllable pipeline elements to adjust a temperature, a pressure, a flow rate, or a composition of the gas according to the one or more control decisions” (Abstract, [0003]) and “one or more control decisions are determined to meet one or more control objectives. In some embodiments, the one or more control objectives include at least one of limiting a formation of hydrates in the gas…reducing a likelihood of a fracture of a pipeline of the pipeline system” ([0012]; [0041] determining the probability of gas hydrate formation in a pipeline). Further, Otto discloses “The controller 102 includes processing circuitry 108 including a processor 110 and a memory 112… The processor 110 may be configured to execute computer code and/or instructions stored in the memory 112 or received from other computer readable media” ([0052] a processor; a non-transitory computer-readable memory accessible by the processor and having executable code stored thereon).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have combined the teachings of Otto as known in the art with Sahith et al. for monitoring and limiting the development of gas hydrates in pipelines, thereby improving the functionality and utility of the Sahith et al.
Regarding claim 21, Sahith et al. and Otto teach the limitations of claim 15 as indicated above. Further, Otto teaches “The controller 102 can use the sensor data obtained from the sensing unit 30 to determine one or more properties (e.g., a phase) of the fluid 16…The controllable pipeline elements 106 may be configured…to adjust/control one or more properties of the fluid 16 (or the fluid slug 18) that flows through the pipeline 12…temperature, pressure, flow rate and composition can be controlled” ([0047] adjusting a temperature or pressure associated with the pipeline based on the gas hydrate formation probability).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have combined the teachings of Otto as known in the art with Sahith et al. for monitoring and limiting the development of gas hydrates in pipelines, thereby improving the functionality and utility of the Sahith et al.
Claim(s) 9 and 16 is/are rejected under 35 U.S.C. 103 as being unpatentable over Sahith et al. in Non-Patent Literature “Application of Artificial Neural Networks on Measurement of Gas Hydrates in Pipelines” (see IDS filed 2024 Feb 26) and Otto in U.S. Patent Publication 2022/0154889 as applied to claims 8 and 15 above, and further in view of view of Wen-Long et al. in Foreign Patent Document CN-113326665-A (see Machine Translation).
Regarding claim 9, Sahith et al. and Otto teach the limitation of claim 8 as indicated above. Sahith et al. and Otto differ from the claimed invention in that they do not expressly teach wherein processing the plurality of parameters and respective values comprising normalizing the plurality of respective values to a range.
Wen-Long et al. teaches “a prediction method for generating temperature of acidic natural gas hydrate based on genetic programming algorithm. the method comprises the following steps: obtaining the related data generated by the acid natural gas hydrate in the literature; setting the generation temperature as output variable, natural gas component, pressure, genetic programming algorithm basic frame of input variable; dividing the original data into a training set and a test set and normalizing the data; inputting data and using the genetic programming algorithm to model to obtain the optimal explicit expression; finally, inversely normalizing to obtain the prediction model” (Abstract a training dataset, a testing dataset, temperature and pressure data, normalizing the data to train). Wen-Long et al. teaches “step two…all data normalization processing” (page 2) wherein the normalization parameters for each variable include normalized temperature, normalized pressured and normalized composition of the gas mixture (pages 5-6, claims 1-4 normalizing the plurality of respective values to a range). Wen-Long et al. “solves the problem that the traditional prediction model has low prediction precision of the natural gas hydrate generation temperature” (pages 7-8).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have combined the teachings of Wen-Long et al. with Sahith et al. and Otto for monitoring the development of gas hydrates in pipelines, thereby improving the functionality and utility of the Sahith et al. and Otto.
Regarding claim 16, Sahith et al. and Otto teach the limitation of claim 15 as indicated above. Sahith et al. and Otto differ from the claimed invention in that they do not expressly teach wherein processing the plurality of parameters and respective values comprising normalizing the plurality of respective values to a range.
Wen-Long et al. teaches “a prediction method for generating temperature of acidic natural gas hydrate based on genetic programming algorithm. the method comprises the following steps: obtaining the related data generated by the acid natural gas hydrate in the literature; setting the generation temperature as output variable, natural gas component, pressure, genetic programming algorithm basic frame of input variable; dividing the original data into a training set and a test set and normalizing the data; inputting data and using the genetic programming algorithm to model to obtain the optimal explicit expression; finally, inversely normalizing to obtain the prediction model” (Abstract a training dataset, a testing dataset, temperature and pressure data, normalizing the data to train). Wen-Long et al. teaches “step two…all data normalization processing” (page 2) wherein the normalization parameters for each variable include normalized temperature, normalized pressured and normalized composition of the gas mixture (pages 5-6, claims 1-4 normalizing the plurality of respective values to a range). Wen-Long et al. “solves the problem that the traditional prediction model has low prediction precision of the natural gas hydrate generation temperature” (pages 7-8).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have combined the teachings of Wen-Long et al. with Sahith et al. and Otto for monitoring the development of gas hydrates in pipelines, thereby improving the functionality and utility of the Sahith et al. and Otto.
Claim(s) 10 and 17 is/are rejected under 35 U.S.C. 103 as being unpatentable over Sahith et al. in Non-Patent Literature “Application of Artificial Neural Networks on Measurement of Gas Hydrates in Pipelines” (see IDS filed 2024 Feb 26) and Otto in U.S. Patent Publication 2022/0154889 as applied to claims 8 and 15 above, and further in view of Sayani et al. in Non-Patent Literature “Development of a Simple Statistical Model for the Prediction of Gas Hydrate Formation Conditions”.
Regarding claim 10, Sahith et al. and Otto teach the limitation of claim 8 as indicated above. Sahith et al. and Otto differ from the claimed invention in that they do not expressly teach using the trained gas hydrate formation model to determine a temperature of gas hydrate formation and a pressure of gas hydrate formation.
Sayani et al. teaches “a simple statistical correlation is developed for the prediction of gas hydrate formation temperature” (Abstract, using the trained gas hydrate formation model to determine a temperature of gas hydrate formation). Further, Sayani et al. discloses “The thermodynamic models can predict the formation pressure of hydrate” (pg. 2 par 1, using the trained gas hydrate formation model to determine a pressure of gas hydrate formation) and “Nowadays, an Artificial Neural Network (ANN) is employed to predict the temperature of hydrate formation. Artificial neural networks can be trained to understand correlation patterns between variables and then used to predict outputs based on fresh inputs” (pg. 2 par. 5-6 using the trained gas hydrate formation model to determine a temperature of gas hydrate formation). Sayani et al. establishes that using the trained gas hydrate formation model to determine a temperature of gas hydrate formation and a pressure of gas hydrate formation is part of the knowledge of a person of ordinary skill in the art.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have combined the teachings of Sayani et al. as known in the art with Sahith et al. and Otto for monitoring the development of gas hydrates in pipelines, thereby improving the functionality and utility of the Sahith et al.
and Otto.
Regarding claim 17, Sahith et al. and Otto teach the limitation of claim 15 as indicated above. Sahith et al. and Otto differ from the claimed invention in that they do not expressly teach using the trained gas hydrate formation model to determine a temperature of gas hydrate formation and a pressure of gas hydrate formation.
Sayani et al. teaches “a simple statistical correlation is developed for the prediction of gas hydrate formation temperature” (Abstract, using the trained gas hydrate formation model to determine a temperature of gas hydrate formation). Further, Sayani et al. discloses “The thermodynamic models can predict the formation pressure of hydrate” (pg. 2 par 1, using the trained gas hydrate formation model to determine a pressure of gas hydrate formation) and “Nowadays, an Artificial Neural Network (ANN) is employed to predict the temperature of hydrate formation. Artificial neural networks can be trained to understand correlation patterns between variables and then used to predict outputs based on fresh inputs” (pg. 2 par. 5-6 using the trained gas hydrate formation model to determine a temperature of gas hydrate formation). Sayani et al. establishes that using the trained gas hydrate formation model to determine a temperature of gas hydrate formation and a pressure of gas hydrate formation is part of the knowledge of a person of ordinary skill in the art.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have combined the teachings of Sayani et al. as known in the art with Sahith et al. and Otto for monitoring the development of gas hydrates in pipelines, thereby improving the functionality and utility of the Sahith et al.
and Otto.
Claim(s) 11 and 18 is/are rejected under 35 U.S.C. 103 as being unpatentable over Sahith et al. in Non-Patent Literature “Application of Artificial Neural Networks on Measurement of Gas Hydrates in Pipelines” (see IDS filed 2024 Feb 26) and Otto in U.S. Patent Publication 2022/0154889 as applied to claims 8 and 15 above, and further in view of Shaik et al. in Non-Patent Literature “Experimental investigation and ANN modelling on CO2 hydrate kinetics in multiphase pipeline systems”.
Regarding claim 11, Sahith et al. and Otto teach the limitations of claim 8 as indicated above. Sahith et al. and Otto differ from the claimed invention in that they do not expressly teach wherein the neural network comprises a feed-forward neural network.
Shaik et al. teaches “Artificial Neural Networks (ANN) are developed to study and predict the effect of the multiphase system on the kinetics of gas hydrates formation… two ANN models with single layer perceptron are presented for the two combinations of gas hydrates” (Abstract). Further, Shaik et al. discloses “Mohammadi et al.26–28 provided a statistical model based on a feed-forward artificial neural network (ANN) algorithm that could predict the thermodynamic conditions of the hydrate systems: H2O + H2, H2O + H2 + THF, and H2 + H2O + tetra-n-butyl ammonium bromide. They showed that the projected and experimental results are in good agreement, proving the algorithm’s reliability as a predictive tool.” (pg. 3 par 2, neural network comprises a feed-forward neural network). Shaik et al. establishes that using a neural network that comprises a feed-forward neural network in determining gas hydrate is part of the knowledge of a person of ordinary skill in the art.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have combined the teachings of Shaik et al. as known in the art with Sahith et al. and Otto for monitoring the development of gas hydrates in pipelines, thereby improving the functionality and utility of the Sahith et al. and Otto.
Regarding claim 18, Sahith et al. and Otto teach the limitations of claim 15 as indicated above. Sahith et al. and Otto differ from the claimed invention in that they do not expressly teach wherein the neural network comprises a feed-forward neural network.
Shaik et al. teaches “Artificial Neural Networks (ANN) are developed to study and predict the effect of the multiphase system on the kinetics of gas hydrates formation… two ANN models with single layer perceptron are presented for the two combinations of gas hydrates” (Abstract). Further, Shaik et al. discloses “Mohammadi et al.26–28 provided a statistical model based on a feed-forward artificial neural network (ANN) algorithm that could predict the thermodynamic conditions of the hydrate systems: H2O + H2, H2O + H2 + THF, and H2 + H2O + tetra-n-butyl ammonium bromide. They showed that the projected and experimental results are in good agreement, proving the algorithm’s reliability as a predictive tool.” (pg. 3 par 2, neural network comprises a feed-forward neural network). Shaik et al. establishes that using a neural network that comprises a feed-forward neural network in determining gas hydrate is part of the knowledge of a person of ordinary skill in the art.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have combined the teachings of Shaik et al. as known in the art with Sahith et al. and Otto for monitoring the development of gas hydrates in pipelines, thereby improving the functionality and utility of the Sahith et al. and Otto.
Claim(s) 12 and 19 is/are rejected under 35 U.S.C. 103 as being unpatentable over Sahith et al. in Non-Patent Literature “Application of Artificial Neural Networks on Measurement of Gas Hydrates in Pipelines” (see IDS filed 2024 Feb 26) and Otto in U.S. Patent Publication 2022/0154889 as applied to claims 8 and 15 above, and further in view of Rosli et al. in Non-Patent Literature “Neural Network Architecture Selection for Efficient Prediction Model of Gas Metering System”.
Regarding claim 11, Sahith et al. and Otto teach the limitations of claim 8 as indicated above. Sahith et al. and Otto differ from the claimed invention in that they do not expressly teach wherein the neural network comprises a multilayer perceptron.
Rosli et al. teaches “election of a suitable model architecture for the purpose of predicting accurate and reliable energy measurements. This is because the selection of the architecture is fundamental to neural network modeling and design. The proposed Artificial Neural Network (ANN) prediction model is optimized with particle swarm optimization (PSO). A very good structure of neural network model ensures improved performance of the model.” (p. 1 Introduction par. 4) and Rosli discloses “Neural systems are intense as nonlinear signal processors, however results are regularly a long way from satisfactory. The most essential criteria in building up a neural system model are the network architecture and parameter selection. There are various neural system structures which are generally depicted in the literature [1-4].. The most well known system engineering utilized was multilayer perceptron (MLP) system. MLP is one of the favored neural system topology of most analysts [5]” (p. 1 Network Architecture par. 1; Fig. 1 the neural network comprises a multilayer perceptron). Rosli establishes that using a multilayer perceptron neural network for modeling in the oil and gas industry is part of the knowledge of a person of ordinary skill in the art.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have combined the teachings of Rosli et al. as known in the art with Sahith et al. and Otto for monitoring the development of gas hydrates in pipelines, thereby improving the functionality and utility of the Sahith et al. and Otto.
Regarding claim 18, Sahith et al. and Otto teach the limitations of claim 15 as indicated above. Sahith et al. and Otto differ from the claimed invention in that they do not expressly teach wherein the neural network comprises a multilayer perceptron.
Rosli et al. teaches “election of a suitable model architecture for the purpose of predicting accurate and reliable energy measurements. This is because the selection of the architecture is fundamental to neural network modeling and design. The proposed Artificial Neural Network (ANN) prediction model is optimized with particle swarm optimization (PSO). A very good structure of neural network model ensures improved performance of the model.” (p. 1 Introduction par. 4) and Rosli discloses “Neural systems are intense as nonlinear signal processors, however results are regularly a long way from satisfactory. The most essential criteria in building up a neural system model are the network architecture and parameter selection. There are various neural system structures which are generally depicted in the literature [1-4].. The most well known system engineering utilized was multilayer perceptron (MLP) system. MLP is one of the favored neural system topology of most analysts [5]” (p. 1 Network Architecture par. 1; Fig. 1 the neural network comprises a multilayer perceptron). Rosli establishes that using a multilayer perceptron neural network for modeling in the oil and gas industry is part of the knowledge of a person of ordinary skill in the art.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have combined the teachings of Rosli et al. as known in the art with Sahith et al. and Otto for monitoring the development of gas hydrates in pipelines, thereby improving the functionality and utility of the Sahith et al. and Otto.
Claim(s) 13 and 20 is/are rejected under 35 U.S.C. 103 as being unpatentable over Sahith et al. in Non-Patent Literature “Application of Artificial Neural Networks on Measurement of Gas Hydrates in Pipelines” (see IDS filed 2024 Feb 26) and Otto in U.S. Patent Publication 2022/0154889 as applied to claims 8 and 15 above, and further in view of Hossain et al. in U.S. Patent Publication 2013/0318016.
Regarding claim 13, Sahith et al. and Otto teach the limitations of claim 8 as indicated above. Sahith et al. and Otto differ from the claimed invention in that it does not expressly teach calculating a metric between a gas hydrate formation probability produced by the gas hydrate formation model and an indication of gas hydrate formation in the training data, wherein the metric comprises a mean absolute error, a mean squared error, or a root mean squared error.
Hossain et al. “relates to predicting gas composition” ([0002]) and discloses “In recent years, computational intelligence techniques, such as artificial neural network (ANNs), have gained enormous popularity in predicting various petroleum reservoirs' properties” ([0004]). Further, Hossain et al. teaches “For such ANN methods, common techniques for performance evaluation include the correlation coefficient (CC) and the root mean squared error (RMSE). The CC measures the statistical correlation between the predicted and the actual values…The RMSE is one of the most commonly used measures of success for numeric prediction…The RMSE is simply the square root of the mean squared error. The RMSE gives the error value with the same dimensionality as the actual and predicted values” ([0014]-[0015] calculating a metric between actual and predicted values comprising a mean squared error or root mean squared error). Hossain et al. establishes metrics for measuring success for a numeric prediction as part of the knowledge of the ordinary skill in the art.
It would have been obvious to one of ordinary skill in the art to have applied the most commonly used measures of success for numeric prediction, mean squared error or root mean squared error, as taught in Hossain et al. for calculating a metric between a gas hydrate formation probability produced by the gas hydrate formation model and an indication of gas hydrate formation in the training data to improve Sahith et al. with a reasonable expectation that it would result in improving the model for determining the probability of gas hydrate formation, thereby improving the utility of Sahith et al. and Otto.
Regarding claim 20, Sahith et al. and Otto teach the limitations of claim 15 as indicated above. Sahith et al. and Otto differ from the claimed invention in that it does not expressly teach calculating a metric between a gas hydrate formation probability produced by the gas hydrate formation model and an indication of gas hydrate formation in the training data, wherein the metric comprises a mean absolute error, a mean squared error, or a root mean squared error.
Hossain et al. “relates to predicting gas composition” ([0002]) and discloses “In recent years, computational intelligence techniques, such as artificial neural network (ANNs), have gained enormous popularity in predicting various petroleum reservoirs' properties” ([0004]). Further, Hossain et al. teaches “For such ANN methods, common techniques for performance evaluation include the correlation coefficient (CC) and the root mean squared error (RMSE). The CC measures the statistical correlation between the predicted and the actual values…The RMSE is one of the most commonly used measures of success for numeric prediction…The RMSE is simply the square root of the mean squared error. The RMSE gives the error value with the same dimensionality as the actual and predicted values” ([0014]-[0015] calculating a metric between actual and predicted values comprising a mean squared error or root mean squared error). Hossain et al. establishes metrics for measuring success for a numeric prediction as part of the knowledge of the ordinary skill in the art.
It would have been obvious to one of ordinary skill in the art to have applied the most commonly used measures of success for numeric prediction, mean squared error or root mean squared error, as taught in Hossain et al. for calculating a metric between a gas hydrate formation probability produced by the gas hydrate formation model and an indication of gas hydrate formation in the training data to improve Sahith et al. with a reasonable expectation that it would result in improving the model for determining the probability of gas hydrate formation, thereby improving the utility of Sahith et al. and Otto.
Conclusion
Regarding the rejection under 35 U.S.C. 101, the Examiner notes that the specification, see e.g. [0026], recites language that would facilitate integrating the abstract idea into a practical application. A section of [0026] is provided with emphasis:
The prediction may be used to take action or make decisions regarding the potential gas hydrate formations (block 212). For example, based on the probability of gas hydrate formation, operating conditions may be adjusted or preventative measures taken to avoid gas hydrate formation in the pipeline. For example, the temperature of the pipeline may be actively managing, such as by insulating the pipeline, heating the pipeline or both. In some instances, a hydrate inhibitor (including low dosage hydrate inhibitors (LDHIs)) may be added to the gas mixture in the pipeline. Such hydrate inhibitors may include methanol, ethanol, glycols, and salts. In another instance, the pressure in the pipeline may be maintained, such as by increasing or decreasing the pressure based on considerations of the temperature (for example, increasing the pressure may raise the hydrate formation temperature).
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure:
Duan et al. in Non-Patent Literature “Prediction of Gas Hydrate Formation in the Wellbore” teaches “The formation of gas hydrates due to temperature and pressure changes during gas storage in the wellbore poses significant danger, necessitating the prediction of temperature and pressure distribution as well as of hydrate formation locations. We establish a temperature model that couples total thermal resistance and temperature in the wellbore-stratum composite medium system. Utilizing the two-phase pressure model alongside the temperature model, we conduct coupling calculations of temperature and pressure. Based on both temperature and pressure distribution within the wellbore and hydrate formation curve, we predict hydrate formation regions during production and analyze factors influencing temperature and pressure distribution. Results indicate that gas production rate and specific gravity of natural gas are major influencers on wellbore temperature and pressure distribution, while production time has minimal impact” (Abstract).
Tamzor et al. in Non-Patent Literature “Modelling and Optimization Techniques for Gas Hydrate Formation in Pipeline: A Review” teaches “a classification system for hydrate modeling techniques and their subcategories, including kinetic techniques, thermodynamic techniques, machine learning techniques, and simulation techniques. According to the results, computational and numerical methods are used because of the sustainable formation forecast of the hydrate scheme, even if a rising pattern is seen in the usage of simulation frameworks in conjunction with artificial intelligence approaches. Due to their propensity to handle ambiguity and uncertain data sets more effectively than numerical techniques, simulation and integrated frameworks are in high demand. However, numerical methods do a good job of handling deterministic data sets” (Abstract).
Hegeman et al. in U.S. Patent Publication 2009/0030858 teaches “The performance of the ANN 400 can be measured by entering data from the training set portion of a training database, and comparing the output data generated by the ANN 400 to true output values (i.e., laboratory-measured values). From these comparisons, a mean relative error, a mean absolute relative error, and a standard deviation can be determined. A similar performance measurement process can be performed using the validation set portion of the training database.” ([0063], emphasis added).
Any inquiry concerning this communication or earlier communications from the examiner should be directed to MISCHITA HENSON whose telephone number is (571)270-3944. The examiner can normally be reached Monday-Thursday 9am-6pm EST.
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, Arleen Vazquez can be reached at 571-272-2619. 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.
/MI'SCHITA' HENSON/ Primary Examiner, Art Unit 2857
Prosecution Insights