Data analysis method and system of aviation accessory measuring device system

Abstract

The invention relates to the field of measurement data analysis, in particular to a data analysis method and system of an aviation accessory measurement device system.The method comprises the steps that compressor surface vibration data in an initial time window are obtained, and a time-frequency diagram is obtained through a frequency domain analysis algorithm; and calculating a surge time window adaptation coefficient corresponding to the current time according to the time-frequency diagram, and adjusting the length of the initial time window according to the surge time window adaptation coefficient to obtain the optimal length of the next time window. The method has the effect of remarkably reducing the abnormal signal detection delay.

Description

Technical Field

[0001] The present application relates to the field of measurement data analysis, and in particular to a data analysis method and system for an aviation accessory measurement device system. Background Art

[0002] Aviation accessories refer to various auxiliary devices installed on aircraft or aircraft engines to ensure their normal operation, usually including: engine accessories: such as generators, starters, fuel pumps, lubricating oil pumps, hydraulic pumps, anti-icing systems, etc.; aircraft accessories: such as control systems, environmental control systems, hydraulic systems, fuel systems, electrical systems, etc.; other accessories: such as wheels, propellers, landing gear, etc.

[0003] Surge is a serious aerodynamic instability phenomenon in aircraft engines, which manifests as low-frequency, high-amplitude oscillations of the airflow along the compressor axis. The main reasons for its occurrence are: the actual operating flow is less than the surge flow, such as excessive production reduction, insufficient intake air source, inlet filter blockage, etc.; or the outlet pressure of the compressor is lower than the pipeline pressure, causing the operating point to move to the small flow area. In addition, external interference such as component aging, thunderstorms, dust, etc. may also cause surge. Surge is extremely harmful to aircraft engines, causing flames in the inlet or tail nozzle, unstable combustion, forced vibration of the rotor blades, damage to the structural integrity of the engine, and even shutdown, which seriously threatens flight safety.

[0004] At present, surge detection usually collects compressor vibration data through the aviation accessory measurement device system. Surge detection is achieved by performing frequency domain analysis on the vibration data and utilizing the frequency domain change characteristics. When using frequency domain information for surge detection, the acquisition data of a fixed time window is often used for surge detection. As the speed of the aircraft engine increases, the occurrence and development of the surge phenomenon may accelerate. Therefore, in order to detect surge in time and take measures to prevent it from further deteriorating, it is necessary to shorten the surge detection time. If the detection time is too long, the surge phenomenon may have developed to a more serious stage when the surge is detected, thus causing greater harm. Summary of the invention

[0005] In order to solve the above-mentioned technical problem of low timeliness in data collection and detection using a fixed time window, the present application provides a data analysis method and system for an aviation accessory measurement device system.

[0006] In a first aspect, the present application provides a data analysis method for an aviation accessory measurement device system, which adopts the following technical solution: A data analysis method for an aviation accessory measuring device system comprises the following steps: obtaining compressor surface vibration data within an initial time window, obtaining a time-frequency diagram through a frequency domain analysis algorithm; calculating a surge time window adaptation coefficient corresponding to the current time according to the time-frequency diagram, and adjusting the length of the initial time window according to the surge time window adaptation coefficient to obtain an optimal length of the window at the next moment; the calculation method of the surge time window adaptation coefficient is: obtaining a spectrum curve corresponding to the maximum value of the time domain projection of the time-frequency diagram, constructing a histogram of frequency values ​​according to the spectrum curve, and taking the frequency of occurrence of the frequency values ​​as the histogram frequency; calculating all modes of the histogram frequency, and constructing a histogram frequency mode sequence; calculating an approximate mode, and the expression of the approximate mode is: ; represents the approximate mode; Indicates the current time The corresponding The degree of abnormality of the histogram frequency; Indicates the current time The minimum mode value in the corresponding histogram frequency mode sequence; represents a hyperparameter; Indicates An exponential function with the base ; the mode with the smallest Euclidean distance to the approximate mode is taken as the optimal histogram frequency, the optimal histogram frequency mode sequence is constructed, and the information entropy value of the optimal histogram frequency mode sequence is calculated and used as the surge time window coefficient of the corresponding window at the next moment.

[0007] The beneficial effect is that the method using a dynamic time window can significantly reduce the detection delay of abnormal signals compared to the traditional fixed time window. Under high-speed engine operation conditions, this method can greatly improve the response speed of the system and effectively capture instantaneous surge precursors, thereby giving early warnings and taking measures to avoid serious damage to the engine caused by surge. In addition, the adjustment of the dynamic time window is based on the surge time window adaptation coefficient, which is calculated by analyzing the frequency distribution characteristics in the time-frequency diagram. It can automatically adjust the length of the time window according to the actual changes in the signal, ensuring that the best detection sensitivity and accuracy can be maintained under different conditions. At the same time, by optimizing the processing of histogram frequencies and the calculation of information entropy values, the reliability of surge detection is further improved, and the possibility of misjudgment and missed judgment is reduced.

[0008] Optionally, the degree of anomaly is the absolute difference between the histogram frequency and the mean of the histogram frequency.

[0009] The beneficial effects are: providing a method for quantifying the degree of abnormality, which can comprehensively capture the degree to which the frequency value deviates from the normal level. Whether it is higher or lower than the mean, it can be quantified as the degree of abnormality, thereby providing a more comprehensive reference for subsequent analysis.

[0010] Optionally, the calculation expression for the degree of abnormality is: ; Indicates the current time The corresponding The degree of abnormality of the histogram frequency; is a linear rectification function, Indicates the current time The corresponding Histogram frequencies; Indicates the current time The histogram frequency mean of .

[0011] The beneficial effects are: it provides another method to quantify the degree of abnormality, using a linear rectification function to process the difference between the histogram frequency and the mean, which can highlight high-amplitude abnormal signals while ignoring low-amplitude normal fluctuations. It can accurately identify abnormal signals that may cause surges, thereby providing early warnings and taking measures to avoid potential safety risks.

[0012] Optionally, the length of the initial time window is adjusted according to the surge time window adaptation coefficient to obtain the optimal length of the current time window, including the steps of: performing binary classification on the optimal histogram frequency mode sequence to obtain a normal mode cluster and an abnormal mode cluster; calculating the optimal length; the expression of the optimal length is: ; In the formula, express The optimal length corresponding to the moment, Indicates the current time The reciprocal of the minimum frequency value corresponding to the mode in the corresponding abnormal mode cluster; represents the first hyperparameter; represents the second hyperparameter; Indicates An exponential function with base ; Indicates the current time The corresponding surge time window adaptation coefficient.

[0013] The beneficial effects are as follows: the inverse of the minimum frequency value in the abnormal mode cluster is used as a reference for the time window length, ensuring that the detection window can focus on the key abnormal signal area. The first hyperparameter is used to adjust the multiple of the time window length to ensure the integrity of data acquisition; the second hyperparameter is used to control the influence of the surge time window adaptation coefficient on the window length. By reasonably adjusting these parameters, it is possible to adapt to different engine operating conditions and detection requirements and further optimize the detection performance.

[0014] Optionally, the length of the initial time window is adjusted according to the surge time window adaptation coefficient to obtain the optimal length of the current time window, including the steps of: performing binary classification on the optimal histogram frequency mode sequence to obtain a normal mode cluster and an abnormal mode cluster; calculating the optimal length; the expression of the optimal length is: ; In the formula, express The optimal length corresponding to the moment, Indicates the current time The reciprocal of the minimum frequency value corresponding to the mode in the corresponding abnormal mode cluster; represents the second hyperparameter; Indicates An exponential function with base ; Indicates the current time The corresponding surge time window adaptation coefficient.

[0015] The beneficial effect is that the calculation complexity is reduced by adopting a simplified time window length calculation method, that is, no additional multiple adjustment parameters are introduced.

[0016] Optionally, the optimal histogram frequency mode sequence is classified into two categories to obtain a normal mode cluster and an abnormal mode cluster; the optimal length is calculated; the expression of the optimal length is: ; In the formula, express The optimal length corresponding to the moment, Indicates the current time The reciprocal of the minimum frequency value corresponding to the mode in the corresponding abnormal mode cluster; Indicates An exponential function with base ; Indicates the current time The corresponding surge time window adaptation coefficient.

[0017] Optionally, a K-means clustering algorithm is used for binary classification.

[0018] Optionally, the frequency domain analysis algorithm is a music algorithm.

[0019] Optionally, the frequency domain analysis algorithm is a wavelet decomposition algorithm.

[0020] In a second aspect, the present application provides a data analysis system for an aviation accessory measurement device system, which adopts the following technical solution: A data analysis system for an aviation accessory measuring device system comprises: a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the data analysis method for the aviation accessory measuring device system is implemented.

[0021] The beneficial effect is that the data analysis method of the above-mentioned aviation accessory measuring device system is generated into a computer program and stored in a memory so as to be loaded and executed by a processor, thereby making a system based on the memory and the processor for easy use.

[0022] This application has the following technical effects: 1. The method of using dynamic time window can significantly reduce the detection delay of abnormal signals compared with the traditional fixed time window. Under the condition of high-speed engine operation, this method can greatly improve the response speed of the system and effectively capture the precursor of instantaneous surge, so as to give early warning and take measures to avoid serious damage to the engine caused by surge.

[0023] 2. The adjustment of the dynamic time window is based on the surge window adaptation coefficient, which is calculated by analyzing the frequency distribution characteristics in the time-frequency diagram. This method can automatically adjust the length of the time window according to the actual changes in the signal to ensure that the best detection sensitivity and accuracy can be maintained under different working conditions. At the same time, by optimizing the processing of histogram frequency and the calculation of information entropy value, the reliability of surge detection is further improved, and the possibility of misjudgment and missed judgment is reduced. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 It is a method flow chart of steps S1 to S2 in a data analysis method of an aviation accessory measuring device system according to an embodiment of the present application.

[0025] Figure 2 It is a method flow chart of step S2 in a data analysis method of an aviation accessory measurement device system according to an embodiment of the present application. DETAILED DESCRIPTION

[0026] The present application embodiment discloses a data analysis method for an aviation accessory measurement device system, referring to Figure 1 , including steps S1-S2, which are as follows: S1: Obtain the compressor surface vibration data within the initial time window and obtain the time-frequency diagram through the frequency domain analysis algorithm.

[0027] The aviation accessory measurement device system includes a vibration sensor that uses a wide-band model (such as PCB 352C33, with a bandwidth of 0.5Hz~10kHz). The sensor of the aviation accessory measurement device system is placed at the compressor intake section (low-pressure area), and four sensors are evenly arranged circumferentially with a phase difference of 90° to realize the vibration data collection of the aircraft engine.

[0028] In one embodiment, the initial detection window length is set to Z=2s, and the collected data of the initial window length is the collected vibration data within Z=2s before the current moment. Specifically, assuming that the current time is T, the data in the initial detection window refers to the vibration data collected from T-2 seconds to T, that is, starting from the current moment, going back 2 seconds, and the vibration data within these 2 seconds is used as the data in the initial detection window.

[0029] Set the data collected in the initial window to , Indicates the current time. Use the music algorithm to obtain the current The corresponding time-frequency diagram The music algorithm is a spectrum estimation method, which is mainly used for the frequency analysis of signals. By analyzing the covariance matrix of the signal, the signal space is divided into a signal subspace and a noise subspace, thereby achieving high-precision estimation of the signal frequency. The prior art will not be described in detail here.

[0030] In other embodiments, other frequency domain analysis algorithms such as wavelet packet decomposition can also be used to obtain the time-frequency diagram. Wavelet packet decomposition is a multi-resolution analysis method based on wavelet transform, which can decompose a signal into sub-signals at different frequencies and time scales. For example, the Db4 wavelet basis function is used, and the number of decomposition layers is set to 4. The prior art will not be described in detail here.

[0031] S2: Calculate the surge time window adaptation coefficient corresponding to the current time according to the time-frequency diagram, and adjust the length of the initial time window according to the surge time window adaptation coefficient to obtain the optimal length of the window at the next moment.

[0032] In the obtained time-frequency diagram After that, we can combine the time-frequency diagram and other data such as air flow temperature for surge detection. However, if at the next moment (e.g. If the detection interval is too long, the surge phenomenon may not be discovered in time; if the detection interval is too short (for example seconds), it may be too short to complete a complete surge detection process.

[0033] Therefore, it is necessary to analyze the surge time window adaptation coefficient of the current time-frequency diagram. Since the surge signal is mainly manifested as low frequency and high amplitude, this application sets the low-frequency threshold to 30Hz, that is, only low-frequency data below 30Hz is processed (30Hz is an adjustable hyperparameter, which can be adjusted by the implementer according to the specific scenario). The abnormal degree of the current surge is indicated by calculating the entropy value of the low-frequency information. When the low-frequency amplitude increases, the data will become more dispersed, and the corresponding entropy value will also increase.

[0034] However, when surge occurs, there is less high-amplitude frequency data generated, and directly calculating the entropy value may lead to inaccurate results, thereby affecting the judgment of surge anomaly. In order to avoid the interference of low-amplitude data on high-amplitude data, this application pre-processes the data before calculating the entropy value, so that the data form is more suitable for using the entropy value as an indicator for surge anomaly detection, and at the same time, it can more accurately judge the rationality of the time window length.

[0035] This application uses the time-frequency diagram The frequency spectrum curve is preprocessed and the histogram frequency of the frequency value is adjusted to highlight the abnormal characteristics and reduce interference. The adjusted entropy value is calculated as the surge window adaptation coefficient. Specifically, the calculation method of the surge window adaptation coefficient includes steps S20-S22, which are as follows: S20: Obtain a frequency spectrum curve corresponding to the maximum value of the time-frequency graph at the time domain projection, construct a histogram of the frequency values ​​according to the frequency spectrum curve, and use the frequency at which the frequency values ​​appear as the histogram frequency.

[0036] After obtaining the time-frequency graph, extract the spectrum curve corresponding to the maximum value of the time-frequency graph in the time domain projection. It is the distribution diagram of the signal in time and frequency. Through time domain projection, we can find the frequency range corresponding to the maximum energy of the signal at a certain moment. The spectrum curve at the maximum value of the time domain projection is selected because it reflects the main frequency characteristics of the signal at the current moment.

[0037] S21: Calculate all modes of the histogram frequency and construct a histogram frequency mode sequence.

[0038] Set the current time to , extract the first Frequency value And all frequency values The corresponding histogram frequency , among which Frequency value The corresponding histogram frequency is . Calculate the histogram frequency The mean and all mode values , among which The mode value is .

[0039] For each frequency value , calculate its histogram frequency value With the mean The absolute value of the difference ,Will As the degree of abnormality. The larger the value of the degree of abnormality, the higher the degree of abnormality of the amplitude of the frequency value, and its abnormal characteristics need to be retained without merging with the mode. The smaller the value of the degree of abnormality, the frequency value belongs to normal amplitude fluctuations and needs to be merged to reduce interference. Calculate the difference between each frequency value and the overall mean on the spectrum curve, and use these differences to distinguish the changes in amplitude. By calculating the difference between each frequency value and the overall mean on the spectrum curve, the changes in amplitude can be distinguished. High-amplitude frequency values ​​are usually associated with surge, while low-amplitude frequency values ​​may be noise or normal signals.

[0040] The histogram frequency corresponding to each frequency value on the spectrum curve is adjusted to the mode of the closest histogram frequency value. This can reduce the interference of low-amplitude data on high-amplitude data, thereby increasing the range of entropy value variation, making the entropy value more accurately reflect the surge abnormality, and at the same time improving the effectiveness of subsequent time window division.

[0041] In other embodiments, the calculation expression of the abnormality degree is: ; Indicates the current time The corresponding The degree of abnormality of the histogram frequency; Indicates the current time The corresponding Histogram frequencies; Indicates the current time The histogram frequency mean of . is a linear rectification function, when hour, ;when hour, .

[0042] when Greater than or equal to hour, = If a frequency value is not less than the average frequency, its abnormality is proportional to the excess. The larger the value, the higher the abnormality of the frequency. Less than hour, , indicating that the situation below the average frequency will not be considered abnormal, and the abnormality is zero. When the histogram frequency is less than the histogram frequency mean, The value is 0, that is, the low amplitude situation is not considered; when the histogram frequency is greater than or equal to the histogram frequency mean, The value is the difference between the histogram frequency and the mean, that is, only the high amplitude situation is considered. In this way, high amplitude abnormal signals can be highlighted while ignoring low amplitude normal fluctuations, thereby improving the sensitivity and reliability of detection.

[0043] In order to adjust the frequency value to the most appropriate mode, define the local adjustment coefficient . For the histogram frequency mode sequence If there are continuous modes, discretize them by sampling at equal intervals (for example, the interval is 2). Get the maximum value in the mode value sequence and minimum value . For the Frequency value The histogram frequency values ​​of The local adjustment coefficient corresponding to Adjust to and The most appropriate mode is determined to reduce the interference of low-frequency and low-amplitude vibrations and increase the difference of low-frequency and high-amplitude vibrations.

[0044] The specific acquisition process is: Get the histogram frequency mode sequence Middle Mode ,exist There may be a situation where the majority is continuous. If the majority is continuous, the continuous majority is sampled at equal intervals to obtain a discrete majority sequence, where the continuous judgment method is achieved through a counting method, which is not repeated in this scheme. The interval length of the equal interval sampling is 2, which can be adjusted by the implementer according to the specific implementation scenario.

[0045] In one embodiment, in order to avoid the extreme situation where the mode is too small, if the mode is lower than a preset number (5), it is defaulted to detect sensor failure.

[0046] S22: Calculate the approximate mode; take the mode with the smallest Euclidean distance to the approximate mode as the optimal histogram frequency, construct the optimal histogram frequency mode sequence, calculate the information entropy value of the optimal histogram frequency mode sequence and use it as the surge time window coefficient of the corresponding window at the next moment.

[0047] The expression for the approximate mode is: ; represents the approximate mode; Indicates the current time The corresponding The degree of abnormality of the histogram frequency; Indicates the current time The minimum mode value in the corresponding histogram frequency mode sequence; Indicates An exponential function with base . represents the third hyperparameter, which can be 1 for example. The value can be adjusted according to the actual application scenario.

[0048] The degree of abnormality Negative correlation mapping, the mapped value and the minimum mode Multiply them together to get the approximate mode, which is an adjusted frequency value. When is smaller (i.e. the frequency value is close to the normal level), the adjusted frequency value is closer to the mode, thus achieving merging and unification. When it is large (i.e. the frequency value is highly abnormal), the adjusted frequency value is quite different from the original value and should be avoided as much as possible.

[0049] The optimal histogram frequency mode sequence is constructed according to the adjusted frequency value (optimal histogram frequency), and the information entropy value of the obtained new sequence is calculated as the surge time window adaptation coefficient of the corresponding window at the current moment.

[0050] The larger the surge time window adaptation coefficient is, the more chaotic the low-frequency frequency is, and the greater the possibility of surge is. Conversely, the smaller the possibility of surge is. In order to detect surge anomalies in a timely manner, the time window should be reduced and the detection frequency should be increased. However, the time window cannot be too small to cause excessive loss of information. The surge time window adaptation coefficient cannot be too small to prevent excessive loss of information. Therefore, this application sets the minimum window length value to 0.5s, and 0.5s can be adjusted by the implementer according to the specific implementation scenario. The minimum window length value is not directly used because if the minimum window length value is directly used, more low-frequency data may be lost, and the time window needs to be adjusted according to the current frequency domain distribution.

[0051] The length of the initial time window is adjusted according to the surge window adaptation coefficient to obtain the optimal length of the window at the next moment. The calculation method of the optimal length is as follows: The optimal histogram frequency mode sequence is binary classified to obtain normal mode clusters and abnormal mode clusters; the mode in the optimal histogram frequency mode sequence should be divided into two parts, one part of the data with a small difference from the original data mean represents the normal mode, and the other part of the data with a large difference from the original data mean represents the abnormal mode, and then a new adjusted frequency value sequence is obtained, and these frequency values ​​are binary classified to distinguish normal and abnormal modes.

[0052] Calculate the optimal length; the expression for the optimal length is: ; In the formula, express The optimal length corresponding to the moment, Indicates the current time The reciprocal of the minimum frequency value corresponding to the mode in the corresponding abnormal mode cluster; Indicates An exponential function with base ; Indicates the current time The corresponding surge time window adaptation coefficient.

[0053] In order to make the optimal length calculation adapt to more scenarios, the expression of the optimal length can be: ; In the formula, express The optimal length corresponding to the moment, Indicates the current time The reciprocal of the minimum frequency value corresponding to the mode in the corresponding abnormal mode cluster; Indicates An exponential function with base ; Indicates the current time The corresponding surge time window adaptation coefficient.

[0054] in, represents the first hyperparameter; Represents the second hyperparameter; illustratively, the first hyperparameter may be 5, and the second hyperparameter may be 1.5; the first hyperparameter and the second hyperparameter may be adjusted or canceled in the calculation of the optimal length according to the actual application scenario, which will not be elaborated here.

[0055] In one embodiment, the K-means clustering algorithm is used to divide the optimal histogram frequency mode sequence into two categories. The mode in each category corresponds to a frequency value, and the abnormality of these frequency values ​​(denoted as The values ​​are used to distinguish normal and abnormal modes. The The average value (denoted as Then, for all The values ​​are averaged again to obtain the overall average value of the category (denoted as ). Finally, compare the two categories Value. Among them, The category with the larger value is considered as the abnormal majority category because the larger A value of indicates that the frequency value in that category has a higher degree of abnormality.

[0056] Since real-time sampling is not possible, this solution chooses to perform surge detection at the start time of the next time window. In order to ensure the continuity and coverage of the detection, the time point selected is the time corresponding to the 30% overlap rate after the end of the current time window. This can ensure the continuity of the detection process and avoid missing key information due to long time intervals.

[0057] The embodiment of the present application also discloses a data analysis system for an aviation accessory measuring device system, including a processor and a memory, the memory storing computer program instructions, and when the computer program instructions are executed by the processor, a data analysis method for an aviation accessory measuring device system according to the present application is implemented. The above system also includes other components well known to those skilled in the art, such as a communication bus and a communication interface, whose settings and functions are known in the art, and therefore will not be described in detail here.

[0058] In the present application, the aforementioned memory may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. For example, a computer-readable storage medium may be any suitable magnetic storage medium or magneto-optical storage medium, or any other medium that can be used to store the desired information and can be accessed by an application, module, or both.

[0059] The above are all preferred embodiments of the present application, and the protection scope of the present application is not limited thereto. Therefore, any equivalent changes made according to the structure, shape, and principle of the present application should be included in the protection scope of the present application.

Claims

1. A data analysis method for an aviation accessory measuring device system, characterized in that: The method comprises the following steps: obtaining compressor surface vibration data within an initial time window, obtaining a time-frequency diagram through a frequency domain analysis algorithm; calculating a surge time window adaptation coefficient corresponding to the current time according to the time-frequency diagram, and adjusting the length of the initial time window according to the surge time window adaptation coefficient to obtain an optimal length of the window at the next moment; The calculation method of the surge time window adaptation coefficient is as follows: obtain the spectrum curve corresponding to the maximum value of the time-frequency diagram at the time domain projection, construct a histogram of the frequency value according to the spectrum curve, and take the frequency of occurrence of the frequency value as the histogram frequency; Calculate all modes of the histogram frequency and construct a histogram frequency mode sequence; calculate the approximate mode, and the expression of the approximate mode is: ; represents the approximate mode; Indicates the current time The corresponding The degree of abnormality of the histogram frequency; Indicates the current time The minimum mode value in the corresponding histogram frequency mode sequence; represents a hyperparameter; Indicates An exponential function with the base ; the mode with the smallest Euclidean distance to the approximate mode is taken as the optimal histogram frequency, the optimal histogram frequency mode sequence is constructed, and the information entropy value of the optimal histogram frequency mode sequence is calculated and used as the surge time window coefficient of the corresponding window at the next moment.

2. The data analysis method of the aviation accessory measuring device system according to claim 1, characterized in that: The degree of abnormality is the absolute difference between the histogram frequency and the mean of the histogram frequency.

3. The data analysis method of the aviation accessory measuring device system according to claim 1, characterized in that: The calculation expression of abnormality degree is: ; Indicates the current time The corresponding The degree of abnormality of the histogram frequency; is a linear rectification function, Indicates the current time The corresponding Histogram frequencies; Indicates the current time The histogram frequency mean of .

4. The data analysis method for the aviation accessory measuring device system according to claim 1, characterized in that: The length of the initial time window is adjusted according to the surge time window adaptation coefficient to obtain the optimal length of the current time window, including the following steps: The optimal histogram frequency mode sequence is classified into two categories to obtain normal mode clusters and abnormal mode clusters; the optimal length is calculated; the expression of the optimal length is: ; In the formula, express The optimal length corresponding to the moment, Indicates the current time The reciprocal of the minimum frequency value corresponding to the mode in the corresponding abnormal mode cluster; represents the first hyperparameter; represents the second hyperparameter; Indicates An exponential function with base ; Indicates the current time The corresponding surge time window adaptation coefficient.

5. The data analysis method for the aviation accessory measuring device system according to claim 1, characterized in that: The length of the initial time window is adjusted according to the surge time window adaptation coefficient to obtain the optimal length of the current time window, including the following steps: The optimal histogram frequency mode sequence is classified into two categories to obtain normal mode clusters and abnormal mode clusters; the optimal length is calculated; the expression of the optimal length is: ; In the formula, express The optimal length corresponding to the moment, Indicates the current time The reciprocal of the minimum frequency value corresponding to the mode in the corresponding abnormal mode cluster; represents the second hyperparameter; Indicates An exponential function with base ; Indicates the current time The corresponding surge time window adaptation coefficient.

6. The data analysis method for the aviation accessory measuring device system according to claim 1, characterized in that: The length of the initial time window is adjusted according to the surge time window adaptation coefficient to obtain the optimal length of the current time window, including the following steps: The optimal histogram frequency mode sequence is classified into two categories to obtain normal mode clusters and abnormal mode clusters; the optimal length is calculated; the expression of the optimal length is: ; In the formula, express The optimal length corresponding to the moment, Indicates the current time The reciprocal of the minimum frequency value corresponding to the mode in the corresponding abnormal mode cluster; Indicates An exponential function with base ; Indicates the current time The corresponding surge time window adaptation coefficient.

7. The data analysis method of the aviation accessory measuring device system according to any one of claims 4 to 6, characterized in that: The K-means clustering algorithm is used for binary classification.

8. The data analysis method for the aviation accessory measuring device system according to claim 1, characterized in that: The frequency domain analysis algorithm is the music algorithm.

9. The data analysis method for the aviation accessory measuring device system according to claim 1, characterized in that: The frequency domain analysis algorithm is wavelet decomposition algorithm.

10. A data analysis system for an aviation accessory measuring device system, characterized in that: include: A processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, a data analysis method for an aviation accessory measuring device system according to any one of claims 1 to 9 is implemented.

Images