DETAILED ACTION
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Responsive to the communication dated 12/17/2025
Claims 15 – 20 are cancelled.
Claims 1, 4, 8, 11, 21, 24 are amended.
Claims 1 – 14, 21 – 26 are presented for examination.
Continued Examination
A request for continued examination under 37 CFR 1.114, including the fee set forth in 37 CFR 1.17(e), was filed in this application after final rejection. Since this application is eligible for continued examination under 37 CFR 1.114, and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114. Applicant's submission filed on 12/17/2025 has been entered.
Response to Arguments
Claim Rejections - 35 USC § 103
The Applicant, in the request for continued examination dated 12/17/2025 indicated that the arguments are the same as those presented in the after final response dated 12/1/2025. An advisory action dated 12/11/2025 was previously issued. Box 12 of the advisory action responded to the arguments and amendment.
Nevertheless, further response is provided below.
In the Applicant’s Arguments dated 12/01/2025 the Applicant referencing claims 1, 8, and 21 asserts that the claims recite “… providing the surrogate model, the vehicle configuration, and a vehicle movement request to a vehicle…” and that the art of record does not make such elements obvious to those of ordinary skill in the art. More specifically the Applicant, citing page 782 of TOL_2016 states that applying a controller to an F-16 aircraft model does not make obvious “providing the surrogate model, the vehicle configuration, and a vehicle movement request to a vehicle” as recited in, for example, claim 1.
In response the argument is not persuasive.
The Applicant is improperly conflating the F-16 aircraft model with the onboard model integrated into the non-linear control system. The onboard model, as illustrated in Figures Figure 1 and 2 are part of the onboard aircraft control system that sends control signals to actuators of an aircraft. The F-16 aircraft model cited by the Applicant is a simulation model of the F-16 aircraft that is controlled by the onboard aerodynamic model used within the flight control system. The F-16 aircraft model is used by Tol_2016 in a proof-of-concept type simulation to demonstrate the onboard model that is integrated into the control system. It is the onboard model to which the Office action is mapping the claim elements. The Applicant is simply ignoring the onboard control system model and incorrectly pointing towards the F-16 aircraft simulation model.
Also, the rejection is based on a combination of references. The Applicant is merely selecting the TOL_2016 reference and cherry picking one teaching from that reference without considering other teachings in TOL_2016 or the teachings of TOL_2016 in combination with the other references. One cannot show nonobviousness by attacking references individually where the rejections are based on combinations of references. See In re Keller, 642 F.2d 413, 208 USPQ 871 (CCPA 1981); In re Merck & Co., 800 F.2d 1091, 231 USPQ 375 (Fed. Cir. 1986).
For example, Stahl_2020 teaches “a generic and structured safeguarding concept, allowing for the derivation of an online verification (OV) module for autonomous vehicles (AVs)” (introduction) which has an onboard trajectory planning supervisor that receives a planned trajectory from a trajectory planning module and verifies the trajectory to ensure “a safe overall (sub)system is attained” (abstract).
PNG
media_image1.png
389
596
media_image1.png
Greyscale
In combination, the illustrated in Fig. 4 above contains the onboard system model taught by Tol_2016. Notice that both Tol_2016 and Stahl_2020 teach that the model receives vehicle movement requests. Fig. 4 illustrates this as inputs from the “planning” block. Tol_2016 and also Stahl_2020 teach to control actuators. The actuators move the actual control surfaces of an aircraft (e.g., elevators, flaps, ailerons, etc.).
Accordingly, the combination of references teach to provide a surrogate model because Tol_2016 teaches an onboard model integrated into the nonlinear controller as illustrated in Figures 1, 2. Stahl_2020 clearly illustrates to receive movement plans both into and from the supervisor and to provide these plans to a controller. Therefore, in combination the controller has been provided with an onboard model that is integrated into the controller and the controller receives movement plans.
Further, Tol_2016 illustrates a feedback loop in the control system as illustrated in Figure 1 and Figure 2. The feedback loop clearly illustrates the concept of providing vehicle configuration because the state of the aircraft (i.e., “X”) such as actuator controls are being looped back. Also notice that Figure 2 clearly shows “pilot” as inputs and page 786 section V states: “… to avoid unachievable commands due to the actuator constraints, a first-order lag prefilter is used for the pilot commands…”. This clearly indicates to those of ordinary skill in the art that movement requests (i.e., pilot commands) are provided.
Additionally, Johnson_2017 clearly teaches to provide vehicle configuration and movement commands. For example, FIG. 9 recites “… Route Assignments” and “flight operations/Trajectory/Control”. FIG. 10 recites “control-settings – thrust Climb Rate” and “Trajectory-Air/Approach”. Paragraph 21 states: “… industrial systems, such as, for example, on or more aircraft… the targeted physical state being controlled for may be automatically and dynamically adjusted, to achieve one or more key performance outcomes… involves adjusting various aspects of the industrial system, such as, for example… the configuration of those components, the real time physical control settings of engine fuel and air…”
The above citations clearly teach providing at least vehicle configuration and movement requests.
Therefore, in combination the references make obvious to provide the surrogate model (i.e., onboard model integrated into the control system), the vehicle configuration (i.e., current state “X”), and a vehicle movement request to a vehicle (i.e., pilot commands).
Moreover, these three items (i.e., surrogate model, vehicle configuration, and movement requests) are simply the three items found in any feedback control system. This is because, fundamentally, a feedback controller always involves an input (i.e., movement request), a way to measure the current state of the system/process (i.e., vehicle configuration), and a prediction or expectation used to determine an error that used to make adjustments to the system (i.e., surrogate model). PID and LQR controllers are common controllers that have such models.
End Response to Arguments
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.
Claims 1 – 14, 21 - 26 are rejected under 35 U.S.C. 103 as being unpatentable over Johnson_2017 (US 2017/0323274 A1) in view of NASA_1983 (Determination of Airplane Model Structure From Flight Data Using Splines and Stepwise Regression, NASA Technical Paper 2126 March 1983) in view Tol_2016 (Multivariate Spline-Based Adaptive Control of High-Performance Aircraft with Aerodynamic Uncertainties, Journal of Guidance, Control., And Dynamics Vol. 89, No. 4, April 2016) in view of Stahl_2020 (Online Verification Concept for Autonomous Vehicles – Illustrative Study for a Trajectory Planning Module, IEEE 2020).
Claim 1. Johnson_2017 makes obvious “A method (abstract: “a method of providing a recommendation for optimizing operations of a set of industrial assets…”; par 20: “the description that follows includes illustrative systems, methods, techniques, instruction sequences, and computing machine program products…”), comprising: generating a first principles model for vehicle movements (Par 25: “in example embodiments, engine state estimation (e.g., including damage state estimation) is determined… over historical, current, and future time horizons using historical data… in other instances, Physics based first principle engineering models are derived with, for example, thermodynamics, chemical and metallurgical analysis… data may be aggregated from a plurality of sources, such as engine sensors… lab tests (images, chemical, physical measures… weather services… the data may be used… in conjunction with operating patterns or control patterns…”; par 35: “the example embodiments, a physics-based approach is accepted in addition to data driven methods into the simulation…”; Par 71: “… the actual usage of the engine by the customer is simulated over the lifetime of the asset, including all service shop visits and service repairs, based on specific data pertaining to the planned use of the asset, including operation policies of the engines, weather through which the engines will be flying, and so on… the operations and service risks that may be forecasted using empirical evidence and first principle models…”; Par 283: “… some engine component temperatures and pressures are not directly measured, but instead are reconciled using a model that represents the thermodynamic or operational physics of the industrial apparatus 1226. These models may be first principle in nature such as a heat balance or may be a surrogate model such as a neural net… for the purpose of physics based state estimation…”), using a first set of inputs for a vehicle configuration (Par 24: “… operating policies, such as thrust limit…”; Par 71: “… the actual usage of the engine by the customer is simulated over the lifetime of the asset, including all service shop visits and service repairs, based on specific data pertaining to the planned use of the asset, including operation policies of the engines, weather through which the engines will be flying, and so on…” NOTE: the “specific data” includes, for example, operation policies and weather. These are examples of a set of first inputs. Also, the vehicle configuration is simulated according to “actual usage of the engine” and simulations includ “all service shop visits and repairs”. The servicing and repairs result in a vehicle configuration. NOTE: operation policies of the engine include, for example, thrust limit (see par 24 above). Therefore, thrust limit is also among a first set of inputs for a vehicle configuration. Par 198: “the operations model 306 may be configured to provide one or more sets of policies or rules regarding operation of the power asset 205. In one example, such policies may be set based on information received, at that operations model 306 from the physics-based model…”; par 284 - 285: “…the ambient conditions that the assets and their subcomponents are exposed to are recorded 1230. For example, the temperatures and pressures that the engine and its parts have been exposed to. These data are used for duty cycle analysis 1250 and state change estimation… simulated future dispositions 1240 is recorded for the purpose of assumptions accuracy and for control point settings… an example of a control point setting is one which is computed that optimizes one or more key process indicators, the optimized setting being computed from an enumeration of scenarios (apparatus design an operation) and replication of scenarios so as to determine the KPIs… which is most robust to changing exogenous factors such as weather…” NOTE: vehicle configuration includes the enumeration of scenarios of apparatus design and operation. Ambient conditions such as temperature and pressure are examples of a first set of inputs. NOTE: outputs include the values associated with state change estimation.), where the first principles model comprises a plurality of modeled outputs for the first set of inputs for the vehicle configuration (FIG. 5 illustrates, for example, Lifting Model, Thermal Performance Model, Control Model. FIG. 9 illustrates an optimizer that optimizes (i.e., outputs) Engine & Route Assignments and Flight Operations/Trajectory/Control. NOTE: The Thermal Performance Model outputs thermal performance. The Control Model outputs, for example, trajectory. Par 283: “… physics based state estimation, for example, oxidation and degradation of a metal part at a certain temperature and atmospheric condition for a certain duration and load…” NOTE: The “certain temperature, atmospheric condition, duration, and load” are a first set of inputs” and the physics based simulation outputs a state estimation that include modeled outputs such as “oxidation and degradation”. A physics based simulation is a first principles model. Par 286: “the duty cycle of the physical assets 1250, in the presently disclosed control system are comprised of observed and simulated forward ambient conditions, settings such as thrust and calculated parameters…” Par 295: “… in example embodiments, fuel consumption and asset lifting state changes are computed in response to a candidate duty cycle that differentially degrades engine performance… a flight schedule of an aircraft may be beneficially changed…”)[adjusting control of], the vehicle configuration, and a vehicle movement request to a vehicle (Abstract: “… the digital twins are analyzed with respect to simulated operating performances to determine an optimized control of operations of the industrial assets… the recommendation is presented… automatically changing operating setpoints pertaining to the industrial equipment.” Par 21: “a large, complex industrial system, such as, for example, one or more aircraft engines and the aircraft… can be dynamically controlled to achieve a specified physical state… the targeted physical state being controlled for may be automatically and dynamically adjusted, to achieve one or more key performance outcomes… adjusting various aspects of the industrial system, such as, for example, the operational assignment… technical capabilities of the component of the system the configuration of those components, the real time physical control setting…”; par 22: “… the digital twins are analyzed with respect to simulated operating performance to determine an optimized control of operations of the industrial asset… the recommendation is presented… or automatically changing operating setpoints pertaining to the industrial assets.”; par 23: “… a flight schedule of an aircraft may be beneficially changed to reduce fuel and service costs while meeting airline asset utilization criteria associated with operating the aircraft…”; Par 24: “the schedule of asset utilization, duty cycles and operating policies, such as thrust limits…” FIG. 9 Operations Optimization, Engine & Route Assignments, Flight Operations/Trajectory/Control)”
While Johnson_2017 teaches to optimize flight operations by automatically adjust vehicle control (e.g., trajectory, set points, polices: thrust limits, etc.), Johnson_2017 does not explicitly teach that such adjustments include “providing the surrogate model” along with providing the vehicle configuration, and the vehicle movement request to a vehicle.
Additionally, while Johnson_2017 teaches a digital twin model comprised of first principal models (i.e., physics-based models) and neural networks. See, for example, FIG. 5 and par 283. Johnson_2017 does not explicitly teach “determining a domain for a surrogate model of the first principles model; generating the surrogate model within the domain to represent the modeled outputs as approximation functions across the domain for the vehicle configuration; verifying a fidelity of the surrogate model against the first principles model.”
Also, Johnson_2017 does not teach “verifying a vehicle movement plan or a flight operation at the vehicle based on the surrogate model and the vehicle movement request.”
NASA_1983, however, makes obvious “determining a domain for a surrogate model of the first principles model; generating the surrogate model within the domain to represent the modeled outputs as approximation functions across the domain for the vehicle configuration (Page 7: “… a space of these splines is constructed by taking the tensor product of one-dimensional spaces of polynomial splines. Because of the tensor nature of the resulting space, many of the simple algebraic properties of ordinary polynomial spines in one dimension are carried over. A spline in two variables X1 and X2 can be introduced for the approximation of a function f(x1, X2) for X1 ϵ [X10, X1max] and X2 ϵ [X20, X2max]. Then, as in the one-dimensional case, the two ranges [X10, X1max], [X20, X2max] are subdivided by sets of knots… partition the above rectangle into rectangular panels…”;
Page 10: “… Ultimately, the model should be a good predictor of airplane motion within the region of its assumed validity…” NOTE: the domain is the above-described rectangular mathematical domain. It represents, mathematically, the physical operating region (i.e., domain). The Approximation functions across the domain are the tensor product spline functions. NOTE: the region of airplane motion over which the model is assumed valid is the flight envelope. This is the domain of the surrogate model.); Verifying a fidelity of the surrogate model against the first principles model” (Page 9 – 10: “… the postulation of terms which might enter the final model, the selection of an adequate model, and the verification of the model selected… e(i) represents the equation error. An adequate model for the aerodynamic coefficients can be determined by applying the stepwise regression… the last step in model structure determination and parameter estimation is model verification. The parameter estimates must have realistic values and should be compared with wind-tunnel results and theoretical predictions. Whenever possible, the least-squares estimate should also be compared with the estimates using different techniques, that is, the maximum-likelihood estimate method. Ultimately, the model should be a good predictor of airplane motion within the region of its assumed validity…” NOTE: theoretical predictions are, for example, physics based or first principal models. Page 18: “… this number usually increases to some maximum value as new variables enter the regression, but then decreases slightly as the new terms are less effective in reducing the residuals… R2 is calculated… R2 would be 100 percent for a model that perfectly fit the data…” NOTE: the above teaches two ways to verify fidelity of the model.).
Johnson_2017 and NASA_1983 are analogous art because they are from the same field of endeavor called aircraft control. Before the effective filing date, it would have been obvious to a person of ordinary skill in the art to combine Johnson_2017 and NASA_1983. The rationale for doing so would have been that Johnson_2017 teaches to model aircraft dynamics using physics-based models and to optimize aircraft control to adjust flight operations/trajectory/control to reduce damage (i.e., life consumption) of the aircraft. NASA_1983 teaches a method for creating an estimator that predicts airplane motion using spline functions because “splines avoid some difficulties of polynomials because they are defined on preselected intervals and because the low-order terms may approximate various nonlinearities quite well” (page 1) and that “it can provide valuable information about aerodynamic forces and moments acting upon the airplane in large-amplitude maneuvers and/or maneuvers in high-angle-of-attack regions” (page 16). Therefore, it would have been obvious to combine the modeling system of Johnson_2017 that estimates the degradation/damage to aircraft that occurs due to duty cycles and flight paths (i.e., trajectories) with the tensor-product spline function surrogate models that approximate nonlinearities in flight well and can calculate the aerodynamic forces and moments acting on aircraft for the benefit of having valuable information for predicting predict damage that large-amplitude maneuvers and high-angle-of-attack can cause and also to adjust the control of the aircraft to avoid or reduce such damage to obtain the invention as specified in the claims.
Johnson_2017 and NASA_1983 does not explicitly recite “providing the surrogate model” along with providing the vehicle configuration, and the vehicle movement request to a vehicle.
Johnson_2017 and NASA_1983 does not teach “verifying a vehicle movement plan or a flight operation at the vehicle based on the surrogate model and the vehicle movement request.”
Tol_2016 makes obvious to control a vehicle comprising the vehicle configuration by “providing the surrogate model, the vehicle configuration, and a vehicle movement request to a vehicle”(Page 784 Fig. 1 illustrates Onboard spline model (i.e., surrogate model) and feedback of “X” (i.e., current vehicle configuration). Fig. 2 illustrates pilot control inputs (i.e., vehicle movement requests).
Page 782: “… onboard spline models were first integrated into a non-linear control system… the actuators based on the onboard aerodynamic spline model… spline based NDI results in superior tracking performance…”; Page 784 section IV. Spline-Based Adaptive Nonlinear Dynamic Inversion Control: Overview Components: “… onboard spline models were first integrated in an NDI control system… this structure is now augmented with an online estimator for the spline model parameters, resulting in an adaptive spline-based control allocation system that is robust to model uncertainties. The control diagram is shown in Fig. 1; Page 786 section V. “… prefilter is used for the pilot commands…”; page 793 section VII A. onboard aerodynamic model…”).
Johnson_2017 and NASA_1983 and Tol_2016 are analogous art because they are from the same field of endeavor called aircraft control. Before the effective filing date, it would have been obvious to a person of ordinary skill in the art to combine Johnson_2017 and NASA_1983 and Tol_2016. The rationale for doing so would have been that Johnson_2017 teaches to model an aircraft and to optimize the flight operations/trajectory/control of the aircraft to meet operational goals such as reducing damage caused by aircraft use (e.g., movement). NASA_1998 teaches to model aircraft movement using splines as estimator that accurately predicts nonlinearities quite well and provides valuable information about aerodynamic forces and moments acting upon aircraft in large-amplitude maneuvers and/or maneuvers in high-angle-of-attack regions. Tol_2016 teaches to have an aircraft controller that uses spine estimators to control an aircraft. Therefore; it would have been obvious to combine the controller of Tol_2016 by installing the spline estimators that model large-amplitude maneuvers and/or high-angle-of-attack regions as taught by NASA_1998 into the aircraft of Johnson_2017 to adjust the control of the aircraft to the optimal flight operations/trajectories/control for the benefit of avoiding or reducing damage to the aircraft to obtain the invention as specified in the claims.
Johnson_2017 and NASA_1983 and Tol_2016 does not teach “verifying a vehicle movement plan or a flight operation at the vehicle based on the surrogate model and the vehicle movement request.”
Stahl_2020 makes obvious “verifying a vehicle movement plan or a flight operation at the vehicle based on the surrogate model and the vehicle movement request.” (introduction: “a generic and structured safeguarding concept, allowing for the derivation of an online verification (OV) module for autonomous vehicles (AVs)”; Fig. 1 and 4 which has an onboard trajectory planning supervisor that receives a planned trajectory from a trajectory planning module and verifies the trajectory. See below.
PNG
media_image1.png
389
596
media_image1.png
Greyscale
Johnson_2017 and Stahl_2020 are analogous art because they are from the same field of endeavor called vehicle. Before the effective filing date it would have been obvious to a person of ordinary skill in the art to combine Johnson_2017 and Stahl_2020. The rationale for doing so would have been that Johnson_2017 teaches to model an aircraft and to optimize the flight operations/trajectory/control of the aircraft to meet operational goals such as reducing damage caused by aircraft use (e.g., movement).
Stahl_2020 teaches to verify the safety of trajectory modifications to “help to reduce the number of traffic accidents” (introduction) and that this can be achieved by integrating a verification into the control system to achieve “a safe overall (sub)system” (abstract). Therefore, it would have been obvious to combine Johnson_2017 and Stahl_2020 for the benefit of having a safe trajectory planning and control system that ensure the planned trajectory is safe prior to execution of the trajector to obtain the invention as specified in the claims.
Claim 8. The limitations of claim 8 are substantially the same as those of claim 1 and are rejected due to the same reasons as outlined above for claim 1. Additionally, Johnson_2017 makes obvious the further limitations of “A system, comprising: A processor; A memory storage device including instructions that when executed by the processor enable performance of an operation comprising” (FIG. 11; par 20: “the description that follows includes illustrative systems, methods, techniques, instruction sequences, and computing machine program products…”; par 272: “the example of the processing system 1000 includes a processor 1002 (e.g., central processing unit (CPU)… random-access memory… machine-readable medium 1022 on which is stored one or more sets of data structures and instructions 1024 (e.g., software) embodying or utilized by any one or more of the methodologies or functions described herein…”).
Claim 21. The limitations of claim 21 are substantially the same as those of claim 1 and are therefore rejected due to the same reasons as outlined above for claim 1. Additionally, Johnson_2017 makes obvious “a non-transitory computer-readable medium storing a set of instructions the set of instructions comprising: one or more instructions that, when executed by one or more processors of a system, cause the system to:” (par 272: “the example of the processing system 1000 includes a processor 1002 (e.g., central processing unit (CPU)… random-access memory… machine-readable medium 1022 on which is stored one or more sets of data structures and instructions 1024 (e.g., software) embodying or utilized by any one or more of the methodologies or functions described herein…”).
Claims 2, 9, 22. NASA_1983 makes obvious “further comprising: determining, from modeling settings for the vehicle configuration, a set of point constants for a first set of modeling variables; and determining, from the modeling settings for the vehicle configuration, a set of region constraints for a second set of modeling variables” (Page 7: “… a space of these splines is constructed by taking the tensor product of one-dimensional spaces of polynomial splines. Because of the tensor nature of the resulting space, many of the simple algebraic properties of ordinary polynomial spines in one dimension are carried over. A spline in two variables X1 and X2 can be introduced for the approximation of a function f(x1, X2) for X1 ϵ [X10, X1max] and X2 ϵ [X20, X2max]. Then, as in the one-dimensional case, the two ranges [X10, X1max], [X20, X2max] are subdivided by sets of knots X1i and X2i where
X10 < X11 < … < Xik < I1max
X20 < X21 < … < X2L < X2max
The points (x1i, X2i) partition the above rectangle into rectangular panels…”;
NOTE: the knots are a set of point constraints and the panels in the rectangle region of the operating domain are the region constraints.).
Claims 3, 10, 23. NASA_1983 makes obvious “wherein generating the surrogate model comprises: generating a tensor-product spline function approximation for each of the modeled outputs using the domain for the surrogate model, the set of point constraints and the set of region constraints” (Page 7: “… a space of these splines is constructed by taking the tensor product of one-dimensional spaces of polynomial splines. Because of the tensor nature of the resulting space, many of the simple algebraic properties of ordinary polynomial spines in one dimension are carried over. A spline in two variables X1 and X2 can be introduced for the approximation of a function f(x1, X2) for X1 ϵ [X10, X1max] and X2 ϵ [X20, X2max]. Then, as in the one-dimensional case, the two ranges [X10, X1max], [X20, X2max] are subdivided by sets of knots X1i and X2i where
X10 < X11 < … < Xik < I1max
X20 < X21 < … < X2L < X2max
The points (x1i, X2i) partition the above rectangle into rectangular panels…”)
It would further be obvious to “and combining the tensor-product spline function approximations into the surrogate model” because Johnson_2017 teaches to model an aircraft and to optimize the flight operations/trajectory/control of the aircraft to meet operational goals such as reducing damage caused by aircraft use (e.g., movement). NASA_1998 teaches to model aircraft movement using splines as estimator that accurately predicts nonlinearities quite well and provides valuable information about aerodynamic forces and moments acting upon aircraft in large-amplitude maneuvers and/or maneuvers in high-angle-of-attack regions. Tol_2016 teaches to have an aircraft controller that uses spine estimators to control an aircraft. Therefore; it would have been obvious to combine the controller of Tol_2016 by installing the spline estimators that model large-amplitude maneuvers and/or high-angle-of-attack regions as taught by NASA_1998 into the aircraft of Johnson_2017 to adjust the control of the aircraft to the optimal flight operations/trajectories/control for the benefit of avoiding or reducing damage to the aircraft to obtain the invention as specified in the claims.
Claims 4, 11, 24. NASA_1998 makes obvious “wherein verifying the fidelity of the surrogate model comprises: providing one or more test inputs to the surrogate model to generate a surrogate output from the tensor-product spline function approximations across the domain; providing the one or more test inputs to the first principles model to generate a first principles output; Comparing the first principles output to the surrogate output; and Updating one or more surrogate model parameters based on a fidelity value and the comparison of the first principles output and the surrogate output” (Page 9 – 10: “… the postulation of terms which might enter the final model, the selection of an adequate model, and the verification of the model selected… e(i) represents the equation error. An adequate model for the aerodynamic coefficients can be determined by applying the stepwise regression… the last step in model structure determination and parameter estimation is model verification. The parameter estimates must have realistic values and should be compared with wind-tunnel results and theoretical predictions. Whenever possible, the least-squares estimate should also be compared with the estimates using different techniques, that is, the maximum-likelihood estimate method. Ultimately, the model should be a good predictor of airplane motion within the region of its assumed validity…” NOTE: theoretical predictions are, for example, physics based or first principal models. Page 18: “… this number usually increases to some maximum value as new variables enter the regression, but then decreases slightly as the new terms are less effective in reducing the residuals… R2 is calculated… R2 would be 100 percent for a model that perfectly fit the data…” NOTE: the above teaches two ways to verify fidelity of the model.).
Claims 5, 12, 25. Johnson_2017 makes obvious “further comprising: receiving a movement plan request comprising a plurality of inputs representing a current condition of the vehicle and field conditions for the vehicle; Inputting the plurality of inputs to a first principles engine or to the surrogate model to generate an approved movement plan for the vehicle; and providing the approved movement plan for the vehicle to the vehicle” (abstract: “… the digital twins include data structures representing state of each of a plurality of subsystems of the set of industrial assets… the digital twins are analyzed with respect to simulated operating performance to determine an optimized control of operations of the industrial assets… recommendation is presented… automatically changing operating setpoints pertaining to the industrial assets…”; par 23 – 24: “… a flight schedule of an aircraft may be beneficially changed to reduce fuel and service costs… the schedules of asset utilization, duty cycle and operating policies, such as thrust limits… which are directed by the computational control system…”; par 25: “… physics based first principle engineering models are derived… data may be aggregated from a plurality of sources, such as engine sensors… weather services… to create assumptions… in conjunction with operating patterns or control patterns…”; par 35: “… a physics-based approach is accepted in addition to data driven methods into the simulation…”; par 120: “… aircraft engines, power turbines… the exogenous elements… (temperatures, humidity, and so on) are able to be simulated along with the specific operation scenarios such as flight schedules… loads, torque… and other aspects of the operations…”; par 185: “in example embodiments, the simulation may actually simulate the trajectory of the flight itself (e.g., via the incorporation an Aircraft Digital Twin that can model the performance of the entire aircraft through the flight using typical aircraft performance methods (e.g., using L/D, T/W, drag polars, and so no). in this way, the aircraft digital twin will enable the ability to consider scenarios “beyond the engine.” Par 263: “… the physical state of the industrial system components that are being measured, automatically estimated and adaptively controlled…”; FIG. 5; FIG. 9 optimization of operations including “flight operations/trajectory/control” FIG. 10: “control settings – thrust climb rate… trajectory – ground, trajectory – air/approach…”; FIG. 14: “flight schedule and policy PAST|FUTURE”; FIG. 8A Digital Twin Optimization produces “aircraft routing and maintenance schedule assignment”, “Flight assignment optimization”, “flight rout assignment for fuel efficiency”, “flight operational strategy”).
Claims 6, 13, 26. Johnson_2017 makes obvious “wherein generating the approved movement plan for the vehicle utilizes a first amount of computational processing power, and wherein providing inputs to the surrogate model to generate surrogate model output utilizes a second amount of computational processing power, wherein the second amount of computational processing power is less than the first amount of computational processing power (par 289 FIG. 13 is a block diagram of a constrained and unconstrained computational control system schema for estimation of thermodynamic performance and asset utilization. The system to manage time and specificity for the operational decision optimization 1300 is disclosed. Two modes of computation are enabled – an unconstrained 1302 method and a constrained mechanism 1310. An unconstrained compute of scenarios and their replication has no time or computing resource limits…”
NOTE: The instant specification indicates that the first amount of computational processing power is result of performing first principles calculations. See paragraph 43 of the instant specification: “… the first principles calculation engine 220 utilizes computationally expensive first principles equations and calculations… while using large amounts of computation processing power…”
In the teachings of Johnson_2017, the computer that performs the first principles modeling/calculations is a ground-based computer system that may have no computing resource limits when calculating performance optimization using first principles models.
The aircraft of Johnson_2017, and thus the aircraft computing system, is separate from the ground-based computing system and is not performing the optimizations and therefore not performing first principles modeling. This implies to one of ordinary skill in the art that the aircraft control system, which is adjusted by installing the surrogate model after the optimization process, is NOT one that has no computing resource limits. This is due to the obvious size and weight limits that one of ordinary skill in the art recognizes are inherent to aircraft. This is additionally made obvious in the context of Johnson_2017, which also has the objective of minimizing fuel cost (see par 23: “… a flight schedule of an aircraft may be beneficially changed to reduce fuel and service cost… associated with operating the aircraft…”). Therefore, even if an aircraft has no weight or size restrictions, it would certainly not reduce fuel costs to fly with an unlimited amount of computing resources compared to flying with a smaller and less powerful computing system. In other words, a computerized aircraft control system that controls, for example, trajectory (i.e., movement plan) has less computational power than the disclosed ground-based physics simulation and optimization computer that has unlimited processing power.)
Claims 7, 14. Johnson_2017 makes obvious “wherein the vehicle comprises an aircraft, and wherein the vehicle configuration comprises at least a model for the aircraft and an engine pairing for the aircraft” (par 27: “in example embodiments, combinations of engine assets (such as an engine pair on a given aircraft) are determined…”).
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to BRIAN S COOK whose telephone number is (571)272-4276. The examiner can normally be reached 8:00 AM - 5:00 PM.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Emerson Puente can be reached at 571-272-3652. 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.
/BRIAN S COOK/Primary Examiner, Art Unit 2187