Metrology traceability method, apparatus, computer device, storage medium and program product

Abstract

The application relates to a metrological traceability method and device, computer equipment, a storage medium and a program product. The method comprises the following steps: obtaining measurement values of a plurality of measurement parameters corresponding to each measured component of an aero-engine, the measurement values comprising first measurement values of each measured component in a static state and second measurement values of each measured component in a running state; for each measured component, determining static error data corresponding to the measured component according to the first measurement values and a plurality of preset reference measurement sets, and determining dynamic difference data corresponding to the measured component according to the first measurement values and the second measurement values; and determining a metrological traceability result of the measured component according to the static error data, the dynamic difference data and a preset longitudinal and transverse nested network. The method can improve the accuracy of the metrological traceability result when the civil aero-engine is in a running state.

Description

Technical Field

[0001] This application relates to the field of aero-engine technology, and in particular to a metrological traceability method, apparatus, computer equipment, storage medium, and program product. Background Technology

[0002] In the field of civil aviation engines, to ensure the reliability and safety of aviation engines, it is necessary to conduct metrological traceability of the measurement parameters of the core tested components of aviation engines. Metrological traceability refers to tracing the accuracy of measurement results through an uninterrupted, documented chain of evidence, all the way back to national or international measurement standards.

[0003] In traditional technology, parameters of the core components of an aero-engine are typically measured under static conditions, and then the measurement results are used for metrological traceability.

[0004] However, the accuracy of the above-mentioned measurement traceability method is low when the civil aircraft engine is in operation. Summary of the Invention

[0005] Therefore, it is necessary to provide a metrological traceability method, device, computer equipment, storage medium, and program product that can improve the accuracy of metrological traceability results when civil aircraft engines are in operation, in order to address the above-mentioned technical problems.

[0006] Firstly, this application provides a method for metrological traceability. The method includes:

[0007] The measured values ​​of multiple measurement parameters corresponding to each tested component of the aero-engine are obtained. The measured values ​​include a first measured value of each tested component in a static state and a second measured value in an operating state.

[0008] For each of the tested components, static error data corresponding to the tested component is determined based on the first measured value and a preset multi-level benchmark measurement set, and dynamic difference data corresponding to the tested component is determined based on the first measured value and the second measured value.

[0009] The metrological traceability results of the tested component are determined based on the static error data, the dynamic difference data, and the preset nested network.

[0010] In one embodiment, the nested network includes a horizontal nested transformation subnetwork and a vertical difference feature extraction subnetwork. Determining the metrological traceability result of the tested component based on the static error data, the dynamic difference data, and the preset nested network includes:

[0011] The static error data is input into the horizontally nested transformation sub-network to obtain the horizontal error characteristics output by the horizontally nested transformation sub-network;

[0012] The dynamic difference data is input into the longitudinal difference feature extraction subnetwork to obtain the longitudinal correction features output by the longitudinal difference feature extraction subnetwork;

[0013] The metrological traceability result is determined based on the horizontal error characteristics and the vertical correction characteristics.

[0014] In one embodiment, determining the metrological traceability result based on the lateral error characteristic and the longitudinal correction characteristic includes:

[0015] Calculate the product between the lateral error feature and the longitudinal correction feature;

[0016] Calculate the difference between the product and a preset benchmark error threshold;

[0017] If the difference is less than or equal to 0, then the measurement traceability result is determined to be successful.

[0018] If the difference is greater than 0, the measurement traceability result is determined to be a traceability failure.

[0019] In one embodiment, the laterally nested transformation subnetwork includes multiple cascaded physical field influence encoders; the step of inputting the static error data into the laterally nested transformation subnetwork to obtain lateral error features includes:

[0020] The static error data is input into the first-level physical field influence encoder in the plurality of cascaded physical field influence encoders to obtain the first-level error characteristics;

[0021] The first-level error feature is input into the next-level physical field influence encoder of the first-level physical field influence encoder, until the lateral error feature output by the last-level physical field influence encoder in the plurality of cascaded physical field influence encoders is obtained.

[0022] In one embodiment, the longitudinal difference feature extraction subnetwork includes a feature extraction module and a feature recombination module. The step of inputting the dynamic difference data into the longitudinal difference feature extraction subnetwork to obtain longitudinally corrected features includes:

[0023] The dynamic difference data is input into the feature extraction module to obtain the perturbation feature vector corresponding to the dynamic difference data output by the feature extraction module;

[0024] The perturbation feature vector is input into the feature recombination module to obtain the longitudinally corrected feature output by the feature recombination module.

[0025] In one embodiment, the first measurement value includes multiple static measurement values ​​obtained by performing static measurements on the component under test using multiple measuring devices, and the step of determining the static error data corresponding to the component under test based on the first measurement value includes:

[0026] Based on the multi-level benchmark measurement set, benchmark measurement values ​​of benchmark measurement devices at multiple traceability levels are obtained, wherein the multi-level benchmark measurement set includes the benchmark measurement value corresponding to each benchmark measurement device;

[0027] For each measurement parameter, a target reference measurement value for the reference measurement device under the multiple traceability levels corresponding to the measurement parameter is determined, and a first difference between the static measurement value corresponding to the measurement parameter and each target reference measurement value is calculated respectively.

[0028] The first element in the static error data is determined based on each of the first differences, and the coordinate position of the first element in the static error data is determined by the measurement parameters, the identifier of the measurement device, and the traceability level index of the reference measurement device.

[0029] In one embodiment, the second measurement value includes multiple dynamic measurement values ​​obtained by dynamically measuring the component under test using multiple measuring devices. The step of calculating the dynamic difference data corresponding to the component under test based on the first measurement value and the second measurement value includes:

[0030] For each of the measurement parameters, calculate a second difference between the dynamic measurement value corresponding to the measurement parameter and the first measurement value corresponding to the measurement parameter;

[0031] The second element in the dynamic difference data is determined based on the second difference, and the second element is the element at the coordinate position of the measuring device and the measuring parameter index.

[0032] Secondly, this application also provides a metrological traceability device. The device includes:

[0033] The acquisition module is used to acquire the measurement value of at least one measurement parameter corresponding to each tested component of the aero-engine, the measurement value including a first measurement value of each tested component in a static state and a second measurement value in an operating state;

[0034] The first determining module is used to determine, for each of the tested components, the static error data corresponding to the tested component based on the first measured value and a preset multi-level benchmark measurement set, and the dynamic difference data corresponding to the tested component based on the first measured value and the second measured value.

[0035] The second determining module is used to determine the metrological traceability result of the tested component based on the static error data, the dynamic difference data, and the preset nested network. The nested network includes a horizontal nested transformation sub-network and a vertical difference feature extraction sub-network.

[0036] Thirdly, this application also provides a computer device. The computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the steps of the method described in the first aspect.

[0037] Fourthly, this application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program thereon, which, when executed by a processor, implements the steps of the method described in the first aspect.

[0038] Fifthly, this application also provides a computer program product. The computer program product includes a computer program that, when executed by a processor, implements the steps of the method described in the first aspect.

[0039] The aforementioned metrological traceability method, apparatus, computer equipment, computer-readable storage medium, and computer program product first acquire the measured values ​​of multiple measurement parameters corresponding to each tested component of the aero-engine. These measured values ​​include a first measured value for each tested component in a static state and a second measured value in an operational state. Then, for each tested component, static error data is determined based on the first measured value and a preset multi-level benchmark measurement set, and dynamic difference data is determined based on the first and second measured values. Finally, based on the static error data, dynamic difference data, and a preset nested network, [the system] determines... The metrological traceability results of the tested components enable deep fusion and joint analysis of the first measurement value under static conditions and the second measurement value under operational conditions of the aero-engine. By simulating the interference environment under operational conditions through a nested network, it overcomes the problem of difficulty in achieving accurate traceability in the high-temperature, high-pressure, and high-vibration operating environment of the engine, which is difficult to achieve in traditional methods. Thus, it is possible to achieve high-precision and high-efficiency evaluation of the metrological traceability results of the tested components of the engine under operational conditions without deploying high-cost and high-precision benchmark measurement devices, thereby improving the credibility of the metrological traceability results and thus improving the accuracy of the metrological traceability results. Attached Figure Description

[0040] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0041] Figure 1 This is a diagram illustrating the application environment of a metrological traceability method in one embodiment.

[0042] Figure 2 This is a flowchart illustrating a metrological traceability method in one embodiment;

[0043] Figure 3 This is a flowchart illustrating step 203 in one embodiment;

[0044] Figure 4 This is a flowchart illustrating step 303 in one embodiment;

[0045] Figure 5 This is a flowchart illustrating step 301 in one embodiment;

[0046] Figure 6 This is a flowchart illustrating step 302 in one embodiment;

[0047] Figure 7 This is a flowchart illustrating step 202 in one embodiment;

[0048] Figure 8 This is a flowchart illustrating step 202 in another embodiment;

[0049] Figure 9 This is a schematic diagram of the structure of a nested network in one embodiment;

[0050] Figure 10 This is a structural block diagram of a metering traceability device in one embodiment;

[0051] Figure 11 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0052] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0053] Core components of civil aero engines include blades, turbines, and combustion chambers. Each core component has numerous measurement parameters, requiring complex measuring equipment. For example, rotor assembly measurement parameters may include dynamic balance accuracy, journal roundness, and mounting edge flatness; blade assembly measurement parameters may include blade thickness, tip clearance, and tenon position accuracy; combustion chamber assembly measurement parameters may include flame tube wall temperature distribution, fuel nozzle flow rate, and vortex generator angle deviation; turbine assembly measurement parameters may include interstage axial clearance, blade mounting angle, and rotor radial runout. Typical measuring equipment includes rigid-support dynamic balancing machines, online dynamic balancing systems, infrared thermal imagers, oil particle counters, eddy current sensors, fiber optic grating sensors, diode laser thermometers, radiation pyrometers, high-temperature pressure probes, laser Doppler velocimeters, laser Doppler vibration meters, and capacitive tip clearance sensors. Typically, after measuring the core component parameters under static conditions, the accuracy of the measured values ​​is assessed using metrological traceability methods.

[0054] Existing engine metrology traceability schemes focus on key performance parameters, tracing measurement results back to national / international standards through a tiered calibration chain. For example, power parameters (power, torque) can be traced to national force / speed standards using calibrated dynamometers and torque meters; economic parameters (fuel consumption) can be traced to mass / volume standards using metrology-certified flow meters; emission parameters (CO, NOx, etc.) can be traced to national gas concentration standards using gas analyzers compliant with ISO or national standards; and reliability parameters such as vibration and temperature can be traced to vibration or temperature standards using calibrated sensors. The entire process is ensured by regular standard value transfers (e.g., by national / provincial metrology institutes) and laboratory proficiency testing (CNAS accreditation), guaranteeing the controllability of measurement uncertainty and forming an uninterrupted traceability chain of "measuring equipment - calibration standard - national standard."

[0055] However, existing engine metrology traceability schemes have several limitations. First, they lack adaptability to complex operating conditions, with limited coverage of traceability standards for transient responses and dynamic parameters (such as instantaneous fuel consumption and variable load emissions) under extreme environments (such as high temperature and high pressure, and high altitude), making it difficult to fully match actual testing scenarios. Second, the coordination of multiple parameters is weak; the traceability of indicators such as power, economy, and emissions is often carried out independently, lacking a comprehensive assessment of cross-parameter correlation errors, which affects the consistency of overall engine performance evaluation. Third, the adaptation to emerging technologies is lagging behind; the metrology traceability standards for electrified engines (such as electric drive system efficiency and battery thermal management parameters) are not yet perfect, and traditional internal combustion engine schemes are difficult to directly extend. Fourth, on-site calibration is difficult; there are deviations between high-precision laboratory standards and actual usage environments (such as vibration and electromagnetic interference), and the equipment and methods for rapid on-site calibration still need optimization. Fifth, there is a conflict between cost and efficiency; frequent testing of high-precision instruments (such as dynamometers and gas analyzers) is time-consuming and labor-intensive, putting small and medium-sized enterprises under resource pressure, and the traceability of some low-frequency parameters is easily simplified.

[0056] Furthermore, civil aircraft engines, due to their complex structure and the challenges of high-temperature, high-pressure, and high-frequency dynamic testing, experience distortions in measurement signals caused by the coupling of multiple physical fields (thermal, mechanical, fluid, and magnetic fields) during engine operation. This interference with the traceability of engine measurements is significant. For example, core components typically face extreme environments such as ultra-high temperatures (2000-3000℃), ultra-high pressures (30-50 atm), high speeds (tens of thousands of rpm), and strong vibrations (above 100g). Under dynamic high-temperature conditions, existing thermocouples (such as type K and type B) are prone to oxidation and failure at ultra-high temperatures, and radiation thermometry is greatly affected by flue gas interference. Traceability to platinum resistance thermometers (PT100) or fixed points (such as metal solidification points) is required. However, the reproducibility accuracy of high-temperature fixed points (such as cobalt-cobalt oxidation points) is only ±0.5℃. Therefore, existing methods of metrological traceability under static conditions are insufficient to meet the traceability requirements under engine operating conditions, resulting in low accuracy of metrological traceability results.

[0057] In view of this, this application proposes a metrological traceability method, which can improve the accuracy of metrological traceability results of measurement parameter values ​​of civil aviation engines under operating conditions by integrating the influence of different physical fields on measurement parameters.

[0058] The metrological traceability method provided in this application can be applied to, for example... Figure 1In the application environment shown, terminal 102 communicates with measuring device 104 via a network. Terminal 102 first acquires the measured values ​​of multiple parameters corresponding to each tested component of the aero-engine. These measured values ​​include a first measured value in a static state and a second measured value in an operational state for each tested component. Then, for each tested component, it determines the corresponding static error data based on the first measured value and a preset multi-level benchmark measurement set, and determines the corresponding dynamic difference data based on the first and second measured values. Finally, based on the static error data, dynamic difference data, and a preset nested network, it determines the metrological traceability result of the tested component. Terminal 102 can be, but is not limited to, various personal computers, laptops, smartphones, tablets, IoT devices, and portable wearable devices. IoT devices can include smart speakers, smart TVs, smart air conditioners, and smart vehicle devices. Portable wearable devices can include smartwatches, smart bracelets, and head-mounted devices. Measuring device 104 can be a pressure sensor, speed sensor, infrared thermometer, laser particle size analyzer, flow meter, or other device used to measure parameters of the tested components of the aero-engine.

[0059] In one exemplary embodiment, such as Figure 2 As shown, a metrological traceability method is provided, which can be applied to... Figure 1 Taking the terminal in the example, the explanation includes the following steps:

[0060] Step 201: Obtain the measured values ​​of multiple measurement parameters corresponding to each tested component of the aero-engine.

[0061] The measured values ​​include the first measured value of each measured component in a static state and the second measured value in an operating state.

[0062] It should be noted that aero-engines include multiple tested components. To ensure the safety and reliability of each component, it is necessary to measure its operating parameters using measuring equipment. Furthermore, to ensure the accuracy of the measurement results, metrological traceability can be used to trace the results. Because the coupling of multiple physical fields (thermal, mechanical, fluid, and magnetic) during engine operation can distort engine measurement signals, interfering with the traceability of engine measurements, this interference can occur. Therefore, by simulating the signal interference caused by physical field coupling based on the measured values ​​of each component in its static state, its operating state, and the corresponding benchmark measurements from the reference equipment, the metrological traceability results can be corrected based on the simulation results, thereby improving the accuracy of the metrological traceability results for aero-engines in operation.

[0063] In this context, the static state refers to the non-working state of the tested component when there is no power input, no relative motion, and it is in a thermally / mechanically stable state, i.e., the shutdown state. The operating state refers to the working state of the tested component when it is in operation, with power input, relative motion, and parameters that change dynamically with operating conditions.

[0064] Optionally, each measuring device may correspond to one or more measurement parameters when measuring the component under test. Each component under test may require one or more measuring devices for measurement; therefore, each component under test will correspond to multiple measurement values. When correcting the metrological traceability results, it is necessary to obtain the measurement values ​​of the multiple measurement parameters corresponding to each component under test. In this embodiment, the measurement value of the component under test in a static state is determined as the first measurement value, and the measurement value of the component under test in an operating state is determined as the second measurement value. For example, the first measurement value may be the measured values ​​of parameters such as rotor speed, rotor temperature, turbine blade size, and turbine blade temperature of the component under test in a static state, and the second measurement value may be the measured values ​​of parameters such as rotor speed, rotor temperature, turbine blade size, and turbine blade temperature of the component under test in an operating state.

[0065] It is understandable that the second measurement value will contain both real measurement information and interference information due to the high temperature, high pressure and vibration caused by the engine being in operation.

[0066] In this embodiment, the terminal can receive the first measurement value measured by each measuring device when the component under test is in a static state, and the second measurement value measured by each measuring device when the component under test is in an operating state, through a wired network or a wireless network.

[0067] Step 202: For each component under test, determine the static error data corresponding to the component under test based on the first measurement value and the preset multi-level benchmark measurement set, and determine the dynamic difference data corresponding to the component under test based on the first measurement value and the second measurement value.

[0068] Among them, the multi-level reference measurement set refers to the set of multiple measurement values ​​obtained by each reference device for each measurement parameter and for each measured component under ideal static conditions.

[0069] It is understandable that the first measured value of the component under test in a static state is the actual measured value, while the multi-level benchmark measurement set is the standard measured value. To determine whether there is an error in the first measured value, it can be determined by comparing the first measured value with the standard measured values ​​in the multi-level benchmark measurement set. In this embodiment, the error between the first measured value and the standard measured values ​​in the multi-level benchmark measurement set is defined as static error data. The static error data can be tensor data, for example, a three-dimensional tensor. The index position of each element in this three-dimensional tensor can be determined by the test parameters, the measuring equipment, and the benchmark measuring equipment at multiple traceability levels corresponding to the multi-level benchmark measurement set. The three-dimensional tensor is used to describe the linear relationship between the three dimensions.

[0070] To determine the interference with the measurement parameters during operation, the interference can be determined based on the first and second measurement values. In this embodiment, the difference between the first and second measurement values ​​is defined as dynamic difference data. This dynamic difference data can be a two-dimensional matrix; for example, the index position of each element in the two-dimensional matrix can be determined by the measurement parameters and the measuring device.

[0071] In this embodiment, the terminal can obtain static error data for each tested component based on the error between the first measured value of the tested component and a preset multi-level benchmark measurement set, and obtain dynamic difference data based on the difference between the tested components determined by the first measured value and the second measured value.

[0072] Step 203: Determine the metrological traceability results of the tested component based on static error data, dynamic difference data, and a preset nested network.

[0073] It should be noted that in actual measurement scenarios, when the engine is running, it is impossible to deploy high-precision measurement equipment that can be directly used for metrological traceability, while the accuracy of measurement parameter values ​​collected by traditional measurement equipment is relatively low. Therefore, neural network models can be used to perform metrological traceability on the measurement results.

[0074] Among them, the nested network is a deep neural network model with specific physical constraints and dual-path information processing capabilities. By integrating theoretical predictions and actual measurement results, the nested network can output predictions that closely approximate the measurement values ​​under real-world operating conditions, thus enabling metrological traceability based on the output of the nested network.

[0075] In this embodiment, the terminal can use static error data and dynamic difference data as input to a nested network. The nested network is used to analyze and process the disturbance factors of the static error data and dynamic difference data to obtain the metrological traceability results of the tested component.

[0076] In some embodiments, static error data can be input into a nested network to obtain intermediate results. Then, the intermediate results and dynamic difference data can be input into the nested network to obtain the metrological traceability results of the tested component.

[0077] In the aforementioned metrological traceability method, the terminal first acquires the measured values ​​of multiple measurement parameters corresponding to each tested component of the aero-engine. The measured values ​​include the first measured value of each tested component in a static state and the second measured value in an operational state. Then, for each tested component, the static error data corresponding to the tested component is determined based on the first measured value and a preset multi-level benchmark measurement set, and the dynamic difference data corresponding to the tested component is determined based on the first and second measured values. Subsequently, the metrological traceability result of the tested component is determined based on the static error data, the dynamic difference data, and a preset nested network. In this way, the first measured value in the static state and the second measured value in the operational state of the aero-engine can be deeply integrated and jointly analyzed. By simulating the interference environment in the operational state through the nested network, the problem of difficulty in achieving accurate traceability in the high-temperature, high-pressure, and high-vibration operating environment of the engine in traditional methods can be overcome. Thus, high-precision and high-efficiency evaluation of the metrological traceability results of the tested components of the engine in the operational state can be achieved without deploying high-cost, high-precision benchmark measurement devices, improving the credibility of the metrological traceability results and thus improving the accuracy of the metrological traceability results.

[0078] In one exemplary embodiment, such as Figure 3 As shown, the nested network includes a horizontal nested transformation subnetwork and a vertical difference feature extraction subnetwork. This embodiment relates to the process by which the terminal determines the metrological traceability result of the tested component based on static error data, dynamic difference data, and a preset nested network. Step 203 includes:

[0079] Step 301: Input the static error data into the horizontally nested transformation sub-network to obtain the horizontal error features output by the horizontally nested transformation sub-network.

[0080] Among them, the horizontally nested transformation subnetwork is a neural network that simulates the multi-physics coupling influence law under engine operation. It can use the output of the previous level as the input of the next level to realize the correlation of different physical field couplings, thereby simulating the multi-physics interference environment brought about by engine operation.

[0081] Among them, the lateral error feature is a feature representation with clear physical semantics generated after the lateral nested transformation sub-network processes the static error data. The lateral error feature can characterize the error variation between the first measurement value and the reference measurement value under different combinations of physical fields.

[0082] In this embodiment, the terminal can input static error data into the horizontally nested transformation sub-network. After the horizontally nested transformation sub-network simulates the static error data, it outputs the horizontal error characteristics.

[0083] Step 302: Input the dynamic difference data into the longitudinal difference feature extraction subnetwork to obtain the longitudinal corrected features output by the longitudinal difference feature extraction subnetwork.

[0084] The longitudinal difference feature extraction subnetwork is a neural network that extracts real perturbation features from the measured dynamic data. By comparing static error data with dynamic difference data, the interfering features that cause errors in the measured values ​​are identified.

[0085] Among them, the longitudinal correction feature is a feature representation extracted from dynamic difference data by the longitudinal difference feature extraction subnetwork. It is used to correct the horizontal theoretical prediction and characterize the disturbance effect under the actual operating state.

[0086] In this embodiment, the terminal can input dynamic difference data into the longitudinal difference feature extraction subnetwork. After the longitudinal difference feature extraction subnetwork simulates the dynamic difference data, it outputs longitudinal correction features.

[0087] Step 303: Determine the metrological traceability results based on the horizontal error characteristics and the vertical correction characteristics.

[0088] It is understandable that the lateral error feature can include multiple feature vectors, and the longitudinal correction feature can also include multiple feature vectors.

[0089] In this embodiment, the terminal can fuse the lateral error features and the longitudinal correction features, and determine the fused result as the metrological traceability result.

[0090] For example, the horizontal error features and the vertical correction features can be added element by element, and the result of the summation can be determined as the measurement traceability result.

[0091] In this embodiment, the terminal inputs static error data into a horizontally nested transformation subnetwork to obtain the horizontal error features output by the horizontally nested transformation subnetwork, and inputs dynamic difference data into a vertical difference feature extraction subnetwork to obtain the vertical correction features output by the vertical difference feature extraction subnetwork. Based on the horizontal error features and the vertical correction features, the terminal can determine the metrological traceability results, effectively realizing the coupling between static error benchmark characteristics and dynamic difference operating condition characteristics. This improves the accuracy and consistency of metrological traceability results under multiple parameters and operating conditions, and enables the output of highly reliable metrological traceability judgment results under extremely complex operating conditions. Without the need to deploy high-cost benchmark measurement equipment, the terminal can achieve high-precision and high-efficiency evaluation of the metrological traceability results of the tested components of the engine in operation.

[0092] In one exemplary embodiment, such as Figure 4 As shown, this embodiment relates to the process by which the terminal determines the metrological traceability result based on the lateral error characteristics and the longitudinal correction characteristics. Step 303 includes:

[0093] Step 401: Calculate the product between the lateral error feature and the longitudinal correction feature.

[0094] It is understandable that the lateral error feature can characterize the contribution of the coupling effect of each physical field to the error value between the first measurement value and the reference measurement value, and the longitudinal correction feature can characterize the error effect of the disturbance signal on the first measurement value. Therefore, the above product can characterize the interaction between the effect strength of the physical field coupling and the significance of the effect strength under actual measurement conditions.

[0095] In this embodiment, the terminal can perform a dot product on the elements at corresponding positions in the lateral error feature and the longitudinal correction feature, and determine the dot product result as the product between the lateral error feature and the longitudinal correction feature.

[0096] Step 402: Calculate the difference between the product and the preset benchmark error threshold.

[0097] The reference error threshold refers to the pre-set maximum permissible error limit value used to determine whether traceability to a specific measurement level has been successful.

[0098] Understandably, this difference can characterize the excess or safety margin relative to the acceptable standard.

[0099] In this embodiment, the terminal can determine the difference by subtracting a preset benchmark error threshold from the product.

[0100] Step 403: If the difference is less than or equal to 0, then the measurement traceability result is determined to be successful.

[0101] Understandably, if the difference is less than or equal to 0, then the error is less than or equal to the maximum allowable value, and therefore, the traceability can be considered successful. Successful traceability means that the error value of the second measurement in the operational state is controllable.

[0102] In this implementation, the terminal can calculate and compare the difference with 0 to obtain the comparison result. If the comparison result is that the difference is less than or equal to 0, the measurement traceability result is determined to be successful.

[0103] Step 404: If the difference is greater than 0, the measurement traceability result is determined to be traceability failure.

[0104] Among them, traceability failure refers to the fact that the error value of the second measurement value in the running state is uncontrollable.

[0105] In this embodiment, the terminal can determine that the error value of the second measurement value is uncontrollable if the difference is greater than 0, thereby determining that the measurement traceability result is traceability failure.

[0106] In this embodiment, the terminal modulates the nonlinearity of dynamic error by calculating the product between the lateral error feature and the longitudinal correction feature, overcoming the deviation that may be caused by simple linear superposition. Then, it calculates the difference between the product and the preset reference error threshold. Thus, when the difference is less than or equal to 0, the measurement traceability result is determined to be successful, and when the difference is greater than 0, the measurement traceability result is determined to be unsuccessful. This enables the provision of efficient, reliable, and reproducible measurement traceability conclusions for the tested components of the aero-engine in operation without human intervention, improving the objectivity, consistency, and credibility of the measurement traceability result determination process.

[0107] In one exemplary embodiment, such as Figure 5 As shown, the laterally nested transformation subnetwork includes multiple cascaded physical field influence encoders. This embodiment relates to the process by which the terminal inputs static error data into the laterally nested transformation subnetwork to obtain the laterally error features. Step 301 above includes:

[0108] Step 501: Input the static error data into the first-stage physical field influence encoder in the multiple cascaded physical field influence encoders to obtain the first-stage error characteristics.

[0109] It should be noted that each physical field influence encoder corresponds to the influence law of a specific physical field or combination of physical fields on the measurement error. For example, taking multiple cascaded physical field influence encoders as a 4-layer cascade, they can be respectively included as follows: E1: thermophysical field encoder, used to learn the error change patterns caused by temperature field, thermal expansion, thermal stress, etc.; E2: thermophysical field and fluid physical field encoder, that is, an encoder that superimposes a fluid physical field on the existing thermophysical field; E3: thermophysical field, fluid physical field and magnetic physical field encoder, that is, an encoder that superimposes a magnetic physical field on the existing thermophysical field and fluid physical field; E4: thermophysical field, fluid physical field, magnetic physical field and force physical field encoder, that is, an encoder that superimposes a force physical field on the existing thermophysical field, fluid physical field, and magnetic physical field.

[0110] In this embodiment, the terminal can use static error data as input data and input it into the first-level physical field influence encoder of multiple cascaded physical field influence encoders. In the first-level physical field influence encoder, features related to the current physical field can be extracted from the static error data, and the parameters or state information of the current physical field (such as temperature distribution map, pressure field data, vibration spectrum) are used as conditional input or context to perform fusion calculation with the extracted features, and then an updated feature is output as the first-level error feature.

[0111] Step 502: Input the first-level error feature into the next level physical field influence encoder of the first-level physical field influence encoder, until the lateral error feature of the output of the last level physical field influence encoder in the multiple cascaded physical field influence encoders is obtained.

[0112] It should be noted that for multiple cascaded physical field influence encoders, the output of the previous physical field influence encoder can be sequentially input into the next physical field influence encoder until the output of the last physical field influence encoder is obtained.

[0113] In this embodiment, the terminal can input the first-level error feature into the next-level physical field influence encoder of the first-level physical field influence encoder to obtain a new first-level error feature. Then, the new first-level error feature is input into the next-level physical field influence encoder to obtain a new first-level error feature again. This process is repeated until the output result of the last physical field influence encoder in the multiple cascaded physical field influence encoders is obtained, and the output result is determined as the lateral error feature.

[0114] For example, taking a 4-layer cascade of multiple cascaded physical field influence encoders, the terminal can input the first-level error feature into the second-level physical field influence encoder to obtain the second-level error feature. Then, the second-level error feature is input into the third-level physical field influence encoder to obtain the third-level error feature. Finally, the third-level error feature is input into the fourth-level physical field influence encoder to obtain the lateral error feature.

[0115] In this embodiment, the terminal obtains the first-level error feature by inputting static error data into the first-level physical field influence encoder of multiple cascaded physical field influence encoders. The first-level error feature is then input into the next-level physical field influence encoder of the first-level physical field influence encoder, until the lateral error feature output by the last-level physical field influence encoder of the multiple cascaded physical field influence encoders is obtained. In this way, by simulating the process of physical fields gradually superimposing and coupling in the real environment, and using the processing architecture of cascaded encoders, the dynamic evolution law of static measurement error under multiple physical field conditions is accurately simulated. As a result, the final output lateral error feature integrates the features of multiple physical fields, thereby improving the authenticity of the lateral error feature.

[0116] In one exemplary embodiment, such as Figure 6 As shown, the longitudinal difference feature extraction subnetwork includes a feature extraction module and a feature recombination module. This embodiment relates to how the terminal inputs dynamic difference data into the longitudinal difference feature extraction subnetwork to obtain longitudinally corrected features. Step 302 above includes:

[0117] Step 601: Input the dynamic difference data into the feature extraction module to obtain the perturbation feature vector corresponding to the dynamic difference data output by the feature extraction module.

[0118] Among them, the feature extraction module is a neural network unit that identifies, separates, and encodes various heterogeneous perturbation features from dynamic differential data.

[0119] The perturbation feature vector is a low-dimensional vector output by the feature extraction module after performing in-depth analysis and abstraction of the dynamic difference data. The perturbation feature vector can be used to characterize all key specific perturbations decoded from the dynamic difference data.

[0120] In this embodiment, the terminal can input dynamic difference data into the feature extraction module, and extract features from the dynamic difference data through the convolutional layer, pooling layer and fully connected layer of the feature extraction module to obtain the perturbation feature vector.

[0121] Step 602: Input the perturbation feature vector into the feature recombination module to obtain the longitudinally corrected feature output by the feature recombination module.

[0122] The feature recombination module is used to map and recombine perturbation features into neural network units aligned with the lateral error feature dimension.

[0123] The longitudinal correction feature is a tensor output by the feature reorganization module, with the same dimension as the lateral error feature. Each specific data value at each position in this tensor represents a correction value. The longitudinal correction feature characterizes how the perturbation signal obtained from the actual measurements is allocated to each measurement item to correct the deviation of the lateral theoretical measurements.

[0124] In this embodiment, the terminal can input the perturbation feature vector into the feature recombination module, and perform feature recombination processing on the perturbation feature vector through the fully connected layer of the feature recombination module to obtain the vertically corrected feature.

[0125] In this embodiment, the terminal inputs dynamic difference data into the feature extraction module to obtain the disturbance feature vector corresponding to the dynamic difference data output by the feature extraction module. Then, the disturbance feature vector is input into the feature recombination module to obtain the longitudinal correction feature output by the feature recombination module. This effectively realizes the accurate extraction and structured recombination of disturbance information in dynamic difference data. It not only retains the core feature that the dynamic difference data is strongly correlated with the working condition, but also eliminates the interference of redundant information through feature recombination, thereby improving the pertinence and effectiveness of the longitudinal correction feature. This provides feature support for the dynamic correction of subsequent measurement traceability results, and thus improves the accuracy of measurement traceability results.

[0126] In one exemplary embodiment, such as Figure 7 As shown, the first measurement value includes multiple static measurement values ​​obtained by performing static measurements on the component under test using multiple measuring devices. This embodiment relates to the process by which the terminal determines the static error data corresponding to the component under test based on the first measurement value. Step 202 above includes:

[0127] Step 701: Based on the multi-level benchmark measurement set, obtain the benchmark measurement values ​​of the benchmark measurement devices under multiple traceability levels.

[0128] The multi-level reference measurement set includes the reference measurement values ​​corresponding to each reference measurement device.

[0129] It should be noted that multiple traceability levels can be set according to different metrological traceability accuracies. For each measuring device, a reference measuring device that performs the same measurement function as the measuring device can be set at each traceability level. Therefore, the multi-level reference measurement set can include the device identifier of each reference measuring device at each traceability level, as well as the reference measurement value corresponding to each device identifier. The device identifier of the measuring device is the same as the device identifier of the corresponding reference measuring device.

[0130] Optionally, if a reference measuring device corresponds to multiple measuring parameters, then a reference measuring device corresponds to multiple reference measuring values.

[0131] In this embodiment, the terminal can search for and obtain the device identifiers of multiple reference measurement devices under different traceability levels from the multi-level reference measurement set based on the device identifier of the measurement device, and determine the multiple reference measurement values ​​corresponding to the multiple device identifiers as the reference measurement values ​​of the reference measurement devices under the multiple traceability levels.

[0132] Step 702: For each measurement parameter, determine the target reference measurement value of the reference measurement device under multiple traceability levels corresponding to the measurement parameter, and calculate the first difference between the static measurement value corresponding to the measurement parameter and each target reference measurement value.

[0133] It is understood that the first measurement value may include multiple static measurement values ​​corresponding to multiple measuring devices, and each static measurement value corresponds to the measurement result of a measuring device when the measured component is in a static state.

[0134] Optionally, if a measuring device corresponds to multiple measuring parameters, the result of a static measurement of the measured component by a measuring device includes multiple static measurement values.

[0135] Here, the target benchmark measurement value refers to the benchmark measurement value of the benchmark measuring device corresponding to the measurement parameter. It should be noted that since each measurement parameter corresponds to one measuring device, and one measuring device corresponds to multiple benchmark measuring devices under multiple traceability levels, each measurement parameter can correspond to multiple benchmark measuring devices under multiple traceability levels. Furthermore, since each benchmark measuring device under a traceability level corresponds to one benchmark measurement value, each measurement parameter can correspond to multiple target benchmark measurement values.

[0136] The first difference refers to the difference between the static measurement value and the target benchmark measurement value.

[0137] In this embodiment, taking each measurement parameter as an example, the terminal can first obtain the benchmark measurement value of the benchmark measurement device corresponding to the measurement parameter under multiple traceability levels from the above multiple benchmark measurement values, determine the obtained benchmark measurement value as each target benchmark measurement value, and then calculate the first difference between the static measurement value corresponding to the measurement parameter and each target benchmark measurement value.

[0138] Step 703: Determine the first element in the static error data based on each first difference.

[0139] The coordinate position of the first element in the static error data is indexed by the measurement parameters, the identifier of the measurement equipment, and the traceability level of the reference measurement equipment.

[0140] For example, static error data can be three-dimensional tensor data. Static error data can include multiple three-dimensional tensor data. It is understood that the index position of a three-dimensional tensor data, i.e., the index position of the first element, can be determined based on the measurement parameters, the identifier of the measuring device, and the traceability level. For example, if the measurement parameter is h, the identifier of the measuring device is k, and the traceability level of the reference measuring device is m, then the index position of the first element can be represented as C(h, k, m).

[0141] In this embodiment, the terminal can determine the measurement parameters, measurement equipment, and traceability level of the reference measurement equipment corresponding to each first difference as the index of the position of each first element, thereby obtaining static error data based on each index and each first difference.

[0142] In this embodiment, the terminal obtains the benchmark measurement values ​​of benchmark measurement devices at multiple traceability levels based on a multi-level benchmark measurement set. The multi-level benchmark measurement set includes the benchmark measurement values ​​corresponding to each benchmark measurement device. Then, for each measurement parameter, the terminal determines the target benchmark measurement values ​​of the benchmark measurement devices at multiple traceability levels corresponding to the measurement parameter, and calculates the first difference between the static measurement value corresponding to the measurement parameter and each target benchmark measurement value. Then, the terminal determines the first element in the static error data based on each first difference. The coordinate position of the first element in the static error data is indexed by the measurement parameter, the identifier of the measurement device, and the traceability level of the benchmark measurement device. In this way, the terminal can effectively realize the refined representation of static error data at multiple traceability levels and multiple measurement parameter dimensions. It not only fully preserves the correlation between static error and the metrological traceability level, but also ensures the traceability and uniqueness of error data through the coordinate indexing mechanism, providing a high-dimensional and highly correlated static error data foundation for the subsequent accurate extraction of lateral error features.

[0143] In one exemplary embodiment, such as Figure 8 As shown, the second measurement value includes multiple dynamic measurement values ​​obtained by dynamically measuring the component under test using multiple measuring devices. This embodiment relates to the process by which the terminal calculates the dynamic difference data corresponding to the component under test based on the first and second measurement values. Step 202 above includes:

[0144] Step 801: For each measurement parameter, calculate the second difference between the dynamic measurement value corresponding to the measurement parameter and the first measurement value corresponding to the measurement parameter.

[0145] The second measurement value may include multiple corresponding dynamic measurement values, each dynamic measurement value corresponding to the result of a measurement device measuring the component under test in a dynamic operating state.

[0146] Optionally, if a measuring device corresponds to multiple measuring parameters, the result of a measuring device performing dynamic measurement on the measured component includes multiple dynamic measurement values.

[0147] The second difference refers to the difference between the dynamic measurement value and the first measurement value under static conditions.

[0148] In this embodiment, taking each measurement parameter as an example, the terminal can subtract the first measurement value corresponding to the same measurement parameter from the dynamic measurement value corresponding to the measurement parameter, and then determine the result as the second difference.

[0149] Step 802: Determine the second element in the dynamic difference data based on the second difference.

[0150] The second element consists of the element at the coordinate position indexed by the measuring device and measuring parameters.

[0151] For example, dynamic difference data can be in matrix form. The index position of each element in the matrix can be determined by the measuring device and measurement parameters corresponding to each difference.

[0152] In this embodiment, the terminal can determine the index of the position of each second element for each measuring device and the corresponding measuring parameters of each measuring device, and then obtain dynamic difference data based on each index and each second difference.

[0153] In this embodiment, the terminal calculates a second difference between the dynamic measurement value corresponding to each measurement parameter and the first measurement value corresponding to the measurement parameter. Based on the second difference, it determines a second element in the dynamic difference data. The second element is the element at the coordinate position indexed by the measuring device and the measuring parameter. In this way, the difference between the dynamic measurement value and the first measurement value can be effectively quantified and structuredly stored. This not only accurately captures the fluctuation characteristics of the measurement parameter under dynamic operating conditions, but also ensures the uniqueness and location of the dynamic difference data through the dual indexing mechanism of the measuring device and the measuring parameter. This provides a dynamic data foundation for the subsequent extraction of disturbance feature vectors and the generation of longitudinal correction features, thereby improving the accuracy of the dynamic correction process.

[0154] In some embodiments, see Figure 9 The aforementioned nested network can be obtained by training an initial nested network, which includes an initial horizontal nesting transformation subnetwork and an initial vertical difference feature extraction subnetwork. This training process may include:

[0155] Step A: Obtain the sample error tensor between the first sample measurement value and the reference measurement value of the component under test in a static state. The sample difference matrix between the second sample measurement and the first sample measurement while the sample is in operation. The physical field coupling parameters A1, A2, A3, and A4 are determined based on the different physical fields corresponding to the operating state.

[0156] Among them, the sample difference matrix It can be represented as:

[0157]

[0158] in, ,in This represents the test result of test device i on test parameter j during operation. This represents the test result of test device i on test parameter j in a static state.

[0159] Wherein, A1 is the thermophysical field under the simulation environment, A2 is the thermophysical field and fluid mixed field under the simulation environment, A3 is the thermophysical field, fluid field and magnetic mixed field under the simulation environment, and A4 is the thermophysical field, fluid field, magnetic field and force mixed field under the simulation environment.

[0160] Step B, convert the sample error tensor Intermediate test results were obtained by inputting the first initial physics encoder E1 of the initial transverse nested transformation subnetwork. (Also known as testing the first-level error characteristics), the intermediate test results Input the data into the second initial physics encoder E2 to obtain intermediate test results. intermediate test results The intermediate test results were obtained by inputting the third initial physics encoder E3. intermediate test results Inputting the data into the fourth initial physics encoder E4 yields the final test results. (Also known as testing lateral error characteristics).

[0161] Step C, generate the sample difference matrix The initial feature extraction module R1 of the initial longitudinal difference feature extraction subnetwork is input to obtain intermediate test results (also known as test perturbation feature vectors). Then, these intermediate test results are input to the initial feature reconstruction module R2 of the initial longitudinal difference feature extraction subnetwork to obtain the final test results (also known as test longitudinal correction features). The relationship between the above test results and the physical field and sample error tensor can be expressed as:

[0162]

[0163]

[0164]

[0165]

[0166] in, It can represent operations such as dot product and tensor addition, which help guide the initial nested network to find the optimal solution.

[0167] Step D: Final test results By gradually stripping away the influence of the physical field from the initial decoders D4-D1 of the initial horizontally nested transformation subnetwork, a static source tracing approximation result is obtained. .

[0168] Step E: Calculate multilayer loss Backpropagation updates the network parameters. The multi-layer loss can be expressed as:

[0169]

[0170]

[0171]

[0172]

[0173]

[0174] Step F: Train until the loss converges to obtain the nested network F.

[0175] Based on the above embodiments, in some embodiments, the process of determining the metrological traceability results of the tested component using nested networks may include:

[0176] S1, Obtain the error tensor between the first measured value and the reference measured value of the tested component. The difference matrix between the second measurement value and the first measurement value when the system is in operation. And construct the benchmark comparison result matrix M, where M represents the specified error range between each measurement parameter, measurement device and the benchmark measurement device under each traceability level.

[0177] Among them, the difference matrix It can be represented as:

[0178]

[0179] in, ,in This represents the measurement result of measuring device i for measuring parameter j during operation. This represents the measurement result of measuring device i on measuring parameter j in a static state.

[0180] S2, the error tensor The intermediate result is obtained by inputting it into the first physics encoder E1 of the laterally nested transformation subnetwork. (Also known as the first-level error characteristic), intermediate results The intermediate results are obtained by inputting the data into the second physics encoder E2. intermediate results The intermediate results are obtained by inputting the data into the third physics encoder, E3. intermediate results The final result is obtained by inputting the data into the fourth physics encoder, E4. (Also known as lateral error characteristics).

[0181] S3, the difference matrix The feature extraction module R1 of the longitudinal difference feature extraction subnetwork is input to obtain intermediate results (also known as perturbation feature vectors). Then, these intermediate results are input to the feature recombination module R2 of the longitudinal difference feature extraction subnetwork to obtain the final results (also known as longitudinal corrected features). The relationship between the above results and the physical field and sample error tensor can be expressed as:

[0182]

[0183]

[0184]

[0185] S4, based on the above horizontal error characteristics and vertical correction characteristics, the output of the nested network is as follows:

[0186]

[0187] in, Indicates the output result. It can represent operations such as dot product and tensor addition, which help guide nested networks to find the optimal solution.

[0188] S5, based on the output of the nested network By comparing the matrix M with the benchmark, the source tracing results are obtained. This process can be represented as:

[0189]

[0190] Where H is the result of the source tracing calculation, which can be represented as: Optionally, if If the value is less than or equal to 0, then the n-level traceability of the measurement parameter i and the measurement device j is successful; otherwise, the traceability fails.

[0191] To facilitate understanding by those skilled in the art, the metrological traceability method provided in this application will be described in detail below. This method may include:

[0192] S1 acquires the measured values ​​of multiple measurement parameters corresponding to each tested component of the aero-engine.

[0193] The measured values ​​include the first measured value of each measured component in a static state and the second measured value in an operating state.

[0194] S2, for each component under test, obtains the reference measurement values ​​of reference measurement devices at multiple traceability levels based on a multi-level reference measurement set.

[0195] The multi-level reference measurement set includes the reference measurement values ​​corresponding to each reference measurement device.

[0196] S3, for each measurement parameter, determine the target reference measurement value of the reference measurement equipment under multiple traceability levels corresponding to the measurement parameter, and calculate the first difference between the static measurement value corresponding to the measurement parameter and each target reference measurement value.

[0197] S4, determine the first element in the static error data based on each first difference.

[0198] The coordinate position of the first element in the static error data is indexed by the measurement parameters, the identifier of the measurement equipment, and the traceability level of the reference measurement equipment.

[0199] S5, for each tested component and for each measurement parameter, calculate the second difference between the dynamic measurement value corresponding to the measurement parameter and the first measurement value corresponding to the measurement parameter.

[0200] S6, determine the second element in the dynamic difference data based on the second difference.

[0201] The second element consists of the element at the coordinate position indexed by the measuring device and measuring parameters.

[0202] S7. Input the static error data into the first-stage physical field influence encoder in the multiple cascaded physical field influence encoders to obtain the first-stage error characteristics.

[0203] S8, input the first-level error characteristics into the next level of the physical field influence encoder of the first-level physical field influence encoder, until the lateral error characteristics of the output of the last level of the physical field influence encoder in the multiple cascaded physical field influence encoders are obtained.

[0204] S9. Input the dynamic difference data into the feature extraction module to obtain the perturbation feature vector corresponding to the dynamic difference data output by the feature extraction module.

[0205] S10, input the perturbation feature vector into the feature recombination module to obtain the longitudinally corrected feature output by the feature recombination module.

[0206] S11, calculate the product between the lateral error feature and the longitudinal correction feature.

[0207] S12, calculate the difference between the product and the preset baseline error threshold.

[0208] S13. If the difference is less than or equal to 0, the measurement traceability result is determined to be successful.

[0209] S14. If the difference is greater than 0, the measurement traceability result is determined to be traceability failure.

[0210] It should be noted that the descriptions in S1-S14 above can be found in the relevant descriptions in the above embodiments, and their effects are similar, so they will not be repeated here.

[0211] It should be understood that although the steps in the flowcharts of the above embodiments are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the above embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0212] Based on the same inventive concept, this application also provides a metrological traceability device for implementing the metrological traceability method described above. The solution provided by this device is similar to the solution described in the above method; therefore, the specific limitations in one or more metrological traceability device embodiments provided below can be found in the limitations of the metrological traceability method described above, and will not be repeated here.

[0213] In one embodiment, such as Figure 10 As shown, a measurement traceability device is provided, comprising: an acquisition module 1001, a first determination module 1002, and a second determination module 1003, wherein:

[0214] The acquisition module 1001 is used to acquire the measurement value of at least one measurement parameter corresponding to each tested component of the aero-engine. The measurement value includes a first measurement value of each tested component in a static state and a second measurement value in an operating state.

[0215] The first determining module 1002 is used to determine the static error data corresponding to each tested component based on the first measured value and a preset multi-level benchmark measurement set, and to determine the dynamic difference data corresponding to each tested component based on the first measured value and the second measured value.

[0216] The second determining module 1003 is used to determine the metrological traceability results of the tested component based on static error data, dynamic difference data, and a preset nested network.

[0217] In one embodiment, the nested network includes a horizontally nested transformation subnetwork and a vertically nested difference feature extraction subnetwork, and the second determining module 1003 includes:

[0218] The first acquisition unit is used to input static error data into the horizontally nested transformation sub-network to obtain the horizontal error features output by the horizontally nested transformation sub-network.

[0219] The second acquisition unit is used to input dynamic difference data into the longitudinal difference feature extraction subnetwork to obtain the longitudinal correction features output by the longitudinal difference feature extraction subnetwork.

[0220] The first determining unit is used to determine the metrological traceability result based on the horizontal error characteristics and the vertical correction characteristics.

[0221] In one embodiment, the determining unit is specifically used for:

[0222] Calculate the product between the lateral error feature and the longitudinal correction feature;

[0223] Calculate the difference between the product and the preset baseline error threshold;

[0224] If the difference is less than or equal to 0, the measurement traceability result is determined to be successful.

[0225] If the difference is greater than 0, the measurement traceability result is determined to be traceability failure.

[0226] In one embodiment, the laterally nested transformation subnetwork includes multiple cascaded physical field influence encoders; the aforementioned first acquisition unit is specifically used for:

[0227] The static error data is input into the first-stage physical field influence encoder in a series of cascaded physical field influence encoders to obtain the first-stage error characteristics.

[0228] The first-level error characteristics are input into the next level of the physical field-affected encoder of the first-level physical field-affected encoder, until the lateral error characteristics of the output of the last level of the physical field-affected encoder in the multiple cascaded physical field-affected encoders are obtained.

[0229] In one embodiment, the longitudinal difference feature extraction subnetwork includes a feature extraction module and a feature recombination module, and the aforementioned second acquisition unit is specifically used for:

[0230] The dynamic difference data is input into the feature extraction module to obtain the perturbation feature vector corresponding to the dynamic difference data output by the feature extraction module.

[0231] The perturbation feature vector is input into the feature reconstruction module to obtain the longitudinally corrected feature output by the feature reconstruction module.

[0232] In one embodiment, the first measurement value includes multiple static measurement values ​​obtained by performing static measurements on the component under test using multiple measuring devices. The first determining module 1002 includes:

[0233] The third acquisition unit is used to acquire the benchmark measurement values ​​of benchmark measurement devices under multiple traceability levels based on the multi-level benchmark measurement set, which includes the benchmark measurement values ​​corresponding to each benchmark measurement device.

[0234] The second determining unit is used to determine the target reference measurement value of the reference measurement device under multiple traceability levels corresponding to each measurement parameter, and to calculate the first difference between the static measurement value corresponding to the measurement parameter and each target reference measurement value respectively.

[0235] The third determining unit is used to determine the first element in the static error data based on each first difference. The coordinate position of the first element in the static error data is indexed by the measurement parameters, the identifier of the measuring equipment, and the traceability level of the reference measuring equipment.

[0236] In one embodiment, the first measurement value includes multiple static measurement values ​​obtained by performing static measurements on the component under test using multiple measuring devices. The first determining module 1002 includes:

[0237] The calculation unit is used to calculate the second difference between the dynamic measurement value corresponding to the measurement parameter and the first measurement value corresponding to the measurement parameter for each measurement parameter;

[0238] The fourth determining unit is used to determine the second element in the dynamic difference data based on the second difference, wherein the second element is the element at the coordinate position indexed by the measuring device and the measuring parameters.

[0239] Each module in the aforementioned metrological traceability device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the corresponding operations of each module.

[0240] In one exemplary embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 11 As shown, the computer device includes a processor, memory, input / output interfaces, a communication interface, a display unit, and an input device. The processor, memory, and input / output interfaces are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The input / output interfaces are used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, NFC (Near Field Communication), or other technologies. When the computer program is executed by the processor, it implements a metrological traceability method. The display unit is used to form a visually visible image and can be a display screen, a projection device, or a virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device of the computer device can be a touch layer covering the display screen, or buttons, trackballs, or touchpads set on the casing of the computer device, or external keyboards, touchpads, or mice, etc.

[0241] Those skilled in the art will understand that Figure 11 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. The specific computer device may include more or fewer test components than shown in the figure, or combine certain test components, or have different arrangements of test components.

[0242] In one embodiment, a computer device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above method embodiments.

[0243] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements the steps in the above method embodiments.

[0244] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above method embodiments.

[0245] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0246] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0247] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0248] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for metrological traceability, characterized in that, The method includes: The measured values ​​of multiple measurement parameters corresponding to each tested component of the aero-engine are obtained. The measured values ​​include a first measured value of each tested component in a static state and a second measured value in an operating state. For each of the tested components, static error data corresponding to the tested component is determined based on the first measured value and a preset multi-level benchmark measurement set, and dynamic difference data corresponding to the tested component is determined based on the first measured value and the second measured value. The static error data is input into the first-level physical field influence encoder in a plurality of cascaded physical field influence encoders to obtain the first-level error feature. The first-level error feature is then input into the next-level physical field influence encoder in the first-level physical field influence encoder, until the lateral error feature output by the last-level physical field influence encoder in the plurality of cascaded physical field influence encoders is obtained. The plurality of cascaded physical field influence encoders are encoders included in the lateral nested transformation subnetwork in a preset longitudinal and transverse nested network. The dynamic difference data is input into the feature extraction module to obtain the disturbance feature vector corresponding to the dynamic difference data output by the feature extraction module. The disturbance feature vector is input into the feature recombination module to obtain the longitudinal correction feature output by the feature recombination module. The feature extraction module and the feature recombination module are modules included in the longitudinal difference feature extraction subnetwork in the longitudinal and transverse nested network. Based on the lateral error feature and the longitudinal correction feature, the metrological traceability result of the measured component is determined.

2. The method according to claim 1, characterized in that, The step of determining the metrological traceability result of the tested component based on the lateral error characteristics and the longitudinal correction characteristics includes: Calculate the product between the lateral error feature and the longitudinal correction feature; Calculate the difference between the product and a preset benchmark error threshold; If the difference is less than or equal to 0, then the measurement traceability result is determined to be successful. If the difference is greater than 0, the measurement traceability result is determined to be a traceability failure.

3. The method according to claim 1, characterized in that, The first measurement value includes multiple static measurement values ​​obtained by performing static measurements on the component under test using multiple measuring devices. The step of determining the static error data corresponding to the component under test based on the first measurement value and a preset multi-level benchmark measurement set includes: Based on the multi-level benchmark measurement set, benchmark measurement values ​​of benchmark measurement devices at multiple traceability levels are obtained, wherein the multi-level benchmark measurement set includes the benchmark measurement value corresponding to each benchmark measurement device; For each measurement parameter, a target reference measurement value for the reference measurement device under the multiple traceability levels corresponding to the measurement parameter is determined, and a first difference between the static measurement value corresponding to the measurement parameter and each target reference measurement value is calculated respectively. The first element in the static error data is determined based on each of the first differences, and the coordinate position of the first element in the static error data is determined by the measurement parameters, the identifier of the measurement device, and the traceability level index of the reference measurement device.

4. The method according to claim 1, characterized in that, The second measurement value includes multiple dynamic measurement values ​​obtained by dynamically measuring the component under test using multiple measuring devices. The step of determining the dynamic difference data corresponding to the component under test based on the first measurement value and the second measurement value includes: For each of the measurement parameters, calculate a second difference between the dynamic measurement value corresponding to the measurement parameter and the first measurement value corresponding to the measurement parameter; The second element in the dynamic difference data is determined based on the second difference, and the coordinate position of the second element in the dynamic difference data is indexed by the measuring device and the measuring parameters.

5. The method according to claim 1, characterized in that, The multi-level reference measurement set is obtained by each reference device measuring each of the measured components under ideal static conditions for each of the measurement parameters.

6. The method according to claim 1, characterized in that, The lateral error feature characterizes the error variation between the first measurement value and the benchmark measurement values ​​included in the multi-level benchmark measurement set under different combinations of physical fields.

7. A metering traceability device, characterized in that, The device includes: The acquisition module is used to acquire the measurement value of at least one measurement parameter corresponding to each tested component of the aero-engine, the measurement value including a first measurement value of each tested component in a static state and a second measurement value in an operating state; The first determining module is used to determine, for each of the tested components, the static error data corresponding to the tested component based on the first measured value and a preset multi-level benchmark measurement set, and the dynamic difference data corresponding to the tested component based on the first measured value and the second measured value. The second determining module is used to input the static error data into the first-level physical field influence encoder of a plurality of cascaded physical field influence encoders to obtain the first-level error feature, and input the first-level error feature into the next-level physical field influence encoder of the first-level physical field influence encoder, until the lateral error feature output by the last-level physical field influence encoder of the plurality of cascaded physical field influence encoders is obtained. The plurality of cascaded physical field influence encoders are encoders included in the lateral nested transformation subnetwork of a preset longitudinal and transverse nested network. The dynamic difference data is input into the feature extraction module to obtain the disturbance feature vector corresponding to the dynamic difference data output by the feature extraction module, and the disturbance feature vector is input into the feature recombination module to obtain the longitudinal correction feature output by the feature recombination module. The feature extraction module and the feature recombination module are modules included in the longitudinal difference feature extraction subnetwork of the longitudinal and transverse nested network. Based on the lateral error feature and the longitudinal correction feature, the metrological traceability result of the measured component is determined.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

Images