An aero-engine fault diagnosis method and system

Abstract

The application discloses an aero-engine fault diagnosis method and system, and relates to the technical field of fault diagnosis. The method comprises the following steps: acquiring a time-domain vibration signal of a specified part of an aero-engine during rated speed operation; performing empirical mode decomposition on the time-domain vibration signal to obtain m time-domain signal components corresponding to the time-domain vibration signal; selecting the first n time-domain signal components from the m time-domain signal components to obtain n time-domain signal components; sampling the n time-domain signal components to obtain n component value sequences corresponding to the n time-domain signal components; constructing a feature vector matrix based on the n component value sequences to obtain a vibration signal component feature matrix corresponding to the time-domain vibration signal; and taking the vibration signal component feature matrix as an input of a pre-trained fault diagnosis model to perform operation, thereby obtaining a fault diagnosis result of the aero-engine. The aero-engine fault diagnosis method and system can realize accurate diagnosis of aero-engine faults and reduce fault diagnosis costs.

Description

Technical Field

[0001] The present invention belongs to the technical field of fault diagnosis, and in particular relates to an aero-engine fault diagnosis method and system. Background Art

[0002] As the core power unit of aircraft, aircraft engines are crucial to aircraft flight safety, so fault diagnosis of aircraft engines is particularly important.

[0003] At present, the fault diagnosis of some aircraft engines has long relied on expert systems, which simulate the expert decision-making process through rule bases and inference engines to achieve fault pattern matching. However, existing expert systems have significant limitations. The construction of rule bases requires reliance on manual experience, and they are not sensitive enough to early and weak fault characteristics. They are prone to missed detections or misjudgments due to deviations in threshold setting, resulting in less than ideal accuracy in aircraft engine fault diagnosis.

[0004] Therefore, how to provide an effective solution to achieve accurate diagnosis of aircraft engine failures has become a difficult problem that needs to be solved urgently in the existing technology. Summary of the Invention

[0005] The purpose of the present invention is to provide an aircraft engine fault diagnosis method and system to solve the above-mentioned problems existing in the prior art.

[0006] In order to achieve the above object, the present invention adopts the following technical solutions:

[0007] In a first aspect, the present invention provides an aircraft engine fault diagnosis method, comprising:

[0008] Obtain the time domain vibration signal of a specified part of an aircraft engine during operation at rated speed;

[0009] Performing empirical mode decomposition on the time-domain vibration signal to obtain m time-domain signal components corresponding to the time-domain vibration signal, where m is a positive integer greater than 2;

[0010] Selecting the first n of the m time-domain signal components to obtain n time-domain signal components, where n is a positive integer less than m;

[0011] Sampling the n time-domain signal components to obtain n component value sequences corresponding to the n time-domain signal components;

[0012] constructing a characteristic vector matrix based on the n component value sequences to obtain a vibration signal component characteristic matrix corresponding to the time domain vibration signal;

[0013] Using the vibration signal component feature matrix as input of a pre-trained fault diagnosis model to perform calculations to obtain a fault diagnosis result of the aircraft engine;

[0014] Among them, the fault diagnosis model is trained by using the sample vibration signal component feature matrix corresponding to the historical sample time domain vibration signal of the specified part of the aircraft engine during the operation at rated speed as sample input, and the fault classification result of the aircraft engine when the historical sample time domain vibration signal is obtained as sample output.

[0015] Based on the above disclosure, the present invention obtains a time-domain vibration signal of a specified part of an aircraft engine during operation at rated speed; performs empirical mode decomposition on the time-domain vibration signal to obtain m time-domain signal components corresponding to the time-domain vibration signal, where m is a positive integer greater than 2; selects the first n of the m time-domain signal components to obtain n time-domain signal components, where n is a positive integer less than m; samples the n time-domain signal components to obtain n component value sequences corresponding to the n time-domain signal components; constructs a feature vector matrix based on the n component value sequences to obtain a vibration signal component feature matrix corresponding to the time-domain vibration signal; and uses the vibration signal component feature matrix as input to a pre-trained fault diagnosis model for calculation to obtain an aircraft engine fault diagnosis result. Since aircraft engine faults cause abnormal aircraft engine vibration, when performing empirical mode decomposition on the time-domain vibration signal, energy is usually concentrated in the first few time-domain signal components obtained by decomposition, that is, the component value sequences corresponding to the first few time-domain signal components obtained by decomposition can highlight the local feature information of the vibration signal, thereby achieving accurate diagnosis of aircraft engine faults, while also reducing the amount of fault diagnosis calculations and the cost of fault diagnosis.

[0016] In one possible design, sampling the n time-domain signal components to obtain n component value sequences corresponding to the n time-domain signal components includes:

[0017] For any one of the n time domain signal components, dividing the any one time domain signal component into a plurality of signal component segments with the same time intervals, to obtain a sequence of n signal component segments corresponding one-to-one to the n time domain signal components;

[0018] Extracting the component amplitude corresponding to each signal component segment in each signal component segment sequence to obtain a component value sequence corresponding to each signal component segment sequence;

[0019] The component value sequence corresponding to any signal component segment sequence is used as the component value sequence of the time domain signal component corresponding to the any signal component segment sequence, thereby obtaining n component value sequences corresponding to the n time domain signal components.

[0020] In one possible design, extracting the component amplitude corresponding to each signal component segment in each signal component segment sequence to obtain a component value sequence corresponding to each signal component segment sequence includes:

[0021] The component amplitude average value corresponding to each signal component segment in each signal component segment sequence is calculated to obtain a component value sequence corresponding to each signal component segment sequence.

[0022] In one possible design, constructing a feature vector matrix based on the n component value sequences to obtain a vibration signal component feature matrix corresponding to the time-domain vibration signal includes:

[0023] Normalizing the n component value sequences to obtain n normalized component value sequences corresponding one-to-one to the n component value sequences;

[0024] The n normalized component value sequences are combined to obtain a vibration signal component feature matrix corresponding to the time domain vibration signal.

[0025] In a possible design, the number of designated locations is multiple, and the vibration signal component feature matrix is ​​used as input to a pre-trained fault diagnosis model to perform calculations to obtain a fault diagnosis result for the aircraft engine, including:

[0026] The vibration signal component feature matrices corresponding to the time-domain vibration signals of multiple designated parts are combined and used as inputs of a pre-trained fault diagnosis model for calculation to obtain a fault diagnosis result of the aircraft engine.

[0027] In one possible design, the value range of m is [5, 10], and the value range of n is [2, 5].

[0028] In one possible design, the fault diagnosis model is a convolutional neural network model or a recurrent neural network model.

[0029] In a second aspect, the present invention provides an aircraft engine fault diagnosis system, comprising:

[0030] An acquisition unit, used to acquire a time domain vibration signal of a specified part of the aircraft engine during operation at rated speed;

[0031] a decomposition unit, configured to perform empirical mode decomposition on the time-domain vibration signal to obtain m time-domain signal components corresponding to the time-domain vibration signal, where m is a positive integer greater than 2;

[0032] a selection unit, configured to select first n of the m time domain signal components to obtain n time domain signal components, where n is a positive integer less than m;

[0033] a sampling unit, configured to sample the n time-domain signal components to obtain n component value sequences corresponding to the n time-domain signal components;

[0034] a construction unit, configured to construct a characteristic vector matrix based on the n component value sequences to obtain a vibration signal component characteristic matrix corresponding to the time domain vibration signal;

[0035] a fault diagnosis unit, configured to perform calculations on the vibration signal component characteristic matrix as input to a pre-trained fault diagnosis model to obtain a fault diagnosis result of the aircraft engine;

[0036] Among them, the fault diagnosis model is trained by using the sample vibration signal component feature matrix corresponding to the historical sample time domain vibration signal of the specified part of the aircraft engine during the operation at rated speed as sample input, and the fault classification result of the aircraft engine when the historical sample time domain vibration signal is obtained as sample output.

[0037] In a third aspect, the present invention provides an electronic device comprising a memory, a processor and a transceiver that are communicatively connected in sequence, wherein the memory is used to store computer programs, the transceiver is used to send and receive messages, and the processor is used to read the computer program and execute the aircraft engine fault diagnosis method as described in the first aspect or any possible design of the first aspect.

[0038] In a fourth aspect, the present invention provides a computer-readable storage medium having instructions stored thereon. When the instructions are run on a computer, the aircraft engine fault diagnosis method described in the first aspect or any possible design of the first aspect is executed.

[0039] In a fifth aspect, the present invention provides a computer program product comprising instructions, which, when executed on a computer, cause the computer to execute the aircraft engine fault diagnosis method as described in the first aspect or any possible design of the first aspect.

[0040] Beneficial effects:

[0041] The aircraft engine fault diagnosis method and system provided by the present invention perform empirical mode decomposition on the time domain vibration signal. The component value sequence corresponding to the first few time domain signal components obtained by the decomposition can highlight the local characteristic information of the vibration signal, thereby achieving accurate diagnosis of aircraft engine faults. At the same time, it can also reduce the computational complexity of fault diagnosis, reduce the fault diagnosis cost, and facilitate practical application and promotion. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 A flowchart of an aircraft engine fault diagnosis method provided in an embodiment of the present application;

[0043] Figure 2 A block diagram of an aero-engine fault diagnosis system according to an embodiment of the present application is provided.

[0044] Figure 3 A block diagram of an electronic device according to an embodiment of the present application is provided. DETAILED DESCRIPTION

[0045] In order to more clearly illustrate the technical solutions of the embodiments of the present application or the prior art, the present application will be briefly introduced below with reference to the drawings and the description of the embodiments or the prior art. Obviously, the following description of the drawings is only some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor. It should be noted that the description of these embodiments is used to help understand the present application, but does not constitute a limitation on the present application.

[0046] It should be understood that although the terms first, second, etc. may be used herein to describe various elements, these elements should not be limited by these terms. These terms are only used to distinguish one element from another. For example, a first element can be called a second element, and similarly, a second element can be called a first element without departing from the scope of the example embodiments of the present application.

[0047] It should be understood that for the term "and / or" that may appear herein, it is only a description of the association relationship of the associated objects, which means that there can be three kinds of relationships, for example, A and / or B, which means that there are three cases of A alone, B alone, and A and B together; for the term " / and" that may appear herein, it is another description of the association relationship of another associated object, which means that there can be two kinds of relationships, for example, A / and B, which means that there are two cases of A alone and A and B together; in addition, for the character " / " that may appear herein, it generally means that the associated objects before and after are an "or" relationship.

[0048] In order to realize accurate diagnosis of aero-engine faults, the present application provides an aero-engine fault diagnosis method and system, which can realize accurate diagnosis of aero-engine faults and also reduce fault diagnosis costs.

[0049] The aero-engine fault diagnosis method provided by the present application can be applied to an aero-engine fault diagnosis system. It can be understood that the execution subject does not constitute a limitation on the embodiments of the present application.

[0050] As Figure 1, which is a flow chart of the aircraft engine fault diagnosis method provided in the first aspect of this embodiment. The aircraft engine fault diagnosis method may include, but is not limited to, the following steps S101 to S106.

[0051] Step S101: Acquire a time domain vibration signal of a specified part of an aircraft engine during operation at rated speed.

[0052] In an embodiment of the present application, a vibration sensor may be installed at a designated location of an aircraft engine. When performing fault diagnosis on the aircraft engine, the aircraft engine may be first controlled to operate at a rated speed, and then the vibration sensor may be used to detect a time domain vibration signal at a designated location of the aircraft engine during operation at the rated speed. The time domain vibration signal is used to indicate the vibration amplitude of the designated location that changes over time.

[0053] Step S102: Perform empirical mode decomposition on the time-domain vibration signal to obtain m time-domain signal components corresponding to the time-domain vibration signal, where m is a positive integer greater than 2.

[0054] Specifically, a time-domain vibration signal of a certain duration (such as 0.2s, 0.5s, 1s, etc.) can be selected and empirical mode decomposition (EMD) performed on the time-domain vibration signal to obtain m time-domain signal components corresponding to the time-domain vibration signal, where m is a positive integer greater than 2 and the value range of m is generally [5,10].

[0055] Step S103: Select the first n time-domain signal components from the m time-domain signal components to obtain n time-domain signal components, where n is a positive integer less than m.

[0056] The energy of the vibration signal during an aircraft engine failure is typically concentrated in the first few time-domain signal components obtained by empirical mode decomposition. These components are more likely to highlight the local characteristics of the vibration signal. Therefore, the first n time-domain signal components out of m can be selected for aircraft engine fault diagnosis. n is a positive integer less than m, and the value of n is generally in the range [2, 5].

[0057] Step S104: Sample the n time-domain signal components to obtain n component value sequences corresponding to the n time-domain signal components.

[0058] Sampling the n time-domain signal components may include, but is not limited to, the following steps S1041 - S1043 .

[0059] Step S1041. For any time domain signal component among the n time domain signal components, divide any time domain signal component into multiple signal component segments with the same time intervals, and obtain a sequence of n signal component segments corresponding one-to-one to the n time domain signal components.

[0060] For example, if the duration of a time-domain signal component is 0.2 seconds, and if each 0.01 second segment is divided into a signal component segment, the time-domain signal component can be divided into a signal component segment sequence consisting of 20 signal component segments. Through division, each time-domain signal component can correspond to a signal component segment sequence. Therefore, for n time-domain signal components, n signal component segment sequences corresponding to the n time-domain signal components can be obtained.

[0061] Step S1042: Extract the component amplitude corresponding to each signal component segment in each signal component segment sequence to obtain a component value sequence corresponding to each signal component segment sequence.

[0062] Specifically, the component amplitude average corresponding to each signal component segment in each signal component segment sequence can be calculated to obtain a component value sequence corresponding to each signal component segment sequence. Still based on the example in step S1041 above, the time domain signal component is divided into 20 signal component segments. For each signal component segment sequence, a component value sequence of length 20 can be extracted.

[0063] Step S1043: Use the component value sequence corresponding to any signal component segment sequence as the component value sequence of the time domain signal component corresponding to any signal component segment sequence, and obtain n component value sequences corresponding to the n time domain signal components.

[0064] Step S105: Construct a characteristic vector matrix based on the n component value sequences to obtain a vibration signal component characteristic matrix corresponding to the time domain vibration signal.

[0065] Specifically, the n component value sequences can be normalized to obtain n normalized component value sequences corresponding to the n component value sequences. The n normalized component value sequences are then combined to obtain a vibration signal component feature matrix corresponding to the time-domain vibration signal. Each row in the vibration signal component feature matrix corresponds to one normalized component value sequence.

[0066] Step S106: Using the vibration signal component feature matrix as the input of the pre-trained fault diagnosis model to perform calculations to obtain the fault diagnosis results of the aircraft engine.

[0067] In an embodiment of the present application, a fault diagnosis model for fault diagnosis is pre-trained. The fault diagnosis model is trained using a sample vibration signal component feature matrix corresponding to a historical sample time-domain vibration signal of a specified part of the aircraft engine during operation at rated speed as sample input, and the aircraft engine fault classification result when the historical sample time-domain vibration signal is obtained as sample output. The sample vibration signal component feature matrix can be obtained by processing the historical sample time-domain vibration signal in the same manner as in steps S102-S105 described above. The aircraft engine fault classification result when the historical sample time-domain vibration signal is obtained can be manually pre-labeled. The fault diagnosis model can be, but is not limited to, a convolutional neural network (CNN) model or a recurrent neural network (RNN) model.

[0068] The fault classification results of the aircraft engine may be a normal aircraft engine, an aircraft engine valve fault (the valve clearance is too small or too large), an aircraft engine blade fault, an aircraft engine disk shaft fault, or an aircraft engine casing crack, etc.

[0069] In one or more embodiments, the designated location may be multiple. Accordingly, the operation of using the vibration signal component feature matrix as the input of a pre-trained fault diagnosis model to obtain the fault diagnosis result of the aircraft engine includes:

[0070] The vibration signal component feature matrices corresponding to the time-domain vibration signals of multiple designated parts are combined and used as inputs of a pre-trained fault diagnosis model for calculation to obtain a fault diagnosis result of the aircraft engine.

[0071] The aircraft engine fault diagnosis method provided by the present invention obtains a time domain vibration signal of a specified position of the aircraft engine during operation at rated speed; performs empirical mode decomposition on the time domain vibration signal to obtain m time domain signal components corresponding to the time domain vibration signal, where m is a positive integer greater than 2; selects the first n of the m time domain signal components to obtain n time domain signal components, where n is a positive integer less than m; samples the n time domain signal components to obtain n component value sequences corresponding to the n time domain signal components; constructs a feature vector matrix based on the n component value sequences to obtain a vibration signal component feature matrix corresponding to the time domain vibration signal; and uses the vibration signal component feature matrix as input of a pre-trained fault diagnosis model to perform calculations to obtain an aircraft engine fault diagnosis result. Since aircraft engine failures will cause abnormal aircraft engine vibration, when performing empirical mode decomposition on the time domain vibration signal, the energy is usually concentrated in the first few time domain signal components obtained by decomposition. That is, the component value sequence corresponding to the first few time domain signal components obtained by decomposition can highlight the local characteristic information of the vibration signal, thereby achieving accurate diagnosis of aircraft engine failures. At the same time, it can also reduce the computational complexity of fault diagnosis, reduce the cost of fault diagnosis, and facilitate practical application and promotion.

[0072] See also Figure 2 In a second aspect, an embodiment of the present application provides an aircraft engine fault diagnosis system, the aircraft engine fault diagnosis system comprising:

[0073] An acquisition unit, used to acquire a time domain vibration signal of a specified part of the aircraft engine during operation at rated speed;

[0074] a decomposition unit, configured to perform empirical mode decomposition on the time-domain vibration signal to obtain m time-domain signal components corresponding to the time-domain vibration signal, where m is a positive integer greater than 2;

[0075] a selection unit, configured to select first n of the m time domain signal components to obtain n time domain signal components, where n is a positive integer less than m;

[0076] a sampling unit, configured to sample the n time-domain signal components to obtain n component value sequences corresponding to the n time-domain signal components;

[0077] a construction unit, configured to construct a characteristic vector matrix based on the n component value sequences to obtain a vibration signal component characteristic matrix corresponding to the time domain vibration signal;

[0078] a fault diagnosis unit, configured to perform calculations on the vibration signal component characteristic matrix as input to a pre-trained fault diagnosis model to obtain a fault diagnosis result of the aircraft engine;

[0079] Among them, the fault diagnosis model is trained by using the sample vibration signal component feature matrix corresponding to the historical sample time domain vibration signal of the specified part of the aircraft engine during the operation at rated speed as sample input, and the fault classification result of the aircraft engine when the historical sample time domain vibration signal is obtained as sample output.

[0080] The working process, working details and technical effects of the aircraft engine fault diagnosis system provided in the second aspect of this embodiment can be found in the first aspect of the embodiment and will not be repeated here.

[0081] like Figure 3 As shown, the third aspect of an embodiment of the present application provides an electronic device, comprising a memory, a processor and a transceiver that are communicatively connected in sequence, wherein the memory is used to store computer programs, the transceiver is used to send and receive messages, and the processor is used to read the computer program and execute the aircraft engine fault diagnosis method as described in the first aspect of the embodiment.

[0082] For example, the memory may include, but is not limited to, random access memory (RAM), read-only memory (ROM), flash memory, first-in-first-out memory (FIFO) and / or first-in-last-out memory (FILO), etc.; the processor may include, but is not limited to, a microprocessor of the STM32F105 series, an ARM (Advanced RISC Machines), an X86 or other architecture processor, or a processor with an integrated NPU (neural-network processing units); the transceiver may include, but is not limited to, a WiFi (Wireless Fidelity) wireless transceiver, a Bluetooth wireless transceiver, a General Packet Radio Service (GPRS) wireless transceiver, a ZigBee protocol (a low-power local area network protocol based on the IEEE802.15.4 standard, ZigBee) wireless transceiver, a 3G transceiver, a 4G transceiver and / or a 5G transceiver, etc.

[0083] A fourth aspect of this embodiment provides a computer-readable storage medium storing instructions containing the aircraft engine fault diagnosis method described in the first aspect of the embodiment. Specifically, the computer-readable storage medium stores instructions that, when executed on a computer, execute the aircraft engine fault diagnosis method described in the first aspect. The computer-readable storage medium refers to a data storage medium and may include, but is not limited to, a floppy disk, a CD, a hard disk, a flash memory, a USB flash drive, and / or a memory stick. The computer may be a general-purpose computer, a dedicated computer, a computer network, or other programmable device.

[0084] The fifth aspect of this embodiment provides a computer program product containing instructions, which, when executed on a computer, causes the computer to execute the aircraft engine fault diagnosis method as described in the first aspect of the embodiment, wherein the computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device.

[0085] It should be understood that certain details are provided in the following description to facilitate a thorough understanding of the example embodiments. However, one of ordinary skill in the art will appreciate that the example embodiments can be practiced without these specific details. For example, a system may be shown in block diagrams to avoid obscuring the example with unnecessary detail. In other instances, well-known processes, structures, and techniques may be shown without unnecessary detail to avoid obscuring the example embodiments.

[0086] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention shall be included in the scope of protection of the present invention.

Claims

1. A method for diagnosing aircraft engine faults, characterized in that: include: Obtain the time domain vibration signal of a specified part of an aircraft engine during operation at rated speed; Performing empirical mode decomposition on the time-domain vibration signal to obtain m time-domain signal components corresponding to the time-domain vibration signal, where m is a positive integer greater than 2; Selecting the first n of the m time-domain signal components to obtain n time-domain signal components, where n is a positive integer less than m; Sampling the n time-domain signal components to obtain n component value sequences corresponding to the n time-domain signal components; constructing a characteristic vector matrix based on the n component value sequences to obtain a vibration signal component characteristic matrix corresponding to the time domain vibration signal; Using the vibration signal component feature matrix as input of a pre-trained fault diagnosis model to perform calculations to obtain a fault diagnosis result of the aircraft engine; Among them, the fault diagnosis model is trained by using the sample vibration signal component feature matrix corresponding to the historical sample time domain vibration signal of the specified part of the aircraft engine during the operation at rated speed as sample input, and the fault classification result of the aircraft engine when the historical sample time domain vibration signal is obtained as sample output.

2. The method for diagnosing aero-engine faults according to claim 1, wherein: The sampling of the n time domain signal components to obtain n component value sequences corresponding to the n time domain signal components includes: For any one of the n time domain signal components, dividing the any one time domain signal component into a plurality of signal component segments with the same time intervals, to obtain a sequence of n signal component segments corresponding one-to-one to the n time domain signal components; Extracting the component amplitude corresponding to each signal component segment in each signal component segment sequence to obtain a component value sequence corresponding to each signal component segment sequence; The component value sequence corresponding to any signal component segment sequence is used as the component value sequence of the time domain signal component corresponding to the any signal component segment sequence, thereby obtaining n component value sequences corresponding to the n time domain signal components.

3. The method for diagnosing aircraft engine faults according to claim 2, wherein: The extracting the component amplitude corresponding to each signal component segment in each signal component segment sequence to obtain a component value sequence corresponding to each signal component segment sequence includes: The component amplitude average value corresponding to each signal component segment in each signal component segment sequence is calculated to obtain a component value sequence corresponding to each signal component segment sequence.

4. The method for diagnosing aircraft engine faults according to claim 1, wherein: The constructing of a characteristic vector matrix based on the n component value sequences to obtain a vibration signal component characteristic matrix corresponding to the time domain vibration signal includes: Normalizing the n component value sequences to obtain n normalized component value sequences corresponding one-to-one to the n component value sequences; The n normalized component value sequences are combined to obtain a vibration signal component feature matrix corresponding to the time domain vibration signal.

5. The method for diagnosing aircraft engine faults according to claim 1, characterized in that: There are multiple designated locations, and the vibration signal component feature matrix is ​​used as an input of a pre-trained fault diagnosis model to perform calculations to obtain a fault diagnosis result for the aircraft engine, including: The vibration signal component feature matrices corresponding to the time-domain vibration signals of multiple designated parts are combined and used as inputs of a pre-trained fault diagnosis model for calculation to obtain a fault diagnosis result of the aircraft engine.

6. The method for diagnosing aircraft engine faults according to claim 1, wherein: The value range of m is [5,10], and the value range of n is [2,5].

7. The method for diagnosing aircraft engine faults according to claim 1, characterized in that: The fault diagnosis model is a convolutional neural network model or a recurrent neural network model.

8. An aircraft engine fault diagnosis system, characterized in that: include: An acquisition unit, used to acquire a time domain vibration signal of a specified part of the aircraft engine during operation at rated speed; a decomposition unit, configured to perform empirical mode decomposition on the time-domain vibration signal to obtain m time-domain signal components corresponding to the time-domain vibration signal, where m is a positive integer greater than 2; a selection unit, configured to select first n of the m time domain signal components to obtain n time domain signal components, where n is a positive integer less than m; a sampling unit, configured to sample the n time-domain signal components to obtain n component value sequences corresponding to the n time-domain signal components; a construction unit, configured to construct a characteristic vector matrix based on the n component value sequences to obtain a vibration signal component characteristic matrix corresponding to the time domain vibration signal; a fault diagnosis unit, configured to perform calculations on the vibration signal component characteristic matrix as input to a pre-trained fault diagnosis model to obtain a fault diagnosis result of the aircraft engine; Among them, the fault diagnosis model is trained by using the sample vibration signal component feature matrix corresponding to the historical sample time domain vibration signal of the specified part of the aircraft engine during the operation at rated speed as sample input, and the fault classification result of the aircraft engine when the historical sample time domain vibration signal is obtained as sample output.

9. An electronic device, characterized in that: The invention comprises a memory, a processor and a transceiver which are communicatively connected in sequence, wherein the memory is used to store a computer program, the transceiver is used to send and receive messages, and the processor is used to read the computer program and execute the aircraft engine fault diagnosis method according to any one of claims 1 to 7.

10. A computer program product comprising a computer program or instructions, characterized in that When executed by a computer, the computer program or the instructions implements the aircraft engine fault diagnosis method according to any one of claims 1 to 7.

Images