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
The amendment filed June 18, 2026 has been entered. Claims 1-9 and 12-15 remain pending in the instant application. Applicant’s amendments to the Claims have overcome each and every 112(b) rejection previously set forth in the Non-Final Office Action mailed April 2, 2026
Response to Arguments
Applicant’s arguments, filed June 18, 2026, regarding rejections under 35 U.S.C 103 of Claim(s) 1-9 and 12-15 have been fully considered, but they are not persuasive.
Applicant argues that Hamann does not teach a machine learning model that modulates a magnitude of a relationship between the physics-based measurement of corrosion and the operational parameters. Specifically, Applicant argues that weighting models in the multi-model blending process of Hamann (e.g., Hamann, paragraph [0021]), is not the same as modulating a relationship between a physics-based measurement and operational parameters. Further, Applicant argues that the multi-model blending used to predict corrosion in Hamann (e.g., Hamann, figure 6 and paragraph [0029]) also does not disclose modulating a relationship between a measurement and operational parameters.
Regarding this argument, the Examiner disagrees. Figure 6 of Hamann is reproduced below:
PNG
media_image1.png
687
743
media_image1.png
Greyscale
Figure 6 of Hamann discloses a plurality of models, which may comprise a machine learning model (corrosion model A) and a physics-based model (corrosion model N), being input into a multi-model blending system which uses machine learning to blend said models. As described in Hamann, “the machine learning algorithm may be a weighted average of two or more of the algorithms mentioned above” (e.g., Hamann, paragraph [0021]). A weighted average, given its broadest reasonable interpretation, describes a relationship between the input corrosion models, wherein the weights applied to the input models describe the contribution, (i.e., magnitude of relationship) of each input model to the final blended output. Further, figure 6 discloses measured corrosion data, interpreted as operational parameters, being fed into the multi-model blending system. The multi-model blending system thus also modulates a relationship between a physics-based measurement (corrosion model N) and operational parameters (measured corrosion data).
An updated rejection under U.S.C 103, necessitated by Applicant’s amendment, is provided below.
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) 1-9 and 12-15 is/are rejected under 35 U.S.C. 103 as being unpatentable over Hamann et al. (U.S. Pub. No. 2015/0347922 A1), hereinafter Hamann, in view of Opondo (Opondo, Kizito M. Corrosion tests in cooling circuit water at Olkaria I plant and scale predictions for Olkaria and Reykjanes fluids. United Nations University, 2002.), hereinafter Opondo, further in view of Agarwala (Agarwala, Vinod S. "Control of corrosion and service life." In NACE CORROSION, pp. NACE-04257. NACE, 2004.), hereinafter Agarwala.
Regarding Claim 1, Hamann teaches A method comprising: […] determining, via a computing system (“FIG. 1 is an overview of a multi-model blending system 100 according to an embodiment of the invention. The system 100 includes an input interface 113, one or more processors 115, one or more memory devices 117.”) (e.g., paragraph [0016]).
a physics-based measurement of corrosion using a physics-based model for the fluid's corrosion of a substrate based, at least in part on, the lab-based measurements (“Collecting historical measurements, at block 210, is a process that is performed according to one embodiment. According to that embodiment, the sources 120 shown in FIG. 1 are sources of the historical measurements […] Also according to that embodiment, executing one or more models based on the historical measurements (at block 220) is performed by the processor 115 of the system 100 to obtain predictions of historical conditions […] At least one of the one or more models used by the system 100 is a physical model [...] While FIG. 3 was discussed above with specific reference to meteorological models, the sources 120 could, as well, provide outputs of corrosion models.” The output of a physical model is interpreted as a physics-based measurement of corrosion, wherein the historical measurements are interpreted as lab-based measurements.) (e.g., paragraphs [0017] and [0027]).
wherein the physics-based model correlates (a) the physics-based measurement of corrosion to (b) an operational parameter (“For example, a corrosion model may model the pitting corrosion propagation rate as a function of several different inputs (e.g., CO2, H2S, partial pressure, temperature, pressure) independently yielding a pitting corrosion rate due to each input (e.g., H2S, temperature).” The several different inputs are interpreted as operational parameters, and the pitting corrosion propagation rate is interpreted as a physics-based measurement.) (e.g., paragraph [0018]).
determining, via the computing system, a machine learning-based measurement of corrosion using a machine learning-based model for the fluid's corrosion of the substrate based, at least in part on, in-field-based measurements (“At block 250, training a machine learning algorithm based on the predictor variables and the response variables is according to known machine learning processes. Essentially, the actual historical conditions facilitate obtaining a set of weighting coefficients that indicate how well the models worked under different circumstances.” The output of the machine learning algorithm is interpreted as a machine learning-based measurement of corrosion.) (e.g., paragraph [0021]).
wherein the machine-learning model correlates (a) the machine learning-based measurement of corrosion to (b) the physics-based measurement of corrosion and the operational parameters (“As shown, corrosion variables (e.g., pipe materials, physical parameters) are provided to some number of corrosion prediction models which act as the sources 120 (A through N) in this case. The outputs (forecasts of these models are used as inputs to the multi-model blending system 100, which outputs a blended predicted corrosion rate based on the machine learning algorithm that was developed using historical predictions from the models and measured (actual) corrosion data according to the embodiments discussed above. In alternate embodiments, the corrosion variables used by the models (sources 120) may also be used by the system 100.” The physics-based measurements and operational parameters may be provided as sources 120 to the machine learning algorithm, wherein blending the sources 120 to determine a blended prediction is interpreted as correlating the machine learning-based measurement with the physics-based measurement and operational parameters.) (e.g., paragraph [0029]).
and modulates a magnitude of a relationship between the physics-based measurement of corrosion and the operational parameters (“the machine learning algorithm may be a weighted average of two or more of the algorithms mentioned above […] As shown, corrosion variables (e.g., pipe materials, physical parameters) are provided to some number of corrosion prediction models which act as the sources 120 (A through N) in this case. The outputs (forecasts) of these models are used as inputs to the multi-model blending system 100, which outputs a blended predicted corrosion rate based on the machine learning algorithm.”) (e.g., paragraphs [0021] and [0029]).
and applying, via the computing system, an ensemble method to the physics-based measurement of corrosion and the machine learning-based measurement of corrosion to yield an estimated measure of corrosion of the substrate (“Resulting predictions of historical conditions may be provided by the sources 120. That is, the system 100 may use not only the outputs of one or more models […] The output of the machine learning algorithm is the multi-model blending process […] At block 270, executing the multi-model blending on the outputs of the one or more models provides a blended forecast.” The sources 120 may include the output of the machine learning algorithm, wherein the blending system, interpreted as performing an ensemble method, may be used again on the physics and machine learning-based measurements to yield another estimated measure of corrosion.”) (e.g., paragraphs [0017] and [0022]).
However, Hamann does not appear to specifically teach measuring, in a laboratory, lab-based measurements of a substrate relating to the fluid’s corrosion of the substrate and one or more of: repairing and/or replacing a component comprising the substrate based on the estimated measure of corrosion; building a system or portion thereof comprising a component that comprises the substrate, wherein a composition of the substrate is chosen based on the estimated measure of corrosion; and refining a feedstock, based on the estimated measure of corrosion, wherein the feedstock or a downstream product and/or distillate thereof is the fluid.
On the other hand, Opondo, which relates to laboratory corrosion testing on coupons, does teach measuring, in a laboratory, lab-based measurements of a substrate relating to the fluid’s corrosion of the substrate (“Corrosion tests were conducted using a set of eight metal coupons involving different exposure periods which were dependent on the periods during which the metal coupons were exposed to fluids. The metal coupons were exposed for periods ranging between 2 and 5 days, depending on the duration of the pH test. […] Material loss and corrosion rates for each pH adjustment are shown in Table 2 for the metal coupons that showed significant changes in weight.” Table 2 discloses measurements for material lost (ML) and corrosion rate (CR), which are interpreted as lab-based measurements of a substrate relating to the fluid’s corrosion of the substrate.) (e.g., page 6, paragraph 1; page 9, table 2).
However, neither Hamann nor Opondo teaches one or more of: repairing and/or replacing a component comprising the substrate based on the estimated measure of corrosion; building a system or portion thereof comprising a component that comprises the substrate, wherein a composition of the substrate is chosen based on the estimated measure of corrosion; and refining a feedstock, based on the estimated measure of corrosion, wherein the feedstock or a downstream product and/or distillate thereof is the fluid.
On the other hand, Agarwala, which relates to corrosion prevention and maintenance, does teach a method comprising one or more of: repairing and/or replacing a component comprising the substrate based on the estimated measure of corrosion; building a system or portion thereof comprising a component that comprises the substrate, wherein a composition of the substrate is chosen based on the estimated measure of corrosion; and refining a feedstock, based on the estimated measure of corrosion, wherein the feedstock or a downstream product and/or distillate thereof is the fluid (The Examiner notes the use of one or more of, and the prior art teaches repairing and/or replacing a component. “Parameters that track corrosion assisted damage serve best in creating a reliable database for predictive modeling and structural ‘health’ monitoring. The accuracy of a database is essential in developing a cue when repair is needed and also in the assessment of remaining life or life expended. A paradigm shift from schedule based periodic maintenance to condition based maintenance (CBM) is preferable because finding a problem early and then fixing it through small repairs saves numerous maintenance man-hours later on by avoiding cumulative damage.” Condition based maintenance is interpreted as repairing a component based on an estimated measure of corrosion.) (e.g., page 6, paragraph 2).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the Applicant's claimed invention to combine Hamann with Opondo. The claimed invention is considered to be merely combining prior art elements according to known methods to yield predictable results, see MPEP § 2143(I)(A). Hamann teaches a method for combining estimated measures of corrosion from a physics based model and a machine learning based model using historical measurements. However, Hamann does not appear to specifically teach how the historical measurements are acquired. On the other hand, Opondo, which relates to testing the corrosivity of cooling circuit water at a geothermal plant, does teach a method for obtaining lab-based measurements of a substrate relating to a fluid’s corrosion of the substrate. The only difference between the claimed invention and the prior art is a lack of actual combination of the elements into a single prior art reference. As Hamann generally teaches the use of historical measurements in the multi-model blending method, one of ordinary skill in the art could have merely used the lab-based measurements of Opondo as a source of historical measurements for the multi-model blending in Hamann. Furthermore, one of ordinary skill in the art would have recognized the results of the combination as predictably providing a physics-based model based on lab-based measurements. Therefore, it would have been obvious to a person of ordinary skill in the art before the effective filing date of the Applicant’s claimed invention to combine the corrosion prediction of Hamann with the lab-based measurements of Opondo in order to provide a further source of historical measurements.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the Applicant's claimed invention to combine the modified reference of Hamann in view of Opondo with Agarwala. The claimed invention is considered to be merely combining prior art elements according to known methods to yield predictable results, see MPEP § 2143(I)(A). Hamann teaches a method for combining estimated measures of corrosion from a physics based model and a machine learning based model. However, Hamann does not appear to specifically teach using the estimated measures of corrosion to build or repair a system or a component of a system. On the other hand, Agarwala, which relates to corrosion management, does teach a method comprising designing and repairing a component or system based on corrosion resistance. The only difference between the claimed invention and the prior art is a lack of actual combination of the elements into a single prior art reference. Furthermore, Agarwala discloses that corrosion prevention and control is fundamental to any equipment that experiences recurring corrosion costs (e.g., Agarwala; page 7, paragraph 3). As Hamann relates to forecasting pipeline corrosion (e.g., Hamann; paragraph [0003]), one of ordinary skill in the art could have combined the corrosion forecasting of Hamann with the actual design implementation of Agarwala. In combination, each element merely performs the same function as it does separately, and one of ordinary skill in the art would have recognized the results of the combination as predictable. Therefore, it would have been obvious to a person of ordinary skill in the art prior to the effective filing date of the Applicant’s claimed invention to combine the corrosion prediction of Hamann with the corrosion aware design and maintenance of Agarwala in order to utilize corrosion predictions in real world designs.
Regarding Claim 2, Hamann in view of Opondo and Agarwala teaches The method of claim 1. Hamann further teaches wherein the operational parameter is selected from the group consisting of: a total acid number (TAN) of the fluid, a composition of the TAN, a total reactive sulfur (TRS) of the fluid, a composition of the TRS, an origin of the fluid, a composition of the fluid, a temperature of the fluid, a fluid density, a fluid velocity, a corrosion inhibitor concentration in the fluid, a corrosion inhibitor composition, composition of the substrate, configuration of the substrate, phases of the fluid, a phase behavior of the fluid, an absence or presence of scale on the substrate, a composition of said scale, a density of said scale, and any combination thereof (The Examiner notes the use of any combination thereof, and the prior art provides operational parameters selected from temperature and pressure. “For example, a corrosion model may model the pitting corrosion propagation rate as a function of several different inputs (e.g., CO2, H2S, partial pressure, temperature, pressure) independently yielding a pitting corrosion rate due to each input (e.g., H2S, temperature).”) (e.g., paragraph [0018]).
Regarding Claim 3, Hamann in view of Opondo and Agarwala teaches The method of claim 1. Agarwala further teaches wherein the method comprises the repairing and/or replacing the component comprising the substrate based on the estimated measure of corrosion (The Examiner notes that this claim is indefinite under 112(b). For the purposes of compact prosecution, the following mapping is provided. “Parameters that track corrosion assisted damage serve best in creating a reliable database for predictive modeling and structural ‘health’ monitoring. The accuracy of a database is essential in developing a cue when repair is needed and also in the assessment of remaining life or life expended. A paradigm shift from schedule based periodic maintenance to condition based maintenance (CBM) is preferable because finding a problem early and then fixing it through small repairs saves numerous maintenance man-hours later on by avoiding cumulative damage.” Condition based maintenance is interpreted as repairing a component based on an estimated measure of corrosion.) (e.g., page 6, paragraph 2).
Regarding Claim 4, Hamann in view of Opondo and Agarwala teaches The method of claim 1. Agarwala further teaches wherein the method comprises building the system or portion thereof comprising a component that comprises the substrate, wherein the composition of the substrate is chosen based on the estimated measure of corrosion (The Examiner notes that this claim is indefinite under 112(b). For the purposes of compact prosecution, the following mapping is provided. “Presently, there are numerous substitute alloys and better alloy tempers (heat treatment) available which can solve this problem [of intergranular corrosion]. For example, it has been well studied and known that T-7 is a much superior corrosion resistant temper with only less than 10% penalty in strength compared to the T-6 temper [...] All components must be designed with an understanding of where and how they will be used. If the operational environment is corrosive and wet, careful attention should be given to its design to avoid any possibility of water accumulation, condensation, or collection during service.” Designing components with respect to their use is interpreted as building a system comprising choosing a composition of a component based on an estimated measure of corrosion, wherein choosing a T-7 temper is analogous to choosing a composition of a substrate.) (e.g., page 4, paragraph 2; page 7, last paragraph).
Regarding Claim 8, Hamann teaches A method for predicting corrosion (“The present invention relates to forecast models, and more specifically, to multi-model blending […] to forecast pipeline corrosion in the oil and gas pipeline field.”) (e.g., paragraphs [0002] and [0003]).
comprising: providing a hybrid model that correlates two or more operational parameters to an estimated measure of corrosion (“Embodiments of the systems and methods described herein relate to multi-model blending to facilitate prediction or estimation over a broad range of inputs [...] Two exemplary embodiments are specifically discussed. One involves the system 100 both executing one or more models and developing the blended model based on the model outputs while the other involves the system 100 receiving outputs from one or more models and developing the blended model.”) (e.g., paragraphs [0015] and [0016]).
comprising: a physics-based model for a fluid's corrosion of a substrate (“Collecting historical measurements, at block 210, is a process that is performed according to one embodiment. According to that embodiment, the sources 120 shown in FIG. 1 are sources of the historical measurements […] Also according to that embodiment, executing one or more models based on the historical measurements (at block 220) is performed by the processor 115 of the system 100 to obtain predictions of historical conditions […] At least one of the one or more models used by the system 100 is a physical model [...] While FIG. 3 was discussed above with specific reference to meteorological models, the sources 120 could, as well, provide outputs of corrosion models.” The output of a physical model is interpreted as a physics-based measurement of corrosion, wherein the historical measurements are interpreted as lab-based measurements.) (e.g., paragraphs [0017] and [0027]).
wherein the physics-based model correlates (a) the physics-based measurement of corrosion to (b) two or more operational parameters (“For example, a corrosion model may model the pitting corrosion propagation rate as a function of several different inputs (e.g., CO2, H2S, partial pressure, temperature, pressure) independently yielding a pitting corrosion rate due to each input (e.g., H2S, temperature).” The several different inputs are interpreted as operational parameters, and the pitting corrosion propagation rate is interpreted as a physics-based measurement.) (e.g., paragraph [0018]).
a machine learning-based model for the fluid's corrosion of the substrate based, at least in part on, in-field measurements (“At block 250, training a machine learning algorithm based on the predictor variables and the response variables is according to known machine learning processes. Essentially, the actual historical conditions facilitate obtaining a set of weighting coefficients that indicate how well the models worked under different circumstances.” The output of the machine learning algorithm is interpreted as a machine learning-based measurement of corrosion.) (e.g., paragraph [0021]).
wherein the machine-learning model correlates (a) a machine learning-based measurement of corrosion to (b) the physics-based measurement of corrosion and the two or more operational parameters (“As shown, corrosion variables (e.g., pipe materials, physical parameters) are provided to some number of corrosion prediction models which act as the sources 120 (A through N) in this case. The outputs (forecasts of these models are used as inputs to the multi-model blending system 100, which outputs a blended predicted corrosion rate based on the machine learning algorithm that was developed using historical predictions from the models and measured (actual) corrosion data according to the embodiments discussed above. In alternate embodiments, the corrosion variables used by the models (sources 120) may also be used by the system 100.” The physics-based measurements and operational parameters may be provided as sources 120 to the machine learning algorithm, wherein blending the sources 120 to determine a blended prediction is interpreted as correlating the machine learning-based measurement with the physics-based measurement and operational parameters.) (e.g., paragraph [0029]).
and modulates a magnitude of a relationship between the physics-based measurement of corrosion and the operational parameters (“the machine learning algorithm may be a weighted average of two or more of the algorithms mentioned above […] As shown, corrosion variables (e.g., pipe materials, physical parameters) are provided to some number of corrosion prediction models which act as the sources 120 (A through N) in this case. The outputs (forecasts) of these models are used as inputs to the multi-model blending system 100, which outputs a blended predicted corrosion rate based on the machine learning algorithm.”) (e.g., paragraphs [0021] and [0029]).
an ensemble method that correlates (a) the physics-based measurement of corrosion and the machine learning-based measurement of corrosion to (b) the estimated measure of corrosion (“Resulting predictions of historical conditions may be provided by the sources 120. That is, the system 100 may use not only the outputs of one or more models […] The output of the machine learning algorithm is the multi-model blending process […] At block 270, executing the multi-model blending on the outputs of the one or more models provides a blended forecast.” The sources 120 may include the output of the machine learning algorithm, wherein the blending system, interpreted as performing an ensemble method, may be used again on the physics and machine learning-based measurements to yield another estimated measure of corrosion.”) (e.g., paragraphs [0017] and [0022]).
simulating values or ranges of values in the hybrid model for a first operational parameter of the two or more operational parameters and the estimated measure of corrosion (“Embodiments of the systems and methods described herein relate to multi-model blending to facilitate prediction or estimation over a broad range of inputs [...] The forecasts may be of temperature, pressure, humidity, wind speed, global solar irradiance, direct normal solar irradiance, accumulated rain, or snow depth, for example […] The outputs (forecasts of these models are used as inputs to the multi-model blending system 100, which outputs a blended predicted corrosion rate based on the machine learning algorithm that was developed using historical predictions from the models and measured (actual) corrosion data according to the embodiments discussed above.” Forecasting and modeling are analogous to simulating.) (e.g., paragraphs [0015], [0024], and [0029]).
and generating a value or range of values for a second operational parameter of the two or more operational parameters (“Embodiments of the systems and methods described herein relate to multi-model blending to facilitate prediction or estimation over a broad range of inputs [...] The forecasts may be of temperature, pressure, humidity, wind speed, global solar irradiance, direct normal solar irradiance, accumulated rain, or snow depth, for example.”) (e.g., paragraphs [0015] and [0024]).
wherein: the second operational parameter is a composition of the substrate (“As shown, corrosion variables (e.g., pipe materials, physical parameters) are provided to some number of corrosion prediction models which act as the sources 120 (A through N) in this case.” Pipe materials are interpreted as an operational parameter relating to a composition of the pipe substrate.) (e.g., paragraph [0029]).
wherein the substrate corresponds to a component in a system (“As another example, information obtained from inspections, direct measurements, or a combination are used by corrosion models to forecast pipeline corrosion in the oil and gas pipeline field.” The pipeline is interpreted as a system comprising the pipe and said pipe’s corresponding substrate.) (e.g., paragraph [0003]).
or wherein the second operational parameter is a composition of the fluid (“Other variables and materials that contribute to the complexity of corrosion behavior include pipe materials (e.g., carbon steel, stainless steel), primary fluid carried by the pipes (e.g., oil, gas, water), ionic constituents (e.g., [H+], [C+], [Fe++], pH), gasses and acids (e.g., H2S, water (H2O), CO2, carbonic acid (H2CO3)), and physical parameters (e.g., gas/liquid phase mix, pipe stress, flow, temperature, pressure, Reynolds number).” The primary fluid carried by the pipes and its ionic constituents are interpreted as a composition of the fluid.) (e.g., paragraph [0027]).
wherein the substrate corresponds to a component in a system and the fluid is a potential feedstock to the system (“As another example, information obtained from inspections, direct measurements, or a combination are used by corrosion models to forecast pipeline corrosion in the oil and gas pipeline field […] As shown, corrosion variables (e.g., pipe materials, physical parameters) are provided to some number of corrosion prediction models which act as the sources 120 (A through N) in this case.” Pipe materials are interpreted as a substrate corresponding to a pipeline, wherein the pipeline is a system. The primary fluid carried by the pipes, above, is interpreted as a fluid that is a potential feedstock to the system.) (e.g., paragraphs [0003] and [0029]).
However, Hamann does not appear to specifically teach a physics based-model for a fluid’s corrosion of a substrate based, at least in part on, lab measurements relating to the fluid’s corrosion of the substrate […] wherein the method further comprises using the component having the composition in the system; or […] wherein the method further comprises using the feedstock in the system based on the value or range of values for a second operational parameter.
On the other hand, Opondo, which relates to laboratory corrosion testing on coupons, does teach a physics based-model for a fluid’s corrosion of a substrate based, at least in part on, lab measurements relating to the fluid’s corrosion of the substrate (“Corrosion tests were conducted using a set of eight metal coupons involving different exposure periods which were dependent on the periods during which the metal coupons were exposed to fluids. The metal coupons were exposed for periods ranging between 2 and 5 days, depending on the duration of the pH test. […] Material loss and corrosion rates for each pH adjustment are shown in Table 2 for the metal coupons that showed significant changes in weight.” Table 2 discloses measurements for material lost (ML) which is interpreted as a lab-based measurement of a substrate relating to the fluid’s corrosion of the substrate. Equation (7) further describes an equation for corrosion rate (CR), interpreted as a physics based-model.) (e.g., page 6, paragraph 1; page 9, equation (7) and table 2).
However, neither Hamann nor Opondo teaches wherein the method further comprises using the component having the composition in the system; or […] wherein the method further comprises using the feedstock in the system based on the value or range of values for a second operational parameter.
On the other hand, Agarwala, which relates to corrosion prevention and maintenance, does teach wherein the method further comprises using the component having the composition in the system; or […] wherein the method further comprises using the feedstock in the system based on the value or range of values for a second operational parameter (The Examiner notes the use of or, and the prior art provides using the component having the composition in the system. “Corrosion prevention and control concepts should be rudimentary to designing, fabrication, operation and maintenance of any equipment or hardware to minimize recurring corrosion costs and to sustain service life. In addition to the choice of proper corrosion resistant material, discussed earlier, use of corrosion engineering principles in design of a component should be very basic concept in reducing future corrosion concerns.” Using corrosion engineering principles in design of a component is interpreted as analogous to using a component having a corrosion resistant composition in a system.) (e.g., page 7, paragraph 3).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the Applicant's claimed invention to combine Hamann with Opondo for the same reasons as in Claim 1, above.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the Applicant's claimed invention to combine the modified reference of Hamann in view of Opondo with Agarwala for the same reasons as in Claim 1, above.
Regarding Claim 9, the claim recites substantially similar limitations to Claim 2, and the claim is rejected under 35 U.S.C 103 for the same reasons.
Regarding Claim 12, Hamann teaches A computing system comprising: a processor; a non-transitory, computer-readable medium (“FIG. 1 is an overview of a multi-model blending system 100 according to an embodiment of the invention. The system 100 includes an input interface 113, one or more processors 115, one or more memory devices 117.”) (e.g., paragraph [0016]).
comprising a hybrid model that correlates one or more operational parameters to an estimated measure of corrosion (“Embodiments of the systems and methods described herein relate to multi-model blending to facilitate prediction or estimation over a broad range of inputs [...] Two exemplary embodiments are specifically discussed. One involves the system 100 both executing one or more models and developing the blended model based on the model outputs while the other involves the system 100 receiving outputs from one or more models and developing the blended model.”) (e.g., paragraphs [0015] and [0016]).
a non-transitory, computer-readable medium comprising instructions configured to accept inputs (“FIG. 1 is an overview of a multi-model blending system 100 according to an embodiment of the invention. The system 100 includes an input interface 113, one or more processors 115, one or more memory devices 117.”) (e.g., paragraph [0016]).
that include one or more operational parameters and/or an estimated measure of corrosion (“Collecting historical measurements, at block 210, is a process that is performed according to one embodiment. According to that embodiment, the sources 120 shown in FIG. 1 are sources of the historical measurements […] According to alternate embodiments, both historical measurements and resulting predictions of historical conditions may be provided by the sources 120.”) (e.g., paragraph [0017]).
and run the hybrid model to produce an output that includes one or more operational parameters and/or an estimated measure of corrosion that are not inputs (“At block 270, executing the multi-model blending on the outputs of the one or more models provides a blended forecast.”) (e.g., paragraph [0022]).
wherein the hybrid model comprises: a physics-based model for a fluid's corrosion of a substrate (“Collecting historical measurements, at block 210, is a process that is performed according to one embodiment. According to that embodiment, the sources 120 shown in FIG. 1 are sources of the historical measurements […] Also according to that embodiment, executing one or more models based on the historical measurements (at block 220) is performed by the processor 115 of the system 100 to obtain predictions of historical conditions […] At least one of the one or more models used by the system 100 is a physical model [...] While FIG. 3 was discussed above with specific reference to meteorological models, the sources 120 could, as well, provide outputs of corrosion models.” The output of a physical model is interpreted as a physics-based measurement of corrosion, wherein the historical measurements are interpreted as lab-based measurements.) (e.g., paragraphs [0017] and [0027]).
wherein the physics-based model correlates (a) the physics-based measurement of corrosion to (b) the one or more operational parameters (“For example, a corrosion model may model the pitting corrosion propagation rate as a function of several different inputs (e.g., CO2, H2S, partial pressure, temperature, pressure) independently yielding a pitting corrosion rate due to each input (e.g., H2S, temperature).” The several different inputs are interpreted as operational parameters, and the pitting corrosion propagation rate is interpreted as a physics-based measurement.) (e.g., paragraph [0018]).
a machine learning-based model for the fluid's corrosion of the substrate based, at least in part on, in-field measurements (“At block 250, training a machine learning algorithm based on the predictor variables and the response variables is according to known machine learning processes. Essentially, the actual historical conditions facilitate obtaining a set of weighting coefficients that indicate how well the models worked under different circumstances.” The output of the machine learning algorithm is interpreted as a machine learning-based measurement of corrosion.) (e.g., paragraph [0021]).
wherein the machine-learning model correlates (a) a machine learning-based measurement of corrosion to (b) the physics-based measurement of corrosion and the one or more operational parameters (“As shown, corrosion variables (e.g., pipe materials, physical parameters) are provided to some number of corrosion prediction models which act as the sources 120 (A through N) in this case. The outputs (forecasts of these models are used as inputs to the multi-model blending system 100, which outputs a blended predicted corrosion rate based on the machine learning algorithm that was developed using historical predictions from the models and measured (actual) corrosion data according to the embodiments discussed above. In alternate embodiments, the corrosion variables used by the models (sources 120) may also be used by the system 100.” The physics-based measurements and operational parameters may be provided as sources 120 to the machine learning algorithm, wherein blending the sources 120 to determine a blended prediction is interpreted as correlating the machine learning-based measurement with the physics-based measurement and operational parameters.) (e.g., paragraph [0029]).
and modulates a magnitude of a relationship between the physics-based measurement of corrosion and the operational parameters (“the machine learning algorithm may be a weighted average of two or more of the algorithms mentioned above […] As shown, corrosion variables (e.g., pipe materials, physical parameters) are provided to some number of corrosion prediction models which act as the sources 120 (A through N) in this case. The outputs (forecasts) of these models are used as inputs to the multi-model blending system 100, which outputs a blended predicted corrosion rate based on the machine learning algorithm.”) (e.g., paragraphs [0021] and [0029]).
and an ensemble method that correlates (a) the physics-based measurement of corrosion and the machine learning-based measurement of corrosion to (b) the estimated measure of corrosion (“Resulting predictions of historical conditions may be provided by the sources 120. That is, the system 100 may use not only the outputs of one or more models […] The output of the machine learning algorithm is the multi-model blending process […] At block 270, executing the multi-model blending on the outputs of the one or more models provides a blended forecast.” The sources 120 may include the output of the machine learning algorithm, wherein the blending system, interpreted as performing an ensemble method, may be used again on the physics and machine learning-based measurements to yield another estimated measure of corrosion.”) (e.g., paragraphs [0017] and [0022]).
wherein the computing system is a portion of a hydrocarbon transportation system, a hydrocarbon refinery system, hydrocarbon production system, or an alkylation system (“While FIG. 3 was discussed above with specific reference to meteorological models, the sources 120 could, as well, provide outputs of corrosion models, and the relative reduction in error sigma when comparing the models' output to the blended output may be on the same order. Corrosion of pipelines in the oil and gas sectors or in the transportation or infrastructure sectors, for example, can result in significant cost and safety issues.”) (e.g., paragraph [0027]).
However, Hamann does not appear to specifically teach a physics based-model for a fluid’s corrosion of a substrate based, at least in part on, lab measurements relating to the fluid’s corrosion of the substrate […], which is configured for one or more of repairing and/or replacing a component comprising the substrate based on the estimated measure of corrosion; building the system or portion thereof comprising a component that comprises the substrate, wherein a composition of the substrate is chosen based on the estimated measure of corrosion; and refining a feedstock, based on the estimated measure of corrosion, wherein the feedstock or a downstream product and/or distillate thereof is the fluid.
On the other hand, Opondo, which relates to laboratory corrosion testing on coupons, does teach a physics based-model for a fluid’s corrosion of a substrate based, at least in part on, lab measurements relating to the fluid’s corrosion of the substrate (“Corrosion tests were conducted using a set of eight metal coupons involving different exposure periods which were dependent on the periods during which the metal coupons were exposed to fluids. The metal coupons were exposed for periods ranging between 2 and 5 days, depending on the duration of the pH test. […] Material loss and corrosion rates for each pH adjustment are shown in Table 2 for the metal coupons that showed significant changes in weight.” Table 2 discloses measurements for material lost (ML) which is interpreted as a lab-based measurement of a substrate relating to the fluid’s corrosion of the substrate. Equation (7) further describes an equation for corrosion rate (CR), interpreted as a physics based-model.) (e.g., page 6, paragraph 1; page 9, equation (7) and table 2).
However, neither Hamann nor Opondo teaches the system configured for one or more of repairing and/or replacing a component comprising the substrate based on the estimated measure of corrosion; building the system or portion thereof comprising a component that comprises the substrate, wherein a composition of the substrate is chosen based on the estimated measure of corrosion; and refining a feedstock, based on the estimated measure of corrosion, wherein the feedstock or a downstream product and/or distillate thereof is the fluid.
On the other hand, Agarwala, which relates to corrosion prevention and maintenance, does teach a system configured for one or more of repairing and/or replacing a component comprising the substrate based on the estimated measure of corrosion; building the system or portion thereof comprising a component that comprises the substrate, wherein a composition of the substrate is chosen based on the estimated measure of corrosion; and refining a feedstock, based on the estimated measure of corrosion, wherein the feedstock or a downstream product and/or distillate thereof is the fluid (The Examiner notes the use of one or more of, and the prior art provides repairing and/or replacing a component. “Parameters that track corrosion assisted damage serve best in creating a reliable database for predictive modeling and structural ‘health’ monitoring. The accuracy of a database is essential in developing a cue when repair is needed and also in the assessment of remaining life or life expended. A paradigm shift from schedule based periodic maintenance to condition based maintenance (CBM) is preferable because finding a problem early and then fixing it through small repairs saves numerous maintenance man-hours later on by avoiding cumulative damage.” Condition based maintenance is interpreted as repairing a component based on an estimated measure of corrosion.) (e.g., page 6, paragraph 2).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the Applicant's claimed invention to combine Hamann with Opondo for the same reasons as in Claim 1, above.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the Applicant's claimed invention to combine the modified reference of Hamann in view of Opondo with Agarwala for the same reasons as in Claim 1, above.
Regarding Claim 13, Hamann in view of Opondo and Agarwala teaches The computing system of claim 12. Hamann further teaches wherein the output comprises a value or range of values for an operational parameter that is not an input (“Embodiments of the systems and methods described herein relate to multi-model blending to facilitate prediction or estimation over a broad range of inputs [...] That is, the system 100 may use not only the outputs of one or more models but also other data that may or may not have been an input to a model.”) (e.g., paragraphs [0015] and [0017]).
Regarding Claim 14, Hamann in view of Opondo and Agarwala teaches The computing system of claim 12. Hamann further teaches wherein the output comprises the estimated measure of corrosion that is not an input (“The output of the machine learning algorithm is the multi-model blending process […] At block 270, executing the multi-model blending on the outputs of the one or more models provides a blended forecast.” The blended forecast may be used without said forecast being re-input into the system 100.) (e.g., paragraph [0022]).
Regarding Claim 15, the claim recites substantially similar limitations to Claim 2, and the claim is rejected under 35 U.S.C 103 for the same reasons.
Claim(s) 5-7 is/are rejected under 35 U.S.C. 103 as being unpatentable over Hamann in view of Opondo and Agarwala, further in view of Chimenti et al. (U.S. Pat. No. 7,160,728 B2), hereinafter Chimenti. The Examiner notes that these claims are indefinite under 35 U.S.C 112(b). For the purposes of compact prosecution, a rejection is provided below.
Regarding Claim 5, Hamann in view of Opondo and Agarwala teaches The method of claim 1. Hamann further teaches measuring the operational parameter in real-time; and monitoring the estimated measure of corrosion over time (“That is, the sources 120 may provide the current measurements and the executing one or more models may be performed by the processor 115 of the system 100, or the sources 120 may provide the predictions of future conditions based on executing one or more models on the current measurements.” The current measurements are interpreted as measurements of operational parameters in real-time, and predicting future conditions based on the current measurements are interpreted as monitoring the estimated measure of corrosion over time.) (e.g., paragraph [0022]).
However, neither Hamann nor Opondo nor Agarwala teaches wherein the method comprises refining the feedstock, based on the estimated measure of corrosion, wherein the feedstock or the downstream product and/or distillate thereof is the fluid.
On the other hand, Chimenti, which relates to predicting the corrosivity of petroleum feedstocks, does teach refining the feedstock, based on the estimated measure of corrosion, wherein the feedstock or the downstream product and/or distillate thereof is the fluid (“A method to optimize the addition of organic acid neutralizing agents to a petroleum feedstream that is processed into process streams comprising […] (f) controlling the amount or blend of neutralizing agents, and/or the temperature, pressure, mixing, or flow conditions in the neutralizing process to achieve the target acid level and/or corrosion rate in the treated feedstream and/or processed streams.” Controlling the amount or blend of neutralizing agents in a feedstream is interpreted as refining a feedstock, wherein the blend is controlled to achieve a target corrosion rate which may be based on the estimated corrosion.) (e.g., claim 21).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the Applicant's claimed invention to combine the modified reference of Hamann in view of Opondo and Agarwala with Chimenti. The claimed invention is considered to be merely combining prior art elements according to known methods to yield predictable results, see MPEP § 2143(I)(A). Hamann teaches a method for combining estimated measures of corrosion from a physics based model and a machine learning based model using measurements. However, Hamann does not appear to specifically refining or sourcing a feedstock based on the estimated measure of corrosion. On the other hand, Chimenti, which relates similarly to corrosion estimation in petroleum applications, does teach a method comprising refining and sourcing a feedstock based on an estimated measure of corrosion. The only difference between the claimed invention and the prior art is a lack of actual combination of the elements into a single prior art reference. As both Hamann and Chimenti relate to forecasting pipeline corrosion (e.g., Hamann; paragraph [0003]; Chimenti; column 2, lines 12-15), one of ordinary skill in the art could have combined the corrosion forecasting of Hamann with the feedstock refining and sourcing of Chimenti. In combination, each element merely performs the same function as it does separately, and one of ordinary skill in the art would have recognized the results of the combination as predictable. Therefore, it would have been obvious to a person of ordinary skill in the art prior to the effective filing date of the Applicant’s claimed invention to combine the corrosion prediction of Hamann with the feedstock refining and sourcing of Chimenti in order to utilize corrosion predictions in real world applications
Regarding Claim 6, Hamann in view of Opondo and Agarwala teaches The method of claim 1. Hamann further teaches measuring the operational parameter in real-time (“That is, the sources 120 may provide the current measurements and the executing one or more models may be performed by the processor 115 of the system 100, or the sources 120 may provide the predictions of future conditions based on executing one or more models on the current measurements.” The current measurements are interpreted as measurements of operational parameters in real-time.) (e.g., paragraph [0022]).
However, neither Hamann nor Opondo nor Agarwala teaches wherein the method comprises refining the feedstock, based on the estimated measure of corrosion, wherein the feedstock or the downstream product and/or distillate thereof is the fluid and changing a composition of the feedstock based on the estimated measure of corrosion over time.
On the other hand, Chimenti, which relates to predicting the corrosivity of petroleum feedstocks, does teach the method comprising refining the feedstock, based on the estimated measure of corrosion, wherein the feedstock or the downstream product and/or distillate thereof is the fluid (“A method to optimize the addition of organic acid neutralizing agents to a petroleum feedstream that is processed into process streams comprising […] (f) controlling the amount or blend of neutralizing agents, and/or the temperature, pressure, mixing, or flow conditions in the neutralizing process to achieve the target acid level and/or corrosion rate in the treated feedstream and/or processed streams.” Controlling the amount or blend of neutralizing agents in a feedstream is interpreted as refining a feedstock, wherein the blend is controlled to achieve a target corrosion rate which may be based on the estimated corrosion.) (e.g., claim 21).
and changing a composition of the feedstock based on the estimated measure of corrosion over time (“(e) predicting the remaining acid content and/or the corrosion rate of the treated feedstream and/or processed streams without removing the neutralized products or unreacted neutralizing agent; and (f) controlling the amount or blend of neutralizing agents.”) (e.g., claim 21).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the Applicant's claimed invention to combine the modified reference of Hamann in view of Opondo and Agarwala with Chimenti for the same reasons as in Claim 5, above.
Regarding Claim 7, Hamann in view of Opondo and Agarwala teaches The method of claim 1. Hamann further teaches projecting the estimated measure of corrosion based on a change to the operational parameter (“That is, the sources 120 may provide the current measurements and the executing one or more models may be performed by the processor 115 of the system 100, or the sources 120 may provide the predictions of future conditions based on executing one or more models on the current measurements.” The current measurements are interpreted as measurements of operational parameters in real-time, and predicting future conditions based on the current measurements are interpreted as projecting the estimated measure of corrosion based on a change to an operational parameter.) (e.g., paragraph [0022]).
However, neither Hamann nor Opondo nor Agarwala teaches wherein the method comprises the refining the feedstock, based on the estimated measure of corrosion, wherein the feedstock or the downstream product and/or distillate thereof is the fluid.
On the other hand, Chimenti, which relates to predicting the corrosivity of petroleum feedstocks, does teach refining the feedstock, based on the estimated measure of corrosion, wherein the feedstock or the downstream product and/or distillate thereof is the fluid. (“A method to optimize the addition of organic acid neutralizing agents to a petroleum feedstream that is processed into process streams comprising […] (f) controlling the amount or blend of neutralizing agents, and/or the temperature, pressure, mixing, or flow conditions in the neutralizing process to achieve the target acid level and/or corrosion rate in the treated feedstream and/or processed streams.” Controlling the amount or blend of neutralizing agents in a feedstream is interpreted as refining a feedstock, wherein the blend is controlled to achieve a target corrosion rate which may be based on the estimated corrosion.) (e.g., claim 21).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the Applicant's claimed invention to combine the modified reference of Hamann in view of Opondo and Agarwala with Chimenti for the same reasons as in Claim 5, above.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Salami et al. (Salami, Babatunde Abiodun, Syed Masiur Rahman, Tajudeen Adeyinka Oyehan, Mohammed Maslehuddin, and Salah U. Al Dulaijan. "Ensemble machine learning model for corrosion initiation time estimation of embedded steel reinforced self-compacting concrete." Measurement 165 (2020): 108141.) discloses a random forest based ensemble method for predicting corrosion initiation time.
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 KYLE HWA-KAI TSENG whose telephone number is (571)272-3731. The examiner can normally be reached M-F 9A-5P PST.
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, Rehana Perveen can be reached at (571) 272-3676. 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.
/K.H.T./ Examiner, Art Unit 2189
/REHANA PERVEEN/ Supervisory Patent Examiner, Art Unit 2189
Prosecution Insights