A method and apparatus for evaluating and correcting an engine digital twin model

Abstract

This invention provides a method and apparatus for evaluating and correcting a digital twin model of an engine, comprising: establishing a digital twin model of the engine; acquiring and processing physical space data required for the operation of the digital twin model; transmitting the physical space data to the digital twin model for simulation; evaluating the digital twin model based on the simulation timeliness and the accuracy of the simulation results; and correcting the digital twin model based on the evaluation results, and outputting simulation results that meet preset requirements.

Description

Technical Field

[0001] This invention relates to the field of engine modeling and simulation, and in particular to an evaluation and correction method and apparatus for an engine digital twin model. Background Technology

[0002] Aero-engines are high-end and complex products, exhibiting high levels of complexity in design, manufacturing, assembly, operation, and maintenance. By introducing digital twin technology into the development of aero-engines throughout their product lifecycle, real-time simulation of various physical activities of the aero-engine can be achieved. This effectively improves the control of aero-engine physical activities and optimizes the level of intelligence and digitalization in the engine development process.

[0003] Existing technologies also include several solutions utilizing digital twin models, such as virtual display interaction based on digital twin models. These solutions involve constructing a scene, using sensors to drive the virtual scene to monitor physical entities in real time, and then employing VR devices to achieve virtual reality interaction. There are also solutions for evaluating and correcting digital twin models. For example, by comparing virtual and physical data spaces, deep neural networks can be used to learn errors and correct the digital twin model's errors when the errors are significant.

[0004] However, these solutions often fail to consider the timeliness of the interaction process between digital twin models, making it impossible to correct the model when latency requirements are not met. They also struggle to assess the timeliness of interactions in large-scale, complex simulations, hindering timely corrections to ensure synchronized mapping. Furthermore, they lack multi-dimensional evaluations of digital twin models based on the performance, functional status, and key performance indicators of the product's physical activities, making it difficult to comprehensively and effectively reflect the simulation performance of the digital twin model.

[0005] To overcome the aforementioned deficiencies in existing technologies, there is an urgent need in this field for an evaluation and correction method and apparatus for engine digital twin models. This apparatus is used to evaluate the timeliness of the real-time simulation process of the digital twin model based on the construction of the aero-engine digital twin model, ensuring that the digital twin model can achieve simulation mapping of physical space activities within the allowable time delay range. At the same time, it evaluates the performance of the digital twin model from multiple dimensions and ensures that the model is corrected in a timely and rapid manner when deviations occur, so as to guarantee the efficient and high-quality simulation performance of the digital twin model. Summary of the Invention

[0006] The following provides a brief overview of one or more aspects to offer a basic understanding of them. This overview is not an exhaustive summary of all conceived aspects, nor is it intended to identify key or decisive elements of all aspects, nor to define the scope of any or all aspects. Its sole purpose is to present some concepts of one or more aspects in a simplified form to prepare for the more detailed descriptions that follow.

[0007] To overcome the aforementioned deficiencies in the existing technology, the present invention provides an evaluation and correction method for an engine digital twin model, comprising: establishing a digital twin model of the engine; acquiring and processing the physical space data required for the operation of the digital twin model; transmitting the physical space data to the digital twin model for simulation; evaluating the digital twin model based on the simulation timeliness and the accuracy of the simulation results; and correcting the digital twin model based on the evaluation results, and outputting simulation results that meet preset requirements.

[0008] In one embodiment, preferably, establishing a digital twin model of the engine includes: establishing a digital twin model of the engine body, specifically including the engine's structure and strength model, high / low pressure compressor aerodynamic model, aerodynamic and thermodynamic model, and performance model of the engine as a whole and control system; establishing a digital twin model of external entities that interact with the engine body during its operation, specifically including tools, equipment, machines, personnel, and environment involved in the operation of the engine body; and integrating and connecting the digital twin model of the engine body and the digital twin model of the external entities through interfaces and algorithms.

[0009] In one embodiment, preferably, the establishment of the digital twin model of the engine body further includes: after the establishment of the digital twin model of the engine body, the established model is simplified and lightweighted, specifically including: model format conversion, omitting or simplifying non-key feature information of the model, deleting unnecessary components, and abstracting and simplifying the mathematical expression of physical phenomena and working environment features in the model.

[0010] In one embodiment, preferably, the evaluation of the digital twin model based on simulation timeliness and simulation result accuracy includes: determining the maximum time thresholds for the simulation time of a single activity, the simulation time of coupled activities, and the overall total simulation time in the simulation activities of the digital twin model, where a single activity refers to a single simulation activity of a single digital twin sub-model, a coupled activity refers to a single coupled activity between multiple digital twin sub-models, and the overall total simulation time refers to the time required for the digital twin model to complete all simulation activities; and evaluating the digital twin model based on the simulation timeliness, where the simulation timeliness means that in the simulation activities of the digital twin model, the simulation time of a single activity, the simulation time of coupled activities, and the overall total simulation time do not exceed their respective maximum time thresholds.

[0011] In one embodiment, preferably, the evaluation of the digital twin model based on simulation timeliness and simulation result accuracy further includes: in response to the simulation timeliness meeting preset conditions, determining the simulation values ​​of multiple single key performance indicators in the digital twin model and their corresponding actual values ​​in the engine, wherein the single key performance indicators include dimensional accuracy, roughness, and strength indicators during engine manufacturing and assembly, and starting performance, thrust performance, and emission performance indicators during engine operation and maintenance; determining the comprehensive performance indicator of the digital twin model based on the multiple single key performance indicators; and evaluating the digital twin model based on the simulation result accuracy, wherein the simulation result accuracy refers to the deviation between the simulation value and the actual value of each single key performance indicator meeting the preset deviation range of the single key performance indicator, and the comprehensive performance indicator not exceeding a preset comprehensive performance threshold.

[0012] In one embodiment, preferably, determining the comprehensive performance index of the digital twin model based on the plurality of individual key performance indicators includes: determining the degree of deviation between the simulated value and the actual value of each individual key performance indicator according to the following formula:

[0013]

[0014] in, This indicates the degree of deviation between the simulated value and the actual value of the j-th single key performance indicator. This represents the simulated value of the j-th single key performance indicator. Let represent the actual value of the j-th single key performance indicator corresponding to the simulation value; and let represent the weight value of each single key performance indicator in the digital twin model determined by the analytic hierarchy process (AHP), and calculate the comprehensive performance indicator according to the following formula:

[0015]

[0016] Among them, perform simu For this comprehensive performance index of the digital twin model, w j This represents the weight value corresponding to the j-th single key performance indicator.

[0017] In one embodiment, preferably, the correction of the digital twin model based on the evaluation results includes: if the simulation timeliness of the digital twin model does not meet the preset requirements, the digital twin model requests more memory and bandwidth resources to correct the digital twin model and improve the simulation speed; if the simulation result accuracy of the digital twin model does not meet the preset requirements, the acquired physical space data is added to the model training library, and the model is retrained based on the new physical space data to optimize the parameters of the digital twin model and correct the model; and the simulation timeliness and simulation result accuracy of the corrected digital twin model are further evaluated, and in response to the corrected model meeting the preset requirements, the corrected digital twin model is uploaded to the cloud for use.

[0018] In one embodiment, preferably, the correction of the digital twin model based on the evaluation results further includes: in response to the fact that the simulation timeliness or the accuracy of the simulation results of the corrected digital twin model still does not meet the preset requirements, generating model warning information to push to the operation and maintenance personnel of the digital twin model, so that the digital twin model can be manually reconstructed.

[0019] In one embodiment, preferably, the acquisition and processing of physical space data required for the operation of the digital twin model includes: configuring multiple data acquisition devices in the engine body, the physical space environment in which the engine is located, and external entities that interact with the engine body; and acquiring physical space data of different sources and formats based on the multiple data acquisition devices.

[0020] In one embodiment, preferably, the acquisition and processing of the physical space data required for the operation of the digital twin model further includes: performing preprocessing on the acquired physical space data, including removing redundant and erroneous data, imputing missing data, and removing information irrelevant to the analysis; performing data integration and transformation on the preprocessed data, including extracting and integrating to form time-series data, converting data formats to meet the input requirements of simulation analysis, and converting data representation methods to compress data; and marking the processed physical space data according to its source and purpose, adding data tags, and storing it locally and in the cloud for transmission to the digital twin model for simulation work.

[0021] In one embodiment, preferably, the output of the simulation result that meets the preset requirements includes: in response to the simulation result meeting the preset requirements of simulation timeliness and simulation result accuracy, displaying the simulation result in real time through three-dimensional visual, VR and AR tools to achieve the synchronous mapping simulation of the engine and its physical space activities by the above-mentioned digital twin model.

[0022] Another aspect of the present invention provides an evaluation and correction apparatus for an engine digital twin model, comprising: a memory; and a processor coupled to the memory, the processor being configured to perform the steps of the evaluation and correction method for the engine digital twin model described in any of the preceding claims.

[0023] The present invention also provides a computer-readable medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the evaluation and correction method for the engine digital twin model described in any of the preceding claims. Attached Figure Description

[0024] The above-described features and advantages of the present invention will be better understood after reading the following detailed description of embodiments of the present disclosure in conjunction with the accompanying drawings. In the drawings, components are not necessarily drawn to scale, and components having similar related characteristics or features may have the same or similar reference numerals.

[0025] Figure 1 This is a schematic flowchart illustrating an evaluation and correction method for an engine digital twin model according to one aspect of the present invention;

[0026] Figure 2 This is a schematic flowchart illustrating a method for correcting a digital twin model of an engine according to an embodiment of the present invention; and

[0027] Figure 3 This is a schematic diagram of the device structure for evaluating and correcting an engine digital twin model, according to another aspect of the present invention. Detailed Implementation

[0028] The following specific embodiments illustrate the implementation of the present invention. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. Although the description of the present invention is presented in conjunction with preferred embodiments, this does not mean that the features of the invention are limited to these embodiments. On the contrary, the purpose of describing the invention in conjunction with embodiments is to cover other options or modifications that may be derived based on the claims of the present invention. To provide a thorough understanding of the invention, many specific details will be included in the following description. The invention may also be implemented without using these details. Furthermore, to avoid confusion or obscuring the focus of the invention, some specific details will be omitted in the description.

[0029] In the description of this invention, it should be noted that, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this invention based on the specific circumstances.

[0030] Furthermore, the terms "upper," "lower," "left," "right," "top," "bottom," "horizontal," and "vertical" used in the following description should be understood as the orientations shown in the relevant paragraphs and accompanying drawings. These relative terms are for illustrative purposes only and do not imply that the described apparatus must be manufactured or operated in a specific orientation, and therefore should not be construed as limiting the invention.

[0031] It is understood that although terms such as "first," "second," and "third" may be used herein to describe various components, regions, layers, and / or parts, these components, regions, layers, and / or parts should not be limited by these terms, and these terms are only used to distinguish different components, regions, layers, and / or parts. Therefore, the first components, regions, layers, and / or parts discussed below may be referred to as second components, regions, layers, and / or parts without departing from some embodiments of the present invention.

[0032] To overcome the aforementioned deficiencies in the existing technology, this invention provides an evaluation and correction method and apparatus for an engine digital twin model. Based on the construction of an aero-engine digital twin model, it evaluates the timeliness of the real-time simulation process of the digital twin model, ensuring that the digital twin model can achieve simulation mapping of physical space activities within an allowable time delay range. Simultaneously, it evaluates the performance of the digital twin model from multiple dimensions and ensures that the model is corrected promptly and quickly when deviations occur, thereby guaranteeing efficient and high-quality simulation performance of the digital twin model.

[0033] Figure 1 This is a schematic flowchart illustrating an evaluation and correction method for an engine digital twin model according to one aspect of the present invention.

[0034] Please refer to Figure 1 The evaluation and correction method 100 for the digital twin model of an engine provided by the present invention includes:

[0035] Step 101: Establish a digital twin model of the engine.

[0036] In one embodiment, establishing a digital twin model of the engine may include: establishing a digital twin model of the engine body, specifically including the engine's structural and strength model, high / low pressure compressor aerodynamic model, aerodynamic and thermodynamic model, and performance model of the engine as a whole and its control system.

[0037] In one embodiment, after the digital twin model of the engine body is established, the established model is simplified and lightweighted. Specifically, this may include: model format conversion, omitting or simplifying non-critical feature information of the model, deleting unnecessary components, and abstracting and simplifying the mathematical expressions of physical phenomena and working environment characteristics in the model. Simplifying and lightweighting the engine body model can reduce the computational load of the model, thereby enabling rapid simulation of the engine using the digital twin model.

[0038] In one embodiment, the establishment of the digital twin model of the engine may further include: the establishment of a digital twin model of an external entity that interacts with the engine body during its operation, wherein the external entity specifically includes tools, equipment, machines, personnel and environment involved in the operation of the engine body.

[0039] Meanwhile, the digital twin model of the engine can also include: a digital twin model of the engine itself and a digital twin model of the external entity integrated and connected through interfaces and algorithms. For example, FMI (functional mock-up interface) can be used for model conversion to connect different types of models, a unified interface protocol can be used to integrate models, and intelligent algorithms can be used to couple upstream and downstream models to achieve joint simulation of the physical space activities of aero-engine products.

[0040] Please return to Figure 1 The evaluation and correction method 100 for the engine digital twin model provided by the present invention further includes:

[0041] Step 102: Acquire and process the physical space data required for the operation of the digital twin model.

[0042] In one embodiment, acquiring and processing the physical space data required for the operation of the digital twin model includes configuring multiple data acquisition devices in the engine body, the physical space environment in which the engine is located, and external entities that interact with the engine body.

[0043] For example, vibration sensors, pressure sensors, temperature sensors, speed sensors, and audio-visual equipment can be configured in the physical space of the engine.

[0044] This system uses multiple data acquisition devices to acquire physical space data from different sources and in different formats. For example, the data can be structured, semi-structured, or unstructured. Structured data includes time-series data acquired by sensors; semi-structured data includes operation and maintenance logs and fault information logs; and unstructured data includes acquired audio and video data.

[0045] These data acquisition devices are configured within the engine itself and can be integrated with the engine's control system to acquire performance and status data generated by the engine, including manufacturing and assembly data, flight and route data, fuel data, and control data. Sensors can also be configured in the physical environment in which the engine is located and in external entities that interact with it to acquire operating environment data, such as temperature, humidity, air pressure, altitude, and spatial scene data, as well as behavioral and status data of corresponding external entities such as tools, equipment, machines, and personnel.

[0046] After acquiring multi-source, heterogeneous data through a configured data acquisition device, in one embodiment, acquiring and processing the physical space data required for the operation of the digital twin model may further include: performing preprocessing on the acquired physical space data, including removing redundant and erroneous data, imputing missing data, and removing information irrelevant to the analysis; performing data integration and transformation on the preprocessed data, including extracting and integrating to form time-series data, converting data formats to meet the input requirements of simulation analysis, and converting data representation methods to compress data; and marking the processed physical space data according to its source and purpose, adding data tags, and storing it locally and in the cloud for transmission to the digital twin model for simulation. After acquiring the data, the simulation of the digital twin model can be started based on this data.

[0047] Please continue to refer to this. Figure 1 The evaluation and correction method 100 for the engine digital twin model provided by the present invention further includes:

[0048] Step 103: Transmit the physical space data to the digital twin model for simulation, and evaluate the digital twin model based on the simulation timeliness and the accuracy of the simulation results.

[0049] Based on the input data types and requirements of the digital twin model simulation, physical space data is extracted from the database and transmitted to the virtual space. The digital twin model is then used to simulate the behavior and state of the physical space of the aero-engine product.

[0050] In one embodiment, evaluating the digital twin model based on simulation timeliness and simulation result accuracy may include: determining maximum time thresholds for the simulation time of a single activity, the simulation time of coupled activities, and the overall total simulation time in the simulation activities of the digital twin model, where a single activity refers to a single simulation activity of a single digital twin sub-model, a coupled activity refers to a single coupled activity between multiple digital twin sub-models, and the overall total simulation time refers to the time required for the digital twin model to complete all simulation activities; and evaluating the digital twin model based on simulation timeliness, where simulation timeliness means that in the simulation activities of the digital twin model, the simulation time of a single activity, the simulation time of coupled activities, and the overall total simulation time do not exceed their respective maximum time thresholds.

[0051] For example, determining the maximum time threshold allowed for a single simulation process of a digital twin simulation model, that is, the maximum time consumed by a single digital twin sub-model to perform a single simulation activity, can be expressed as:

[0052]

[0053] In the formula, This indicates that the m-th digital twin model performs the m-th... n The maximum time threshold for a simulation activity.

[0054] Simultaneously, the maximum allowable time threshold for the coupled simulation process of the digital twin simulation model, which is the maximum time consumed in simulating a single coupled activity between multiple digital twin sub-models, can be expressed as:

[0055]

[0056] In the formula, This indicates that the r-th digital twin model performs the r-th... s The maximum time threshold required for the coupled simulation activity.

[0057] Furthermore, it is also necessary to determine the maximum time threshold allowed for simulating all actual physical activities of an aero-engine, that is, the time required for the digital twin model to complete all simulation processes of physical activities is expressed as:

[0058]

[0059] In the formula, This represents the maximum simulation time threshold required for the a-th physical activity.

[0060] Next, the actual simulation time for the physical activities of aero-engine products using a digital twin model should be calculated. This should meet the requirements for the simulation time of individual or coupled activities, as well as the total simulation time. In other words, this is the timeliness requirement of the digital twin model, which can be expressed by the formula:

[0061]

[0062] In the formula, This represents the actual simulation time required for the digital twin model of the engine to complete each individual or coupled activity when performing this physical activity. This represents the total simulation time of the digital twin model. It can be seen that the preset timeliness requirement can only be met if the actual simulation time of a single or coupled activity is less than its respective maximum time threshold, and the total simulation time of all activities is less than the maximum time threshold of the overall total simulation time.

[0063] In addition to timeliness, the evaluation and correction method for engine digital twin models provided by this invention also evaluates the accuracy of the simulation results of the digital twin models.

[0064] In one embodiment, the evaluation of the digital twin model based on simulation timeliness and simulation result accuracy may further include: in response to the simulation timeliness meeting preset conditions, determining the simulated values ​​of multiple single key performance indicators in the digital twin model and their corresponding actual values ​​in the engine, wherein the single key performance indicators include dimensional accuracy, roughness, and strength indicators during engine manufacturing and assembly, and starting performance, thrust performance, and emission performance indicators during engine operation and maintenance; determining the comprehensive performance indicator of the digital twin model based on the multiple single key performance indicators; and evaluating the digital twin model based on the simulation result accuracy, wherein the simulation result accuracy refers to the deviation between the simulated value and the actual value of each single key performance indicator meeting the preset deviation range of the single key performance indicator, and the comprehensive performance indicator not exceeding a preset comprehensive performance threshold.

[0065] For example, a single key performance indicator of the digital twin model simulation results can be determined first. This could be dimensional accuracy, roughness, and strength indicators during engine manufacturing and assembly, or starting performance, thrust performance, or emission performance indicators during engine operation and maintenance. This can be expressed as:

[0066]

[0067] In the formula, This represents the simulated value of the j-th key indicator.

[0068] Then, through the multiple data acquisition devices set up in the previous steps, the actual values ​​of the key performance indicators of the aero-engine product are obtained, and expressed as follows:

[0069]

[0070] In the formula, This represents the actual value of the j-th key indicator of the aero-engine product.

[0071] Next, the preset deviation range for each individual key performance indicator of the aero-engine is determined, which is the maximum allowable range of deviation between the actual value and the simulated value of each individual key performance indicator. This can be expressed as:

[0072]

[0073] In the formula, This represents the preset deviation range of the j-th key indicator of the aero-engine. The preset deviation range is determined based on engineering experience and actual simulation requirements, and can be an interval value or a value with uncertainty.

[0074] Furthermore, the degree to which individual key performance indicators (KPIs) are met in the digital twin model is evaluated. All KPIs must meet preset accuracy requirements, which can be expressed by the formula:

[0075]

[0076] The accuracy of a digital twin model requires evaluation of not only individual key performance indicators (KPIs) but also comprehensive performance indicators. In one embodiment, determining the comprehensive performance indicator of the digital twin model based on these multiple KPIs may include: determining the degree of deviation between the simulated and actual values ​​of each KPI according to the following formula:

[0077]

[0078] in, This indicates the degree of deviation between the simulated value and the actual value of the j-th single key performance indicator. This represents the simulated value of the j-th single key performance indicator. This represents the actual value of the j-th single key performance indicator (KPI) corresponding to the simulated value. The deviations of all KPIs are regularized; a larger relative deviation indicates worse model performance.

[0079] Next, the weight value of each individual key performance indicator in the digital twin model is determined using the analytic hierarchy process (AHP), and the overall performance indicator is calculated according to the following formula:

[0080]

[0081] Among them, perform simu For this comprehensive performance index of the digital twin model, w j This represents the weight value corresponding to the j-th single key performance indicator. It's easy to understand that the smaller the overall performance indicator value, the better the overall performance.

[0082] After calculating the simulated values ​​of the comprehensive performance index, the maximum allowable threshold for the comprehensive performance index of the digital twin model is determined, i.e., the preset comprehensive performance threshold, which can be expressed as:

[0083] perform_β

[0084] Then, the overall performance of the digital twin model can be evaluated. The simulated value of the overall performance index should not exceed the preset overall performance threshold, which can be expressed by the formula:

[0085] perform simu ≤perform_β

[0086] Once the evaluation is completed, the digital twin model can be revised based on the evaluation results, and simulation results that meet the preset requirements can be output.

[0087] Please return to Figure 1 The evaluation and correction method 100 for the engine digital twin model provided by the present invention further includes:

[0088] Step 104: Based on the evaluation results, revise the digital twin model and output simulation results that meet the preset requirements.

[0089] In one embodiment, if the simulation results meet the preset requirements for timeliness and accuracy, the output of the simulation results that meet the preset requirements may include: in response to the simulation results meeting the preset requirements for timeliness and accuracy, displaying the simulation results in real time through three-dimensional visual, VR and AR tools to achieve the synchronous mapping simulation of the engine and its physical space activities by the above-mentioned digital twin model.

[0090] If the simulation results do not meet the preset requirements, the digital twin model needs to be corrected based on the evaluation results. In one embodiment, correcting the digital twin model based on the evaluation results may include: if the simulation timeliness of the digital twin model does not meet the preset requirements, the digital twin model requests more memory and bandwidth resources to correct the digital twin model and improve the simulation speed; if the simulation result accuracy of the digital twin model does not meet the preset requirements, the acquired physical space data is added to the model training library, and the model is retrained based on the new physical space data to optimize the parameters of the digital twin model and correct the model; and the simulation timeliness and simulation result accuracy of the corrected digital twin model are further evaluated, and in response to the corrected model meeting the preset requirements, the corrected digital twin model is uploaded to the cloud for use.

[0091] In one embodiment, the modification of the digital twin model based on the evaluation results may further include: in response to the fact that the simulation timeliness or the accuracy of the simulation results of the modified digital twin model still does not meet the preset requirements, generating model warning information to push to the operation and maintenance personnel of the digital twin model, so that the digital twin model can be manually reconstructed.

[0092] Figure 2 This is a schematic flowchart illustrating a method for correcting a digital twin model of an engine according to an embodiment of the present invention.

[0093] like Figure 2 As shown, in one embodiment, steps 201 and 202 are first executed: the physical space data is transmitted to the digital twin model, and the model and data are invoked to carry out the simulation work.

[0094] Next, step 203 is executed: determine whether the simulation of the digital twin model meets the preset timeliness requirements. If the timeliness does not meet the requirements, then step 204 is executed: adaptively correct and update the timeliness of the digital twin model. Specifically, this may include the digital twin model initiating a request to obtain more memory and bandwidth resources, thereby improving the simulation speed of the digital twin model.

[0095] If the simulation timeliness of the digital twin model meets the preset requirements, proceed to step 205: determine whether the simulation results of the digital twin model meet the preset accuracy requirements. If they do, proceed to step 206: perform adaptive correction and update of the accuracy of the digital twin model, specifically, for example, putting newly acquired data into the model training library, retraining and correcting the parameters of the digital twin model based on the new model training library to improve the accuracy of the model simulation.

[0096] If the accuracy of the digital twin model also meets the preset requirements, proceed to step 207: output simulation results that meet the preset requirements. For example, simulation results can be presented to users in real time using tools and methods such as 3D visualization, VR, and AR, realizing synchronous mapping simulation of physical space activities by the digital twin model of the aero-engine.

[0097] After completing steps 204 and 206 respectively, step 208 needs to be executed: determine whether the corrected digital twin model meets the preset requirements for timeliness and accuracy. If it does, proceed to step 209: upload and store the digital twin model that meets the preset requirements to the cloud for future use.

[0098] If the timeliness and accuracy of the corrected model still do not meet the preset requirements, then steps 210 and 211 are executed: an early warning message is generated and uploaded to the operation and maintenance personnel of the digital twin model, and the model is reconstructed and verified by manual intervention. The manually corrected and optimized model that meets the conditions is then uploaded to the cloud for future use.

[0099] Although the methods described above are illustrated and depicted as a series of actions for the sake of simplicity, it should be understood and appreciated that these methods are not limited by the order of the actions, as some actions may occur in a different order and / or concurrently with other actions from the illustrations and descriptions herein or not illustrated and described herein but which may be understood by those skilled in the art, according to one or more embodiments.

[0100] Figure 3 This is a schematic diagram of the device structure for evaluating and correcting an engine digital twin model, according to another aspect of the present invention.

[0101] like Figure 3 As shown, another aspect of the present invention provides an evaluation and correction apparatus 300 for an engine digital twin model, comprising: a memory 301; and a processor 302 coupled to the memory 301, the processor 302 being configured to perform the steps of the evaluation and correction method for the engine digital twin model described in any of the above.

[0102] According to another aspect of the invention, an embodiment of a computer storage medium is also provided herein.

[0103] The computer storage medium contains a computer program. When executed by a processor, this computer program can implement the steps of any of the aforementioned evaluation and correction methods for engine digital twin models.

[0104] Those skilled in the art will understand that information, signals, and data can be represented using any of a variety of different techniques and arts. For example, the data, instructions, commands, information, signals, bits, symbols, and chips described throughout the above description can be represented by voltage, current, electromagnetic waves, magnetic fields or magnetic particles, light fields or optical particles, or any combination thereof.

[0105] Those skilled in the art will further appreciate that the various illustrative logic blocks, modules, circuits, and algorithm steps described in conjunction with the embodiments disclosed herein can be implemented as electronic hardware, computer software, or a combination of both. To clearly illustrate this interchangeability between hardware and software, the various illustrative components, blocks, modules, circuits, and steps are described above in a generalized manner in terms of their functionality. Whether such functionality is implemented as hardware or software depends on the specific application and the design constraints imposed on the overall system. Those skilled in the art may implement the described functionality in different ways for each specific application, but such implementation decisions should not be construed as departing from the scope of the invention.

[0106] The processors described herein can be implemented using electronic hardware, computer software, or any combination thereof. Whether such processors are implemented as hardware or software will depend on the specific application and the overall design constraints imposed on the system. As an example, the processors, any portion thereof, or any combination thereof presented in this disclosure can be implemented using microprocessors, microcontrollers, digital signal processors (DSPs), field-programmable gate arrays (FPGAs), programmable logic devices (PLDs), state machines, gated logic, discrete hardware circuitry, and other suitable processing components configured to perform the various functions described throughout this disclosure. The functionality of the processors, any portion thereof, or any combination thereof presented in this disclosure can be implemented using software executed by a microprocessor, microcontroller, DSP, or other suitable platform.

[0107] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of both. The software module may reside in RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium known in the art. An exemplary storage medium is coupled to a processor such that the processor can read and write information to / from the storage medium. In an alternative, the storage medium may be integrated into the processor. The processor and storage medium may reside in an ASIC. The ASIC may reside in a user terminal. In an alternative, the processor and storage medium may reside as discrete components in the user terminal.

[0108] In one or more exemplary embodiments, the described functionality may be implemented in hardware, software, firmware, or any combination thereof. If implemented in software as a computer program product, the functionality may be stored or transmitted as one or more instructions or code on or through a computer-readable medium. A computer-readable medium includes both computer storage media and communication media, encompassing any medium that facilitates the transfer of a computer program from one location to another. A storage medium may be any available medium accessible to a computer. By way of example and not limitation, such a computer-readable medium may include RAM, ROM, EEPROM, CD-ROM or other optical disc storage, disk storage or other magnetic storage devices, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and is accessible to a computer. Any connection is also legitimately referred to as a computer-readable medium. For example, if the software is transmitted from a website, server, or other remote source using coaxial cable, fiber optic cable, twisted pair, digital subscriber line (DSL), or wireless technologies such as infrared, radio, and microwave, then the coaxial cable, fiber optic cable, twisted pair, DSL, or wireless technologies such as infrared, radio, and microwave are included in the definition of a medium. As used in this article, disk and disc include compact discs (CDs), laser discs, optical discs, digital multi-purpose discs (DVDs), floppy disks, and Blu-ray discs. Disks typically reproduce data magnetically, while discs reproduce data optically using lasers. Combinations of these should also be included within the scope of computer-readable media.

[0109] The prior description of this disclosure is provided to enable any person skilled in the art to make or use this disclosure. Various modifications to this disclosure will be apparent to those skilled in the art, and the general principles defined herein may be applied to other variations without departing from the spirit or scope of this disclosure. Therefore, this disclosure is not intended to be limited to the examples and designs described herein, but should be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for evaluating and correcting a digital twin model of an engine, comprising: Establish a digital twin model of the engine; Acquire and process the physical space data required for the operation of the digital twin model; The physical space data is transmitted to the digital twin model for simulation, and the digital twin model is evaluated based on the simulation timeliness and the accuracy of the simulation results. as well as The digital twin model is revised based on the evaluation results, and simulation results that meet the preset requirements are output. The evaluation of the digital twin model based on simulation timeliness and simulation result accuracy includes: In the simulation activities of the digital twin model, maximum time thresholds are determined for the simulation time of a single activity, the simulation time of coupled activities, and the overall total simulation time. A single activity refers to a single simulation activity of a single digital twin sub-model; a coupled activity refers to a single coupled activity between multiple digital twin sub-models; and the overall total simulation time refers to the time required for the digital twin model to complete all simulation activities. The digital twin model is evaluated based on the simulation timeliness, where simulation timeliness refers to the fact that the simulation time of a single activity, the simulation time of coupled activities, and the overall total simulation time in the simulation activities of the digital twin model do not exceed their respective maximum time thresholds. The evaluation of the digital twin model based on simulation timeliness and simulation result accuracy also includes: In response to the simulation timeliness meeting the preset conditions, the simulation values ​​of multiple single key performance indicators in the digital twin model and their corresponding actual values ​​in the engine are determined. The single key performance indicators include dimensional accuracy, roughness and strength indicators in the engine manufacturing and assembly process, as well as starting performance, thrust performance and emission performance indicators in the engine operation and maintenance process. The comprehensive performance index of the digital twin model is determined based on the multiple single key performance indicators; and The accuracy of the digital twin model is evaluated based on the simulation results. The accuracy of the simulation results refers to the fact that the deviation between the simulated value and the actual value of each individual key performance indicator meets the preset deviation range of that individual key performance indicator, and the comprehensive performance indicator does not exceed the preset comprehensive performance threshold.

2. The evaluation and correction method as described in claim 1, characterized in that, The establishment of the digital twin model of the engine includes: Establish a digital twin model of the engine body, specifically including the engine's structural and strength model, high / low pressure compressor aerodynamic model, aerodynamic and thermodynamic model, and the overall performance model of the engine and its control system; A digital twin model is established for external entities that interact with the engine body during its operation. These external entities specifically include tools, equipment, machines, personnel, and the environment involved in the engine body's operation. The digital twin model of the engine body and the digital twin model of the external entity are integrated and connected through interfaces and algorithms.

3. The evaluation and correction method as described in claim 2, characterized in that, The establishment of the digital twin model of the engine body also includes: After the digital twin model of the engine body is established, the established model is simplified and lightweighted, specifically including: model format conversion, omitting or simplifying non-critical feature information of the model, deleting unnecessary components, and abstracting and simplifying the mathematical expression of physical phenomena and working environment features in the model.

4. The evaluation and correction method as described in claim 1, characterized in that, The determination of the comprehensive performance index of the digital twin model based on the multiple single key performance indicators includes: The degree of deviation between the simulated and actual values ​​of each individual key performance indicator is determined using the following formula: in, This indicates the degree of deviation between the simulated value and the actual value of the j-th single key performance indicator. This represents the simulated value of the j-th single key performance indicator. Represents the actual value of the j-th single key performance indicator corresponding to the simulation value; and The weight value of each individual key performance indicator in the digital twin model is determined using the analytic hierarchy process (AHP), and the comprehensive performance indicator is calculated according to the following formula: Among them, perform simu The comprehensive performance index of the digital twin model is... This represents the weight value corresponding to the j-th single key performance indicator.

5. The evaluation and correction method as described in claim 1, characterized in that, The process of revising the digital twin model based on the evaluation results includes: If the simulation timeliness of the digital twin model does not meet the preset requirements, the digital twin model requests more memory and bandwidth resources to correct the digital twin model and improve the simulation speed. If the accuracy of the simulation results of the digital twin model does not meet the preset requirements, the acquired physical space data is added to the model training library, and the model is retrained based on the new physical space data to optimize the parameters of the digital twin model and correct the model; and Continue to evaluate the simulation timeliness and the accuracy of the simulation results of the revised digital twin model. In response to the revised model meeting the preset requirements, upload the revised digital twin model to the cloud for use.

6. The evaluation and correction method as described in claim 5, characterized in that, The process of revising the digital twin model based on the evaluation results also includes: If the simulation timeliness or the accuracy of the simulation results of the corrected digital twin model still does not meet the preset requirements, a model warning message is generated and pushed to the operation and maintenance personnel of the digital twin model, so that the digital twin model can be manually reconstructed.

7. The evaluation and correction method as described in claim 1, characterized in that, The acquisition and processing of the physical space data required for the operation of the digital twin model includes: Multiple data acquisition devices are configured in the engine body, the physical space environment in which the engine is located, and external entities that interact with the engine body; The physical space data from different sources and in different formats are acquired using the multiple data acquisition devices.

8. The evaluation and correction method as described in claim 1, characterized in that, The acquisition and processing of the physical space data required for the operation of the digital twin model also includes: The acquired physical space data is preprocessed, including removing redundant and erroneous data, imputing missing data, and removing information irrelevant to the analysis. The preprocessed data undergoes data integration and transformation, including extraction and integration to form time-series data, conversion of data formats to meet the input requirements of simulation analysis, and conversion of data representation to compress the data; and The processed physical space data is labeled according to its source and purpose, data tags are added, and the data is stored locally and in the cloud for transmission to the digital twin model to perform simulation work.

9. The evaluation and correction method as described in claim 1, characterized in that, The output simulation results that meet the preset requirements include: In response to the simulation results meeting the preset requirements of simulation timeliness and accuracy, the simulation results are displayed in real time using 3D visuals, VR, and AR tools to achieve synchronous mapping simulation of the engine and its physical space activities by the aforementioned digital twin model.

10. An evaluation and correction device for a digital twin model of an engine, comprising: Memory; as well as A processor coupled to the memory, the processor being configured to perform the steps of the evaluation and correction method for the digital twin model of the engine as described in any one of claims 1 to 9.

11. A computer-readable medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the evaluation and correction method for the engine digital twin model as described in any one of claims 1 to 9.

Images