Engine fault diagnosis method and device, electronic equipment and storage medium

Abstract

The invention relates to the technical field of engines, in particular to an engine fault diagnosis method and device, electronic equipment and a storage medium. Acquiring a first deviation of the current fuel flow corresponding to the target engine relative to the fuel flow of the preset steady-state working point during fault diagnosis; based on the first deviation, a first rotor fault rotating speed deviation value, a second rotor fault rotating speed deviation value and a fault fuel flow deviation value corresponding to the target engine are calculated; and based on the first rotor fault rotating speed deviation value, the second rotor fault rotating speed deviation value and the fault fuel flow deviation value, the fault type corresponding to the target engine is determined. According to the method, the accuracy of the determined fault type corresponding to the target engine is ensured, misdiagnosis and missed diagnosis are not easily caused, in addition, a plurality of sensors do not need to be arranged in the target engine, so that the cost is relatively low, and resource waste is not caused. Therefore, the method not only ensures the accuracy of the determined fault type corresponding to the target engine, but also is high in universality and wide in application.

Description

Technical Field

[0001] The present invention relates to the field of engine technology, and in particular to an engine fault diagnosis method, device, electronic equipment and storage medium. Background Art

[0002] With the continuous development and application of aircraft engine technology, the complexity and reliability requirements of engines are getting higher and higher. As a key part of the engine, the normal operation of the air path system of the aircraft engine is crucial to the flight safety of the aircraft. However, due to the complex structure of the engine air path system and the harsh working environment, fault diagnosis has become a key link in ensuring the reliability of the engine.

[0003] At present, the gas circuit fault diagnosis technology has made certain progress, among which the mainstream fault diagnosis algorithms mainly include the following: Small deviation fault equation method: This method analyzes the parameter changes in the engine gas circuit system and establishes a fault equation to diagnose the fault. However, this method can only diagnose known fault modes and lacks effective diagnostic capabilities for unknown fault modes. Model-based method: This method identifies faults by establishing a mathematical model of the engine gas circuit system and combining the differences between the actual measured parameters and the model predicted values. Although this method can diagnose known fault modes more accurately, it is insufficient in verifying the diagnostic results and has high requirements for the number of measured parameters.

[0004] The existing gas path fault diagnosis methods have the following problems: the existing methods are difficult to effectively diagnose unknown fault modes, which easily leads to misdiagnosis and missed diagnosis. How to ensure that the fault type corresponding to the determined target engine is accurate has become an urgent problem to be solved. Summary of the invention

[0005] In view of this, the present invention provides an engine fault diagnosis method, device, electronic device and storage medium to solve the problem of how to ensure that the fault type corresponding to the determined target engine is accurate, which has become an urgent problem to be solved.

[0006] In a first aspect, the present invention provides an engine fault diagnosis method, the method comprising:

[0007] Acquire a first deviation of a current fuel flow rate corresponding to a target engine during fault diagnosis relative to a preset steady-state operating point fuel flow rate;

[0008] Based on the first deviation, a first rotor fault speed deviation value, a second rotor fault speed deviation value, and a fault fuel flow deviation value corresponding to the target engine are calculated;

[0009] Based on the first rotor fault speed deviation value, the second rotor fault speed deviation value, and the fault fuel flow deviation value, a fault type corresponding to the target engine is determined.

[0010] The engine fault diagnosis method provided in the embodiment of the present application obtains the first deviation of the current fuel flow corresponding to the target engine relative to the preset steady-state operating point fuel flow during fault diagnosis; based on the first deviation, the first rotor fault speed deviation value, the second rotor fault speed deviation value and the fault fuel flow deviation value corresponding to the target engine are calculated, ensuring the accuracy of the calculated first rotor fault speed deviation value, the second rotor fault speed deviation value and the fault fuel flow deviation value corresponding to the target engine. Based on the first rotor fault speed deviation value, the second rotor fault speed deviation value and the fault fuel flow deviation value, the fault type corresponding to the target engine is determined, ensuring the accuracy of the fault type corresponding to the determined target engine. The above method is not prone to misdiagnosis and missed diagnosis, and in addition, it does not require the layout of many sensors in the target engine, so the cost is low and does not cause waste of resources. Therefore, the above method not only ensures the accuracy of the fault type corresponding to the determined target engine, but also has strong universality and is widely used.

[0011] In an optional implementation, based on the first deviation, estimating a first rotor fault speed deviation value, a second rotor fault speed deviation value, and a fault fuel flow deviation value corresponding to the target engine includes:

[0012] Inputting the first deviation into a preset Kalman filter, and outputting a fault factor corresponding to the target engine; the fault factor is used to characterize the fault level corresponding to the target engine;

[0013] According to the fault factor, the first rotor fault speed deviation value, the second rotor fault speed deviation value and the fault fuel flow deviation value are calculated.

[0014] The engine fault diagnosis method provided in the embodiment of the present application inputs the first deviation into a preset Kalman filter, outputs the fault factor corresponding to the target engine, and ensures the accuracy of the output fault factor. According to the fault factor, the first rotor fault speed deviation value, the second rotor fault speed deviation value, and the fault fuel flow deviation value are calculated, and the accuracy of the calculated first rotor fault speed deviation value, the second rotor fault speed deviation value, and the fault fuel flow deviation value is ensured.

[0015] In an optional implementation, the first deviation is input into a preset Kalman filter, and the fault factor corresponding to the target engine is output, including:

[0016] Obtaining a linear model of the working state corresponding to the target engine;

[0017] Generate a preset Kalman filter based on the linear model;

[0018] The first deviation is input into a preset Kalman filter, and a fault factor corresponding to the target engine is output.

[0019] The engine fault diagnosis method provided by the embodiment of the present application obtains a linear model of the working state corresponding to the target engine; based on the linear model, a preset Kalman filter is generated to ensure the accuracy of the generated preset Kalman filter. The first deviation is input into the preset Kalman filter to output the fault factor corresponding to the target engine, thereby ensuring the accuracy of the output fault factor corresponding to the target engine.

[0020] In an optional implementation, the first deviation is input into a preset Kalman filter, and the fault factor corresponding to the target engine is output, including:

[0021] Inputting the first deviation to the target engine, and outputting a first operating parameter change corresponding to the target engine;

[0022] Inputting the first deviation into a preset Kalman filter, and outputting a change amount of a second operating parameter corresponding to the target engine;

[0023] Comparing the first operating parameter change amount with the second operating parameter change amount;

[0024] If the parameter difference between the first operating parameter change and the second operating parameter change is within a first preset difference range, the first deviation is input into a preset Kalman filter, and a fault factor corresponding to the target engine is output.

[0025] The engine fault diagnosis method provided in the embodiment of the present application inputs the first deviation into the target engine, outputs the first operating parameter change corresponding to the target engine, and ensures the accuracy of the output first operating parameter change. The first deviation is input into a preset Kalman filter, and the second operating parameter change corresponding to the target engine is output, and ensures the accuracy of the output second operating parameter change corresponding to the target engine. The first operating parameter change and the second operating parameter change are compared; if the parameter difference between the first operating parameter change and the second operating parameter change is within the first preset difference range, it is determined that the preset Kalman filter is stable, the first deviation is input into the preset Kalman filter, and the fault factor corresponding to the target engine is output, and the accuracy of the output fault factor corresponding to the target engine is ensured.

[0026] In an optional implementation, there are multiple preset Kalman filters, each preset Kalman filter corresponds to a different fault type, and according to the fault factor, the first rotor fault speed deviation value, the second rotor fault speed deviation value, and the fault fuel flow deviation value are calculated, including:

[0027] According to the fault type corresponding to the preset Kalman filter, determine the first rotor preset speed deviation value, the second rotor preset speed deviation value, and the preset fuel flow deviation value corresponding to the fault type; wherein the first rotor preset speed deviation value, the second rotor preset speed deviation value, and the preset fuel flow deviation value are respectively used to characterize the first rotor speed deviation value, the second rotor speed deviation value, and the fuel flow deviation value corresponding to the target engine when a preset level fault occurs;

[0028] The fault factor is multiplied by the first rotor preset speed deviation value, the second rotor preset speed deviation value and the preset fuel flow deviation value to calculate the first rotor fault speed deviation value, the second rotor fault speed deviation value and the fault fuel flow deviation value.

[0029] The engine fault diagnosis method provided in the embodiment of the present application determines the first rotor preset speed deviation value, the second rotor preset speed deviation value, and the preset fuel flow deviation value corresponding to the fault type according to the fault type corresponding to the preset Kalman filter. The accuracy of the first rotor preset speed deviation value, the second rotor preset speed deviation value, and the preset fuel flow deviation value corresponding to the determined fault type is guaranteed. The fault factor is multiplied by the first rotor preset speed deviation value, the second rotor preset speed deviation value, and the preset fuel flow deviation value to calculate the first rotor fault speed deviation value, the second rotor fault speed deviation value, and the fault fuel flow deviation value, thereby ensuring the accuracy of the calculated first rotor fault speed deviation value, the second rotor fault speed deviation value, and the fault fuel flow deviation value.

[0030] In an optional implementation manner, each preset Kalman filter corresponds to at least one fault type, and the preset Kalman filter outputs a fault factor corresponding to each fault type; the fault factor is multiplied by the first rotor preset speed deviation value, the second rotor preset speed deviation value, and the preset fuel flow deviation value to calculate the first rotor fault speed deviation value, the second rotor fault speed deviation value, and the fault fuel flow deviation value, including:

[0031] Obtaining a first rotor preset speed deviation value, a second rotor preset speed deviation value, and a preset fuel flow deviation value for each fault type corresponding to a preset Kalman filter;

[0032] Multiply the fault factor corresponding to each fault type by the corresponding first rotor preset speed deviation value, second rotor preset speed deviation value and preset fuel flow deviation value to obtain the first rotor sub-fault speed deviation value, second rotor sub-fault speed deviation value and sub-fault fuel flow deviation value corresponding to each fault type;

[0033] Adding the first rotor fault speed deviation values ​​to obtain the first rotor fault speed deviation value;

[0034] Adding the second rotor fault speed deviation values ​​to obtain the second rotor fault speed deviation value;

[0035] The fault fuel flow deviation values ​​of each sub-fault are added together to obtain the fault fuel flow deviation value.

[0036] The engine fault diagnosis method provided by the embodiment of the present application obtains the first rotor preset speed deviation value, the second rotor preset speed deviation value and the preset fuel flow deviation value of each fault type corresponding to the preset Kalman filter; the fault factor corresponding to each fault type is multiplied by the corresponding first rotor preset speed deviation value, the second rotor preset speed deviation value and the preset fuel flow deviation value to obtain the first rotor sub-fault speed deviation value, the second rotor sub-fault speed deviation value and the sub-fault fuel flow deviation value corresponding to each fault type, thereby ensuring the accuracy of the first rotor sub-fault speed deviation value, the second rotor sub-fault speed deviation value and the sub-fault fuel flow deviation value corresponding to each fault type. Each first rotor sub-fault speed deviation value is added to obtain the first rotor fault speed deviation value, thereby ensuring the accuracy of the calculated first rotor fault speed deviation value. Each second rotor sub-fault speed deviation value is added to obtain the second rotor fault speed deviation value, thereby ensuring the accuracy of the calculated second rotor fault speed deviation value. Each sub-fault fuel flow deviation value is added to obtain the fault fuel flow deviation value, thereby ensuring the accuracy of the calculated fault fuel flow deviation value.

[0037] In an optional implementation, determining the fault type corresponding to the target engine based on the first rotor fault speed deviation value, the second rotor fault speed deviation value, and the fault fuel flow deviation value includes:

[0038] Obtaining a first rotor actual speed deviation value, a second rotor actual speed deviation value, and an actual fuel flow deviation value of a target engine;

[0039] Subtract the first rotor fault speed deviation value corresponding to each preset Kalman filter from the first rotor actual speed deviation value and square it to obtain a first square value;

[0040] Subtract the second rotor fault speed deviation value corresponding to each preset Kalman filter from the second rotor actual speed deviation value and then square it to obtain a second square value;

[0041] Subtract the fault fuel flow deviation value and the actual fuel flow deviation value corresponding to each preset Kalman filter and then square it to obtain a third square value;

[0042] After adding the first square value, the second square value and the third square value, a square root calculation is performed to obtain a square root value;

[0043] If there is a square root value corresponding to a preset Kalman filter within the second preset difference range, it is determined that the fault type corresponding to the preset Kalman filter is the fault type corresponding to the target engine, and the fault factor output by the preset Kalman filter is the fault level corresponding to the target engine.

[0044] The engine fault diagnosis method provided by the embodiment of the present application obtains the actual speed deviation value of the first rotor, the actual speed deviation value of the second rotor, and the actual fuel flow deviation value of the target engine; the first rotor fault speed deviation value corresponding to each preset Kalman filter is squared after being subtracted from the actual speed deviation value of the first rotor to obtain a first square value, thereby ensuring the accuracy of the first square value obtained, so that the difference between the first rotor fault speed deviation value and the actual speed deviation value of the first rotor can be represented based on the first square value. The second rotor fault speed deviation value corresponding to each preset Kalman filter is squared after being subtracted from the actual speed deviation value of the second rotor to obtain a second square value. The accuracy of the second square value obtained is ensured, so that the difference between the second rotor fault speed deviation value and the actual speed deviation value of the second rotor can be represented based on the second square value. The fault fuel flow deviation value corresponding to each preset Kalman filter is squared after being subtracted from the actual fuel flow deviation value to obtain a third square value. The accuracy of the third square value obtained is ensured, and then the difference between the fault fuel flow deviation value and the actual fuel flow deviation value can be represented based on the third square value. After adding the first square value, the second square value and the third square value, a square root calculation is performed to obtain a square root value. If there is a square root value corresponding to a preset Kalman filter within the second preset difference range, the fault type corresponding to the preset Kalman filter is determined to be the fault type corresponding to the target engine, and the fault factor output by the preset Kalman filter is the fault level corresponding to the target engine. The accuracy of the fault type and fault level corresponding to the determined target engine is guaranteed.

[0045] In a second aspect, the present invention provides an engine fault diagnosis device, the device comprising:

[0046] An acquisition module, used for acquiring a first deviation of a current fuel flow rate corresponding to a target engine relative to a preset steady-state operating point fuel flow rate during fault diagnosis;

[0047] A calculation module, configured to calculate a first rotor fault speed deviation value, a second rotor fault speed deviation value, and a fault fuel flow deviation value corresponding to the target engine based on the first deviation;

[0048] The determination module is used to determine the fault type corresponding to the target engine based on the first rotor fault speed deviation value, the second rotor fault speed deviation value and the fault fuel flow deviation value.

[0049] The engine fault diagnosis device provided in the embodiment of the present application obtains the first deviation of the current fuel flow corresponding to the target engine relative to the preset steady-state operating point fuel flow during fault diagnosis; based on the first deviation, the first rotor fault speed deviation value, the second rotor fault speed deviation value and the fault fuel flow deviation value corresponding to the target engine are calculated, thereby ensuring the accuracy of the calculated first rotor fault speed deviation value, the second rotor fault speed deviation value and the fault fuel flow deviation value corresponding to the target engine. Based on the first rotor fault speed deviation value, the second rotor fault speed deviation value and the fault fuel flow deviation value, the fault type corresponding to the target engine is determined, thereby ensuring the accuracy of the fault type corresponding to the determined target engine. The above device is not prone to misdiagnosis and missed diagnosis, and in addition, it does not require the layout of many sensors in the target engine, so the cost is low and does not cause waste of resources. Therefore, the above device method not only ensures the accuracy of the fault type corresponding to the determined target engine, but also the above method has strong universality and is widely used.

[0050] In a third aspect, the present invention provides an electronic device, comprising: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the engine fault diagnosis method of the first aspect or any corresponding embodiment thereof by executing the computer instructions.

[0051] In a fourth aspect, the present invention provides a computer-readable storage medium having computer instructions stored thereon, the computer instructions being used to enable a computer to execute the engine fault diagnosis method of the first aspect or any corresponding embodiment thereof.

[0052] In a fifth aspect, the present invention provides a computer program product, comprising computer instructions for causing a computer to execute the engine fault diagnosis method of the first aspect or any corresponding embodiment thereof. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0054] Figure 1 is a flow chart of an engine fault diagnosis method according to an embodiment of the present invention;

[0055] Figure 2 is a flow chart of another engine fault diagnosis method according to an embodiment of the present invention;

[0056] Figure 3 is a schematic cross-sectional view of a certain type of engine according to an embodiment of the present invention;

[0057] Figure 4 is a schematic diagram of a single fault diagnosis result according to an embodiment of the present invention;

[0058] Figure 5 is a schematic diagram of a dual fault diagnosis result according to an embodiment of the present invention;

[0059] Figure 6 is a schematic diagram of a diagnosis result of a three-fault combination according to an embodiment of the present invention;

[0060] Figure 7 is a schematic diagram of an unknown fault diagnosis result according to an embodiment of the present invention;

[0061] Figure 8 is a structural block diagram of an engine fault diagnosis device according to an embodiment of the present invention;

[0062] Fig. 9 It is a schematic diagram of the hardware structure of the electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0063] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0064] With the continuous development and application of aircraft engine technology, the complexity and reliability requirements of engines are getting higher and higher. As a key part of the engine, the normal operation of the air path system of the aircraft engine is crucial to the flight safety of the aircraft. However, due to the complex structure of the engine air path system and the harsh working environment, fault diagnosis has become a key link in ensuring the reliability of the engine.

[0065] At present, the gas circuit fault diagnosis technology has made certain progress, among which the mainstream fault diagnosis algorithms mainly include the following: Small deviation fault equation method: This method analyzes the parameter changes in the engine gas circuit system and establishes a fault equation to diagnose the fault. However, this method can only diagnose known fault modes and lacks effective diagnostic capabilities for unknown fault modes. Model-based method: This method identifies faults by establishing a mathematical model of the engine gas circuit system and combining the differences between the actual measured parameters and the model predicted values. Although this method can diagnose known fault modes more accurately, it is insufficient in verifying the diagnostic results and has high requirements for the number of measured parameters.

[0066] The existing gas path fault diagnosis methods have the following problems: it is difficult to effectively diagnose unknown fault modes, which can easily lead to misdiagnosis and missed diagnosis. In order to improve the accuracy of diagnosis, more parameters need to be measured, but in practical applications, this requirement is difficult to meet due to limitations of sensor layout, cost and other factors. Even if the number of sensors is increased to cover all possible component characteristics, it will still cause a waste of resources due to the limited number of component characteristics that actually change.

[0067] It should be noted that the execution subject of the engine fault diagnosis method provided in the embodiment of the present application may be an engine fault diagnosis device, and the engine fault diagnosis device may be implemented as part or all of an electronic device through software, hardware, or a combination of software and hardware, wherein the electronic device may be a server or a terminal, wherein the server in the embodiment of the present application may be a single server or a server cluster composed of multiple servers, and the terminal in the embodiment of the present application may be a smart phone, a personal computer, a tablet computer, a wearable device, an intelligent robot, or other intelligent hardware devices. In the following method embodiments, the execution subject is an electronic device as an example for explanation.

[0068] According to an embodiment of the present invention, an embodiment of an engine fault diagnosis method is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0069] In this embodiment, a method for diagnosing engine faults is provided, which can be used in the above-mentioned electronic equipment. Figure 1 : is a flow chart of an engine fault diagnosis method according to an embodiment of the present invention. Figure 1 As shown, the process includes the following steps:

[0070] Step S101, obtaining a first deviation of a current fuel flow rate corresponding to a target engine during fault diagnosis relative to a preset steady-state operating point fuel flow rate.

[0071] Specifically, the electronic device may receive a first deviation of a current fuel flow corresponding to the target engine relative to a preset steady-state operating point fuel flow during fault diagnosis input by a user.

[0072] Among them, it should be noted that the first deviation of the current fuel flow corresponding to the target engine during fault diagnosis relative to the preset steady-state operating point fuel flow can be a fluctuation deviation generated by a fixed deviation of the current fuel flow corresponding to the target engine during fault diagnosis relative to the preset steady-state operating point fuel flow.

[0073] The preset steady-state operating point fuel flow rate refers to the fuel flow rate corresponding to the target engine at a normal steady-state operating point.

[0074] It should be noted that the target engine is an aircraft engine.

[0075] Step S102, based on the first deviation, calculating a first rotor fault speed deviation value, a second rotor fault speed deviation value, and a fault fuel flow deviation value corresponding to the target engine.

[0076] Specifically, the electronic device can calculate the fault factor corresponding to the target engine based on the first deviation corresponding to the target engine, and then calculate the first rotor fault speed deviation value, the second rotor fault speed deviation value and the fault fuel flow deviation value corresponding to the target engine based on the fault factor.

[0077] The first rotor fault speed deviation value is used to characterize the difference between the speed of the high-pressure rotor rotating component of the target engine under fault conditions and the preset speed of the high-pressure rotor rotating component under normal conditions. The second rotor fault speed deviation value is used to characterize the difference between the speed of the low-pressure rotor rotating component of the target engine under fault conditions and the preset speed of the low-pressure rotor rotating component under normal conditions.

[0078] Among them, the rotating parts of the high-pressure rotor may include a high-pressure compressor impeller and a high-pressure turbine. Among them, the high-pressure compressor impeller is one of the key components of the high-pressure rotor, and its main function is to compress the air entering the engine. It sucks air from the air inlet through high-speed rotation, and then uses the high-speed rotation of the blades to do work on the air, so that the pressure and temperature of the air increase. As the air is compressed step by step in the compressor, its pressure can reach dozens of atmospheres, providing sufficient high-pressure air for the subsequent combustion process.

[0079] The high-pressure turbine is connected to the high-pressure compressor impeller through a shaft to form a high-pressure rotor. The main function of the high-pressure turbine is to convert the energy of high-temperature combustion gas into mechanical energy to drive the high-pressure compressor impeller and other accessories. When the engine is working, the high-temperature, high-pressure combustion gas discharged from the combustion chamber impacts the blades of the high-pressure turbine, causing the turbine to rotate at high speed. The rotation of the turbine is transmitted to the high-pressure compressor impeller through the shaft, providing it with the power required to compress air. At the same time, the high-pressure turbine can also drive some auxiliary systems of the engine, such as the fuel pump, lubricating oil pump, etc.

[0080] Among them, the rotating parts of the low-pressure rotor include the fan, the low-pressure compressor impeller and the low-pressure turbine. Among them, the fan is the front part of the low-pressure rotor, which is mainly responsible for inhaling a large amount of air. In modern high-bypass turbofan engines, the role of the fan is particularly important. Part of the air it inhales enters the core engine for compression, combustion and work, and the other part bypasses the core engine to form an external bypass airflow. The large amount of airflow generated by the fan provides the main thrust for the engine, especially during the aircraft takeoff and low-speed flight stages, the fan contributes a lot to thrust.

[0081] In some aircraft engines, the low-pressure rotor also includes a low-pressure compressor impeller. Its function is similar to that of the high-pressure compressor impeller, which also compresses air, but the degree of compression is relatively low. The low-pressure compressor impeller further compresses the air sucked in from the fan, increases the air pressure, and then sends it to the high-pressure compressor for further compression.

[0082] The low-pressure turbine is connected to the fan and the low-pressure compressor impeller through a shaft to form a low-pressure rotor. The main function of the low-pressure turbine is to convert the energy of the gas into mechanical energy to drive the low-pressure rotor to rotate. It receives the gas discharged from the high-pressure turbine and uses the remaining energy of the gas to continue to work and provide power for the fan and the low-pressure compressor impeller. The working efficiency of the low-pressure turbine directly affects the overall performance and economy of the engine.

[0083] The rotation speed of these components is the first rotor speed, and the difference between the speed of the first rotor of these components and the first rotor speed under normal operating conditions is the first rotor fault speed deviation value.

[0084] The fault fuel flow deviation is used to characterize the difference between the actual fuel flow of the target engine under fault conditions and the preset fuel flow under normal conditions.

[0085] This step will be described in detail below.

[0086] Step S103, determining the fault type corresponding to the target engine based on the first rotor fault speed deviation value, the second rotor fault speed deviation value and the fault fuel flow deviation value.

[0087] Specifically, the electronic device can obtain the first rotor actual speed deviation value, the second rotor actual speed deviation value, and the actual fuel flow deviation value corresponding to the target engine, and then determine the fault type corresponding to the target engine according to the relationship between the first rotor fault speed deviation value and the first rotor actual speed deviation value, the relationship between the second rotor fault speed deviation value and the second rotor actual speed deviation value, and the relationship between the fault fuel flow deviation value and the actual fuel flow deviation value.

[0088] Among them, the first rotor actual speed deviation value represents the difference between the actual first rotor speed output by the target engine during fault diagnosis and the actual first rotor speed output by the target engine at the normal steady-state operating point; the second rotor actual speed deviation value represents the difference between the actual second rotor speed output by the target engine during fault diagnosis and the actual second rotor speed output by the target engine at the normal steady-state operating point; the actual fuel flow deviation value represents the difference between the actual fuel flow output by the target engine and the actual fuel flow output by the target engine at the normal steady-state operating point.

[0089] This step will be described in detail below.

[0090] The engine fault diagnosis method provided in the embodiment of the present application obtains the first deviation of the current fuel flow corresponding to the target engine relative to the preset steady-state operating point fuel flow during fault diagnosis; based on the first deviation, the first rotor fault speed deviation value, the second rotor fault speed deviation value and the fault fuel flow deviation value corresponding to the target engine are calculated, ensuring the accuracy of the calculated first rotor fault speed deviation value, the second rotor fault speed deviation value and the fault fuel flow deviation value corresponding to the target engine. Based on the first rotor fault speed deviation value, the second rotor fault speed deviation value and the fault fuel flow deviation value, the fault type corresponding to the target engine is determined, ensuring the accuracy of the fault type corresponding to the determined target engine. The above method is not prone to misdiagnosis and missed diagnosis, and in addition, it does not require the layout of many sensors in the target engine, so the cost is low and does not cause waste of resources. Therefore, the above method not only ensures the accuracy of the fault type corresponding to the determined target engine, but also has strong universality and is widely used.

[0091] In this embodiment, a method for diagnosing engine faults is provided, which can be used in the above-mentioned electronic equipment. Figure 2 : is a flow chart of an engine fault diagnosis method according to an embodiment of the present invention. Figure 2 As shown, the process includes the following steps:

[0092] Step S201, obtaining a first deviation of a current fuel flow rate corresponding to a target engine during fault diagnosis relative to a preset steady-state operating point fuel flow rate.

[0093] For details about this step, please refer to the above description of step S101, which will not be elaborated here.

[0094] Step S202: Based on the first deviation, a first rotor fault speed deviation value, a second rotor fault speed deviation value, and a fault fuel flow deviation value corresponding to the target engine are calculated.

[0095] Specifically, the above step S202 may include the following steps:

[0096] Step S2021, input the first deviation to a preset Kalman filter, and output the fault factor corresponding to the target engine.

[0097] Among them, the fault factor is used to characterize the fault level corresponding to the target engine.

[0098] Specifically, the above step S2021 may include the following steps:

[0099] Step a1, obtaining a linear model of the working state corresponding to the target engine.

[0100] Specifically, the electronic device may receive a linear model of the working state corresponding to the target engine input by a user, or may receive a linear model of the working state corresponding to the target engine sent by other devices. The electronic device may also build a linear model of the working state corresponding to the target engine according to the attribute information of the target engine.

[0101] Exemplarily, the linear model of the working state corresponding to the target engine can be as follows:

[0102]

[0103] Where Δη is the component characteristic deviation vector; ω is the system noise, υ is the measurement noise,

[0104] ΔX=[ΔNH,ΔNL,ΔNP,ΔP25,ΔP4,ΔP43,ΔP47,ΔP6] T , respectively, are the first rotor speed deviation, the second rotor speed deviation, the power turbine speed deviation, the deviation of the total pressure at the outlet of section 25 relative to the steady-state point, the deviation of the total pressure at the outlet of section 4 relative to the steady-state point, the deviation of the total pressure at the outlet of section 43 relative to the steady-state point, the deviation of the total pressure at the outlet of section 47 relative to the steady-state point, and the deviation of the total pressure at the outlet of section 6 relative to the steady-state point, and they are normalized using the steady-state point value.

[0105] ΔY=[ΔNH,ΔNL,ΔNP,ΔP25,ΔP4,ΔP43,ΔP47,ΔP6,ΔP3,ΔT6,ΔQ] T, respectively, are the first rotor speed deviation value, the second rotor speed deviation value, the power turbine speed deviation value, the deviation value of the outlet total pressure of section 25 relative to the steady-state point, the deviation value of the outlet total pressure of section 4 relative to the steady-state point, the deviation value of the outlet total pressure of section 43 relative to the steady-state point, the deviation value of the outlet total pressure of section 47 relative to the steady-state point, the deviation value of the outlet total pressure of section 6 relative to the steady-state point, the pressure deviation value, the exhaust temperature deviation value, and the output torque deviation value, and they are normalized using the steady-state point value.

[0106] ΔU=ΔWFB represents the first deviation of the current fuel flow rate relative to the preset steady-state operating point fuel flow rate, and is normalized using the steady-state point value.

[0107] Δη=[Δη LCE ,Δη LCW ,Δη HTE ,Δη HTW ,Δη LTE ,Δη LTW ], each element represents the relative decay of the second rotor compressor efficiency, the second rotor compressor flow, the first rotor turbine efficiency, the first rotor turbine flow, the second rotor turbine efficiency, and the second rotor turbine flow;

[0108] A, B, C, D, L, M are all constant coefficient matrices, ω, υ are system noise and measurement noise respectively, both are zero-mean, uncorrelated, normally distributed white noise. L=[L LCE, L LCW ,L ETE ,L ETW ,L LTE ,L LTW ],M=[M LCE, M LCW ,M HTE ,M HTW ,M LTE ,M LTW ], respectively representing the influence matrix of each component’s characteristic degradation on the linear model state quantity and measurement.

[0109] It should be noted that the above-mentioned deviation value data all represent the deviation value between the current operating parameters of the target engine and the steady-state operating parameters of the target engine in a normal steady state.

[0110] For example, according to Table 1,

[0111] Table 1: Changes in component characteristics under gas path failure

[0112]

[0113] According to the quantitative relationship constraints between the deviations of component characteristics under gas path faults in Table 1, the component characteristic influence matrices L and M are linearly transformed, so that the two component characteristic parameters that need to be estimated under the 100% fault level become a fault level factor. When the Kalman filter is used later, the component characteristics are no longer estimated, but the fault level factor is directly estimated, which significantly reduces the number of component characteristics that need to be estimated.

[0114] According to Table 1, the elements of the L and M matrices under the same fault can be linearly transformed, taking the compressor fouling fault as an example:

[0115]

[0116] L after linear transformation LCDIRT and M LCDIRT It can still represent the impact of compressor fouling failure at 100% on the linear model. Similarly, the impact matrix of the high / second rotor turbine ablation failure at 100% level can be linearly transformed. After the transformation, the number of parameters that need to be estimated when the three fail at the same time changes from 6 component characteristic deviations to 3 fault level factors.

[0117] Step a2: Generate a preset Kalman filter based on the linear model.

[0118] Specifically, the electronic device can generate a preset Kalman filter based on a linear model.

[0119] Exemplarily, the preset Kalman filter may be:

[0120]

[0121] Where K = PH T R -1 , is the steady-state Kalman filter gain, where H=[CM], ΔX=[ΔNH,ΔNL,ΔNP,ΔP25,ΔP4,ΔP43,ΔP47,ΔP6] T , which are the first rotor speed deviation, the second rotor speed deviation, the power turbine speed deviation, the deviation of the outlet total pressure of section 25 relative to the steady-state point, the deviation of the outlet total pressure of section 4 relative to the steady-state point, the deviation of the outlet total pressure of section 43 relative to the steady-state point, the deviation of the outlet total pressure of section 47 relative to the steady-state point, and the deviation of the outlet total pressure of section 6 relative to the steady-state point, and they are normalized using the steady-state point value.

[0122] ΔY=[ΔNH,ΔNL,ΔNP,ΔP25,ΔP4,ΔP43,ΔP47,ΔP6,ΔP3,ΔT6,ΔQ] T, respectively, are the first rotor speed deviation value, the second rotor speed deviation value, the power turbine speed deviation value, the deviation value of the outlet total pressure of section 25 relative to the steady-state point, the deviation value of the outlet total pressure of section 4 relative to the steady-state point, the deviation value of the outlet total pressure of section 43 relative to the steady-state point, the deviation value of the outlet total pressure of section 47 relative to the steady-state point, the deviation value of the outlet total pressure of section 6 relative to the steady-state point, the pressure deviation value, the exhaust temperature deviation value, and the output torque deviation value, and they are normalized using the steady-state point value.

[0123] ΔU=ΔWFB represents the first deviation of the current fuel flow rate relative to the preset steady-state operating point fuel flow rate, and is normalized using the steady-state point value.

[0124] Δη=[Δη LCE ,Δη LCW ,Δη HTE ,Δη HTW ,Δη LTE ,Δη LTW ], each element represents the relative decay of the second rotor compressor efficiency, the second rotor compressor flow, the first rotor turbine efficiency, the first rotor turbine flow, the second rotor turbine efficiency, and the second rotor turbine flow;

[0125] A, B, C, D, L, M are all constant coefficient matrices, ω, υ are system noise and measurement noise respectively, both are zero-mean, uncorrelated, normally distributed white noise. L=[L LCE, L LCW ,L HTE ,L HTW ,L LTE ,L LTW ],M=[M LCE, M LCW ,M HTE ,M HTW ,M LTE ,M LTW ], respectively representing the influence matrix of each component’s characteristic degradation on the linear model state quantity and measurement quantity.

[0126] P is the solution of the following Riccati equation

[0127] FP+PF T +Q-PH T R -1 HP = 0

[0128] in, is the failure factor.

[0129] Step a3: input the first deviation into a preset Kalman filter, and output the fault factor corresponding to the target engine.

[0130] In an optional implementation, the electronic device may input the first deviation into a preset Kalman filter and output a fault factor corresponding to the target engine.

[0131] Specifically, the above step a3 may include the following steps:

[0132] Step a31, inputting the first deviation to the target engine, and outputting the first operating parameter change corresponding to the target engine.

[0133] Specifically, the electronic device may input the first deviation into the target engine, and output a first operating parameter variation corresponding to the target engine.

[0134] Optionally, the electronic device may also input the first deviation into a nonlinear model corresponding to the target engine, and output a change in the first operating parameter corresponding to the target engine.

[0135] Among them, the first working parameter change may include the first rotor speed deviation value, the second rotor speed deviation value, the power turbine speed deviation value, the deviation value of the outlet total pressure of section 25 relative to the steady-state point, the deviation value of the outlet total pressure of section 4 relative to the steady-state point, the deviation value of the outlet total pressure of section 43 relative to the steady-state point, the deviation value of the outlet total pressure of section 47 relative to the steady-state point, the deviation value of the outlet total pressure of section 6 relative to the steady-state point, the pressure deviation value, the exhaust temperature deviation value, and the output torque deviation value.

[0136] Step a32, inputting the first deviation into a preset Kalman filter, and outputting a change in the second operating parameter corresponding to the target engine.

[0137] Specifically, the electronic device may input the first deviation into a preset Kalman filter, and output a change in the second operating parameter corresponding to the target engine.

[0138] Among them, the second working parameter change may include the first rotor speed deviation value, the second rotor speed deviation value, the power turbine speed deviation value, the deviation value of the total pressure at the outlet of section 25 relative to the steady-state point, the deviation value of the total pressure at the outlet of section 4 relative to the steady-state point, the deviation value of the total pressure at the outlet of section 43 relative to the steady-state point, the deviation value of the total pressure at the outlet of section 47 relative to the steady-state point, the deviation value of the total pressure at the outlet of section 6 relative to the steady-state point, the pressure deviation value, the exhaust temperature deviation value, and the output torque deviation value.

[0139] Step a33, comparing the change in the first operating parameter with the change in the second operating parameter.

[0140] Specifically, the electronic device may compare the first operating parameter change amount with the second operating parameter change amount.

[0141] Step a34, if the parameter difference between the first operating parameter change and the second operating parameter change is within a first preset difference range, the first deviation is input into a preset Kalman filter, and the fault factor corresponding to the target engine is output.

[0142] Specifically, if the parameter difference between the first operating parameter change and the second operating parameter change is within a first preset difference range, the electronic device determines that the preset Kalman filter is stable. Then, the electronic device inputs the first deviation into the preset Kalman filter and outputs a fault factor corresponding to the target engine.

[0143] It should be noted that, in order to enable the preset Kalman filter to work normally and output the fault factor, it is necessary to input the first deviation of the current fuel flow rate relative to the preset steady-state operating point fuel flow rate into the preset Kalman filter.

[0144] Step S2022, calculating the first rotor fault speed deviation value, the second rotor fault speed deviation value and the fault fuel flow deviation value according to the fault factor.

[0145] Specifically, there are multiple preset Kalman filters, and each preset Kalman filter corresponds to a different fault type. The above step S2022 may include the following steps:

[0146] Step b1, according to the fault type corresponding to the preset Kalman filter, determine the first rotor preset speed deviation value, the second rotor preset speed deviation value and the preset fuel flow deviation value corresponding to the fault type.

[0147] Among them, the first rotor preset speed deviation value, the second rotor preset speed deviation value and the preset fuel flow deviation value are respectively used to characterize the first rotor speed deviation value, the second rotor speed deviation value and the fuel flow deviation value corresponding to the target engine when a preset level of fault occurs.

[0148] Specifically, the electronic device can determine the first rotor preset speed deviation value, the second rotor preset speed deviation value and the preset fuel flow deviation value corresponding to the fault type according to the fault type corresponding to the preset Kalman filter.

[0149] Exemplarily, possible fault conditions are combined according to the fault types given in Table 1. There are 7 combinations in total, 3 single faults, 3 double faults, and 1 triple fault. Kalman filters are designed for the 7 fault forms respectively.

[0150] The first rotor preset speed deviation value, the second rotor preset speed deviation value, and the preset fuel flow deviation value corresponding to each fault type may be obtained based on experimental data.

[0151] Step b2, multiplying the fault factor by the first rotor preset speed deviation value, the second rotor preset speed deviation value and the preset fuel flow deviation value, and calculating the first rotor fault speed deviation value, the second rotor fault speed deviation value and the fault fuel flow deviation value.

[0152] In an optional embodiment, the electronic device may multiply the fault factor by the first rotor preset speed deviation value, the second rotor preset speed deviation value, and the preset fuel flow deviation value to calculate the first rotor fault speed deviation value, the second rotor fault speed deviation value, and the fault fuel flow deviation value.

[0153] It should be noted that the calculated first rotor fault speed deviation value, second rotor fault speed deviation value and fault fuel flow deviation value are all fixed values.

[0154] In another optional implementation, each preset Kalman filter corresponds to at least one fault type, and the preset Kalman filter outputs a fault factor corresponding to each fault type; the above step b2 may further include the following steps:

[0155] Step b21, obtaining the first rotor preset speed deviation value, the second rotor preset speed deviation value and the preset fuel flow deviation value of each fault type corresponding to the preset Kalman filter.

[0156] Specifically, the electronic device can obtain a first rotor preset speed deviation value, a second rotor preset speed deviation value, and a preset fuel flow deviation value for each fault type corresponding to a preset Kalman filter.

[0157] Step b22, multiply the fault factor corresponding to each fault type by the corresponding first rotor preset speed deviation value, second rotor preset speed deviation value and preset fuel flow deviation value to obtain the first rotor sub-fault speed deviation value, second rotor sub-fault speed deviation value and sub-fault fuel flow deviation value corresponding to each fault type.

[0158] Specifically, the electronic device will multiply the fault factor corresponding to each fault type by the corresponding first rotor preset speed deviation value, second rotor preset speed deviation value and preset fuel flow deviation value to obtain the first rotor sub-fault speed deviation value, second rotor sub-fault speed deviation value and sub-fault fuel flow deviation value corresponding to each fault type.

[0159] Step b23, adding the first rotor fault speed deviation values ​​to obtain the first rotor fault speed deviation value.

[0160] Specifically, the electronic device adds the first rotor fault speed deviation values ​​to obtain the first rotor fault speed deviation value.

[0161] Step b24, adding the second rotor fault speed deviation values ​​to obtain the second rotor fault speed deviation value.

[0162] Specifically, the electronic device adds the second rotor fault speed deviation values ​​to obtain the second rotor fault speed deviation value.

[0163] Step b25, adding up the sub-fault fuel flow deviation values ​​to obtain the fault fuel flow deviation value.

[0164] Specifically, the electronic device adds up the sub-fault fuel flow deviation values ​​to obtain the fault fuel flow deviation value.

[0165] Step S203, determining the fault type corresponding to the target engine based on the first rotor fault speed deviation value, the second rotor fault speed deviation value and the fault fuel flow deviation value.

[0166] Specifically, the above step S203 may include the following steps:

[0167] Step S2031, obtaining the actual speed deviation value of the first rotor, the actual speed deviation value of the second rotor, and the actual fuel flow deviation value of the target engine.

[0168] Specifically, the electronic device can monitor the target engine and obtain the actual speed deviation value of the first rotor, the actual speed deviation value of the second rotor, and the actual fuel flow deviation value of the target engine.

[0169] Optionally, the electronic device may also input the first deviation into a nonlinear model corresponding to the target engine, and then output a first rotor actual speed deviation value, a second rotor actual speed deviation value, and an actual fuel flow deviation value of the target engine.

[0170] Among them, it should be noted that the actual first rotor speed deviation value represents the difference between the actual first rotor speed output by the target engine during fault diagnosis and the actual first rotor speed output by the target engine at the normal steady-state operating point; the actual second rotor speed deviation value represents the difference between the actual second rotor speed output by the target engine during fault diagnosis and the actual second rotor speed output by the target engine at the normal steady-state operating point; the actual fuel flow deviation value represents the difference between the actual fuel flow output by the target engine during fault diagnosis and the actual fuel flow output by the target engine at the normal steady-state operating point.

[0171] Step S2032, square the difference between the first rotor fault speed deviation value corresponding to each preset Kalman filter and the first rotor actual speed deviation value to obtain a first square value.

[0172] Specifically, the electronic device may square the difference between the first rotor fault speed deviation value corresponding to each preset Kalman filter and the first rotor actual speed deviation value to obtain a first square value.

[0173] Step S2033, square the difference between the second rotor fault speed deviation value corresponding to each preset Kalman filter and the second rotor actual speed deviation value to obtain a second square value.

[0174] Specifically, the electronic device may square the difference between the second rotor fault speed deviation value corresponding to each preset Kalman filter and the second rotor actual speed deviation value to obtain a second square value.

[0175] Step S2034, square the difference between the fault fuel flow deviation value and the actual fuel flow deviation value corresponding to each preset Kalman filter to obtain a third square value.

[0176] Specifically, the electronic device may square the difference between the fault fuel flow deviation value and the actual fuel flow deviation value corresponding to each preset Kalman filter to obtain a third square value.

[0177] Step S2035, after adding the first square value, the second square value and the third square value, perform a square root calculation to obtain a square root value.

[0178] Specifically, the electronic device may add the first square value, the second square value, and the third square value, and then perform a square root calculation to obtain a square root value.

[0179] Step S2036, if there is a square root value corresponding to a preset Kalman filter within the second preset difference range, it is determined that the fault type corresponding to the preset Kalman filter is the fault type corresponding to the target engine, and the fault factor output by the preset Kalman filter is the fault level corresponding to the target engine.

[0180] Specifically, the electronic device can compare the square root value corresponding to the preset Kalman filter with the maximum value and the minimum value within the second preset difference range. If there is a square root value corresponding to the preset Kalman filter within the second preset difference range, the electronic device determines that the fault type corresponding to the preset Kalman filter is the fault type corresponding to the target engine, and the electronic device determines that the fault factor output by the preset Kalman filter is the fault level corresponding to the target engine.

[0181] If there is no square root value corresponding to the preset Kalman filter within the second preset difference range, it is determined that the diagnosis has failed and an unknown fault has occurred, and other methods need to be used to find out the cause of the fault.

[0182] For example, for each fault form, the fault level factor P estimated by the Kalman filter isi is the weight, and the parameter change ΔfaultY is measured at a specific fault level of 100% i Perform weighted summation The measured parameter change ΔY under the fault to be diagnosed dia By making a difference, we can get the diagnostic reliability index vector. When the 2-norm σ<ε of the reliability index vector (ε is the diagnostic threshold), the fault diagnosis is considered successful, and the fault type and fault level factor are output. Otherwise, the diagnosis fails, and it is considered that an unknown fault has occurred, and other methods are needed to find out the cause of the fault.

[0183] The engine fault diagnosis method provided in the embodiment of the present application obtains a linear model of the working state corresponding to the target engine; based on the linear model, a preset Kalman filter is generated to ensure the accuracy of the generated preset Kalman filter. The first deviation is input into the target engine, and the first working parameter change corresponding to the target engine is output, thereby ensuring the accuracy of the output first working parameter change. The first deviation is input into the preset Kalman filter, and the second working parameter change corresponding to the target engine is output, thereby ensuring the accuracy of the output second working parameter change corresponding to the target engine. The first working parameter change is compared with the second working parameter change; if the parameter difference between the first working parameter change and the second working parameter change is within the first preset difference range, it is determined that the preset Kalman filter is stable, the first deviation is input into the preset Kalman filter, and the fault factor corresponding to the target engine is output, thereby ensuring the accuracy of the output fault factor corresponding to the target engine.

[0184] Then, the preset speed deviation value of the first rotor, the preset speed deviation value of the second rotor, and the preset fuel flow deviation value of each fault type corresponding to the preset Kalman filter are obtained; the fault factor corresponding to each fault type is multiplied by the corresponding preset speed deviation value of the first rotor, the preset speed deviation value of the second rotor, and the preset fuel flow deviation value, to obtain the first rotor sub-fault speed deviation value, the second rotor sub-fault speed deviation value, and the sub-fault fuel flow deviation value corresponding to each fault type, thereby ensuring the accuracy of the first rotor sub-fault speed deviation value, the second rotor sub-fault speed deviation value, and the sub-fault fuel flow deviation value corresponding to each fault type. Each first rotor sub-fault speed deviation value is added to obtain the first rotor fault speed deviation value, thereby ensuring the accuracy of the calculated first rotor fault speed deviation value. Each second rotor sub-fault speed deviation value is added to obtain the second rotor fault speed deviation value, thereby ensuring the accuracy of the calculated second rotor fault speed deviation value. Each sub-fault fuel flow deviation value is added to obtain the fault fuel flow deviation value, thereby ensuring the accuracy of the calculated fault fuel flow deviation value.

[0185] Next, when obtaining the actual speed deviation value of the first rotor, the actual speed deviation value of the second rotor, and the actual fuel flow deviation value of the target engine during fault diagnosis; the first rotor fault speed deviation value corresponding to each preset Kalman filter is squared after being subtracted from the actual speed deviation value of the first rotor to obtain the first square value, thereby ensuring the accuracy of the first square value obtained, and thus the difference between the first rotor fault speed deviation value and the actual speed deviation value of the first rotor can be represented based on the first square value. The second rotor fault speed deviation value corresponding to each preset Kalman filter is squared after being subtracted from the actual speed deviation value of the second rotor to obtain the second square value. The accuracy of the second square value obtained is ensured, thereby the difference between the second rotor fault speed deviation value and the actual speed deviation value of the second rotor can be represented based on the second square value. The fault fuel flow deviation value corresponding to each preset Kalman filter is squared after being subtracted from the actual fuel flow deviation value to obtain the third square value. The accuracy of the third square value obtained is ensured, thereby the difference between the fault fuel flow deviation value and the actual fuel flow deviation value can be represented based on the third square value. After adding the first square value, the second square value, and the third square value, a square root calculation is performed to obtain a square root value. If there is a square root value corresponding to a preset Kalman filter within the second preset difference range, the fault type corresponding to the preset Kalman filter is determined to be the fault type corresponding to the target engine, and the fault factor output by the preset Kalman filter is the fault level corresponding to the target engine, thereby ensuring the accuracy of the fault type and fault level corresponding to the determined target engine.

[0186] In order to better introduce the engine fault diagnosis method provided by the embodiment of the present application, the embodiment of the present application provides a specific implementation method of the engine fault diagnosis method. The details are as follows:

[0187] (1) The structure of a certain type of engine is shown in the attached figure. Figure 3 shown. Figure 3 In the figure, the section numbers are: 1-inlet entrance; 2-second rotor compressor inlet; 25-first rotor compressor inlet; 3-first rotor compressor outlet; 4-first rotor turbine inlet; 43-first rotor turbine outlet; 47-second rotor turbine outlet; 5-power turbine outlet; 6-transition section outlet (tail nozzle inlet); 8-tail nozzle outlet.

[0188] (2) The initial linear model used for gas path fault diagnosis is:

[0189]

[0190] in:

[0191] ΔX=[ΔNH,ΔNL,ΔNP,ΔP25,ΔP4,ΔP43,ΔP47,ΔP6] T, are respectively the first rotor speed deviation value, the second rotor speed deviation value, the power turbine speed deviation value, the deviation value of the outlet total pressure of section 25 relative to the steady-state point to the deviation value of the outlet total pressure of section 6 relative to the steady-state point, and are normalized using the steady-state point value;

[0192] ΔY=[ΔNH,ΔNL,ΔNP,ΔP25,ΔP4,ΔP43,ΔP47,ΔP6,ΔP3,ΔT6,ΔQ] T , respectively, are the first rotor speed, the second rotor speed, the power turbine speed, the outlet total pressure of sections 25 to 6, the P3 pressure, the exhaust temperature T6, the deviation value of the output torque Q relative to the steady-state point, and normalized using the steady-state point value;

[0193] ΔU = ΔWFB, which represents the deviation of the fuel flow rate from the steady-state point and is normalized using the steady-state point value;

[0194] Δη=[Δη LCE ,Δη LCW ,Δη HTE ,Δη HTW ,Δη LTE ,Δη LTW ], each element represents the relative decay of the second rotor compressor efficiency, the second rotor compressor flow, the first rotor turbine efficiency, the first rotor turbine flow, the second rotor turbine efficiency, and the second rotor turbine flow;

[0195] A, B, C, D, L, M are all constant coefficient matrices, ω, υ are system noise and measurement noise respectively, and both are zero-mean, uncorrelated, normally distributed white noise.

[0196] (3) Use the fitting method to obtain the coefficient matrices of the linear model of this engine under normal takeoff on a standard day at 0 km altitude, 0 Mach number, and standard day.

[0197]

[0198]

[0199] (4) According to the change of component characteristics at 100% of each fault level in Table 1, the L and M matrices are linearly changed, and the influence of component characteristic changes under gas path fault on the linear model is transformed into the influence of fault level factors under 100% fault on the linear model.

[0200] After transformation, we have:

[0201]

[0202] (5) According to the sensor noise level, the Kalman filter parameters are selected, and the covariance matrix of the measurement noise v is taken as R = 0.0052 I n ; Set the measurement parameter noise level to 0.005 2 ; The state noise ω covariance matrix is ​​Q = 10 -4 I n ;

[0203] (6) Under the same atmospheric conditions as the linear model and at a 100% level of engine compressor fouling failure, the quantitative characteristics of the measurable parameters are:

[0204]

[0205] At the 100% level of the first rotor turbine ablation fault, the quantitative characteristics of the measurable parameters are:

[0206]

[0207] At the 100% level of the second rotor turbine ablation fault, the quantitative characteristics of the measurable parameters are:

[0208]

[0209] (7) Under each gas path fault, the fault diagnosis threshold ε=0.001.

[0210] (8) When the compressor fouling single fault level is 0.7, the measured parameter changes and fault diagnosis results of the fault to be diagnosed are shown in Table 2. Figure 4 .

[0211] Table 2 Compressor fouling single fault diagnosis

[0212]

[0213]

[0214] From a numerical point of view, the quantitative characteristics of the measured parameters under the compressor fouling fault level of 0.6372 are close to the quantitative characteristics of the parameters under the real fault; intuitively, only the quantitative characteristics of the compressor fouling fault fall within the sphere with the change of the measured parameter to be diagnosed as the sphere center and the diagnosis threshold as the radius (see Figure 4 ).

[0215] There are certain errors in Kalman filter estimation, which is determined by model errors, filter parameters and measurement noise. Certain methods can be taken to further improve the accuracy of filter estimation; however, since the purpose of fault diagnosis is mainly to isolate the fault to a certain component, although there is an estimation error of the fault level factor, the fault isolation effect has actually been achieved, and this error has little impact on fault diagnosis.

[0216] (9) Under the combined fault of compressor fouling fault level 0.5 and first rotor turbine ablation fault level 0.7 (preset), the single fault diagnosis results are shown in Table 3. Figure 5 .

[0217] Table 3 Combined fault diagnosis of compressor fouling and first rotor turbine ablation 1

[0218]

[0219] If the single fault exceeds the diagnostic threshold, double faults are used for diagnosis. The diagnostic results are shown in Table 4. Figure 5 .

[0220] Table 4 Combined fault diagnosis of compressor fouling and first rotor turbine ablation 2

[0221]

[0222]

[0223] The diagnostic results of the fouling and first rotor turbine ablation dual fault combination were within the diagnostic threshold, and the diagnosis was successful. The diagnostic results were fouling fault level 0.35 and first rotor turbine ablation fault level 0.69. Compared with the preset fault, fault isolation was achieved and the error was within an acceptable range.

[0224] (10) Under the three-fault combination of compressor fouling fault and high second rotor turbine ablation fault level of 0.3, the fault diagnosis results are shown in Table 5. Figure 6 .

[0225] Table 5 Combined fault diagnosis of compressor fouling and high / second rotor turbine ablation

[0226]

[0227]

[0228] The diagnosis results were that the fouling fault level was 0.21, the first rotor turbine ablation fault level was 0.27, and the second rotor turbine ablation fault level was 0.28. The faults were successfully diagnosed and the error was within an acceptable range.

[0229] (11) The diagnosis results of unknown fault (leakage at the tip of the first rotor turbine, when the fault level is set to 100%, the efficiency of the first rotor turbine decreases by 2.5%, and the flow rate remains unchanged due to the throttling effect of the guide throat) are shown in Table 6. Figure 7 .

[0230] Table 6 Fault diagnosis of leakage at the tip of the first rotor turbine

[0231]

[0232]

[0233] After calculation, all filter diagnosis results exceeded the threshold, the fault diagnosis failed, and an unknown fault did exist. Other methods were needed to find out the cause of the fault.

[0234] In this embodiment, an engine fault diagnosis device is also provided, which is used to implement the above-mentioned embodiments and preferred embodiments, and the descriptions that have been made will not be repeated. As used below, the term "module" can implement a combination of software and / or hardware of a predetermined function. Although the device described in the following embodiments is preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0235] This embodiment provides an engine fault diagnosis device, such as Figure 8 As shown, including:

[0236] An acquisition module 301 is used to acquire a first deviation of a current fuel flow rate corresponding to a target engine relative to a preset steady-state operating point fuel flow rate during fault diagnosis;

[0237] A calculation module 302, configured to calculate a first rotor fault speed deviation value, a second rotor fault speed deviation value, and a fault fuel flow deviation value corresponding to the target engine based on the first deviation;

[0238] The determination module 303 is used to determine the fault type corresponding to the target engine based on the first rotor fault speed deviation value, the second rotor fault speed deviation value and the fault fuel flow deviation value.

[0239] In some optional embodiments, the calculation module 302 is specifically used to input the first deviation into a preset Kalman filter and output a fault factor corresponding to the target engine; the fault factor is used to characterize the fault level corresponding to the target engine; based on the fault factor, the first rotor fault speed deviation value, the second rotor fault speed deviation value and the fault fuel flow deviation value are calculated.

[0240] In some optional embodiments, the calculation module 302 is specifically used to obtain a linear model of the working state corresponding to the target engine; generate a preset Kalman filter based on the linear model; input the first deviation into the preset Kalman filter, and output a fault factor corresponding to the target engine.

[0241] In some optional embodiments, the calculation module 302 is specifically used to input the first deviation into the target engine, and output the first operating parameter change corresponding to the target engine; input the first deviation into a preset Kalman filter, and output the second operating parameter change corresponding to the target engine; compare the first operating parameter change with the second operating parameter change; if the parameter difference between the first operating parameter change and the second operating parameter change is within a first preset difference range, then input the first deviation into the preset Kalman filter, and output the fault factor corresponding to the target engine.

[0242] In some optional embodiments, there are multiple preset Kalman filters, and each preset Kalman filter corresponds to a different fault type. The calculation module 302 is specifically used to determine the first rotor preset speed deviation value, the second rotor preset speed deviation value, and the preset fuel flow deviation value corresponding to the fault type according to the fault type corresponding to the preset Kalman filter; wherein the first rotor preset speed deviation value, the second rotor preset speed deviation value, and the preset fuel flow deviation value are respectively used to characterize the first rotor speed deviation value, the second rotor speed deviation value, and the fuel flow deviation value corresponding to the target engine when a preset level fault occurs; the fault factor is multiplied by the first rotor preset speed deviation value, the second rotor preset speed deviation value, and the preset fuel flow deviation value to calculate the first rotor fault speed deviation value, the second rotor fault speed deviation value, and the fault fuel flow deviation value.

[0243] In some optional embodiments, each preset Kalman filter corresponds to at least one fault type, and the preset Kalman filter outputs a fault factor corresponding to each fault type; the calculation module 302 is specifically used to obtain the first rotor preset speed deviation value, the second rotor preset speed deviation value and the preset fuel flow deviation value of each fault type corresponding to the preset Kalman filter; the fault factor corresponding to each fault type is multiplied by the corresponding first rotor preset speed deviation value, the second rotor preset speed deviation value and the preset fuel flow deviation value to obtain the first rotor sub-fault speed deviation value, the second rotor sub-fault speed deviation value and the sub-fault fuel flow deviation value corresponding to each fault type; each first rotor sub-fault speed deviation value is added to obtain a first rotor fault speed deviation value; each second rotor sub-fault speed deviation value is added to obtain a second rotor fault speed deviation value; each sub-fault fuel flow deviation value is added to obtain a fault fuel flow deviation value.

[0244] In some optional embodiments, the determination module 303 is specifically used to obtain the first rotor actual speed deviation value, the second rotor actual speed deviation value, and the actual fuel flow deviation value of the target engine; the first rotor fault speed deviation value corresponding to each preset Kalman filter is squared by the first rotor actual speed deviation value to obtain a first square value; the second rotor fault speed deviation value corresponding to each preset Kalman filter is squared by the second rotor actual speed deviation value to obtain a second square value; the fault fuel flow deviation value corresponding to each preset Kalman filter is squared by the actual fuel flow deviation value to obtain a third square value; the first square value, the second square value, and the third square value are added together, and a square root calculation is performed to obtain a square root value; if there is a square root value corresponding to a preset Kalman filter within the second preset difference range, it is determined that the fault type corresponding to the preset Kalman filter is the fault type corresponding to the target engine, and the fault factor output by the preset Kalman filter is the fault level corresponding to the target engine.

[0245] The further functional description of each of the above modules and units is the same as that of the above corresponding embodiments and will not be repeated here.

[0246] The engine fault diagnosis device in this embodiment is presented in the form of a functional unit, where the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.

[0247] The embodiment of the present invention also provides an electronic device having the above Figure 8 The engine fault diagnostic device shown.

[0248] See also Fig. 9 , Fig. 9 is a schematic diagram of the structure of an electronic device provided by an optional embodiment of the present invention, such as Fig. 9As shown, the electronic device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. The various components are connected to each other using different buses for communication, and can be installed on a common mainboard or installed in other ways as needed. The processor can process instructions executed in the electronic device, including instructions stored in or on the memory to display graphical information of the GUI on an external input / output device (such as a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple electronic devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Fig. 9 A processor 10 is taken as an example.

[0249] The processor 10 may be a central processing unit, a network processor or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be a dedicated integrated circuit, a programmable logic device or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic or any combination thereof.

[0250] The memory 20 stores instructions executable by at least one processor 10, so that at least one processor 10 executes the method shown in the above embodiment.

[0251] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the electronic device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely arranged relative to the processor 10, and these remote memories may be connected to the electronic device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0252] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid state drive; the memory 20 may also include a combination of the above types of memory.

[0253] The electronic device further includes an input device 30 and an output device 40. The processor 10, the memory 20, the input device 30 and the output device 40 may be connected via a bus or other means. Fig. 9 The example of connecting through bus is taken in the following.

[0254] The input device 30 can receive input digital or character information, and generate key signal input related to the user settings and function control of the electronic device, such as a touch screen, a keypad, a mouse, a track pad, a touch pad, an indicator rod, one or more mouse buttons, a trackball, a joystick, etc. The output device 40 may include a display device, an auxiliary lighting device (e.g., an LED) and a tactile feedback device (e.g., a vibration motor), etc. The above-mentioned display device includes but is not limited to a liquid crystal display, a light emitting diode, a display and a plasma display. In some optional embodiments, the display device can be a touch screen.

[0255] The embodiment of the present invention also provides a computer-readable storage medium. The method according to the embodiment of the present invention can be implemented in hardware, firmware, or can be implemented as a computer code that can be recorded in a storage medium, or can be implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and will be stored in a local storage medium through a network download, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state hard disk, etc.; further, the storage medium can also include a combination of the above types of memories. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor, or hardware, the method shown in the above embodiment is implemented.

[0256] A part of the present invention may be applied as a computer program product, such as a computer program instruction, which, when executed by a computer, can call or provide the method and / or technical solution according to the present invention through the operation of the computer. Those skilled in the art should understand that the existence of the computer program instruction in a computer-readable medium includes, but is not limited to, a source file, an executable file, an installation package file, etc., and accordingly, the way in which the computer program instruction is executed by the computer includes, but is not limited to: the computer directly executes the instruction, or the computer compiles the instruction and then executes the corresponding compiled program, or the computer reads and executes the instruction, or the computer reads and installs the instruction and then executes the corresponding installed program. Here, the computer-readable medium may be any available computer-readable storage medium or communication medium accessible to the computer.

[0257] Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention, and such modifications and variations are all within the scope defined by the appended claims.

Claims

1. An engine fault diagnosis method, characterized in that: The method comprises: Acquire a first deviation of a current fuel flow rate corresponding to a target engine during fault diagnosis relative to a preset steady-state operating point fuel flow rate; Based on the first deviation, calculating a first rotor fault speed deviation value, a second rotor fault speed deviation value, and a fault fuel flow deviation value corresponding to the target engine; Based on the first rotor fault speed deviation value, the second rotor fault speed deviation value, and the fault fuel flow deviation value, a fault type corresponding to the target engine is determined.

2. The method according to claim 1, characterized in that The step of calculating a first rotor fault speed deviation value, a second rotor fault speed deviation value, and a fault fuel flow deviation value corresponding to the target engine based on the first deviation includes: Inputting the first deviation into a preset Kalman filter, and outputting a fault factor corresponding to the target engine; the fault factor is used to characterize the fault level corresponding to the target engine; The first rotor fault speed deviation value, the second rotor fault speed deviation value, and the fault fuel flow deviation value are calculated according to the fault factor.

3. The method according to claim 2, characterized in that The step of inputting the first deviation into a preset Kalman filter and outputting a fault factor corresponding to the target engine includes: Acquire a linear model of the working state corresponding to the target engine; Based on the linear model, generating the preset Kalman filter; The first deviation is input into the preset Kalman filter, and the fault factor corresponding to the target engine is output.

4. The method according to claim 3, characterized in that The step of inputting the first deviation into the preset Kalman filter and outputting the fault factor corresponding to the target engine includes: Inputting the first deviation to the target engine, and outputting a first operating parameter change corresponding to the target engine; Inputting the first deviation into the preset Kalman filter, and outputting a change amount of a second operating parameter corresponding to the target engine; Comparing the first operating parameter change amount with the second operating parameter change amount; If the parameter difference between the first operating parameter change and the second operating parameter change is within a first preset difference range, the first deviation is input into the preset Kalman filter, and the fault factor corresponding to the target engine is output.

5. The method according to claim 2, characterized in that: There are multiple preset Kalman filters, each of which corresponds to a different fault type. The calculating, according to the fault factor, the first rotor fault speed deviation value, the second rotor fault speed deviation value, and the fault fuel flow deviation value includes: According to the fault type corresponding to the preset Kalman filter, determine the first rotor preset speed deviation value, the second rotor preset speed deviation value, and the preset fuel flow deviation value corresponding to the fault type; wherein the first rotor preset speed deviation value, the second rotor preset speed deviation value, and the preset fuel flow deviation value are respectively used to characterize the first rotor speed deviation value, the second rotor speed deviation value, and the fuel flow deviation value corresponding to the target engine when a preset level fault occurs; The fault factor is multiplied by the first rotor preset speed deviation value, the second rotor preset speed deviation value and the preset fuel flow deviation value to calculate the first rotor fault speed deviation value, the second rotor fault speed deviation value and the fault fuel flow deviation value.

6. The method according to claim 5, characterized in that Each of the preset Kalman filters corresponds to at least one fault type, and the preset Kalman filter outputs the fault factor corresponding to each of the fault types; multiplying the fault factor by the first rotor preset speed deviation value, the second rotor preset speed deviation value, and the preset fuel flow deviation value to calculate the first rotor fault speed deviation value, the second rotor fault speed deviation value, and the fault fuel flow deviation value, includes: Acquire the first rotor preset speed deviation value, the second rotor preset speed deviation value, and the preset fuel flow deviation value for each fault type corresponding to the preset Kalman filter; Multiplying the fault factor corresponding to each of the fault types by the corresponding first rotor preset speed deviation value, second rotor preset speed deviation value, and preset fuel flow deviation value to obtain the first rotor sub-fault speed deviation value, second rotor sub-fault speed deviation value, and sub-fault fuel flow deviation value corresponding to each of the fault types; Adding the first rotor fault speed deviation values ​​to obtain the first rotor fault speed deviation value; Adding the second rotor fault speed deviation values ​​to obtain the second rotor fault speed deviation value; The sub-fault fuel flow deviation values ​​are added together to obtain the fault fuel flow deviation value.

7. The method according to claim 6, characterized in that The determining, based on the first rotor fault speed deviation value, the second rotor fault speed deviation value, and the fault fuel flow deviation value, of the fault type of the target engine includes: Obtaining a first rotor actual speed deviation value, a second rotor actual speed deviation value, and an actual fuel flow deviation value of the target engine; Subtract the first rotor fault speed deviation value corresponding to each of the preset Kalman filters from the first rotor actual speed deviation value and then square it to obtain a first square value; Subtract the second rotor fault speed deviation value corresponding to each of the preset Kalman filters from the second rotor actual speed deviation value and then square it to obtain a second square value; Subtract the fault fuel flow deviation value from the actual fuel flow deviation value corresponding to each of the preset Kalman filters and then square it to obtain a third square value; After adding the first square value, the second square value and the third square value, performing a square root calculation to obtain a square root value; If there is a square root value corresponding to the preset Kalman filter within the second preset difference range, it is determined that the fault type corresponding to the preset Kalman filter is the fault type corresponding to the target engine, and the fault factor output by the preset Kalman filter is the fault level corresponding to the target engine.

8. An engine fault diagnosis device, characterized in that: The device comprises: An acquisition module, used for acquiring a first deviation of a current fuel flow rate corresponding to a target engine relative to a preset steady-state operating point fuel flow rate during fault diagnosis; a calculation module, configured to calculate a first rotor fault speed deviation value, a second rotor fault speed deviation value, and a fault fuel flow deviation value corresponding to the target engine based on the first deviation; A determination module is used to determine a fault type corresponding to the target engine based on the first rotor fault speed deviation value, the second rotor fault speed deviation value and the fault fuel flow deviation value.

9. An electronic device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the engine fault diagnosis method according to any one of claims 1 to 7 by executing the computer instructions.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the engine fault diagnosis method according to any one of claims 1 to 7.

11. A computer program product, characterized in that The method comprises computer instructions for causing a computer to execute the engine fault diagnosis method according to any one of claims 1 to 7.

Images