Aero-engine damage detection method, device and equipment and storage medium
By constructing temperature vectors before and after damage and calculating damage location vectors, the problem of being unable to locate damage to aero-engines in existing technologies is solved, thus improving maintenance efficiency.
Patent Information
- Application Number
- CN202511769447.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-11-28
- Publication Date
- 2026-02-24
AI Technical Summary
Existing methods for detecting damage to aircraft engines can only indicate whether damage has occurred, but cannot locate it, resulting in low maintenance efficiency.
By constructing temperature vectors before and after the damage, and using the readings and location of the first temperature probe, the damage location vector is calculated, and its direction is output as the damage location result.
This enabled the initial location of damage to aircraft engines, narrowed the inspection area for maintenance personnel, and improved maintenance efficiency.
Smart Images
Figure CN121558813A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of damage detection technology, and in particular to a method, apparatus, equipment and storage medium for detecting damage in aero-engines. Background Technology
[0002] Aircraft engines are critical components of aircraft, and engine failures can pose significant threats to flight safety. Damage monitoring of engines ensures timely maintenance and prevents accidents. However, current monitoring methods can only indicate whether damage has occurred, but they do not locate the damage. After damage occurs, maintenance personnel must perform a complete troubleshooting process from scratch, resulting in low maintenance efficiency. Summary of the Invention
[0003] The purpose of this invention is to provide a method, apparatus, equipment, and storage medium for detecting damage to aero-engines, which can perform preliminary location of damage to aero-engines, thereby reducing the workload of troubleshooting and improving maintenance efficiency.
[0004] To achieve the above objectives, embodiments of the present invention provide a method for detecting damage in an aero-engine, comprising: Based on the readings and locations of the first temperature probes, construct temperature vectors before and after the damage; wherein the number of first temperature probes is no less than 3 and all of them are located in the circumferential direction of the engine; Subtracting all pre-damage temperature vectors from all post-damage temperature vectors yields the damage location vector; Output the direction of the damage localization vector as the damage localization result.
[0005] As an improvement to the above solution, the following method can be used to determine whether the engine is damaged: During the target cruise period, calculate the temperature difference between any two second temperature probes at each time point and construct a temperature difference sequence for each. Mutation detection was performed on each of the temperature difference sequences. Engine damage is determined when the temperature difference sequence with a sudden change satisfies both the quantity constraint and the time clustering constraint.
[0006] As an improvement to the above solution, the target cruise period is obtained in the following way: The flight phase in which the flight mode is cruise, the duration constraint is met, and the flight altitude meets the cruise altitude constraint is defined as the initial cruise period. Adjacent initial cruise periods that satisfy the time interval constraint are merged to obtain an intermediate cruise period; Boundary optimization is performed on the intermediate cruise period to obtain the target cruise period.
[0007] As an improvement to the above scheme, the boundary optimization of the intermediate cruise period includes: Starting from each endpoint, the intermediate cruise period is gradually reduced point by point until the absolute value of the climb rate at the endpoint of the intermediate cruise period meets the boundary constraint condition, thus obtaining the target cruise period.
[0008] As an improvement to the above solution, the flight mode is obtained in the following way: Calculate the rate of climb at the current time based on the flight altitude; Using the current time point as the center, calculate the change in flight altitude and the average rate of climb within the target time window; When the flight altitude meets the preset requirements, based on the average rate of climb and the change in flight altitude, it is determined whether the climb constraint or descent constraint is met: If the climb constraint is met, the flight mode at the current time point is recorded as climb. If the descent constraint is met, the flight mode at the current time point is recorded as descent; If none of these conditions are met, the flight mode at the current time point will be recorded as cruise.
[0009] As an improvement to the above scheme, the quantity constraint is that the number of temperature difference sequences with abrupt changes is not less than the number of second temperature probes.
[0010] As an improvement to the above scheme, the second temperature probe is located at the lower turbine outlet inside the engine, the upper turbine outlet inside the engine, the lower turbine outlet outside the engine, and the upper turbine outlet outside the engine, respectively.
[0011] To achieve the above objectives, embodiments of the present invention also provide an aircraft engine damage detection device, comprising: The vector construction module is used to construct temperature vectors before and after damage based on the readings and locations of the first temperature probes; wherein the number of first temperature probes is not less than 3 and all of them are located in the circumferential direction of the engine; The vector calculation module is used to subtract all pre-damage temperature vectors from all post-damage temperature vectors to obtain the damage location vector. The result output module is used to output the direction of the damage localization vector as the damage localization result.
[0012] To achieve the above objectives, embodiments of the present invention also provide an aircraft engine damage detection device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, it implements the aircraft engine damage detection method as described in any of the above embodiments.
[0013] To achieve the above objectives, embodiments of the present invention also provide a computer-readable storage medium, the computer-readable storage medium including a stored computer program, wherein, when the computer program is executed, it controls the device where the computer-readable storage medium is located to perform the aero-engine damage detection method as described in any of the above embodiments.
[0014] Compared with the prior art, the aircraft engine damage detection method, apparatus, equipment and storage medium of the present invention constructs temperature vectors before and after damage based on the reading and location of the first temperature probe, subtracts all temperature vectors before damage from all temperature vectors after damage to obtain the damage location vector, and uses the direction of the damage location vector as the damage location result, which can preliminarily locate the damage area, thereby narrowing down the inspection area for maintenance personnel and improving maintenance efficiency. Attached Figure Description
[0015] Figure 1 This is a flowchart of a method for detecting damage to an aero-engine provided in an embodiment of the present invention; Figure 2 This is a schematic diagram of damage localization provided in an embodiment of the present invention; Figure 3 This is a schematic diagram of the structure of an aero-engine damage detection device according to an embodiment of the present invention; Figure 4 This is a schematic diagram of the structure of an aircraft engine damage detection device provided in an embodiment of the present invention. Detailed Implementation
[0016] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.
[0017] In the description of this application, it should be understood that the terms "center", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are only for the convenience of describing this application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this application.
[0018] The terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this application, unless otherwise stated, "a plurality of" means two or more.
[0019] In the description of this application, it should be noted that, unless otherwise expressly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection between two components. Those skilled in the art can understand the specific meaning of the above terms in this application based on the specific circumstances.
[0020] See Figure 1 This is a flowchart of an aero-engine damage detection method provided in an embodiment of the present invention, including steps S1 to S3: S1. Based on the readings and locations of the first temperature probes, construct temperature vectors before and after the damage; wherein, the number of first temperature probes is no less than 3 and all of them are located in the circumferential direction of the engine; S2. Subtract all the temperature vectors before the damage from all the temperature vectors after the damage to obtain the damage location vector; S3. Output the direction of the damage localization vector as the damage localization result.
[0021] It is worth noting that the temperature probes are pre-set at the engine manufacturing stage. In this invention, several temperature probes along the circumference are selected as the first temperature probes, wherein the number of first temperature probes is not less than 3. For example, when the number of first temperature probes is N, the distribution of the first temperature probes should meet the following conditions: the entire 360° circumference is divided into N equal sectors, with each first temperature probe located in one sector; and the circumferential angular distance between any two first temperature probes is greater than [missing information]. Preferably, the first temperature probes are distributed at equal intervals along the circumference, which provides the best damage localization accuracy.
[0022] It should be noted that, for ease of distinction, in this invention, the temperature probe used for damage localization is referred to as the "first temperature probe", and the temperature probe used for damage detection is referred to as the "second temperature probe". In some embodiments, the selected temperature probe can also be used for both damage localization and damage detection. In this case, the first temperature probe and the second temperature probe are equivalent, and no limitation is made here.
[0023] Further, in step S1, after detecting engine damage, the temperature vectors before and after damage for each first temperature probe are constructed. For example, for any first temperature probe, readings during a stable cruise period before the damage time are extracted, and the average temperature is calculated as the modulus of the temperature vector before damage. Then, the direction of the temperature vector is determined based on the azimuth angle of the first temperature probe, and the temperature vector before damage is constructed. Further, readings during a stable cruise period after the damage time are extracted, and the average temperature is calculated as the modulus of the temperature vector after damage. Then, the temperature vector after damage is constructed by combining the direction of the temperature vector.
[0024] Further, in step S2, the damage location vector is obtained by subtracting all pre-damage temperature vectors from all post-damage temperature vectors. For example, assuming there are four first temperature probes, the pre-damage temperature vectors of the four first temperature probes are as follows: , , and The temperature vectors of the four first temperature probes after damage are as follows: , , and From the rules of vector addition and vector subtraction, we know that:
[0025] Therefore, in step S2, the sum of the temperature vectors of all first temperature probes before damage can be calculated first, and then the sum of the temperature vectors of all first temperature probes after damage can be calculated, and finally the sum of the temperature vectors before damage can be subtracted from the sum of the temperature vectors after damage to obtain the damage location vector. Furthermore, in step S2, the temperature vectors before damage can be subtracted from the temperature vectors after damage of each first temperature probe to obtain the temperature change vector of each first temperature probe, and then the temperature change vectors of all first temperature probes can be summed to obtain the damage location vector. The specific calculation steps for the damage location vector are not limited here.
[0026] Furthermore, in step S3, the direction of the damage localization vector is output as the damage localization result.
[0027] To facilitate understanding, the following example illustrates the damage localization method and its effectiveness according to the present invention. It is worth noting that in real-world scenarios, engine temperatures are much higher than the readings in this example; the readings in this example are for illustrative purposes only. See also... Figure 2This is a schematic diagram of damage localization provided in an embodiment of the present invention. The vector in circle (a) is the vector generated by the temperature field before damage, i.e., the vector before damage; the vector in circle (b) is the vector generated by the temperature field after damage, i.e., the vector after damage; and the vector in circle (c) is the damage localization vector calculated using the method of the present invention. The specific calculation process is as follows: In this example, the number of first temperature probes is 4, and their azimuth angles are as follows: , , , , then, by The unit direction vectors of the four first temperature probes can be calculated as follows: , , , .
[0028] Furthermore, assume that there is a non-uniform background temperature field along the circumference. That is, the temperature field before damage, and Furthermore, it is assumed that the direction of the damage / failure is... The temperature increment field caused by the damage is .
[0029] Then, from the background temperature field The temperature readings of each of the first temperature probes before the damage can be calculated as follows: (2) (3) (4) (5) In equations (2) to (5), This indicates the reading of the first temperature probe 1 before the damage occurred; This indicates the reading of the first temperature probe 2 before the damage occurred; This indicates the reading of the first temperature probe 3 before the damage occurred; This indicates the reading of the first temperature probe 4 before the damage occurred; This indicates the azimuth angle of the first temperature probe 1; This indicates the azimuth angle of the first temperature probe 2; This indicates the azimuth angle of the first temperature probe 3; This indicates the azimuth angle of the first temperature probe 4.
[0030] Furthermore, the sum vector before damage is: (6) in, Represents the sum vector before damage; This indicates the first temperature probe before damage. The reading; Indicates the first temperature probe The azimuth angle; Represents the cosine function; This represents the sine function.
[0031] Specifically, the x-axis and y-axis components of the vector before damage are as follows: (7) (8) In equations (7) to (8), Represents the x-axis component of the vector before damage; This represents the y-axis component of the vector before damage.
[0032] Then, the sum vector before damage ,and ,like Figure 2 As shown in (a).
[0033] Furthermore, from the temperature increment The temperature readings of each of the first temperature probes after the damage can be calculated as follows: (9) (10) (11) (12) In equations (9) to (12), This indicates the temperature reading increment of the first temperature probe 1; This indicates the temperature reading increment of the first temperature probe 2; This indicates the temperature reading increment of the first temperature probe 3; This indicates the temperature reading increment of the first temperature probe 4; This indicates the azimuth angle of the first temperature probe 1; This indicates the azimuth angle of the first temperature probe 2; This indicates the azimuth angle of the first temperature probe 3; This indicates the azimuth angle of the first temperature probe 4; Represents the cosine function; Indicates the azimuth angle at which the damage is located.
[0034] Therefore, based on the above calculation results, the temperature readings of each of the first temperature probes after the damage can be obtained as follows: (13) (14) (15) (16) In equations (13) to (16), This indicates the reading of the first temperature probe 1 after the damage. This indicates the reading of the first temperature probe 2 after the damage; This indicates the reading of the first temperature probe 3 after the damage. This indicates the reading of the first temperature probe 4 after the damage; This indicates the reading of the first temperature probe 1 before the damage occurred; This indicates the reading of the first temperature probe 2 before the damage occurred; This indicates the reading of the first temperature probe 3 before the damage occurred; This indicates the reading of the first temperature probe 4 before the damage occurred; This indicates the temperature reading increment of the first temperature probe 1; This indicates the temperature reading increment of the first temperature probe 2; This indicates the temperature reading increment of the first temperature probe 3; This indicates the temperature reading increment of the first temperature probe 4.
[0035] Furthermore, the post-damage sum vector is: (17) in, Represents the sum vector after damage; First temperature probe after damage The reading; Indicates the first temperature probe The azimuth angle; Represents the cosine function; This represents the sine function.
[0036] Specifically, the x-axis and y-axis components of the vector after damage are as follows: (18) (19) In equations (18) to (19), Represents the x-axis component of the vector after damage; This represents the y-axis component of the vector after damage.
[0037] Then, the vector after damage ,and ,like Figure 2 As shown in (b).
[0038] Furthermore, the damage localization vector is as follows: (20) in, Represents the damage localization vector; Represents the sum vector before damage; This represents the vector after damage.
[0039] Specifically, the x-axis and y-axis components of the damage localization vector are as follows: (twenty one) (twenty two) In equations (21) to (22), The x-axis component represents the damage localization vector; This represents the y-axis component of the damage localization vector.
[0040] Then, the damage localization vector ,and , The direction angle is -150°, which translates to 210° in the 0~360° range. Equal, such as Figure 2 As shown in (c).
[0041] Compared with the prior art, the embodiments of the present invention construct temperature vectors before and after damage based on the reading and location of the first temperature probe. By subtracting all the temperature vectors before damage from all the temperature vectors after damage, a damage location vector is obtained. The direction of the damage location vector is used as the damage location result, which can initially locate the damaged area, thereby narrowing down the inspection area for maintenance personnel and improving maintenance efficiency.
[0042] As one alternative implementation method, the engine damage is determined by the following approach: During the target cruise period, calculate the temperature difference between any two second temperature probes at each time point and construct a temperature difference sequence for each. Mutation detection was performed on each of the temperature difference sequences. Engine damage is determined when the temperature difference sequence with a sudden change satisfies both the quantity constraint and the time clustering constraint.
[0043] It is worth noting that existing technologies generally use message data for engine damage detection. However, message data is a single-point sampling at different flight stages, such as thrust, altitude, and temperature collected during takeoff, cruise, and peak climb. This method has two drawbacks: First, the same parameter at different flight stages needs to be converted to a value under standard operating conditions using a conversion formula before use, which introduces additional calculation errors and computational load. Second, excessively long data sampling intervals make it difficult to identify and eliminate observation errors caused by noise, leading to false alarms.
[0044] To address the aforementioned deficiencies in the prior art, this invention utilizes a QAR (Quick Access Recorder) to acquire readings from flight altitude and temperature probes. This allows for accurate identification of the cruise period based on flight altitude and limits engine temperature monitoring to the target cruise period. By monitoring the engine under the same flight conditions, false alarms caused by differences in flight phases can be avoided. Furthermore, continuous monitoring of engine temperature within the target cruise period facilitates observation of the complete trend of engine temperature changes, preventing missed alarms and thus improving the accuracy of damage detection.
[0045] It is worth noting that in this embodiment of the invention, the number of second temperature probes is greater than or equal to three. For example, assuming there are four second temperature probes, and their readings are a, b, c, and d, then at each time point during the target cruise period, the temperature difference between any two second temperature probes is calculated, resulting in the following temperature difference combination: "ab, ac, ad, bc, bd, cd". It can be understood that for any two second temperature probes, there can be two temperature difference calculation methods, such as ab and ba. However, in this embodiment of the invention, only one temperature difference calculation method needs to be used for any two second temperature probes; for example, in the above example, only ab is used. Further, by calculating the temperature difference at each time point during the target cruise period, a temperature difference sequence can be obtained. For the above example, these can be named ab sequence, ac sequence, ad sequence, bc sequence, bd sequence, and cd sequence. Taking the ab sequence as an example, it can be understood that the ab sequence is a sequence composed of "ab" at each time point within the target cruise period.
[0046] Furthermore, before performing abrupt change detection on the temperature difference sequence, the sequence can be filtered to eliminate transient interference. For example, median filtering can be used as the filtering algorithm.
[0047] Furthermore, a Cumulative Sum (CUSUM) change point detection algorithm can be used to detect abrupt changes in the temperature difference sequence. Further, after detecting an abrupt change, within a preset time window, the mean of the temperature difference sequence before and after the abrupt change is calculated, and the difference between these two means is taken as the aberration magnitude of the abrupt change. Further, if the aberration magnitude exceeds a mutation threshold, the abrupt change is retained (i.e., a valid abrupt change); otherwise, it is discarded. It is understood that this embodiment of the invention, by using a time window to extract the temperature difference before and after the abrupt change and calculating the aberration magnitude, can combine this with a mutation threshold to determine whether it is a false positive, thereby improving the reliability of abrupt change detection.
[0048] Furthermore, the quantity constraint means that the number of temperature difference sequences that detect abrupt changes should not be less than the quantity threshold; the time clustering constraint means that the time at which abrupt changes are detected in each temperature difference sequence should not be too dispersed. For example, the time at which abrupt changes are detected in each temperature difference sequence is arranged from earliest to latest, and the time difference between the earliest and latest time points is calculated. If the time difference is less than or equal to the time threshold, the time clustering constraint is considered to be satisfied; otherwise, the time clustering constraint is not satisfied. For example, the time threshold can be 30 seconds.
[0049] As one alternative implementation, the quantity constraint is that the number of temperature difference sequences with abrupt changes is not less than the number of second temperature probes.
[0050] For example, taking the above example, the number of second temperature probes is 4. Therefore, the quantity constraint condition is that the number of temperature difference sequences with abrupt changes is not less than 4. It is worth noting that since this embodiment of the invention uses 4 second temperature probes and monitors abrupt changes in the temperature difference sequences, if one second temperature probe malfunctions, it will cause abrupt changes in three temperature difference sequences. If the quantity threshold in the quantity constraint condition is less than or equal to 3, the data anomaly caused by the temperature probe malfunction may be misidentified as engine damage. Therefore, in this embodiment of the invention, setting the quantity threshold to not less than the number of second temperature probes can avoid misidentification caused by sensor malfunctions and improve the accuracy of engine damage monitoring.
[0051] As one optional implementation method, the target cruise period is obtained in the following way: The flight phase in which the flight mode is cruise, the duration constraint is met, and the flight altitude meets the cruise altitude constraint is defined as the initial cruise period. Adjacent initial cruise periods that satisfy the time interval constraint are merged to obtain an intermediate cruise period; Boundary optimization is performed on the intermediate cruise period to obtain the target cruise period.
[0052] Specifically, the flight mode is determined by the climb rate, where the flight mode is one of climb, descent, and cruise.
[0053] Furthermore, the duration constraint can be a duration ≥ 60 seconds, and the cruising altitude constraint can be a flight altitude ≥ 25,000 feet. For a flight altitude sequence, each time point can be checked to see if the flight altitude is ≥ 25,000 feet and whether the flight mode is cruising. If both conditions are met, it is recorded as a candidate time point. Successive candidate time points are aggregated to obtain candidate cruise periods. If the length of a candidate cruise period meets the duration constraint, it is recorded as an initial cruise period. Further, for adjacent initial cruise periods, if the time interval between the end time of the earlier initial cruise period and the start time of the later initial cruise period meets the time interval constraint, the two initial cruise periods are merged to obtain an intermediate cruise period. The intermediate cruise period starts at the start time of the earlier initial cruise period and ends at the end time of the later initial cruise period. For example, the time interval constraint can be a time interval ≤ 10 minutes. Further, if multiple intermediate cruise periods exist, the longest one can be selected as the final intermediate cruise period.
[0054] Compared with the prior art, the embodiments of the present invention can avoid the omission of cruise periods due to data fluctuations by conditionally merging the initial cruise period, thereby ensuring the integrity of subsequent data acquisition and damage detection and avoiding omissions.
[0055] As one optional implementation, the boundary optimization of the intermediate cruise period includes: Starting from each endpoint, the intermediate cruise period is gradually reduced point by point until the absolute value of the climb rate at the endpoint of the intermediate cruise period meets the boundary constraint condition, thus obtaining the target cruise period.
[0056] It is worth noting that boundary optimization includes left endpoint optimization and right endpoint optimization during the intermediate cruise period. For example, when optimizing the left endpoint, it is determined whether the absolute value of the climb rate of the left endpoint is greater than the climb rate optimization threshold. If so, the time point is deleted, and a new left endpoint is obtained. The above optimization process is repeated for the new left endpoint until the left endpoint meets the boundary constraint condition. That is, when the absolute value of the climb rate of the left endpoint is less than or equal to the climb rate optimization threshold, the current left endpoint is retained, and the left endpoint optimization is completed.
[0057] The optimization of the right endpoint is similar to that of the left endpoint. That is, when optimizing the right endpoint, it is determined whether the absolute value of the climb rate of the right endpoint is greater than the climb rate optimization threshold. If so, the time point is deleted and a new right endpoint is obtained. The above optimization process is repeated for the new right endpoint until the right endpoint meets the boundary constraint condition. That is, when the absolute value of the climb rate of the right endpoint is less than or equal to the climb rate optimization threshold, the current right endpoint is retained and the right endpoint optimization is completed.
[0058] Compared with existing technologies, the embodiments of the present invention can ensure accurate positioning of the cruise period by optimizing the boundaries of the intermediate cruise period, thereby ensuring damage detection in the same flight phase and avoiding misidentification due to differences in time periods. As one optional implementation, the flight mode is obtained in the following way: Calculate the rate of climb at the current time based on the flight altitude; Using the current time point as the center, calculate the change in flight altitude and the average rate of climb within the target time window; When the flight altitude meets the preset requirements, based on the average rate of climb and the change in flight altitude, it is determined whether the climb constraint or descent constraint is met: If the climb constraint is met, the flight mode at the current time point is recorded as climb. If the descent constraint is met, the flight mode at the current time point is recorded as descent; If none of these conditions are met, the flight mode at the current time point will be recorded as cruise.
[0059] For example, before constructing the initial cruise period, the flight altitude sequence can be processed by median filtering to eliminate turbulence and noise interference. Then, the numpy.gradient() function can be used to calculate the gradient of each element in the flight altitude sequence, which serves as the climb rate at each time point. For example, when calculating the flight mode, time windows can be used for calculations at time points in non-boundary regions. Specifically, for time points in non-boundary areas, a flight altitude sequence is extracted using a target time window centered on that time point. Then, the average rate of climb within the target time window and the flight altitude changes at the left and right endpoints of the target time window are calculated. If the flight altitude meets preset requirements, for example, when the flight altitude is ≥25,000 feet, the average rate of climb and the flight altitude changes are used to determine whether climb or descent constraints are met. The climb constraint is defined as "the average rate of climb is greater than a positive rate of climb threshold and the flight altitude change is greater than a positive altitude change threshold." The descent constraint is defined as "the average rate of climb is less than a negative rate of climb threshold and the flight altitude change is less than a negative altitude change threshold." If the climb constraint is met, the flight mode at the current time point is recorded as climb; if the descent constraint is met, the flight mode at the current time point is recorded as descent; if neither the climb nor descent constraint is met, the flight mode at the current time point is recorded as cruise.
[0060] Understandably, data in the boundary region of a flight altitude sequence cannot be extracted using a time window. For example, assuming the target time window length is 7, then half of the target time window length is 3. The first three and last three data points of the flight altitude sequence constitute the boundary region data. For the boundary region data, the flight mode can be determined based on the climb rate and climb rate threshold at each time point. Specifically, if the climb rate at the current time point is greater than the positive climb rate threshold, it is recorded as a climb; if the climb rate at the current time point is less than the negative climb rate threshold, it is recorded as a descent; otherwise, it is recorded as cruise.
[0061] As one optional implementation, the second temperature probe is located at the lower turbine outlet inside the engine, the upper turbine outlet inside the engine, the lower turbine outlet outside the engine, and the upper turbine outlet outside the engine, respectively.
[0062] Compared with the prior art, the embodiments of the present invention can accurately locate abnormal temperature areas by monitoring temperature at different locations on the inner and outer sides of each engine, thereby enabling preliminary damage localization when damage is detected.
[0063] Compared with the prior art, the aero-engine damage detection method of the present invention constructs temperature vectors before and after damage based on the reading and location of the first temperature probe. It subtracts all temperature vectors before damage from all temperature vectors after damage to obtain the damage location vector, and uses the direction of the damage location vector as the damage location result. This method can initially locate the damage area, thereby narrowing down the inspection area for maintenance personnel and improving maintenance efficiency.
[0064] See Figure 3 This invention also provides an aircraft engine damage detection device 10, comprising: The vector construction module 11 is used to construct temperature vectors before and after damage based on the readings and locations of the first temperature probes; wherein the number of first temperature probes is not less than 3 and all of them are located in the circumferential direction of the engine. Vector calculation module 12 is used to subtract all temperature vectors before damage from all temperature vectors after damage to obtain damage location vectors; The result output module 13 is used to output the direction of the damage localization vector as the damage localization result.
[0065] The aircraft engine damage detection device provided in this embodiment of the invention can realize all the process steps of the aircraft engine damage detection method described in the above embodiments. The functions and technical effects of each module and unit in the device are the same as the functions and technical effects of the aircraft engine damage detection method described in the above embodiments. The specific implementation method is not described here.
[0066] See Figure 4 This invention also provides an aircraft engine damage detection device 20, including a processor 21, a memory 22, and a computer program stored in the memory 22 and configured to be executed by the processor 21. When the processor 21 executes the computer program, it implements the steps described in the above-described aircraft engine damage detection method embodiments, for example... Figure 1 The steps S1 to S3 described above; or, when the processor 21 executes the computer program, it implements the functions of each module in the above-described device embodiments.
[0067] The aircraft engine damage detection equipment can be a desktop computer, laptop, handheld computer, or cloud server, etc. The aircraft engine damage detection equipment may include, but is not limited to, processors and memory. Those skilled in the art will understand that the schematic diagram is merely an example of an aircraft engine damage detection equipment and does not constitute a limitation on the equipment. It may include more or fewer components than shown in the diagram, or combine certain components, or use different components. For example, the aircraft engine damage detection equipment may also include input / output devices, network access devices, buses, etc.
[0068] The processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor. The processor is the control center of the aero-engine damage detection equipment, connecting all parts of the equipment via various interfaces and lines.
[0069] The memory can be used to store the computer programs and / or modules. The processor implements various functions of the aero-engine damage detection equipment by running or executing the computer programs and / or modules stored in the memory and by calling data stored in the memory. The memory may mainly include a program storage area and a data storage area. The program storage area may store the operating system, at least one application program required for a function, etc.; the data storage area may store data created according to the use of the controller, etc. In addition, the memory may include high-speed random access memory, and may also include non-volatile memory, such as hard disk, memory, plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, at least one disk storage device, flash memory device, or other volatile solid-state storage device.
[0070] If the integrated modules of the aero-engine damage detection equipment are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the above embodiments of the present invention can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium, etc.
[0071] Compared with the prior art, the aircraft engine damage detection device, equipment and storage medium of the present invention constructs temperature vectors before and after damage based on the reading and location of the first temperature probe, subtracts all temperature vectors before damage from all temperature vectors after damage to obtain the damage location vector, and uses the direction of the damage location vector as the damage location result, which can preliminarily locate the damage area, thereby narrowing down the inspection area for maintenance personnel and improving maintenance efficiency.
[0072] The above description represents the preferred embodiments of the present invention. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principles of the present invention, and these improvements and modifications are also considered to be within the scope of protection of the present invention.
Claims
1. A method for detecting damage in an aero-engine, characterized in that, include: Based on the readings and locations of the first temperature probes, construct temperature vectors before and after the damage; wherein the number of first temperature probes is no less than 3 and all of them are located in the circumferential direction of the engine; Subtracting all pre-damage temperature vectors from all post-damage temperature vectors yields the damage location vector; Output the direction of the damage localization vector as the damage localization result.
2. The aero-engine damage detection method as described in claim 1, characterized in that, Determine if the engine is damaged using the following methods: During the target cruise period, calculate the temperature difference between any two second temperature probes at each time point and construct a temperature difference sequence for each. Mutation detection was performed on each of the temperature difference sequences. Engine damage is determined when the temperature difference sequence with a sudden change satisfies both the quantity constraint and the time clustering constraint.
3. The aero-engine damage detection method as described in claim 2, characterized in that, The target cruise period is obtained through the following methods: The flight phase in which the flight mode is cruise, the duration constraint is met, and the flight altitude meets the cruise altitude constraint is defined as the initial cruise period. Adjacent initial cruise periods that satisfy the time interval constraint are merged to obtain an intermediate cruise period; Boundary optimization is performed on the intermediate cruise period to obtain the target cruise period.
4. The aero-engine damage detection method as described in claim 3, characterized in that, The boundary optimization of the intermediate cruise period includes: Starting from each endpoint, the intermediate cruise period is gradually reduced point by point until the absolute value of the climb rate at the endpoint of the intermediate cruise period meets the boundary constraint condition, thus obtaining the target cruise period.
5. The aero-engine damage detection method as described in claim 3, characterized in that, The flight mode is obtained through the following methods: Calculate the rate of climb at the current time based on the flight altitude; Using the current time point as the center, calculate the change in flight altitude and the average rate of climb within the target time window; When the flight altitude meets the preset requirements, based on the average rate of climb and the change in flight altitude, it is determined whether the climb constraint or descent constraint is met: If the climb constraint is met, the flight mode at the current time point is recorded as climb. If the descent constraint is met, the flight mode at the current time point is recorded as descent; If none of these conditions are met, the flight mode at the current time point will be recorded as cruise.
6. The aero-engine damage detection method as described in claim 2, characterized in that, The quantity constraint is that the number of temperature difference sequences with abrupt changes is not less than the number of second temperature probes.
7. The aero-engine damage detection method as described in claim 2, characterized in that, The second temperature probes are located at the lower turbine outlet inside the engine, the upper turbine outlet inside the engine, the lower turbine outlet outside the engine, and the upper turbine outlet outside the engine, respectively.
8. A damage detection device for an aircraft engine, characterized in that, include: The vector construction module is used to construct temperature vectors before and after damage based on the readings and locations of the first temperature probes; wherein the number of first temperature probes is not less than 3 and all of them are located in the circumferential direction of the engine; The vector calculation module is used to subtract all pre-damage temperature vectors from all post-damage temperature vectors to obtain the damage location vector. The result output module is used to output the direction of the damage localization vector as the damage localization result.
9. An aircraft engine damage detection device, characterized in that, It includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor executes the computer program to implement the aircraft engine damage detection method as described in any one of claims 1 to 7.
10. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored computer program, wherein, when the computer program is executed, it controls the device containing the computer-readable storage medium to perform the aircraft engine damage detection method as described in any one of claims 1 to 7.