Aero-engine fault diagnosis method and device, electronic equipment and storage medium

Abstract

The application discloses an aero-engine fault diagnosis method and device, electronic equipment and a storage medium. The method comprises the following steps: acquiring an ultrasonic signal collected by an ultrasonic sensor, the ultrasonic sensor is arranged on an aero-engine, and the ultrasonic signal represents vibration characteristics of the aero-engine; for a fault type of the aero-engine, a fault signal required for fault diagnosis is extracted from the ultrasonic signal; the value of a fault characteristic parameter is determined according to the fault signal; and the aero-engine is subjected to fault diagnosis according to the value of the fault characteristic parameter. On the one hand, the interference of various kinetic noise signals and environmental noise signals in the aero-engine can be avoided, and the accuracy and robustness of fault diagnosis are improved; on the other hand, a fault signal capable of representing early faults of the aero-engine can be effectively extracted, and early fault diagnosis is realized.

Description

Technical Field

[0001] This invention relates to the field of fault diagnosis technology, and in particular to a fault diagnosis method, device, electronic equipment, and storage medium for aero-engines. Background Technology

[0002] For aero-engines, timely and accurate fault detection can prevent catastrophic consequences. Current technology typically involves collecting vibration signals from aero-engines using vibration sensors, analyzing these signals to extract fault characteristics, and then performing fault diagnosis.

[0003] The frequency response range of vibration signals acquired by vibration sensors is generally below 20kHz. Aero-engine mechanical systems are extremely complex, including low-pressure and high-pressure rotor systems. The low-pressure rotor system further subdivides into subsystems such as the fan, low-pressure compressor, and low-pressure turbine, while the high-pressure rotor system is divided into subsystems such as the high-pressure compressor and high-pressure turbine. Each subsystem contains numerous components such as bearings, couplings, discs, shafts, and gears. Therefore, the signals acquired by vibration sensors contain a large amount of dynamic signals and environmental noise signals with frequencies below 20kHz, resulting in significant signal contamination. This leads to low accuracy in diagnosing aero-engine faults based on these vibration signals. Furthermore, early mechanical fault signals are relatively weak, making it extremely difficult to extract early fault features from vibration signals below 20kHz. Summary of the Invention

[0004] The technical problem to be solved by the present invention is to overcome the shortcomings of the existing technology of fault diagnosis of aero-engine based on vibration signals collected by vibration sensors, which are seriously polluted and result in low accuracy of fault diagnosis. The present invention provides a fault diagnosis method, device, electronic device and storage medium for aero-engines.

[0005] The present invention solves the above-mentioned technical problems through the following technical solution:

[0006] Firstly, a fault diagnosis method for an aero-engine is provided, including:

[0007] The ultrasonic signal is acquired by an ultrasonic sensor, which is mounted on an aircraft engine, and the ultrasonic signal characterizes the vibration characteristics of the aircraft engine.

[0008] For the specific type of fault in the aero-engine, the fault signal required for fault diagnosis is extracted from the ultrasonic signal;

[0009] The values ​​of the fault characteristic parameters are determined based on the fault signal;

[0010] The aircraft engine is diagnosed based on the values ​​of the fault characteristic parameters.

[0011] Optionally, depending on the type of fault in the aero-engine, fault signals required for fault diagnosis are extracted from the ultrasonic signals, including:

[0012] When the fault type is fault diagnosis, envelope spectrum analysis is performed on the ultrasonic signal;

[0013] Based on the results of envelope spectrum analysis, fault signals with frequencies below a frequency threshold are extracted from the ultrasonic signals.

[0014] Optionally, determining the values ​​of fault characteristic parameters based on the fault signal includes:

[0015] Determine the fault characteristic frequencies required for fault diagnosis;

[0016] Based on the envelope spectrum of the fault signal, calculate the values ​​of the fault characteristic parameters corresponding to the fault characteristic frequencies.

[0017] Optionally, depending on the type of fault in the aero-engine, fault signals required for fault diagnosis are extracted from the ultrasonic signals, including:

[0018] In the case where the fault type is an early fault, the fault characteristic frequency band is determined;

[0019] Extract the fault signal corresponding to the fault characteristic frequency band from the ultrasonic signal.

[0020] Optionally, determining the values ​​of fault characteristic parameters based on the fault signal includes:

[0021] Convert the fault signal into a frequency domain signal;

[0022] Based on the frequency domain signal, calculate the values ​​of the fault characteristic parameters corresponding to the fault characteristic frequency band.

[0023] Secondly, a fault diagnosis device for an aircraft engine is provided, comprising:

[0024] An acquisition module is used to acquire ultrasonic signals collected by an ultrasonic sensor, which is installed on the aircraft engine, and the ultrasonic signals characterize the vibration characteristics of the aircraft engine.

[0025] An extraction module is used to extract fault signals required for fault diagnosis from the ultrasonic signals, based on the fault type of the aero-engine.

[0026] The determination module is used to determine the values ​​of fault characteristic parameters based on the fault signal;

[0027] The diagnostic module is used to perform fault diagnosis on the aero-engine based on the values ​​of the fault characteristic parameters.

[0028] Optionally, the extraction module includes:

[0029] An analysis unit is used to perform envelope spectrum analysis on the ultrasonic signal when the fault type is fault diagnosis.

[0030] An extraction unit is used to extract fault signals with frequencies below a frequency threshold from the ultrasonic signal based on the results of envelope spectrum analysis.

[0031] Optionally, the determining module:

[0032] A determination unit is used to determine the fault characteristic frequencies required for fault diagnosis.

[0033] The calculation unit is used to calculate the values ​​of the fault characteristic parameters corresponding to the fault characteristic frequencies based on the envelope spectrum of the fault signal.

[0034] Optionally, the extraction module is used for:

[0035] The determining unit is used to determine the fault characteristic frequency band when the fault type is an early fault.

[0036] An extraction unit is used to extract a fault signal corresponding to the fault characteristic frequency band from the ultrasonic signal.

[0037] Optionally, the determining module is used to:

[0038] A conversion unit is used to convert the fault signal into a frequency domain signal;

[0039] The calculation unit is used to calculate the values ​​of the fault characteristic parameters corresponding to the fault characteristic frequency band based on the frequency domain signal.

[0040] Thirdly, an electronic device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the method described in any of the preceding claims.

[0041] Thirdly, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps of any of the methods described above.

[0042] The positive and progressive effects of this invention are as follows:

[0043] This invention employs ultrasonic signals collected by an ultrasonic sensor to diagnose faults in aero-engines. On the one hand, it avoids interference from various dynamic noise signals and environmental noise signals in the aero-engine, reducing the false alarm rate and improving the accuracy and robustness of fault diagnosis. On the other hand, ultrasonic signals can capture signals that are more sensitive to early faults, thus effectively extracting fault signals that characterize early faults in aero-engines from the ultrasonic signals, thereby achieving early fault diagnosis. Attached Figure Description

[0044] Figure 1 A flowchart illustrating a fault diagnosis method for an aero-engine, provided as an exemplary embodiment of the present invention;

[0045] Figure 2a This is an envelope analysis result diagram of a vibration signal characterizing the vibration characteristics of an aero-engine, provided by an exemplary embodiment of the present invention.

[0046] Figure 2b This is an envelope analysis result diagram of an ultrasonic signal characterizing the vibration characteristics of an aero-engine, provided by an exemplary embodiment of the present invention.

[0047] Figure 3 A schematic diagram of an aero-engine casing structure is provided as an exemplary embodiment of the present invention;

[0048] Figure 4 A flowchart of another fault diagnosis method for an aero-engine provided as an exemplary embodiment of the present invention;

[0049] Figure 5 A flowchart of another fault diagnosis method for an aero-engine provided as an exemplary embodiment of the present invention;

[0050] Figure 6 A schematic diagram of a fault diagnosis device for an aero-engine provided as an exemplary embodiment of the present invention;

[0051] Figure 7 This is a schematic diagram of the structure of an electronic device shown in an example embodiment of the present invention. Detailed Implementation

[0052] The present invention will be further illustrated by way of embodiments below, but the present invention is not limited to the scope of the embodiments described herein.

[0053] Figure 1 A flowchart of a fault diagnosis method for an aero-engine provided as an exemplary embodiment of the present invention, the method comprising the following steps:

[0054] Step 101: Acquire the ultrasonic signal collected by the ultrasonic sensor, which is installed on the aircraft engine.

[0055] The ultrasonic signal characterizes the vibration characteristics of the aero-engine, and is a high-frequency vibration characteristic.

[0056] An ultrasonic sensor is a sensor developed using the properties of ultrasound, whose vibration frequency is higher than 20 kHz. Because the frequency response range of the ultrasonic signals acquired by an ultrasonic sensor is higher than 20 kHz, while the frequency response of various dynamic noise signals in aero-engines and environmental noise signals is lower than 20 kHz, the ultrasonic signals characterizing the vibration characteristics of aero-engines acquired by an ultrasonic sensor contain less noise and interference signals compared to vibration signals acquired by a vibration sensor. High-frequency signals above 20 kHz are called ultrasonic signals, while signals below 20 kHz are called vibration signals.

[0057] Figure 2a This is an envelope analysis result diagram of a vibration signal characterizing the vibration characteristics of an aero-engine, provided by an exemplary embodiment of the present invention. Figure 2b This is an envelope analysis result diagram of an ultrasonic signal characterizing the vibration characteristics of an aero-engine, provided by an exemplary embodiment of the present invention. (Comparison) Figure 2a and Figure 2b As can be seen from the figure, the envelope of the ultrasonic signal is cleaner than that of the vibration signal, indicating that the ultrasonic signal contains less noise. Therefore, fault diagnosis of aero-engines based on ultrasonic signals can reduce the false alarm rate and improve the accuracy and robustness of fault diagnosis.

[0058] Figure 3 A schematic diagram of an aero-engine casing structure is provided as an exemplary embodiment of the present invention. The aero-engine includes a fan, a low-pressure compressor, a high-pressure compressor, a combustion chamber, a high-pressure turbine, a low-pressure turbine, and other related mechanical subsystems (gearbox, fuel oil pump, etc.). See [reference needed]. Figure 3 The ultrasonic sensors are deployed on the aircraft engine. The number of ultrasonic sensors 31 can be set according to actual needs, and is not limited to... Figure 3 The three shown could be one, two, four, or even more. In this embodiment of the invention, the fault diagnosis process of an aero-engine is illustrated by acquiring and analyzing an ultrasonic signal collected by an ultrasonic sensor. The placement of the ultrasonic sensor is not limited to... Figure 3 As shown, an ultrasonic sensor is installed in the low-pressure compressor, the casing, and other related mechanical subsystems. One or more ultrasonic sensors can be installed in suitable locations within the casing as needed.

[0059] Step 102: Based on the fault type of the aero-engine, extract the fault signals required for fault diagnosis from the ultrasonic signals.

[0060] In one embodiment, fault diagnosis of aero-engines is divided into two main categories:

[0061] One type is conventional fault diagnosis, where "fault" refers to defects such as visible chipping, cracks, and pitting on the surface of components, which generally lead to significant mechanical vibration. If the system is in a "fault" state and a vibration sensor with a suitable frequency response range is installed in a nearby location, the fault will be reflected in the frequency domain characteristics of the corresponding vibration signal.

[0062] One type is early fault diagnosis. "Early fault" is a system state distinct from a "fault" state. It refers to a system that is between "healthy" and "faulty," or in a "sub-healthy" state—meaning the system hasn't reached a fault state but has already begun to deteriorate. In terms of defect size, cracks and pitting, generally less than 2mm in diameter and less than 1mm in depth, are considered early faults. They are visible to the naked eye but not obvious. Under early fault conditions, changes in mechanical vibration signals (below 20kHz) are not significant in the frequency domain. If fault diagnosis is based on quantized frequency domain status indicators set according to mechanical vibration signals, the false alarm rate will be relatively high.

[0063] For different types of fault diagnosis, different fault feature indications required for fault diagnosis are extracted from the ultrasonic signals.

[0064] For early fault diagnosis, fault signals with frequencies not lower than the frequency threshold are extracted from the ultrasonic signals (early fault diagnosis) to perform early fault diagnosis.

[0065] For routine fault diagnosis, fault signals with frequencies below a frequency threshold are extracted from the ultrasonic signals for fault diagnosis.

[0066] The frequency threshold can be set according to the actual conditions such as the model of the aero-engine and the operating environment. For example, if the frequency threshold is set to 20kHz, when performing early fault diagnosis, ultrasonic signals with a frequency of not less than 20kHz are identified as fault signals for early fault diagnosis. Furthermore, energy spectra within one or more specific frequency bands are extracted from ultrasonic signals with a frequency of not less than 20kHz as early fault indications for early fault diagnosis. When performing fault diagnosis, ultrasonic signals with a frequency less than 20kHz are identified as fault signals for fault diagnosis. That is, envelope spectrum analysis is performed on ultrasonic signals with a frequency of not less than 20kHz to extract the amplitude at the fault characteristic frequency (below 20kHz) as the fault indication.

[0067] Step 103: Determine the values ​​of the fault characteristic parameters of the aero-engine based on the fault signals.

[0068] Different types of fault diagnosis correspond to different fault characteristic parameters. Therefore, it is necessary to determine the fault characteristic parameters of the aero-engine based on the needs of fault diagnosis. The fault characteristic parameters are determined based on historical test data and actual aircraft data of the aero-engine.

[0069] For example, fault diagnosis includes fault diagnosis of gears in an aircraft engine and fault diagnosis of the rotor. Rotor fault diagnosis includes: diagnosis of rotor dynamic imbalance, rotor loosening, rotor rubbing, etc. Each of these fault types corresponds to its own fault characteristic parameters (fault indications). The fault characteristic parameters corresponding to each fault diagnosis type are generally obtained based on experience, and the number of fault characteristic parameters corresponding to each fault diagnosis type can be one or more. Early fault diagnosis refers to early fault characteristic indications that differ from the aforementioned fault characteristic indications, occurring when various fault types are still in their early stages and the fault size is small.

[0070] Step 104: Perform fault diagnosis on the aero-engine based on the values ​​of the fault characteristic parameters.

[0071] Each fault characteristic parameter corresponds to its own fault state range, which represents a range of values ​​for the fault characteristic parameter when a certain type of fault occurs in the aero-engine. If the calculated value of the fault characteristic parameter falls within the corresponding fault state range, it is determined that the aero-engine has a fault of the corresponding type; if the calculated value of the fault characteristic parameter does not fall within the corresponding fault state range, it is determined that the aero-engine is operating normally and there is no fault.

[0072] In one embodiment, based on actual needs, two fault state ranges can be set for each fault characteristic parameter: a warning state range and an alarm state range. If the value of the fault characteristic parameter falls within the warning state range, it indicates that the aircraft engine has a corresponding fault risk, and a warning is issued to prompt maintenance personnel to promptly troubleshoot the aircraft engine. If the value of the fault characteristic parameter falls within the alarm state range, it indicates that the aircraft engine has a corresponding fault, and an alarm is issued to prompt maintenance personnel to promptly eliminate the aircraft engine fault. Of course, for early-stage faults, only an alarm needs to be set, without a warning.

[0073] The above-mentioned range of fault conditions was determined based on historical test data and actual aircraft data of aero engines.

[0074] Figure 4 A flowchart illustrating another fault diagnosis method for an aero-engine provided as an exemplary embodiment of the present invention is shown in the figure. The flowchart uses fault diagnosis of an aero-engine as an example to describe the fault diagnosis process in detail. (See also...) Figure 4 The fault diagnosis method includes the following steps:

[0075] Step 401: Acquire the ultrasonic signal collected by the ultrasonic sensor, which is installed on the aircraft engine, and the ultrasonic signal characterizes the vibration characteristics of the aircraft engine.

[0076] The specific implementation of step 401 is similar to that of step 101. For the specific implementation process, please refer to step 101, which will not be repeated here.

[0077] Step 402: In the case of fault diagnosis, perform envelope spectrum analysis on the ultrasonic signal and extract fault signals with frequencies below the frequency threshold from the ultrasonic signal.

[0078] Envelope spectrum analysis of ultrasonic signals involves performing a Hilbert transform on the ultrasonic signal, then taking the extreme values, extracting the envelope from the one-dimensional data obtained after taking the extreme values, and performing an FFT (Fast Fourier Transform) on the envelope signal to obtain the envelope spectrum of the ultrasonic signal. The horizontal axis represents frequency, and the vertical axis represents amplitude.

[0079] By performing envelope spectrum analysis on ultrasonic signals, low-frequency characteristics (fault features) can be extracted from high-frequency signals (ultrasonic signals). Since the frequency band of ultrasonic signals is not in the same band as that of noise signals, ultrasonic signals contain very little noise. Therefore, clean fault signals can be extracted from ultrasonic signals for fault diagnosis.

[0080] In one embodiment, the ultrasonic signal is filtered before envelope spectrum analysis is performed, and then envelope spectrum analysis is performed on the filtered ultrasonic signal.

[0081] Step 403: Determine the fault characteristic frequency required for fault diagnosis, and determine the value of the fault characteristic parameter corresponding to the fault characteristic frequency based on the envelope spectrum of the fault signal.

[0082] The fault characteristic frequency is determined based on the historical operating speed and design parameters of the aero-engine. The value of the fault characteristic parameter (fault characteristic indication) can be, for example, the amplitude at the fault characteristic frequency.

[0083] Different types of fault diagnosis correspond to different fault characteristic parameters and fault characteristic frequencies. For example:

[0084] For the diagnosis of rotor dynamic imbalance, the corresponding fault characteristic parameters may include at least one of the following parameters: amplitude at the fundamental frequency (fault characteristic frequency), amplitude distribution skewness at the fundamental frequency, amplitude distribution kurtosis at the fundamental frequency, and amplitude mean of the frequency band including the fundamental frequency.

[0085] For diagnosing rotor loosening, the corresponding fault characteristic parameters may include at least one of the following parameters: amplitude at twice the fundamental frequency, amplitude distribution skewness at twice the fundamental frequency, amplitude distribution kurtosis at twice the fundamental frequency, and the mean amplitude of the frequency band containing twice the fundamental frequency.

[0086] For the diagnosis of rotor rubbing, the corresponding fault characteristic parameters may include at least one of the following parameters: amplitude at the fundamental frequency division, amplitude distribution skewness at the fundamental frequency division, amplitude distribution kurtosis at the fundamental frequency division, and the average amplitude of the frequency band containing the fundamental frequency division.

[0087] For bearing diagnosis, the corresponding fault characteristic parameters may include at least one of the following parameters: amplitude at the fault characteristic frequency of the bearing inner ring, amplitude distribution skewness at the fault characteristic frequency of the bearing inner ring, amplitude distribution kurtosis at the fault characteristic frequency of the bearing inner ring, amplitude at the fault characteristic frequency of the bearing outer ring, amplitude distribution skewness at the fault characteristic frequency of the bearing outer ring, kurtosis of the amplitude distribution at the fault characteristic frequency of the bearing outer ring, and the mean amplitude of the frequency band containing the fault characteristic frequency of the bearing outer ring, etc.

[0088] For the diagnosis of bearing cages, the corresponding fault characteristic parameters may include at least one of the following parameters: amplitude at the fault characteristic frequency of bearing cage and outer ring friction, skewness of amplitude distribution at the fault characteristic frequency of bearing cage and outer ring friction, kurtosis of amplitude distribution at the fault characteristic frequency of bearing cage and outer ring friction, peak factor at the fault characteristic frequency of bearing cage and outer ring friction, and mean amplitude of the frequency band containing the fault characteristic frequency of bearing cage and outer ring friction, etc.

[0089] For the diagnosis of bearing rollers, the corresponding fault characteristic parameters may include at least one of the following parameters: amplitude at the fault characteristic frequency of impacting one side of the raceway, skewness of the amplitude distribution at the fault characteristic frequency of impacting one side of the raceway, kurtosis of the amplitude distribution at the fault characteristic frequency of impacting one side of the raceway, mean amplitude of the frequency band containing the fault characteristic frequency of impacting one side of the raceway, amplitude at the fault characteristic frequency of impacting both sides of the raceway, skewness of the amplitude distribution at the fault characteristic frequency of impacting both sides of the raceway, kurtosis of the fault characteristic frequency of impacting both sides of the raceway, mean amplitude of the frequency band containing the fault characteristic frequency of impacting both sides of the raceway, etc.

[0090] For gear fault diagnosis, the corresponding fault characteristic parameters may include at least one of the following parameters: total energy of the sideband, skewness of the total energy distribution of the sideband, kurtosis of the total energy distribution of the sideband, mean amplitude of the sideband, total energy of the residual sideband, skewness of the total energy distribution of the residual sideband, kurtosis of the total energy distribution of the residual sideband, mean amplitude of the residual sideband, etc.

[0091] The fundamental frequency, also known as the rotational frequency, is the frequency corresponding to the bearing's rotational speed. The calculation formulas for other fault characteristic frequencies are shown in the table below.

[0092]

[0093] Where n represents the bearing rotational speed; d represents the bearing rolling element diameter; D m Indicates the bearing pitch diameter; α represents the bearing rolling element contact angle; z represents the number of rollers; f i The frequency f represents the characteristic frequency of a failure in the inner ring of the bearing. e The characteristic frequency of a failure in the outer ring of a bearing; f 01 This represents the characteristic frequency of a bearing rolling element impacting a single side of the raceway; f 02 This indicates the characteristic frequency of the bearing rolling element impacting the raceways on both sides; f ec This represents the characteristic frequency of failure due to friction between the bearing cage and the outer ring; f ic This represents the characteristic frequency of failure due to friction between the bearing cage and the inner ring; f t Indicates sideband; f z Indicates the meshing frequency of the gears; f r Indicates the fundamental frequency of gear shaft rotation; mf z The superharmonic of the meshing frequency; nf r This represents the superharmonic of the fundamental frequency; n and m are both integers not less than zero (n and m cannot be zero simultaneously). Sideband f t That is, the frequency of a generalized modulated signal formed by using the meshing frequency and its superharmonics as the carrier frequency and the fundamental frequency as the modulation frequency.

[0094] It should be noted that the above-mentioned fault types are merely illustrative examples, and the corresponding fault characteristic parameters are also only illustrative examples. This invention does not impose any particular limitations on the fault types and their corresponding fault characteristic parameters. This invention can also calculate fault characteristic parameters for diagnosing faults such as surge, combustion vibration, engine oil pump, fuel pump, disc cracks, and couplings based on fault signals extracted from ultrasonic signals.

[0095] Step 404: Perform fault diagnosis on the aero-engine based on the values ​​of the fault characteristic parameters.

[0096] In one embodiment, during the fault diagnosis process, the fault state range corresponding to each fault characteristic parameter is determined. If the calculated value of the fault characteristic parameter falls within the corresponding fault state range, it is determined that the aircraft engine has a corresponding type of fault. If the calculated value of the fault characteristic parameter does not fall within the corresponding fault state range, it is determined that the aircraft engine is operating normally and there is no fault.

[0097] The fault state range of each fault characteristic parameter is determined based on historical test data and actual aircraft data of aero engines. The calculation method of the fault state range is similar to steps 401 to 403. According to the above steps, a large number of ultrasonic signals are calculated and statistically analyzed to obtain the fault state range corresponding to each fault characteristic parameter.

[0098] In one embodiment, based on actual needs, two fault state ranges can be set for each fault characteristic parameter: a warning state range and an alarm state range. If the value of the fault characteristic parameter falls within the warning state range, it indicates that the aircraft engine has a corresponding fault risk, and a warning is issued to prompt maintenance personnel to promptly troubleshoot the aircraft engine. If the value of the fault characteristic parameter falls within the alarm state range, it indicates that the aircraft engine has a corresponding fault, and an alarm is issued to prompt maintenance personnel to promptly eliminate the aircraft engine fault.

[0099] For example, suppose the fault characteristic parameters for diagnosing whether a rotor is loose include the amplitude at twice the fundamental frequency and the skewness at twice the fundamental frequency. If the calculated amplitude at twice the fundamental frequency falls within the amplitude fault state range and the skewness at twice the fundamental frequency falls within the skewness fault state range, then a rotor looseness fault is determined to exist. If the calculated amplitude at twice the fundamental frequency does not fall within the amplitude fault state range and the skewness at twice the fundamental frequency does not fall within the skewness fault state range, then a rotor looseness fault is determined not to exist.

[0100] It should be noted that the fault diagnosis strategy can be set according to actual needs. It can be that if a fault characteristic parameter falls into the corresponding fault state range, the corresponding fault is determined to exist; or it can be that all fault characteristic parameters fall into the corresponding fault state range before the corresponding fault is determined to exist.

[0101] In one embodiment, fault diagnosis is achieved using a fault diagnosis model, which is pre-trained on a neural network using a large amount of sample data. Different fault types can be diagnosed using a separate module, or a single model can be trained for all types of fault diagnosis.

[0102] Figure 5 A flowchart illustrating another fault diagnosis method for an aero-engine, as provided in an exemplary embodiment of the present invention, is shown in the figure. The flowchart uses early fault diagnosis of an aero-engine as an example to illustrate the fault diagnosis process in detail. (See also...) Figure 5 The fault diagnosis method includes the following steps:

[0103] Step 501: Acquire the ultrasonic signal collected by the ultrasonic sensor, which is installed on the aircraft engine, and the ultrasonic signal characterizes the vibration characteristics of the aircraft engine.

[0104] The specific implementation of step 501 is similar to that of step 101. For the specific implementation process, please refer to step 101, which will not be repeated here.

[0105] Step 502: In the case of early fault diagnosis, determine the fault characteristic frequency band required for early fault diagnosis, and extract the fault signal corresponding to the fault characteristic frequency band from the ultrasonic signal.

[0106] The impact of early faults on the dynamic characteristics of aero-engines is highly random and sparsity, and thus exhibits strong time-varying characteristics. The fault characteristic parameters corresponding to the early fault characteristic frequency band in the ultrasonic range (above 20kHz) are more time-varying than the fault characteristic parameters corresponding to the aforementioned fault characteristic frequencies. Therefore, in this embodiment of the invention, fault signals corresponding to the fault characteristic frequency band are extracted for early fault diagnosis.

[0107] The fault characteristic frequency bands are determined based on historical test data and actual aircraft data of aero engines, and the bandwidth and number of fault characteristic frequency bands are related to the fault diagnosis type. Different fault characteristic frequency bands can target the same early fault type or different early fault types.

[0108] In one embodiment, the fault characteristic frequency corresponding to the fault characteristic parameter can be determined first, and the characteristic frequency band containing the fault characteristic frequency can be determined as the fault characteristic frequency band.

[0109] Step 503: Perform a fast Fourier transform on the fault signal to obtain a frequency domain signal, and determine the values ​​of the fault characteristic parameters corresponding to the fault characteristic frequency band based on the frequency domain signal.

[0110] In one embodiment, the fault characteristic parameters corresponding to early fault diagnosis include at least one of the following parameters: energy of each fault characteristic frequency band, total energy of all fault characteristic frequency bands, energy distribution skewness of fault characteristic frequency bands, energy distribution kurtosis of fault characteristic frequency bands, etc.

[0111] Step 504: Perform fault diagnosis on the aero-engine based on the values ​​of the fault characteristic parameters.

[0112] In one embodiment, during the fault diagnosis process, the fault state range corresponding to each fault characteristic parameter is determined. If the calculated value of the fault characteristic parameter falls within the corresponding fault state range, it is determined that the aero-engine has an early fault; if the calculated value of the fault characteristic parameter does not fall within the corresponding fault state range, it is determined that the aero-engine is operating normally and there is no early fault.

[0113] Multiple early fault characteristic parameter ranges can also be integrated for early fusion diagnosis. For example, assuming the total energy of two selected fault characteristic frequency bands and the energy distribution skewness of the two fault characteristic frequency bands are used as fault characteristic parameters for early fault diagnosis, if the calculated total energy of the fault characteristic frequency bands falls within the energy fault state range, and the energy distribution skewness of the two fault characteristic frequency bands falls within their respective skewness fault state ranges, then it is determined that the aero-engine has an early fault; otherwise, it is determined that the aero-engine does not have an early fault.

[0114] The fault state range of each fault characteristic parameter is determined based on historical test data and actual aircraft data of aero engines. The calculation method of the fault state range is similar to steps 501 to 503. According to the above steps, a large number of ultrasonic signals are calculated and statistically analyzed to obtain the fault state range corresponding to each fault characteristic parameter.

[0115] It should be noted that the fault diagnosis strategy can be set according to actual needs. It can be that if a fault characteristic parameter falls into the corresponding fault state range, the corresponding fault is determined to exist; or it can be that all fault characteristic parameters fall into the corresponding fault state range before the corresponding fault is determined to exist.

[0116] In this embodiment of the invention, fault information is fused using multiple fault characteristic parameters to obtain a final health indicator for early fault diagnosis, thereby improving the monitoring accuracy and robustness of the algorithm. Furthermore, the method is simple and easy to implement, with significant physical meaning, thus providing reaction time for the full lifespan monitoring of components.

[0117] Corresponding to the aforementioned embodiments of the fault diagnosis method for aero-engines, the present invention also provides embodiments of a fault diagnosis device for aero-engines.

[0118] Figure 6 A schematic diagram of a fault diagnosis device for an aircraft engine, provided as an exemplary embodiment of the present invention, is shown. The device includes:

[0119] Acquisition module 61 is used to acquire ultrasonic signals collected by an ultrasonic sensor, the ultrasonic sensor being installed on the aircraft engine, and the ultrasonic signals characterizing the vibration characteristics of the aircraft engine.

[0120] Extraction module 62 is used to extract fault signals required for fault diagnosis from the ultrasonic signals according to the fault type of the aero-engine.

[0121] The determining module 63 is used to determine the values ​​of the fault characteristic parameters based on the fault signal;

[0122] The diagnostic module 64 is used to perform fault diagnosis on the aero-engine based on the values ​​of the fault characteristic parameters.

[0123] Optionally, the extraction module includes:

[0124] An analysis unit is used to perform envelope spectrum analysis on the ultrasonic signal when the fault type is fault diagnosis.

[0125] An extraction unit is used to extract fault signals with frequencies below a frequency threshold from the ultrasonic signal based on the results of envelope spectrum analysis.

[0126] Optionally, the determining module:

[0127] A determination unit is used to determine the fault characteristic frequencies required for fault diagnosis.

[0128] The calculation unit is used to calculate the values ​​of the fault characteristic parameters corresponding to the fault characteristic frequencies based on the envelope spectrum of the fault signal.

[0129] Optionally, the extraction module is used for:

[0130] The determining unit is used to determine the fault characteristic frequency band when the fault type is an early fault.

[0131] An extraction unit is used to extract a fault signal corresponding to the fault characteristic frequency band from the ultrasonic signal.

[0132] Optionally, the determining module is used to:

[0133] A conversion unit is used to convert the fault signal into a frequency domain signal;

[0134] The calculation unit is used to calculate the values ​​of the fault characteristic parameters corresponding to the fault characteristic frequency band based on the frequency domain signal.

[0135] For the device embodiments, since they basically correspond to the method embodiments, the relevant parts can be referred to in the description of the method embodiments. The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of the present invention according to actual needs. Those skilled in the art can understand and implement this without creative effort.

[0136] Figure 7 This is a schematic diagram of the structure of an electronic device according to an example embodiment of the present invention, showing a block diagram of an exemplary electronic device 70 suitable for implementing embodiments of the present invention. Figure 7The electronic device 70 shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of the present invention.

[0137] like Figure 7 As shown, the electronic device 70 can be manifested as a general-purpose computing device, such as a server device. The components of the electronic device 70 may include, but are not limited to: at least one processor 71, at least one memory 72, and a bus 73 connecting different system components (including memory 72 and processor 71).

[0138] Bus 73 includes a data bus, an address bus, and a control bus.

[0139] The memory 72 may include volatile memory, such as random access memory (RAM) 721 and / or cache memory 722, and may further include read-only memory (ROM) 723.

[0140] The memory 72 may also include a program tool 725 (or utility) having a set (at least one) program module 724, such program module 724 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each or some combination of these examples may include an implementation of a network environment.

[0141] The processor 71 performs various functional applications and data processing, such as the methods provided in any of the above embodiments, by running computer programs stored in the memory 72.

[0142] Electronic device 70 can also communicate with one or more external devices 74 (e.g., keyboard, pointing device, etc.). This communication can be performed via input / output (I / O) interface 75. Furthermore, the model-generated electronic device 70 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public network, such as the Internet) via network adapter 76. As shown, network adapter 76 communicates with other modules of the model-generated electronic device 70 via bus 73. It should be understood that, although not shown in the figure, other hardware and / or software modules can be used in conjunction with the model-generated electronic device 70, including but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID (disk array) systems, tape drives, and data backup storage systems.

[0143] It should be noted that although several units / modules or sub-units / modules of the electronic device have been mentioned in the detailed description above, this division is merely exemplary and not mandatory. In fact, according to embodiments of the present invention, the features and functions of two or more units / modules described above can be embodied in one unit / module. Conversely, the features and functions of one unit / module described above can be further divided and embodied by multiple units / modules.

[0144] This invention also provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the method provided in any of the above embodiments.

[0145] While specific embodiments of the present invention have been described above, those skilled in the art should understand that these are merely illustrative examples, and the scope of protection of the present invention is defined by the appended claims. Those skilled in the art can make various changes or modifications to these embodiments without departing from the principles and essence of the present invention, but all such changes and modifications fall within the scope of protection of the present invention.

Claims

1. A fault diagnosis method for an aero-engine, characterized in that, include: The ultrasonic signal is acquired by an ultrasonic sensor, which is mounted on an aircraft engine, and the ultrasonic signal characterizes the vibration characteristics of the aircraft engine. For the specific type of fault in the aero-engine, the fault signals required for fault diagnosis are extracted from the ultrasonic signals, including: When the fault type is fault diagnosis, a fault signal with a frequency lower than a frequency threshold is extracted from the ultrasonic signal; In the case where the fault type is early fault diagnosis, a fault signal with a frequency not lower than the frequency threshold is extracted from the ultrasonic signal. The values ​​of fault characteristic parameters are determined based on the fault signal; the fault diagnosis of the aero-engine is performed based on the values ​​of the fault characteristic parameters.

2. The fault diagnosis method for an aero-engine according to claim 1, characterized in that, For the fault type of the aero-engine, extracting the fault signal required for fault diagnosis from the ultrasonic signal includes: when the fault type is fault diagnosis, performing envelope spectrum analysis on the ultrasonic signal; and extracting fault signals with frequencies below a frequency threshold from the ultrasonic signal based on the results of the envelope spectrum analysis.

3. The fault diagnosis method for an aero-engine according to claim 2, characterized in that, Determining the values ​​of fault characteristic parameters based on the fault signal includes: determining the fault characteristic frequency required for fault diagnosis; and calculating the values ​​of fault characteristic parameters corresponding to the fault characteristic frequency based on the envelope spectrum of the fault signal.

4. The fault diagnosis method for an aero-engine according to claim 1, characterized in that, For the fault type of the aero-engine, extracting the fault signal required for fault diagnosis from the ultrasonic signal includes: determining the fault characteristic frequency band when the fault type is an early fault; and extracting the fault signal corresponding to the fault characteristic frequency band from the ultrasonic signal.

5. The fault diagnosis method for an aero-engine according to claim 4, characterized in that, Determining the values ​​of fault characteristic parameters based on the fault signal includes: converting the fault signal into a frequency domain signal; and calculating the values ​​of fault characteristic parameters corresponding to the fault characteristic frequency band based on the frequency domain signal.

6. A fault diagnosis device for an aircraft engine, characterized in that, include: An acquisition module is used to acquire ultrasonic signals collected by an ultrasonic sensor, which is installed on the aircraft engine, and the ultrasonic signals characterize the vibration characteristics of the aircraft engine. An extraction module is used to extract fault signals required for fault diagnosis from the ultrasonic signals according to the fault type of the aero-engine; wherein, the extraction module includes: an analysis unit, used to extract fault signals with frequencies lower than a frequency threshold from the ultrasonic signals when the fault type is fault diagnosis, and to extract fault signals with frequencies not lower than a frequency threshold from the ultrasonic signals when the fault type is early fault diagnosis. The determination module is used to determine the values ​​of fault characteristic parameters based on the fault signal; the diagnosis module is used to perform fault diagnosis on the aero-engine based on the values ​​of the fault characteristic parameters.

7. The fault diagnosis device for an aero-engine according to claim 6, characterized in that, The extraction module includes: an analysis unit, used to perform envelope spectrum analysis on the ultrasonic signal when the fault type is fault diagnosis; and an extraction unit, used to extract fault signals with frequencies lower than a frequency threshold from the ultrasonic signal based on the results of the envelope spectrum analysis.

8. The fault diagnosis device for an aero-engine according to claim 7, characterized in that, The determining module: a determining unit, used to determine the fault characteristic frequencies required for fault diagnosis; The calculation unit is used to calculate the values ​​of the fault characteristic parameters corresponding to the fault characteristic frequencies based on the envelope spectrum of the fault signal.

9. The fault diagnosis device for an aero-engine according to claim 6, characterized in that, The extraction module is used for: a determination unit, used to determine the fault characteristic frequency band when the fault type is an early fault; An extraction unit is used to extract a fault signal corresponding to the fault characteristic frequency band from the ultrasonic signal.

10. The fault diagnosis device for an aero-engine according to claim 9, characterized in that, The determining module is configured to: a conversion unit for converting the fault signal into a frequency domain signal; and a calculation unit for calculating the values ​​of fault characteristic parameters corresponding to the fault characteristic frequency band based on the frequency domain signal.

11. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the method of any one of claims 1 to 5.

12. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the fault diagnosis method for an aero-engine as described in any one of claims 1 to 5.

Images