Aero-engine performance detection method and device, electronic equipment and storage medium
By applying the performance detection model of cascade residual network and long and short-term memory network in aero engines, the problems of inconvenience in the diagnosis of faults of aero engines and low detection accuracy in the prior art are solved, and efficient detection of abnormal performance of aero engines is achieved. and early warning.
Patent Information
- Application Number
- CN202411343917.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-25
- Publication Date
- 2025-01-10
AI Technical Summary
The existing aero engine fault diagnosis methods rely on a variety of maintenance manuals and professionals to judge. They are inconvenient to read and are mainly after-repair. They lack real-time status detection functions and are difficult to efficiently detect abnormal performance.
The performance detection model of the cascade residual network and the long and short-term memory network is adopted to convert the performance data of the aircraft engine into two-dimensional image data, and the performance state detection is realized through deep neural networks to improve the accuracy of abnormal detection.
By acquiring and utilizing deep information of performance data, early warning and accurate detection of aircraft engine performance abnormalities is achieved, and detection accuracy is improved.
Smart Images
Figure CN119290402A_ABST
Abstract
Description
Technical Field
[0001] The present disclosure relates to the technical field of aircraft engines, and in particular to a method, device, electronic equipment and storage medium for detecting performance of aircraft engines. Background Art
[0002] As a key power unit of an aircraft, the performance status of an aircraft engine directly affects the operational safety of the aircraft and the lives of the people on board. Therefore, it is of great significance to detect abnormal engine performance.
[0003] For fault diagnosis of aircraft engine systems, the current method mainly relies on the aircraft maintenance manual. However, the manual is too numerous, inconvenient to consult, and difficult to troubleshoot. The troubleshooting effect mainly depends on the professional level of the maintenance personnel, and it is mostly used for post-maintenance and does not have the effect of status detection. Summary of the invention
[0004] In view of this, the purpose of the present disclosure is to propose a method, device, electronic equipment and storage medium for detecting aircraft engine performance, which can solve the existing problems in a targeted manner.
[0005] Based on the above-mentioned purpose, in a first aspect, the present disclosure proposes a method for detecting aircraft engine performance, comprising: obtaining performance data of the aircraft engine from an aircraft, wherein the performance data is data of at least two performance parameters; converting the performance data into two-dimensional image data; inputting the two-dimensional image data into a performance detection model to obtain the performance status of the aircraft engine, wherein the performance detection model includes a cascaded residual network and a long short-term memory network.
[0006] In a second aspect, a device for detecting aircraft engine performance is also provided, comprising: an acquisition unit, configured to acquire performance data of the aircraft engine for an aircraft, wherein the performance data is data of at least two performance parameters; a conversion unit, configured to convert the performance data into two-dimensional image data; an input unit, configured to input the two-dimensional image data into a performance detection model to obtain the performance status of the aircraft engine, wherein the performance detection model comprises a cascaded residual network and a long short-term memory network.
[0007] According to a third aspect, an electronic device is provided, 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 described in the first aspect.
[0008] According to a fourth aspect, a computer-readable storage medium is provided, on which a computer program is stored, and the computer program is executed by a processor to implement any method described in the first aspect.
[0009] In a fifth aspect, a computer program product is also provided, including a computer program, wherein the computer program is executed by a processor to implement any method described in the first aspect.
[0010] In general, the present disclosure has at least the following beneficial effects: the present disclosure can obtain and utilize deep information of performance data through cascaded residual networks and long short-term memory networks, can realize extraction and early warning, and improve the accuracy of performance anomaly detection of aircraft engines. BRIEF DESCRIPTION OF THE DRAWINGS
[0011] In the accompanying drawings, unless otherwise specified, the same reference numerals throughout the multiple drawings represent the same or similar parts or elements. These drawings are not necessarily drawn to scale. It should be understood that these drawings only depict some embodiments disclosed in accordance with the present disclosure and should not be regarded as limiting the scope of the present disclosure.
[0012] Figure 1 A flow chart showing a method for detecting performance of an aircraft engine according to an embodiment of the present disclosure is shown;
[0013] Figure 2 A schematic diagram of the structure of a performance detection model according to an embodiment of the present disclosure is shown;
[0014] Figure 3 A schematic diagram showing an aircraft engine performance detection device according to an embodiment of the present disclosure;
[0015] Figure 4 A schematic diagram of the structure of an electronic device provided by an embodiment of the present disclosure is shown;
[0016] Figure 5 A schematic diagram of a storage medium provided by an embodiment of the present disclosure is shown. DETAILED DESCRIPTION
[0017] The present disclosure is further described in detail below in conjunction with the accompanying drawings and embodiments. It is understood that the specific embodiments described herein are only used to explain the relevant invention, rather than to limit the invention. It is also necessary to explain that, for ease of description, only the parts related to the relevant invention are shown in the accompanying drawings.
[0018] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present disclosure may be combined with each other. The present disclosure will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.
[0019] Figure 1 The present invention shows a method for detecting the performance of an aircraft engine. In an embodiment of the present invention, the method includes:
[0020] Step S101, obtaining performance data of an aircraft engine for an aircraft, wherein the performance data is data of at least two performance parameters.
[0021] In this embodiment, the execution subject of the method for detecting the performance of an aircraft engine may obtain the performance data of the aircraft engine of the aircraft.
[0022] The number of performance parameters is at least two, for example, a left engine low-pressure rotor vibration value, a left engine high-pressure rotor vibration value, a right engine low-pressure rotor vibration value, and a right engine high-pressure rotor vibration value.
[0023] Step S102: converting the performance data into two-dimensional image data.
[0024] In this embodiment, the above-mentioned execution entity can convert the performance data into two-dimensional image data to provide data input for the performance detection model of the aircraft engine performance.
[0025] Step S103, inputting the two-dimensional image data into a performance detection model to obtain the performance status of the aircraft engine, wherein the performance detection model includes a cascaded residual network and a long short-term memory network.
[0026] In this embodiment, the above-mentioned execution subject can input the converted two-dimensional image data into the performance detection model, so as to obtain the performance status output by the performance detection model.
[0027] The performance detection model is used to detect the performance status of aircraft engines. Specifically, the performance status can be divided into normal and abnormal. The performance detection model is a deep neural network, including a cascaded residual network and a long short-term memory network.
[0028] This paper compares and tests the performance of four models, including ResNet18, ResNet34, ResNet50, and the performance detection model of this paper, through the test set. The performance status obtained is shown in the following table:
[0029] Comparative test results table
[0030] Model ResNet18 ResNet34 ResNet50 Performance testing model Accuracy (%) 81.28 83.56 89.87 95.26
[0031] The present disclosure can obtain and utilize deep information of performance data through cascaded residual networks and long short-term memory networks, realize extraction and early warning, and improve the accuracy of performance anomaly detection of aircraft engines.
[0032] In some optional implementations of any embodiment of the present disclosure, converting the performance data into two-dimensional image data includes: mapping the performance data to a specified numerical range of an image color space to visualize the performance data.
[0033] In these optional implementations, the above-mentioned execution entity can map the performance data corresponding to its various performance parameters to the [0,255] interval of the RGB color space to visualize the engine performance data, thereby realizing the use of residual networks and long short-term memory networks that can perform deep processing of images, which helps to improve the detection accuracy of engine performance.
[0034] Optionally, the performance data is a timing matrix, and the matrix parameters of the timing matrix include data timing length; mapping the performance data to a specified numerical range of an image color space includes: mapping the performance data of each performance parameter in the timing matrix at different data timing lengths to a specified numerical range of an image color space.
[0035] Assuming that the aircraft engine performance data has n performance parameters and the data time series length is m, the aircraft engine performance data time series matrix D is:
[0036]
[0037] Among them, d i is the time series data of the i-th performance parameter; d ij is the j-th performance data of the ith performance parameter.
[0038] For the aircraft engine performance data time series matrix D, its various performance parameter time series data can be mapped to the [0,255] interval of the RGB color space to realize the visualization of the engine performance data.
[0039] The aircraft engine performance image P is
[0040]
[0041] Among them, P ij is the RGB pixel value corresponding to the j-th performance data of the ith performance parameter.
[0042]
[0043] The aviation engine performance visualization method converts high-dimensional performance parameter data into two-dimensional performance images by establishing a mapping relationship between the value domain of each engine performance data and the RGB color space, thereby retaining sufficient performance data information for the extraction of correlation features and time series features between performance parameters.
[0044] In some optional implementations of any embodiment of the present disclosure, the performance detection model includes a pre-feature extraction module, and the pre-feature extraction module includes the cascaded residual network; inputting the two-dimensional image data into the performance detection model to obtain the performance status of the aircraft engine includes: inputting the two-dimensional image data into the pre-feature extraction module to obtain pre-features, and the pre-features include correlation features between the at least two performance parameters.
[0045] In some optional implementations of any embodiment of the present disclosure, the performance detection model also includes a time series feature extraction module and an output module, and the time series feature extraction module includes the long short-term memory network; inputting the two-dimensional image data into the performance detection model to obtain the performance status of the aircraft engine includes: inputting the pre-features into the time series feature extraction module to obtain the time series features of the at least two performance parameters; inputting the time series features into the output module to obtain the performance status of the aircraft engine.
[0046] The aircraft engine performance anomaly detection model based on the cascaded residual network and long short-term memory network structure consists of three parts: the pre-feature extraction module, the temporal feature extraction module, and the output module. The pre-feature extraction module is based on the residual network and is used to learn the spatial correlation and other features of the aircraft engine performance image. The temporal feature extraction module is based on the long short-term memory network LSTM and is used to mine the temporal features of the data. The output module integrates the network output and discriminates the output information through the Softmax classifier to achieve engine performance anomaly detection.
[0047] In view of the high-dimensional, large-scale and strongly correlated characteristics of aircraft engine performance data, the engine performance anomaly detection model constructs a pre-feature extraction module with multiple residual units to extract the correlation characteristics between engine performance parameters.
[0048] According to the time series characteristics of aircraft engine performance data, the time series feature extraction module of the aircraft engine performance anomaly detection model is constructed using the LSTM network to extract the time series characteristics between aircraft engine performance parameters.
[0049] In some optional implementations of any embodiment of the present disclosure, the training set of the performance detection model includes: normal state data of a first vibration parameter among the at least two performance parameters, and abnormal state data of a second vibration parameter among the at least two performance parameters.
[0050] The parameters in the training samples of the performance detection model include a plurality of first vibration parameters and a plurality of second vibration parameters in the at least two performance parameters, the plurality of first vibration parameters are positive samples, and the plurality of second vibration parameters are negative samples.
[0051] The airline fleet data was collected and the performance parameters of a certain engine were selected, including the vibration value of the left engine low-pressure rotor, the vibration value of the left engine high-pressure rotor, the vibration value of the right engine low-pressure rotor and the vibration value of the right engine high-pressure rotor, totaling 12 groups of performance data. Among them, 10 groups of normal state data were used as positive samples, and 2 groups of abnormal vibration state data were used as negative samples.
[0052] Figure 2 A structural schematic diagram of the performance detection model is shown.
[0053] The embodiment of the present disclosure provides a device for detecting the performance of an aircraft engine, and the device is used to execute the method for detecting the performance of an aircraft engine described in the above embodiment, such as Figure 3 As shown, the device includes: an acquisition unit 301, configured to acquire performance data of an aircraft engine for an aircraft, wherein the performance data is data of at least two performance parameters; a conversion unit 302, configured to convert the performance data into two-dimensional image data; an input unit 303, configured to input the two-dimensional image data into a performance detection model to obtain a performance state of the aircraft engine, wherein the performance detection model includes a cascaded residual network and a long short-term memory network.
[0054] The aircraft engine performance detection device provided in the above-mentioned embodiment of the present disclosure and the aircraft engine performance detection method provided in the embodiment of the present disclosure are based on the same inventive concept and have the same beneficial effects as the methods adopted, run or implemented by the application programs stored therein.
[0055] The embodiments of the present disclosure also provide an electronic device corresponding to the method for detecting the performance of an aircraft engine provided in the above embodiments, so as to execute the above method for detecting the performance of an aircraft engine. The embodiments of the present disclosure are not limited.
[0056] Please refer to Figure 4 , which shows a schematic diagram of an electronic device provided by some embodiments of the present disclosure. Figure 4 As shown, the electronic device 40 includes: a processor 400, a memory 401, a bus 402 and a communication interface 403, and the processor 400, the communication interface 403 and the memory 401 are connected via the bus 402; the memory 401 stores a computer program that can be run on the processor 400, and the processor 400 executes the method provided in any of the aforementioned embodiments of the present disclosure when running the computer program.
[0057] The memory 401 may include a high-speed random access memory (RAM), and may also include a non-volatile memory, such as at least one disk memory. The communication connection between the system network element and at least one other network element is realized through at least one communication interface 403 (which may be wired or wireless), and the Internet, wide area network, local area network, metropolitan area network, etc. may be used.
[0058] The bus 402 may be an ISA bus, a PCI bus, or an EISA bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. The memory 401 is used to store programs, and the processor 400 executes the programs after receiving execution instructions. The method for detecting the performance of an aircraft engine disclosed in any of the embodiments of the present disclosure may be applied to the processor 400, or implemented by the processor 400.
[0059] The processor 400 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the hardware integrated logic circuit in the processor 400 or the instruction in the form of software. The above processor 400 may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it may also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The disclosed methods, steps and logic block diagrams in the embodiments of the present disclosure can be implemented or executed. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The steps of the method disclosed in conjunction with the embodiments of the present disclosure may be directly embodied as being executed by a hardware decoding processor, or may be executed by a combination of hardware and software modules in the decoding processor. The software module may be located in a mature storage medium in the field such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory 401, and the processor 400 reads the information in the memory 401 and completes the steps of the above method in combination with its hardware.
[0060] The electronic device provided by the embodiment of the present disclosure and the method for detecting the performance of an aircraft engine provided by the embodiment of the present disclosure are based on the same inventive concept and have the same beneficial effects as the methods adopted, operated or implemented therein.
[0061] The present disclosure also provides a computer-readable storage medium corresponding to the method for detecting the performance of an aircraft engine provided in the above-mentioned embodiment. Figure 5 The computer-readable storage medium shown is a CD 50 on which a computer program (ie, a program product) is stored. When the computer program is run by a processor, the method for detecting the performance of an aircraft engine provided in any of the aforementioned embodiments will be executed.
[0062] It should be noted that examples of the computer-readable storage medium may also include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other optical or magnetic storage media, which are not listed here one by one.
[0063] The computer-readable storage medium provided in the above-mentioned embodiments of the present disclosure and the method for detecting the performance of an aircraft engine provided in the embodiments of the present disclosure are based on the same inventive concept and have the same beneficial effects as the method adopted, run or implemented by the application program stored therein.
[0064] It should be noted that:
[0065] In the above text, the term "comprises", "comprising" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprising a ..." does not exclude the presence of other identical elements in the process, method, article or device including the element. In addition, it should be noted that the scope of the method and device in the embodiments of the present disclosure is not limited to performing functions in the order shown or discussed, and may also include performing functions in a substantially simultaneous manner or in reverse order according to the functions involved, for example, the described method may be performed in an order different from that described, and various steps may also be added, omitted, or combined. In addition, the features described with reference to certain examples may be combined in other examples.
[0066] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present disclosure, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, a magnetic disk, or an optical disk), and includes a number of instructions for enabling a terminal (which can be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to execute the methods described in each embodiment of the present disclosure.
[0067] The embodiments of the present disclosure are described above in conjunction with the accompanying drawings, which are only specific implementation modes of the present disclosure. However, the present disclosure is not limited to the above-mentioned specific implementation modes. The above-mentioned specific implementation modes are merely illustrative and not restrictive. Under the guidance of the present disclosure, ordinary technicians in this field can also make many forms without departing from the purpose of the present disclosure and the scope of protection of the claims, all of which are within the protection of the present disclosure.
Claims
1. A method for detecting the performance of an aircraft engine, characterized in that: include: Acquiring performance data of an aircraft engine for an aircraft, wherein the performance data is data of at least two performance parameters; converting the performance data into two-dimensional image data; The two-dimensional image data is input into a performance detection model to obtain the performance status of the aircraft engine. The performance detection model includes a cascaded residual network and a long short-term memory network.
2. The method according to claim 1, characterized in that The converting the performance data into two-dimensional image data comprises: The performance data is mapped to a specified value range in an image color space to visualize the performance data.
3. The method according to claim 2, characterized in that The performance data is a timing matrix, and the matrix parameters of the timing matrix include the data timing length; Mapping the performance data to a specified value range in the image color space includes: The performance data of each performance parameter at different data timing lengths in the timing matrix are mapped to a specified value range in the image color space.
4. The method according to claim 1, characterized in that: The performance detection model includes a pre-feature extraction module, and the pre-feature extraction module includes the cascaded residual network; The step of inputting the two-dimensional image data into a performance detection model to obtain the performance status of the aircraft engine includes: The two-dimensional image data is input into the pre-feature extraction module to obtain pre-features, wherein the pre-features include correlation features between the at least two performance parameters.
5. The method according to claim 1, characterized in that The performance detection model also includes a time series feature extraction module and an output module, and the time series feature extraction module includes the long short-term memory network; The step of inputting the two-dimensional image data into a performance detection model to obtain the performance status of the aircraft engine includes: Inputting the pre-features into the time series feature extraction module to obtain the time series features of the at least two performance parameters; The timing characteristics are input into the output module to obtain the performance status of the aircraft engine.
6. The method according to claim 1, characterized in that The training set of the performance detection model includes: Normal state data of a first vibration parameter among the at least two performance parameters, and abnormal state data of a second vibration parameter among the at least two performance parameters.
7. The method according to claim 1, characterized in that The parameters in the training samples of the performance detection model include a plurality of first vibration parameters and a plurality of second vibration parameters in the at least two performance parameters, the plurality of first vibration parameters are positive samples, and the plurality of second vibration parameters are negative samples.
8. A device for detecting the performance of an aircraft engine, characterized in that: include: An acquisition unit is configured to acquire performance data of an aircraft engine for an aircraft, wherein the performance data is data of at least two performance parameters; a conversion unit configured to convert the performance data into two-dimensional image data; The input unit is configured to input the two-dimensional image data into a performance detection model to obtain the performance status of the aircraft engine. The performance detection model includes a cascaded residual network and a long short-term memory network.
9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: The processor runs the computer program to implement the method according to any one of claims 1 to 7.
10. A computer-readable storage medium having a computer program stored thereon, characterized in that: The program is executed by a processor to implement the method according to any one of claims 1 to 7.