Measurement-based surrogate models for additive manufacturing coupled with digital twin ecosystem

Abstract

A method and system for making or repairing a specified part is provided. For example, a method for creating an optimized manufacturing process to make or repair a specified part is provided. The method includes receiving data from multiple sources, the data including as-designed, as-manufactured, as-simulated, and as-tested data relative to one or more parts similar to the specified part. The method includes updating a surrogate model corresponding to a physics-based model of the specified part in real time, wherein the surrogate model forms a digital twin of the specified part. The method includes further updating the surrogate model with a model of manufacturing differences associated with at least one of the inspection and in-operation data of the similar part. The method includes executing an optimized manufacturing process based on the digital twin to repair or make the specified part.

Description

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims the benefit of U.S. Provisional Patent Application No. 62 / 862,012, filed on June 14, 2019, and Application No. 62 / 862,016, filed on June 14, 2019. The disclosures of these two prior applications are incorporated herein by reference in their entirety. Background Art

[0003] In industrial applications, the production of components often includes consideration of the manufacturing process during the design phase. In this case, the design and manufacturing processes are closely linked, meaning that design decisions may be influenced by manufacturing constraints, or manufacturing choices may arise directly from design aspects. Moreover, operating characteristics may be affected by the capabilities of the manufacturing process. For example, in a typical industrial manufacturing process, parts are produced according to predetermined tolerances, because the as-manufactured parts deployed in the field may differ from their design specifications (i.e., different from the as-designed parts) due to the inherent variations in the manufacturing process.

[0004] With the advent of additive manufacturing technology, another layer of complexity has been introduced into the above manufacturing / design / operation ecosystem due to the inherent aspects of the additive process. For example, additive processes can use layers of material to form a part by adding and use pre-processing / post-processing steps such as heating and curing the layers. Optimizing and validating additive processes requires quantifying and validating the differences in the manufactured parts through destructive testing, which generates a large amount of scrap material depending on the number of tolerances tested.

[0005] Destructive testing alone can verify that a manufactured component meets a specific design tolerance, but does not consider how the effects of multiple tolerance differences within that tolerance difference may collectively affect the performance of the component in operation, or replicate the range of operating mechanisms to which the component is exposed in operation, and therefore quantify the fitness for use of the component manufactured through the operational process. Another risk is that a manufactured component with a useful and serviceable life is scrapped due to the effects of differences occurring during the manufacturing cycle, and the inability to quantify the operational fitness of the component. Summary of the invention

[0006] Embodiments of the features herein help solve or mitigate the above-mentioned problems and other problems known in the art. Embodiments of the features herein integrate operational characteristics measured and analyzed during the life cycle of a component with design and manufacturing (including specific aspects of the additive manufacturing process) to create a model that can mitigate performance and manufacturing variances.

[0007] For example, embodiments provide the ability to directly link as-built, as-manufactured / assembled, as-designed, and as-simulated, as-tested, as-operated, and as-serviced components through a unique digital integration process. This digital integration process includes specific aspects of the additive manufacturing process used at any point during the life cycle of the component. In an embodiment of the features herein, any hardware component has the ability to reference its design goals and derive multiple analysis results based on its hardware specifications and operational data. The novel process also provides for abstracting data types from multiple analyses to form an integrated digital twin of the hardware component. In addition, the novel process provides a framework for improving the fidelity and accuracy of system-level digital twins by aggregating subsystem component-level digital twin predictions.

[0008] Embodiments featured herein provide a technology infrastructure that produces an automated, quantitative, and qualitative assessment of the variability in the additive manufacturing process over the useful life of a part. Thus, in its implementation, the embodiments purposefully and efficiently allow for optimization of a manufacturing or repair process to produce or repair a part to a useful life specified by the applied constraints, while optimizing the amount of material and destructive testing required to produce or repair the part using one or more additive manufacturing processes. For example, but not limited to, where a part requires a coating, the embodiments set forth herein can provide a quantitative assessment of the amount of coating that needs to be added to the part during repair or manufacturing to match the performance of the part; the identified amount of material can be optimized for cost constraints.

[0009] Additional features, modes of operation, advantages, and other aspects of various embodiments are described below with reference to the accompanying drawings. Note that the present disclosure is not limited to the specific embodiments described herein. These embodiments are presented for illustrative purposes only. Based on the teachings provided, other embodiments or modifications of the disclosed embodiments will be apparent to those skilled in the relevant art. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Exemplary embodiments may take the form of various components and arrangements of components. Illustrative embodiments are shown in the accompanying drawings, and similar reference numerals may indicate corresponding or similar parts in the various drawings throughout the drawings. The drawings are for the purpose of illustrating the embodiments only and should not be construed as limiting the present disclosure. Given the following description of the enabling drawings, the novel aspects of the present disclosure will become apparent to those of ordinary skill in the relevant art.

[0011] Figure 1 A process according to an embodiment is shown.

[0012] Figure 2 A digital twin ecosystem according to an embodiment is shown.

[0013] Figure 3 An exemplary process according to an aspect of the embodiment is shown.

[0014] Figure 4 An exemplary process according to an aspect of the embodiment is shown.

[0015] Figure 5 An exemplary process according to an aspect of the embodiment is shown.

[0016] Figure 6 An exemplary process according to an aspect of the embodiment is shown.

[0017] Figure 7 An exemplary process according to an aspect of the embodiment is shown.

[0018] Figure 8 An exemplary process according to an aspect of the embodiment is shown.

[0019] Fig. 9 An exemplary system is shown that is configured to perform one or more aspects of the exemplary processes presented herein. DETAILED DESCRIPTION

[0020] Although illustrative embodiments are described herein for specific applications, it should be understood that the present disclosure is not limited thereto. Those skilled in the art and those who have access to the teachings provided herein will recognize additional applications, modifications and embodiments within its scope and additional areas in which the present disclosure will have significant practical value.

[0021] Embodiments of the features herein have several advantages. For example, they can allow one to accurately assess the quality of a newly manufactured part relative to its design intent. They provide the ability to mix and match different manufactured components in an engine assembly to achieve the desired integrated engine performance. In addition, they improve the time-on-wing assessment of each part and subassembly based on manufacturing variations, operating conditions, and by service conditions. Embodiments use high-fidelity design knowledge to help exploit subsystem component performance, and they improve prediction accuracy as needed. In addition, they enable a feedback loop that helps improve subsequent designs.

[0022] Figure 1An exemplary process 100 is shown in accordance with an exemplary embodiment. Process 100 may be an example process associated with a life cycle of a part and / or a general manufacturing cycle. Although process 100 is described in the context of an aircraft or jet engine part, process 100 may be extended to manufacturing, or generally to the life cycle of any manufactured component. Process 100 includes module 102 which is a product environment spectrum. In other words, module 102 may be a database that stores information about instances of the same product used in the field.

[0023] For example, module 102 may include information about reliability or failure of multiple turbine blades when commissioned in an engine group (i.e., in two or more engines). Module 102 may be configured to organize or present a product environment spectrum upon request from a device communicatively coupled thereto, the product environment spectrum categorizing all products of interest in a predetermined order.

[0024] For example, products may be classified based on their robustness. In one use case, products may be classified from more robust (102a) to least robust (102n). In general, one or more performance criteria may be used to classify these products along the above spectrum. In the case of turbine blades, products may be classified based on their thermal stability performance, which may be measured using one or more field inspection methods.

[0025] The product environment profile may be driven by constraints from the customer, which may be collected and functionalized (i.e., placed in the form of computer instructions) in module 104. In other words, the robustness criteria may be determined by application-specific parameters obtained from the customer. Similarly, the product environment profile may be driven by business constraints, which may be functionalized in module 106. These constraints (for both modules 104 and 106) may be updated as the manufacturing process is updated based on various information sources, as will be further described below.

[0026] The customer constraints of module 104 may also drive the manufacturing functions of module 108, which in turn drive engineering decisions, as functionalized in module 112. Once the engineering decisions are functionalized, they can be used to establish a digital thread configured for design. The digital design thread can also be updated based on the customer's constraints (module 104). Thus, the thread forms a digital twin, which can be formed by multiple data sources representing multiple use cases. In other words, the digital twin integrates multiple use cases to ensure that the manufactured part is produced according to specific performance data, rather than just producing the part according to predetermined dimensional constraints as in a typical manufacturing process.

[0027] Thus, the digital twin allows engineering redesign based on the performance of the part in the field. In this way, the digital twin allows a given manufacturing process to be optimized in order to differentiate the quality of the manufactured parts, thereby driving target performance and business outcomes.

[0028] Typically, a digital design twin may be constructed from multiple sources including newly produced manufacturing data from engineering models, networks, and existing manufacturing models of the part (module 108). Data streams from the network may include, for example, but not limited to, borescope inspection data from field inspections (partial or full, or in some embodiments, functional inspections or dimensional inspections), on-wing probing from engine measurement data during flight. In addition, typically, a digital twin of a component may include at least one of as-manufactured data, as-tested data, as-designed and as-simulated data, as-operational data, and as-service data for the component. In addition, a digital twin of a component may be based on operational data or nominal operating conditions of the component.

[0029] Process 100 allows for continuous data collection. Specifically, the digital design thread is continually updated to provide a model that reflects actual conditions. This is accomplished through an explicit feedback loop of process 100 that ensures that new designs can be manufactured based on the various information sources described above. In this way, process 100 provides the ability to better predict the durability of a part because any manufactured part will have been manufactured based on conditions that reflect design, use, service, etc.

[0030] In summary, process 100 integrates and automates various aspects of the part lifecycle to provide an optimized manufacturing process at the enterprise level. Process 100 also includes a score inspection module that can be updated with field inspection analysis to further enhance the engineering model. Figure 2 The process 100 is further understood in the context of Figure 2 A digital twin ecosystem 200 is depicted that features exemplary relationships between as-designed, as-manufactured, as-tested, as-serviced, and as-operated aspects of a specified part during its lifecycle. The digital twin ecosystem 200 includes aspects that account for differences in additive manufacturing processes, as will be described in further detail below.

[0031] Figure 3 An exemplary process is shown that includes an additive manufacturing-coupled digital twin ecosystem as-designed, as-manufactured, as-tested, as-operated, as-inspected, and as-serviced. Figure 3An operating spectrum and an environmental spectrum are depicted. These spectra form an "operating regime" that represents the level in operation (e.g., from light to hard for a given part), and the environment in which a given part operates (e.g., from benign to harsh). The operating regime is a factor of both the environment and the operation. Therefore, the performance of the component is quantifiable and can be compared to similar components within similar operating regimes. The performance of the part is an indicator of the remaining useful life within the range of operating regimes.

[0032] Process performance is a spectrum from performance and tolerances "as process designed" to out of tolerance. Thus, out of process performance could mean more or less process or material is applied to a part, such as the flow rate of a nozzle indicating that a minimum coating thickness is applied to a part. Figure 3 In the context of process 100 , in an embodiment, a production model of component performance may be created using measurements of inspections of parts in operation and models of manufacturing variations in performance.

[0033] Figure 4 An exemplary process is shown that includes coupled digital twin ecosystems for additive manufacturing by design, by manufacturing, by test, by operation, and by service. Figure 4 In "Process X", when the exemplary system (see Fig. 9 ) When a shift is observed during the manufacturing process, e.g., a change in flow rate from a nozzle that may mean less thermal barrier has been applied, the exemplary system may be configured to determine that a similar shift was observed during the manufacture of parts with serial numbers 1..3 in "Process X." Additionally, the exemplary system may be configured to predict a range of expected in-production performance and performance degradation X over the operational life, "cycle," of manufactured parts based on the operational and environmental regimes X1,2,3 experienced by those parts over their operational life, "cycle," and the performance X, e.g., thermal performance.

[0034] The exemplary system can then be configured to suggest an appropriate operating regime X1,2,3 for the component to achieve optimal in-production performance. The in-service performance and operating regime X can be determined through operational experience of the component in production and / or simulations using computational fluid dynamics, for example. This reduces billing and warranty claims because the exemplary system does not base scrapping on meeting "as designed" or "as designed in process" specifications and warranties, nor does it price components based on their expected useful life or for specific operating regimes.

[0035] Figure 5 An exemplary process is shown that includes coupled digital twin ecosystems for additive manufacturing by design, by manufacturing, by test, by operation, and by service. Figure 5In, the exemplary system can be configured to determine an offset in a manufacturing process, "Process X". The offset can be, for example, but not limited to, a flow rate from a nozzle, which can mean that less thermal barrier has been applied, which will result in a range of performance in production. For example, this range can be a change in thermal performance and performance degradation X, depending on operating regime X1,2,3. With this information, the exemplary system can manufacture a part with an offset in "Process X" to achieve a performance of Y, which is degraded according to the progress of X when operating within operating regime X2Y.

[0036] For example, the part may be manufactured for operation where the operating mechanism X2Y represents light operation in a benign environment. The in-service performance and operating mechanism X may be determined through operational experience of the part in production and / or simulations using computational fluid dynamics, for example. The benefit of manufacturing to Y is the reduction of processes or materials used to obtain the desired performance Y.

[0037] Figure 6 and 7 An exemplary process is shown that includes coupled digital twin ecosystems for additive manufacturing by design, by manufacturing, by test, by operation, and by service. Figure 7 In, an exemplary system can be configured to determine a shift in a manufacturing process, "Process X",. The shift can be, for example, but not limited to, a flow rate from a nozzle, which may mean that less thermal barrier has been applied, which will result in a range of performance in production. For example, such a range can be a change in thermal performance and performance degradation, X, depending on the operating mechanism X1,2,3.

[0038] Given this information, an exemplary system can infer that the in-production performance, such as thermal performance, is within a range of X. A shift in "process Y," such as a post-processing step such as a heat treatment for a thermal barrier, may also independently result in a performance, Y, within an acceptable range. However, if the resulting performance of X+Y=Z is within the range of X1Y1, X2Y2, X3Y3, then the combined impact of X+Y may be greater than the independent impacts of X and Y. Therefore, creating a model of a manufactured part that quantifies quality as a factor of predicted in-production performance, such as thermal performance, has the advantage of allowing prediction of the impact of multiple process influencing factors, X&Y, on final component performance. In addition, in-service performance and operating mechanisms, X&Y, can be determined through operating experience of the part in production and / or simulations using, for example, computational fluid dynamics.

[0039] As such, the exemplary system provides advantages over destructive testing methods where destructive testing cannot independently correlate the combined effects of multiple process influencing factors and cannot reasonably replicate the range of operating mechanisms as may be observed and / or simulated in service. Providing an alternative or parallel qualification process to destructive testing has the benefits of improved safety, reduced warranty claims, and reduced scrap.

[0040] Figure 8 An exemplary process is shown that includes coupled digital twin ecosystems for additive manufacturing by design, by manufacturing, by test, by operation, and by service. Figure 8 In, if we know or can predict through operational experience and / or simulation of manufactured components the in-service performance, X, of operating regimes, X1, X2, X3, of components manufactured to specification, say, D = “as designed”, and how they degrade based on measurements over their operational life, “cycle”, we can quantify the required processes and / or materials, “Process X”, to restore the component to measurements under specification, D, by quantifying the regression from the expected measurements of X and operating regimes, X1, X2, X3, under the operational life, “cycle”, to the specification, D.

[0041] To restore component Y to D, "as designed", where Y's operating performance was X1 and it has been operated under the operating regime of X1Y and 1000 cycles, we need to calculate the regression of X1 under 1000 cycles, the materials and / or processes required, "Process X", to restore to D. This can be used to qualify the repair of a single component Y, or a repair process for a component within a range of X, with the advantage of being used as a qualification of a repair specification or repair process, where the process can also be verified by physical testing; where reduced destructive testing requirements reduce scrap rates. We also have the advantage of being able to predict the cost and material requirements of the repair process as the component is serviced over its entire operating life through the progress of X, to optimize repair costs versus in-service performance versus optimal service intervals.

[0042] Fig. 9 A system 1000 is depicted that is configured to Figure 1-8 The various operations described above are performed in the context of the exemplary digital twin ecosystem described in the described process. The system 1000 includes a dedicated processor 1014 that is configured to perform tasks specific to optimizing the manufacturing process according to 100. The processor 1014 has a specific structure imparted by instructions stored in the memory 1002 and / or by instructions 1018 that can be retrieved by the processor 1014 from a storage device 1020. The storage device 1020 can be co-located with the processor 1014, or it can be located elsewhere and communicatively coupled to the processor 1014, for example via a communication interface 1016.

[0043] System 1000 may be a stand-alone programmable system, or it may be a programmable module in a larger system. For example, system 1000 may be part of a distributed system configured to process various modules of process 100 described above. Processor 1014 may include one or more hardware and / or software components configured to acquire, decode, execute, store, analyze, distribute, evaluate and / or classify information.

[0044] Processor 1014 may include an input / output module (I / O module 1012) that may be configured to ingest data related to a single asset or a group of assets. Processor 1014 may include one or more processing devices or cores (not shown). In some embodiments, processor 1014 may be a plurality of processors, each having one or more cores. Processor 1014 may be configured to execute instructions retrieved from memory 1002 (i.e., from one of storage block 1004, storage block 1006, storage block 1008, and storage block 1010).

[0045] Furthermore, without loss of generality, storage 1020 and / or memory 1002 may include volatile or nonvolatile, magnetic, semiconductor, tape, optical, removable, non-removable, read-only, random access, or any type of non-transitory computer-readable computer media. Storage 1020 may be configured to record data processed, recorded, or collected during operation of processor 1014. The data may be time-stamped, location-stamped, cataloged, indexed, or organized in various manners consistent with data storage practices. Storage 1020 and / or memory 1002 may include programs and / or other information that processor 1014 may use to perform tasks consistent with the tasks described herein.

[0046] For example, processor 1014 can be configured by instructions from storage block 1006, storage block 1008, and storage block 1010 to perform real-time updates of the model for the part based on various input sources (e.g., network and / or field data module 108). Processor 1014 can execute the aforementioned instructions from storage blocks 1006, 1008, and 1010, and output a twin digital model based on data from the various sources described above. In general, processor 1014 can perform real-time updates of the model based on the data from the various sources described above based on the continuous updates. Figure 2-9 The predictive deployment or degradation model described in the context of is used to continuously change the strategy deployment module 110, which includes a model for the part.

[0047] Embodiments provide the ability to improve time-on-wing estimates for each part and its subassemblies based on manufacturing variations, operating conditions, and in-service data. In addition, embodiments use high-fidelity design knowledge to help leverage subsystem component performance and improve prediction accuracy as needed, and they enable feedback loops that help improve subsequent designs.

[0048] Those skilled in the relevant art will appreciate that various modifications and variations of the above embodiments may be constructed without departing from the scope and spirit of the present disclosure. Therefore, it should be understood that within the scope of the appended claims, the present disclosure may be practiced in a manner different from that specifically described herein.

[0049] Further aspects of the invention are provided by the subject matter of the following clauses:

[0050] 1. A method for making or repairing a specified part, the method comprising: creating an optimized manufacturing process to make or repair the specified part, the creation comprising: receiving data from multiple sources, the data comprising design, manufacturing, simulation and test data relative to one or more parts similar to the specified part; updating in real time a substitute model corresponding to a physics-based model of the specified part, wherein the substitute model forms a digital twin of the specified part; further updating the substitute model with a model of manufacturing differences associated with at least one of inspection data and in-operation data of similar parts; and executing the optimized manufacturing process based on the digital twin to repair or make the specified part.

[0051] 2. The method according to any preceding clause, wherein the surrogate model further comprises measurements recorded during inspection of the component, the measurements being able to be related to the operation of the component and the performance of the component in operation.

[0052] 3. A method according to any of the preceding clauses, wherein the surrogate model is further configured to be associated with measurement differences monitored during an additive manufacturing step / reductive manufacturing step / repair step to create a model of the measurement differences observed during the additive manufacturing step / reductive manufacturing step / repair step; and wherein the additive manufacturing step / reductive manufacturing step / repair step includes multiple additive processes / reductive processes and post-processing steps and machines.

[0053] 4. A method according to any preceding clause, wherein the surrogate model is further configured to relate to expected performance of the component in operation.

[0054] 5. The method of any preceding clause, further comprising calculating the useful life of said specified part based on a correlation with said expected performance of the component in operation.

[0055] 6. The method of any preceding clause, further comprising using a surrogate model to compare measurements recorded during component inspection to optimize the additive process / reductive repair process required to return the component to desired performance.

[0056] 7. A method according to any preceding clause, further comprising relating said desired performance of said component to an expected remaining useful life.

[0057] 8. A method according to any preceding clause, wherein optimizing the additive process / reductive repair process reduces material utilization or additive processing / reductive processing by achieving desired component performance relative to as-designed performance.

[0058] 9. A method according to any of the preceding clauses, wherein the surrogate model is further based on correlations between observations / measurements recorded during inspection of the components and component operating data and performance characteristics of the components in operation to group the components according to the observations / measurements and operation of the performance of the components in operation.

[0059] 10. A method according to any of the preceding clauses, further comprising using a model of observed / measured values ​​of performance of a component in operation to create a predictive model of predicted performance of the component in operation based on observed / measured values ​​of the component recorded during inspection of the component at the point of additive manufacturing / reductive manufacturing / repair.

[0060] 11. A method according to any preceding clause, wherein said predictive model of predicted performance of a component in operation is based on observations / measurements of the component recorded during inspection of the component at the point of additive manufacturing / reductive manufacturing / repair.

[0061] 12. A method according to any preceding clause, further comprising using said predictive model to calculate the useful life / remaining useful life of a component or a group of components based on observations / measurements of the component at the point of additive manufacturing / reductive manufacturing / repair.

[0062] 13. A system configured to manufacture or repair a specified part, the system comprising: a processor; a memory containing instructions, which, when executed by the processor, cause the processor to perform operations, the operations comprising: creating an optimized manufacturing process to make or repair the specified part, the creation comprising: receiving data from multiple sources, the data comprising design, manufacturing, simulation and test data relative to one or more parts similar to the specified part; updating in real time a substitute model corresponding to a physics-based model of the specified part, wherein the substitute model forms a digital twin of the specified part; further updating the substitute model with a model of manufacturing differences associated with at least one of inspection data and in-operation data of similar parts; and executing the optimized manufacturing process based on the digital twin to repair or manufacture the specified part.

[0063] 14. The system of any preceding clause, wherein the surrogate model further comprises measurements recorded during inspection of the component, the measurements being relatable to component operation and component performance during operation.

[0064] 15. A system according to any of the preceding clauses, wherein the surrogate model is further configured to be correlated to measurement differences monitored during an additive manufacturing step / reductive manufacturing step / repair step to create a model of the measurement differences observed during additive manufacturing / reductive manufacturing / repair.

[0065] 16. The system of any preceding clause, wherein the surrogate model is further configured to relate to expected performance of the component in operation.

[0066] 17. The system of any preceding clause, wherein said operations further comprise calculating the useful life of said designated part based on a correlation with said expected performance of the component in operation.

[0067] 18. The system of any preceding clause, wherein the operations further comprise using a surrogate model to compare measurements recorded during inspection of the component to optimize the additive process / reductive repair process required to return the component to desired performance.

[0068] 19. The system of any preceding clause, wherein said operations further comprise correlating said desired performance of said component with an expected remaining useful life.

[0069] 20. The system of any preceding clause, wherein the operations further comprise optimizing the additive process / reductive repair process to reduce material utilization or additive / reductive processing by achieving desired component performance relative to as-designed performance.

[0070] 21. A system according to any of the preceding clauses, wherein the surrogate model is further based on correlations between observations / measurements recorded during inspection of the components and component operating data and performance characteristics of the components in operation to group components according to the observations / measurements and operation of the performance of the components in operation.

[0071] 22. A system according to any of the preceding clauses, wherein the operation further includes using a model of observed / measured values ​​of performance of the component in operation to create a predictive model of predicted performance of the component in operation based on observed / measured values ​​of the component recorded during inspection of the component at the point of additive manufacturing / reductive manufacturing / repair.

[0072] 23. A system according to any preceding clause, wherein said predictive model of predicted performance of a component in operation is based on observations / measurements of the component recorded during inspection of the component at the point of additive manufacturing / reductive manufacturing / repair.

[0073] 24. A method according to any preceding clause, wherein the operation further comprises using the predictive model to calculate the useful life / remaining useful life of a component or a group of components based on observations / measurements of the component at the point of additive manufacturing / reductive manufacturing / repair.

Claims

1. A method for making or repairing a specified part, characterized in that: The method comprises: Creating an optimized manufacturing process to make or repair the specified part, the creating comprising: receiving data from a plurality of sources, the data comprising as-designed, as-manufactured, as-simulated, and as-tested data relative to one or more parts similar to the specified part; updating, in real time, a surrogate model corresponding to the physics-based model of the specified part, wherein the surrogate model forms a digital twin of the specified part; further updating the surrogate model with a model of manufacturing variances associated with in-operation performance of the similar part based on at least one of inspection data and in-operation data of the similar part and an operating mechanism of the similar part; Based on the digital twin, the optimized manufacturing process is executed to repair or manufacture the specified part.

2. The method according to claim 1, characterized in that in, The surrogate model further includes measurements recorded during inspection of the component, which measurements may be related to component operation and performance of the component in operation.

3. The method according to claim 2, characterized in that in, The surrogate model is further configured to be associated with measurement differences monitored during the additive manufacturing step / reductive manufacturing step / repair step to create a model of the measurement differences observed during the additive manufacturing step / reductive manufacturing step / repair step; and wherein the additive manufacturing step / reductive manufacturing step / repair step includes multiple additive processes / reductive processes and post-processing steps and machines.

4. The method according to claim 3, characterized in that in, The surrogate model is further configured to relate to expected performance of the component in operation.

5. The method according to claim 4, characterized in that Further included calculating the useful life of the designated part based on a correlation with the expected performance of the component in operation.

6. The method according to claim 1, characterized in that Further included is using a surrogate model to compare measurements recorded during component inspection to optimize the additive process / reductive repair process required to return the component to desired performance.

7. The method according to claim 6, characterized in that Further included correlating the desired performance of the component to an expected remaining useful life.

8. The method according to claim 7, characterized in that in, Optimizing the additive process / reductive repair process reduces material utilization or the additive / reductive process by achieving desired part performance relative to as-designed performance.

9. The method according to claim 2, characterized in that: in, The surrogate model is further based on correlations between observations / measurements recorded during inspection of the components and component operational data and performance characteristics of the components in operation to group components according to observations / measurements and operation of performance of components in operation.

10. The method according to claim 9, characterized in that Further comprising using the model of observed / measured values ​​of performance of the component in operation to create a predictive model of predicted performance of the component in operation based on observed / measured values ​​of the component recorded during inspection of the component at the point of additive manufacturing / reductive manufacturing / repair.

11. The method according to claim 10, characterized in that in, The predictive model of predicted performance of a component in operation is based on observations / measurements of the component recorded during inspection of the component at the point of additive manufacturing / reductive manufacturing / repair.

12. The method according to claim 11, characterized in that Further included is using the predictive model to calculate the useful life / remaining useful life of a component or a group of components based on observations / measurements of the component at the point of additive manufacturing / reductive manufacturing / repair.

13. A system configured to manufacture or repair a specified part, characterized in that: The system comprises: processor; a memory containing instructions that, when executed by the processor, cause the processor to perform operations comprising: Creating an optimized manufacturing process to make or repair the specified part, the creating comprising: receiving data from a plurality of sources, the data comprising as-designed, as-manufactured, as-simulated, and as-tested data relative to one or more parts similar to the specified part; updating, in real time, a surrogate model corresponding to the physics-based model of the specified part, wherein the surrogate model forms a digital twin of the specified part; further updating the surrogate model with a model of manufacturing variances associated with in-operation performance of the similar part based on at least one of inspection data and in-operation data of the similar part and an operating mechanism of the similar part; Based on the digital twin, the optimized manufacturing process is executed to repair or manufacture the specified part.

14. The system according to claim 13, characterized in that in, The surrogate model further includes measurements recorded during inspection of the component, which measurements may be related to component operation and component performance during operation.

15. The system according to claim 14, characterized in that in, The surrogate model is further configured to be correlated with measurement differences monitored during the additive manufacturing step / reductive manufacturing step / repair step to create a model of the measurement differences observed during the additive manufacturing / reductive manufacturing / repair.

16. The system according to claim 15, characterized in that in, The surrogate model is further configured to relate to expected performance of the component in operation.

17. The system according to claim 16, characterized in that in, The operations further include calculating a useful life of the designated part based on a correlation with the expected performance of the component in operation.

18. The system according to claim 16, characterized in that in, The operations further include using the surrogate model to compare measurements recorded during the inspection of the component to optimize the additive process / reductive repair process required to return the component to desired performance.

19. The system according to claim 18, characterized in that in, The operations further include correlating the desired performance of the component with an expected remaining useful life.

20. The system according to claim 19, characterized in that in, The operations further include optimizing the additive process / reductive repair process to reduce material utilization or additive / reductive processing by achieving desired part performance relative to as-designed performance.

21. The system according to claim 14, characterized in that in, The surrogate model is further based on correlations between observations / measurements recorded during inspection of the components and component operational data and performance characteristics of the components in operation to group components according to observations / measurements and operation of performance of components in operation.

22. The system according to claim 21, characterized in that in, The operations further include using the model of observed / measured values ​​of performance of the component in operation to create a predictive model of predicted performance of the component in operation based on observed / measured values ​​of the component recorded during inspection of the component at the point of additive manufacturing / reductive manufacturing / repair.

23. The system according to claim 22, characterized in that in, The predictive model of predicted performance of a component in operation is based on observations / measurements of the component recorded during inspection of the component at the point of additive manufacturing / reductive manufacturing / repair.

24. The system according to claim 23, characterized in that in, The operations further include calculating the useful life / remaining useful life of a component or a group of components using the predictive model based on observations / measurements of the component at the point of additive manufacturing / reductive manufacturing / repair.

Images