Aero-engine combustion chamber service life prediction method, device, equipment and medium

Abstract

The invention discloses an aero-engine combustion chamber life prediction method and device, equipment and a medium, and relates to the technical field of life prediction. First test data and second test data obtained by performing a high-temperature combustion test and a uniaxial tensile test on a combustion chamber of an aero-engine respectively are obtained; performing feature extraction and feature fusion on the first test data to obtain fused features, calculating fatigue damage parameters based on the second test data, and predicting the life of the combustion chamber by using the fused features and the fatigue damage parameters as input and using a trained life prediction model. The influence of the microstructure change on the macromechanical property of the material can be fully captured in the life prediction process, so that the prediction precision of life prediction of the aero-engine combustion chamber can be improved.

Description

Technical Field

[0001] The present application relates to the technical field of life prediction, and in particular to a method, device, equipment and medium for predicting the life of an aircraft engine combustion chamber. Background Art

[0002] As the power core of aircraft, the performance stability and operating life of aircraft engines are directly related to the safety and economy of flight. In actual operation, aircraft engines are inevitably affected by harsh working conditions such as high temperature, high pressure and high-speed rotation, which will lead to material performance degradation and structural damage, thus affecting their service life. The combustion chamber is an important component in aircraft engines. Therefore, accurately predicting the life of aircraft engine combustion chambers is of great significance for formulating maintenance plans, reducing operating costs and ensuring flight safety.

[0003] Traditional life prediction methods are mostly based on empirical formulas or macroscopic mechanical models. These methods often cannot fully capture the impact of microstructural changes on the macroscopic mechanical properties of materials, resulting in limited prediction accuracy, which in turn limits their application in engineering practice. Summary of the invention

[0004] The purpose of the present application is to provide a method, device, equipment and medium for predicting the life of an aircraft engine combustion chamber, which can improve the prediction accuracy of the life prediction of an aircraft engine combustion chamber.

[0005] To achieve the above objectives, this application provides the following solutions.

[0006] In a first aspect, the present application provides a method for predicting the life of an aircraft engine combustion chamber, the method comprising: Acquire first test data obtained by performing a high temperature combustion test on a combustion chamber of an aircraft engine and second test data obtained by performing a uniaxial tensile test on the combustion chamber; the first test data includes the duration of time experienced when the combustion chamber fails and the size of the cracks generated; the second test data includes the stress-strain curve before the combustion chamber fails; Performing feature extraction and feature fusion on the first test data to obtain fusion features; Calculate fatigue damage parameters based on the second test data; The fusion feature and the fatigue damage parameter are used as inputs, and the life of the combustion chamber is predicted using a trained life prediction model.

[0007] Optionally, performing feature extraction and feature fusion on the first test data to obtain fusion features specifically includes: Performing Box-Cox transformation on the first test data to obtain transformed data; Feature extraction and feature fusion are performed on the transformed data to obtain fused features.

[0008] Optionally, performing feature extraction and feature fusion on the first test data to obtain fusion features specifically includes: Taking the first test data as input, extracting features from the first test data using a stacked denoising autoencoder to obtain extracted features; The kernel canonical association analysis algorithm is used to perform feature fusion on all the extracted features to obtain fused features.

[0009] Optionally, calculating the fatigue damage parameter based on the second test data specifically includes: The second test data is logarithmically transformed to obtain a transformed curve, and the transformed curve is linearly fitted to obtain fatigue damage parameters.

[0010] Optionally, the fatigue damage parameter includes a slope and an intercept of a linear line obtained by linearly fitting the converted curve.

[0011] Optionally, the trained life prediction model includes an input layer, a bidirectional gated recurrent unit layer, a Dropout layer, a self-attention mechanism layer, a fully connected layer and an output layer connected in sequence.

[0012] In a second aspect, the present application provides a device for predicting the life of a combustion chamber of an aircraft engine, the device comprising: A test data acquisition module, used to acquire first test data obtained by performing a high temperature combustion test on a combustion chamber of an aircraft engine and second test data obtained by performing a uniaxial tensile test on the combustion chamber; the first test data includes the duration of time experienced when the combustion chamber fails and the size of the cracks generated; the second test data includes a stress-strain curve before the combustion chamber fails; A fusion feature determination module, used for performing feature extraction and feature fusion on the first test data to obtain fusion features; A damage parameter determination module, used for calculating fatigue damage parameters based on the second test data; The life prediction module is used to use the fusion feature and the fatigue damage parameter as input to predict the life of the combustion chamber using a trained life prediction model.

[0013] In a third aspect, the present application provides a computer device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement any of the above-described methods for predicting the life of an aircraft engine combustion chamber.

[0014] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements any of the above-described methods for predicting the life of an aircraft engine combustion chamber.

[0015] According to the specific embodiments provided in this application, this application discloses the following technical effects: The present application provides a method, device, equipment and medium for predicting the life of an aircraft engine combustion chamber. First test data and second test data are obtained by performing a high-temperature combustion test and a uniaxial tensile test on the combustion chamber of the aircraft engine respectively, and feature extraction and feature fusion are performed on the first test data to obtain fusion features. Fatigue damage parameters are calculated based on the second test data. The fusion features and fatigue damage parameters are used as inputs, and the life of the combustion chamber is predicted using a trained life prediction model. The present application introduces a high-temperature combustion test and a uniaxial tensile test, and combines the first test data and the second test data to predict the life of the combustion chamber. The application can fully capture the influence of microstructural changes on the macroscopic mechanical properties of the material during the life prediction process, thereby improving the prediction accuracy of the aircraft engine combustion chamber life prediction. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0017] Figure 1 This is an application environment diagram of an aircraft engine combustion chamber life prediction method provided in Example 1 of the present application.

[0018] Figure 2 A schematic flow chart of a method for predicting the life of an aircraft engine combustion chamber provided in Example 1 of the present application.

[0019] Figure 3 A schematic diagram of the functional modules of an aircraft engine combustion chamber life prediction device provided in Example 2 of the present application.

[0020] Figure 4 A schematic diagram of the structure of a computer device provided in Example 3 of the present application. DETAILED DESCRIPTION

[0021] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0022] Example 1.

[0023] The method for predicting the life of an aircraft engine combustion chamber provided in the embodiment of the present application can be applied to Figure 1 In the application environment shown. Among them, the terminal communicates with the server through the network. The data storage system can store data that the server needs to process. The data storage system can be set up separately, integrated on the server, or placed on the cloud or other servers. The terminal can send the first test data and the second test data to be processed to the server. After the server receives the first test data and the second test data to be processed, for the first test data and the second test data to be processed, the server extracts and fuses features of the first test data to obtain fused features; calculates fatigue damage parameters based on the second test data; and uses the fused features and fatigue damage parameters as input to predict the life of the combustion chamber using the trained life prediction model. The server can feed back the obtained life prediction results to the terminal.

[0024] In addition, in some embodiments, the method for predicting the life of an aircraft engine combustion chamber can also be implemented independently by a server or a terminal. For example, the terminal can directly process the first test data and the second test data to be processed, or the server can obtain the first test data and the second test data to be processed from a data storage system and process the first test data and the second test data to be processed.

[0025] The terminal may be, but is not limited to, various desktop computers, laptops, smart phones, tablet computers, IoT devices, and portable wearable devices. The server may be implemented as an independent server or a server cluster consisting of multiple servers, or may be a cloud server.

[0026] like Figure 2 As shown, a method for predicting the life of an aircraft engine combustion chamber is provided. The method is executed by a computer device, and can be executed by a computer device such as a terminal or a server alone, or by a terminal and a server together. In the embodiment of the present application, the method is applied to Figure 1 Taking the server in as an example, the method for predicting the life of the combustion chamber of an aircraft engine includes the following steps.

[0027] Step S1, obtaining first test data obtained by performing a high-temperature combustion test on a combustion chamber of an aircraft engine and second test data obtained by performing a uniaxial tensile test on the combustion chamber; the first test data includes the duration experienced when the combustion chamber fails and the size of the cracks generated; the second test data includes the stress-strain curve before the combustion chamber fails.

[0028] Step S2, performing feature extraction and feature fusion on the first test data to obtain fusion features.

[0029] Step S3, calculating fatigue damage parameters based on the second test data.

[0030] Step S4, using the fusion feature and the fatigue damage parameter as input, and using the trained life prediction model to predict the life of the combustion chamber.

[0031] By implementing the above-mentioned steps S1 to S4, this embodiment introduces a high-temperature combustion test and a uniaxial tensile test, and combines the first test data and the second test data to determine the fusion characteristics and fatigue damage parameters, and further predicts the life of the combustion chamber. It can fully capture the influence of microstructural changes on the macroscopic mechanical properties of the material during the life prediction process, and can effectively complete the life prediction of the aircraft engine combustion chamber with high accuracy, that is, greatly improve the life prediction accuracy of the combustion chamber.

[0032] In step S1, a high-temperature combustion test is performed on the combustion chamber of the aircraft engine. The high-temperature combustion test can be performed on an engine test bench. Specifically, a sample of the combustion chamber is made, and the sample of the combustion chamber is placed in a high-temperature box. The temperature in the high-temperature box is set to 1300-1800 degrees Celsius. The sample of the combustion chamber is continuously heated and observed every 30 minutes until the sample of the combustion chamber fails. At this time, the time from the start of the test to the failure of the sample of the combustion chamber is recorded, and the size of the crack on the failed sample of the combustion chamber is measured by a sensor to obtain the first test data. The first test data includes the time experienced when the combustion chamber fails and the size of the crack generated, and the size includes the length, width and height of the crack.

[0033] In step S1, a uniaxial tensile test is performed on the combustion chamber of the aircraft engine. The uniaxial tensile test can be completed on a fatigue machine. Specifically, a sample of the combustion chamber is made, and a steel plate of a certain thickness is pasted on each end of the sample of the combustion chamber. Then, stress is applied along the central axis to stretch the sample of the combustion chamber. The tensile force is determined according to the material of the combustion chamber. Generally, the tensile force can be several thousand Newtons. In the process of stretching the sample of the combustion chamber, each time it is stretched several times, generally 5000 times, the sample of the combustion chamber is observed until the sample of the combustion chamber fails, and the stress and strain during the test are recorded. The stress-strain curve is plotted with strain as the horizontal coordinate and stress as the vertical coordinate to obtain the second test data. The second test data includes the stress-strain curve before the failure of the combustion chamber.

[0034] In step S2, feature extraction and feature fusion are performed on the first test data to obtain fused features, specifically including: taking the first test data as input, using a stacked denoising autoencoder to extract features from the first test data, the stacked denoising autoencoder can remove noise and extract deep features to obtain extracted features; using a kernel canonical correlation analysis algorithm (Kernel Canonical Correlation Analysis, KCCA) to fuse all extracted features to obtain fused features.

[0035] In step S2, feature extraction and feature fusion are performed on the first test data to obtain fused features, which specifically includes: performing Box-Cox transformation on the first test data to obtain transformed data; performing feature extraction and feature fusion on the transformed data to obtain fused features. Among them, performing Box-Cox transformation on the first test data to obtain transformed data can reduce the correlation between unobservable errors and predictive variables to a certain extent, and improve its correlation with the flight cycle. Feature extraction and feature fusion are performed on the transformed data to obtain fused features, which specifically includes: taking the transformed data as input, using the stacked denoising autoencoder to extract features from the transformed data to obtain extracted features; using the kernel canonical association analysis algorithm to perform feature fusion on all extracted features to obtain fused features.

[0036] In step S3, fatigue damage parameters are calculated based on the second test data, specifically including: logarithmic transformation of the second test data to obtain a converted curve, and linear fitting of the converted curve to obtain fatigue damage parameters, wherein the fatigue damage parameters include the slope and intercept of the linear line obtained by linear fitting of the converted curve.

[0037] The fatigue damage parameters are obtained by logarithmic transformation and linear regression analysis of the stress-strain curve. Specifically, the stress-strain curve is logarithmically transformed, and the converted curve is further linearly fitted to obtain a linear line. The fatigue damage parameters are determined based on the slope and intercept of the linear line. The fatigue damage parameters include the slope and intercept of the linear line.

[0038] This embodiment combines fusion features and fatigue damage parameters to form a health indicator that reflects the performance degradation of the aircraft engine. The health indicator includes the fusion features and fatigue damage parameters. Subsequently, the fusion features and fatigue damage parameters are directly used as input to predict the life of the combustion chamber using the trained life prediction model.

[0039] In order to improve the completeness of the analysis of the performance degradation of the combustion chamber of an aircraft engine, this embodiment proposes a bidirectional GRU (Bidirectional Gated Recurrent Unit, BiGRU) network model. The BiGRU network model can integrate the hidden states in two directions, enhance the understanding and learning effect of the input data, and thus more accurately capture the information of performance degradation. In the performance degradation analysis of the combustion chamber of an aircraft engine, the introduction of the self-attention mechanism into the BiGRU network model helps the BiGRU network model to extract and fuse key information from historical data and optimize the prediction results.

[0040] In this embodiment, the trained life prediction model includes an input layer, a bidirectional gated recurrent unit layer, a Dropout layer, a self-attention mechanism layer, a fully connected layer and an output layer connected in sequence, and each network layer works together to improve the prediction accuracy of the life of the combustion chamber of an aircraft engine. Among them, the input layer is responsible for receiving health indicator data. The bidirectional gated recurrent unit layer is used to conduct in-depth analysis of the data. In order to improve the generalization ability of the model and reduce the risk of overfitting, the Dropout layer is introduced to randomly deactivate some network connections. The self-attention mechanism layer calculates the weight of each time step, so that the model can identify and focus on the most critical information points for prediction. For the high-dimensional data output by the self-attention mechanism layer, the model is reduced in dimension through two fully connected layers to refine the information and enhance the accuracy of the prediction.

[0041] This embodiment provides an aircraft engine combustion chamber life prediction model that integrates a bidirectional GRU network model and a self-attention mechanism, which can provide a more scientific and effective solution for the health management and life prediction of aircraft engine combustion chambers.

[0042] This embodiment designs a method for predicting the life of an aircraft engine combustion chamber, generates fatigue damage parameters, and further combines them with fusion features to predict the life of an aircraft engine combustion chamber, providing a more scientific and accurate method for predicting the life of an aircraft engine combustion chamber, which can improve the accuracy and reliability of the prediction.

[0043] The embodiment of the present application also provides an application scenario, which applies the above-mentioned aircraft engine combustion chamber life prediction method. Specifically, the aircraft engine combustion chamber life prediction method provided in this embodiment can be applied in the life prediction scenario. The life prediction scenario includes a data acquisition link, a data processing link and a result display link. The data acquisition link is used to obtain the test data (i.e., the first test data and the second test data) obtained by testing the aircraft engine combustion chamber. The data processing link is used to process the test data to obtain the life prediction result of the aircraft engine combustion chamber. The result display link is used to display the life prediction result. The aircraft engine combustion chamber life prediction method provided in this embodiment belongs to the data processing link.

[0044] Example 2.

[0045] Based on the same inventive concept, the embodiment of the present application also provides an aircraft engine combustion chamber life prediction device for implementing the above-mentioned aircraft engine combustion chamber life prediction method. The implementation solution provided by the device to solve the problem is similar to the implementation solution recorded in the above-mentioned method, so the specific limitations in the embodiment of the aircraft engine combustion chamber life prediction device provided below can refer to the above-mentioned limitations on the aircraft engine combustion chamber life prediction method, and will not be repeated here.

[0046] like Figure 3 As shown, a device for predicting the life of a combustion chamber of an aircraft engine is provided, and the device for predicting the life of a combustion chamber of an aircraft engine includes the following modules.

[0047] The test data acquisition module M1 is used to obtain first test data obtained by performing a high-temperature combustion test on the combustion chamber of the aircraft engine and second test data obtained by performing a uniaxial tensile test on the combustion chamber; the first test data includes the time experienced when the combustion chamber fails and the size of the cracks generated; the second test data includes the stress-strain curve before the combustion chamber fails.

[0048] The fusion feature determination module M2 is used to perform feature extraction and feature fusion on the first test data to obtain fusion features.

[0049] The damage parameter determination module M3 is used to calculate the fatigue damage parameters based on the second test data.

[0050] The life prediction module M4 is used to use the fusion feature and the fatigue damage parameter as input to predict the life of the combustion chamber using a trained life prediction model.

[0051] Example 3.

[0052] In an exemplary embodiment, a computer device is provided. The computer device may be a server or a terminal. The internal structure diagram thereof may be as follows: Figure 4 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store test data to be processed. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for predicting the life of an aircraft engine combustion chamber is implemented.

[0053] Those skilled in the art will understand that Figure 4 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0054] In an exemplary embodiment, a computer device is also provided, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the method for predicting the life of an aircraft engine combustion chamber as described in Example 1.

[0055] Example 4.

[0056] An embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the method for predicting the life of an aircraft engine combustion chamber described in Embodiment 1 is implemented.

[0057] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, 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.

[0058] This article uses specific examples to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the method and core ideas of this application. At the same time, for those skilled in the art, according to the ideas of this application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. A method for predicting the life of an aircraft engine combustion chamber, characterized in that: The aero-engine combustion chamber life prediction method comprises: Acquire first test data obtained by performing a high temperature combustion test on a combustion chamber of an aircraft engine and second test data obtained by performing a uniaxial tensile test on the combustion chamber; the first test data includes the duration of time experienced when the combustion chamber fails and the size of the cracks generated; the second test data includes the stress-strain curve before the combustion chamber fails; Performing feature extraction and feature fusion on the first test data to obtain fusion features; Calculate fatigue damage parameters based on the second test data; The fusion feature and the fatigue damage parameter are used as inputs, and the life of the combustion chamber is predicted using a trained life prediction model.

2. The method for predicting the life of an aircraft engine combustion chamber according to claim 1, characterized in that: The first test data is subjected to feature extraction and feature fusion to obtain fusion features, specifically including: Performing Box-Cox transformation on the first test data to obtain transformed data; Feature extraction and feature fusion are performed on the transformed data to obtain fused features.

3. The method for predicting the life of an aircraft engine combustion chamber according to claim 1, characterized in that: The first test data is subjected to feature extraction and feature fusion to obtain fusion features, specifically including: Taking the first test data as input, extracting features from the first test data using a stacked denoising autoencoder to obtain extracted features; The kernel canonical association analysis algorithm is used to perform feature fusion on all the extracted features to obtain fused features.

4. The method for predicting the life of an aircraft engine combustion chamber according to claim 1, characterized in that: The fatigue damage parameters are calculated based on the second test data, specifically including: The second test data is logarithmically transformed to obtain a transformed curve, and the transformed curve is linearly fitted to obtain fatigue damage parameters.

5. The method for predicting the life of an aircraft engine combustion chamber according to claim 4, characterized in that: The fatigue damage parameters include the slope and intercept of a linear line obtained by linearly fitting the converted curve.

6. The method for predicting the life of an aircraft engine combustion chamber according to claim 1, characterized in that: The trained life prediction model includes an input layer, a bidirectional gated recurrent unit layer, a Dropout layer, a self-attention mechanism layer, a fully connected layer and an output layer which are connected in sequence.

7. An aircraft engine combustion chamber life prediction device, characterized in that: The aero-engine combustion chamber life prediction device comprises: A test data acquisition module, used to acquire first test data obtained by performing a high temperature combustion test on a combustion chamber of an aircraft engine and second test data obtained by performing a uniaxial tensile test on the combustion chamber; the first test data includes the duration of time experienced when the combustion chamber fails and the size of the cracks generated; the second test data includes a stress-strain curve before the combustion chamber fails; A fusion feature determination module, used for performing feature extraction and feature fusion on the first test data to obtain fusion features; A damage parameter determination module, used for calculating fatigue damage parameters based on the second test data; The life prediction module is used to use the fusion feature and the fatigue damage parameter as input to predict the life of the combustion chamber using a trained life prediction model.

8. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the method for predicting the life of an aircraft engine combustion chamber 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, the method for predicting the life of an aircraft engine combustion chamber according to any one of claims 1 to 6 is implemented.

Images