CN114061848B - Method for identifying leak hole of reinforced sealing structure of spacecraft - Google Patents

Method for identifying leak hole of reinforced sealing structure of spacecraft Download PDF

Info

Publication number
CN114061848B
CN114061848B CN202111370023.8A CN202111370023A CN114061848B CN 114061848 B CN114061848 B CN 114061848B CN 202111370023 A CN202111370023 A CN 202111370023A CN 114061848 B CN114061848 B CN 114061848B
Authority
CN
China
Prior art keywords
leakage
signal
frequency
frequency domain
leak
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202111370023.8A
Other languages
Chinese (zh)
Other versions
CN114061848A (en
Inventor
孙立臣
綦磊
欧逍宇
王莉娜
隆昌宇
闫荣鑫
张景川
郑悦
郭琦
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Institute of Spacecraft Environment Engineering
Original Assignee
Beijing Institute of Spacecraft Environment Engineering
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Beijing Institute of Spacecraft Environment Engineering filed Critical Beijing Institute of Spacecraft Environment Engineering
Priority to CN202111370023.8A priority Critical patent/CN114061848B/en
Publication of CN114061848A publication Critical patent/CN114061848A/en
Application granted granted Critical
Publication of CN114061848B publication Critical patent/CN114061848B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
    • G01M3/00—Investigating fluid-tightness of structures
    • G01M3/02—Investigating fluid-tightness of structures by using fluid or vacuum
    • G01M3/04—Investigating fluid-tightness of structures by using fluid or vacuum by detecting the presence of fluid at the leakage point
    • G01M3/24—Investigating fluid-tightness of structures by using fluid or vacuum by detecting the presence of fluid at the leakage point using infrasonic, sonic, or ultrasonic vibrations
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
    • Y02T90/00—Enabling technologies or technologies with a potential or indirect contribution to GHG emissions mitigation

Landscapes

  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Examining Or Testing Airtightness (AREA)

Abstract

The invention discloses a method for identifying leakage holes of a reinforced sealing structure of a spacecraft, which comprises the following steps: s1, performing a simulated leakage experiment, extracting characteristic values, and performing learning training to form an identification model library; s2, collecting leakage sound signals, performing 30kHz-500kHz band-pass filtering pretreatment on the leakage sound signals, and obtaining a frequency band f with less reinforcing rib attenuation d ‑f u The method comprises the steps of carrying out a first treatment on the surface of the S3, positioning the leakage holes; s4, compensating according to the number of the bars passing signals; s5, extracting leakage sound signal characteristics, and comparing the leakage sound signal characteristics with an identification model library to obtain leakage hole characteristics. According to the invention, the spacecraft leakage identification of EMD-WPD feature fusion is realized by applying the reliefF algorithm, and the accuracy is greatly improved by utilizing the fusion signal processing method to identify different leak holes compared with the prior pure spectrum signal leak holes, and the identification of the shape, the size and other characteristics of the leak holes is realized.

Description

Method for identifying leak hole of reinforced sealing structure of spacecraft
Technical Field
The invention relates to the technical field of spacecraft leakage detection, in particular to a method for identifying leakage holes of a reinforced sealing structure of a spacecraft.
Background
With the development of aerospace technology and the increasing frequency of human aerospace activities, the number of space fragments is obviously increased, and once the fragments collide with a spacecraft, the sealing structure of the spacecraft is leaked, so that the on-orbit operation of the spacecraft is seriously influenced. Timely and accurately finding leakage, identifying the position, the size, the shape and other characteristics of the leakage holes, and providing support for subsequent plugging and repairing of the spacecraft and emergency escape of astronauts. Currently commonly used spacecraft leakage detection technologies comprise pressure change leakage detection, infrared thermal imaging leakage detection, helium mass spectrometer gun leakage detection, acoustic leakage detection and the like. The pressure change leak detection can only judge whether the leakage exists or not, and the leakage position cannot be determined; the infrared thermal imaging leakage detection sensitivity is poor, and only qualitative analysis is performed; the helium mass spectrometer suction gun leak detection can detect very low leak rate leak holes, but the leak holes cannot be positioned quickly, and once the search range is too large, the leak holes are more difficult to find; the acoustic leak detection is an emerging leak detection technology, and can rapidly judge the leak position, but the quantitative analysis of the leak is difficult, and structures such as reinforcing ribs influence the propagation of sound waves so as to influence the accuracy of acoustic leak detection. The patent provides a method for identifying leakage holes of a reinforcement sealing structure of a spacecraft, which realizes the judgment of leakage and the identification of the size and the shape of the leakage holes by a database training and learning method.
Disclosure of Invention
The invention aims at: in order to solve the problems, a method for identifying leakage holes of a reinforcement sealing structure of a spacecraft is provided.
In order to achieve the above purpose, the present invention adopts the following technical scheme:
a method for identifying leakage holes of a reinforced sealing structure of a spacecraft comprises the following steps:
s1, establishing an identification model library: leakage simulation experiments of leakage holes with different shapes and sizes are performed in advance, leakage sound signals are collected, characteristic values are extracted, and learning and training are performed to form an identification model library;
s2, collecting leakage sound signals: collecting leakage sound signals, filtering and preprocessing at 30kHz-500kHz to remove background noise, observing attenuation condition of sound signals before and after passing through reinforcing ribs, and selecting sound signal frequency band f with weaker attenuation d -f u ；
S3, positioning the leak holes: a coordinate system is established using 3 sensors (number S 1 ，S 2 ,S 3 ) Data, using FIR filters to obtain these sensors f d -f u Band energy signal, S 1 The sensor is exemplified by a sensor such as a sensor,
Figure BDA0003362082580000021
y (f) is the signal amplitude at different frequencies, sensor S 2 、S 3 The same calculation method is used for establishing an equation set: />
Figure BDA0003362082580000022
(x 1 ,y 1 )(x 2 ,y 2 )(x 3 ,y 3 ) Knowing coordinates for three sensors, using a linear iterative algorithm, the equation set can be solved for leak coordinates (x, y);
s4, signal over-reinforcement compensation: after the coordinates of the leak hole are obtained, the original data of the signal of the sensor closest to the leak hole is applied, the number alpha of the reinforcing ribs passing through in the linear propagation process between the leak hole and the sensor can be known, the signal is compensated by the reinforcing ribs, and each reinforcing rib pair f d -f u The attenuation coefficient of this band range is β (f), so multiplying this band of y (f) by the compensation coefficient α×β (f) (α is the number of tendons and β (f) is the attenuation coefficient);
s5, identifying leakage holes: and extracting leakage sound signal characteristics, and comparing the leakage sound signal characteristics with an identification model library to obtain leakage hole characteristics.
Preferably, the method for determining the leakage identification model library through ground learning training in the step S1 includes the following steps:
A1. the following leakage signal extraction is performed in the internal and external air pressure and vacuum degree of the simulated spacecraft: no leakage of distribution extraction,
Figure BDA0003362082580000023
Leakage of round hole>
Figure BDA0003362082580000024
Leakage of round hole>
Figure BDA0003362082580000025
Seven signals of round hole leakage, 1mm multiplied by 1mm square hole leakage, three-side 1mm triangular hole leakage and 0.5mm multiplied by 2mm rectangular hole leakage are simultaneously extracted by two identical sensors (A 1 Sensor and A 2 Sensors) for each group of acoustic signals for 3s, wherein the sensors are 10cm away from the center of the leak hole during signal extraction;
A2. each extracted set of signals was cut into 200 sets (0.015 s each) where A 1 The sensor is used as test group data for testing the accuracy of the classification model, A 2 The sensor data is used as training set data of a classification algorithm model;
A3. the method comprises the steps of carrying out digital filtering on all original signal data, wherein an effective frequency band of an acoustic sensor is selected to comprise 30kHz-500kHz, and filtering is carried out by a band-pass FIR filter to obtain signal components between 30kHz and 500kHz in consideration of background noise influence and the general need of filtering components below 30 kHz;
A4. processing the data by an EMD algorithm and a WPD algorithm respectively, wherein an interpolation function of the EMD adopts cubic spline interpolation, a wavelet mother function of the WPD adopts dmey wavelet, and the two algorithms respectively obtain IMF_1-IMF_n 1 And subband signals 1-n 2 Taking the intermediate 4 groups of IMF obtained by EMD and the first 4 groups of subband signals obtained by WPD, extracting 9 characteristic values by using the 8 groups of signals respectively, and enabling the two methods of EMD and WPD to obtain 36 characteristics respectively, wherein the 9 characteristic values are respectively a time domain kurtosis factor, a skewness factor and a waveform factor, and meanwhile, the frequency domain kurtosis factor, the skewness factor, the waveform factor, a peak frequency, a spectrum bandwidth and a bandwidth centroid frequency, and the algorithm of 9 characteristic parameters is as follows:
[1]time domain kurtosis factor:
Figure BDA0003362082580000031
(x n is a time domain signal value);
[2]time domain skewness factor:
Figure BDA0003362082580000032
(x n for signal time domain values, +.>
Figure BDA0003362082580000033
Is the time domain mean value of the signal);
[3]time domain form factor:
Figure BDA0003362082580000034
(x rms is the signal time domain root mean square value, x avr Is the time domain mean value of the signal); />
[4]Frequency domain kurtosis factor:
Figure BDA0003362082580000035
(y n is a frequency domain value);
[5]frequency domain skewness factor:
Figure BDA0003362082580000036
(y n for signal frequency domain values, +.>
Figure BDA0003362082580000037
Is the mean value of the signal frequency domain values);
[6]frequency domain form factor:
Figure BDA0003362082580000041
(y rms is the root mean square value of the frequency domain, y avr Is the frequency domain mean value);
[7]peak frequency: f (f) max ＝max(y(f))| f The method comprises the steps of carrying out a first treatment on the surface of the (y (f) is a signal frequency domain function, the value of y (f) is called frequency domain amplitude, f max Representing a frequency point corresponding to the maximum amplitude of the frequency domain);
[8]spectrum bandwidth: f (f) dB ＝f up -f down (f up For the frequency domain amplitude y (f) is at the maximum frequency point corresponding to the maximum amplitude of 0.3 times, f down The frequency domain amplitude y (f) is at the lowest frequency point corresponding to the maximum amplitude of 0.3 times);
[9]bandwidth centroid frequency:
Figure BDA0003362082580000042
A5. the two groups of 36 features are respectively applied to a ReliefF feature evaluation algorithm to obtain respective weight values, the weight values are equivalent to the distinguishing capability of the features, and the higher the weight values are, the higher the distinguishing capability of the features to different leakage holes is, so that the application of the ReliefF algorithm is: randomly selecting one sample R from a certain leak leakage characteristic set A, searching k nearest neighbor sample sets H from samples of the same type of R, searching k nearest neighbor sample sets M from samples of different types of R, and updating the weight of each leakage characteristic according to the following two formulas (1) (2):
Figure BDA0003362082580000043
Figure BDA0003362082580000044
obtaining the weight of 36 multiplied by 2 features corresponding to each leak hole from the above steps;
A6. the weights of the same features of each leak hole are all summed and calculated to be average, so that new weights of 36 features of EMD and WPD are obtained, then new weights of 36 features of two groups are ordered, features of 2 before each weight in the two groups are selected to be brought into SVM classification training, a Radial Basis Function (RBF) is adopted as a kernel function of the SVM, a leak hole identification model library after training is tested by test group data, how the leak hole identification model library is distinguished in accuracy is seen, if the accuracy is insufficient, the number of features with high weights can be gradually increased, and experimental results show that the number of the features with high weight is increased, but the training amount is definitely increased, so that the number of the features with high weight is finally determined according to the required requirements;
A7. and finally, determining the characteristics selected in the next simulation test and a trained leak hole identification model library.
Preferably, f in the step S2 d And f u Only the same drain hole is used for collecting signals and comparing the frequency spectrums under the condition of passing the bars and not passing the bars at the same distance, and the frequency spectrum of the passing bars is 80 percent larger than the energy of the frequency spectrum of the not passing barsThe lower frequency limit of (2) is f d The upper frequency limit is f u At the same time, f can also be obtained d -f u Attenuation β (f) of this band.
In summary, due to the adoption of the technical scheme, the beneficial effects of the invention are as follows:
1. in the application, the characteristic evaluation method of the Relieff is applied to realize the screening and mixed application of the characteristic values obtained by the two signal processing methods of the EMD and the WPD, and compared with the conventional characteristic fusion recognition method based on the Relieff for recognizing by acquiring the characteristic values based on a pure frequency spectrum signal, the EMD-WPD characteristic fusion recognition method based on the Relieff not only improves the correct recognition rate, but also effectively controls the quantity of the brought characteristic, and reduces the unnecessary training quantity.
2. In the method, the reinforcing ribs in the spacecraft structure have great influence on acoustic signal propagation and leak hole identification, the number of the reinforcing ribs is calculated by realizing leak hole positioning, signals are compensated according to the reinforcing rib attenuation function, and the interference of the spacecraft reinforcing ribs on leak hole identification is overcome.
Drawings
FIG. 1 shows a schematic diagram of a sensor and a leak layout of a reinforced structure of a spacecraft provided according to an embodiment of the invention;
FIG. 2 illustrates a flow chart of leak detection and leak feature identification provided in accordance with an embodiment of the invention;
fig. 3 shows a flowchart of leak identification model establishment provided according to an embodiment of the invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1-3, the present invention provides a technical solution:
a method for identifying leakage holes of a reinforced sealing structure of a spacecraft comprises the following steps:
s1, performing simulated ground training to determine a leak identification model library, and putting the leak identification model library into actual on-orbit operation of a spacecraft;
s2, observing energy change of a frequency band of 30kHz-500kHz before and after passing the reinforcing rib, and determining a reinforcing rib attenuation frequency band f d -f u Obtaining a tendon attenuation coefficient beta (f);
s3, positioning the leak hole, firstly establishing a coordinate system, wherein the coordinate of each sensor is known, and f is because of d -f u The frequency band is less affected by the reinforcing ribs, so f is used d -f u The frequency band signal is used for positioning, and the positioning principle is as follows: intercepting the sensors f using FIR filters using at least 3 sensor data d -f u Signals in the frequency band, S 1 The sensor is exemplified by a sensor such as a sensor,
Figure BDA0003362082580000061
y (f) is the signal amplitude at different frequencies, sensor S 2 、S 3 The same calculation method is used for establishing an equation set:
Figure BDA0003362082580000062
(x 1 ,y 1 )(x 2 ,y 2 )(x 3 ,y 3 ) Knowing coordinates for three sensors, using a linear iterative algorithm, the equation set can be solved for leak coordinates (x, y);
s4, after the coordinates of the leak holes are obtained, the original data of the signals of the sensor closest to the leak holes are applied, the number alpha of the reinforcing ribs passing through in the linear propagation process between the leak holes and the sensor can be obtained, the signals are subjected to rib passing compensation, and each reinforcing rib pair f d -f u The attenuation coefficient of this band range is β (f), so multiplying this band of y (f) by the compensation coefficient α×β (f) (α is the number of tendons and β (f) is the attenuation coefficient);
s5, extracting leakage sound signal characteristics, and comparing the leakage sound signal characteristics with an identification model library to obtain leakage hole characteristics.
Specifically, as shown in fig. 3, the method for determining the leak identification model library by simulating ground training in step S1 includes the following steps:
A1. the following leakage signal extraction is performed in the internal and external air pressure and vacuum degree of the simulated spacecraft: no leakage of distribution extraction,
Figure BDA0003362082580000071
Leakage of round hole>
Figure BDA0003362082580000072
Leakage of round hole>
Figure BDA0003362082580000073
Seven signals of round hole leakage, 1mm multiplied by 1mm square hole leakage, three-side 1mm triangular hole leakage and 0.5mm multiplied by 2mm rectangular hole leakage. Each time the signal is extracted, two identical sensors (A 1 Sensor and A 2 Sensors) for each group of acoustic signals for 3s, wherein the sensors are 10cm away from the center of the leak hole during signal extraction;
A2. each extracted set of signals was cut into 200 sets (0.015 s each) where A 1 The sensor is used as test group data for testing the accuracy of the classification model, A 2 The sensor data is used as training set data of a classification algorithm model;
A3. all raw signal data are digitally filtered and the active band of the acoustic sensor selected to contain 30kHz-500kHz. Filtering by adopting a band-pass FIR filter in consideration of the influence of background noise, so as to obtain a signal component between 30kHz and 500 kHz;
A4. processing the data by an EMD algorithm and a WPD algorithm respectively, wherein an interpolation function of the EMD adopts cubic spline interpolation, a wavelet mother function of the WPD adopts dmey wavelet, and the two algorithms respectively obtain IMF_1-IMF_n 1 And subband signals 1-n 2 Taking the intermediate 4 groups of IMF obtained by EMD and the first 4 groups of subband signals obtained by WPD, extracting 9 characteristic values from the 8 groups of signals respectively, and obtaining 36 characteristics by the two methods of EMD and WPD, namely 72 characteristics in total, wherein the 9 characteristic valuesThe method is characterized in that the method comprises the steps of respectively obtaining a time domain kurtosis factor, a skewness factor and a waveform factor, and simultaneously obtaining a frequency domain kurtosis factor, a skewness factor, a waveform factor, a peak frequency, a spectrum bandwidth and a bandwidth centroid frequency, wherein the total of 9 characteristic parameters are as follows:
[1]time domain kurtosis factor:
Figure BDA0003362082580000074
(x n is a time domain signal value);
[2]time domain skewness factor:
Figure BDA0003362082580000075
(x n for signal time domain values, +.>
Figure BDA0003362082580000076
Is the time domain mean value of the signal);
[3]time domain form factor:
Figure BDA0003362082580000077
(x rms is the signal time domain root mean square value, x avr Is the time domain mean value of the signal);
[4]frequency domain kurtosis factor:
Figure BDA0003362082580000081
(y n is a frequency domain value);
[5]frequency domain skewness factor:
Figure BDA0003362082580000082
(y n for signal frequency domain values, +.>
Figure BDA0003362082580000083
Is the mean value of the signal frequency domain values);
[6]frequency domain form factor:
Figure BDA0003362082580000084
(y rms is the root mean square value of the frequency domain, y avr Is the frequency domain mean value);
[7]peak frequency: f (f) max ＝max(y(f))| f The method comprises the steps of carrying out a first treatment on the surface of the (y (f) is a signal frequency domain function, the value of y (f) is called frequency domain amplitude, f max Representing a frequency point corresponding to the maximum amplitude of the frequency domain);
[8]spectrum bandwidth: f (f) dB ＝f up -f down (f up For the frequency domain amplitude y (f) is at the maximum frequency point corresponding to the maximum amplitude of 0.3 times, f down The frequency domain amplitude y (f) is at the lowest frequency point corresponding to the maximum amplitude of 0.3 times);
[9]bandwidth centroid frequency:
Figure BDA0003362082580000085
A5. the two groups of 36 features are respectively applied to a ReliefF feature evaluation algorithm to obtain respective weight values, the weight values are equivalent to the distinguishing capability of the features, and the higher the weight values are, the higher the distinguishing capability of the features to different leakage holes is, so that the application of the ReliefF algorithm is: randomly selecting one sample R from a certain leak leakage characteristic set A, searching k nearest neighbor sample sets H from samples of the same type of R, searching k nearest neighbor sample sets M from samples of different types of R, and updating the weight of each leakage characteristic according to the following two formulas (3) (4):
Figure BDA0003362082580000086
Figure BDA0003362082580000087
obtaining the weight of 36 multiplied by 2 features corresponding to each leak hole from the above steps;
A6. the weights of the same features of each leak hole are all summed and calculated to be average, so that new weights of 36 features of EMD and WPD are obtained, then new weights of 36 features of two groups are ordered, features of 2 before each weight in the two groups are selected to be brought into SVM classification training, a Radial Basis Function (RBF) is adopted as a kernel function of the SVM, a leak hole identification model library after training is tested by test group data, how the leak hole identification model library is distinguished in accuracy is seen, if the accuracy is insufficient, the number of features with high weights can be gradually increased, and experimental results show that the number of the features with high weight is increased, but the training amount is definitely increased, so that the number of the features with high weight is finally determined according to the required requirements;
A7. and finally, determining the characteristics selected in the next simulation test and a trained leak hole identification model library.
Specifically, as shown in FIG. 1, f in step S2 d And f u The frequency lower limit of the part of the over-reinforcement spectrum, which is larger than 80% of the over-reinforcement spectrum energy, is f only by using the same drain hole to collect signals and make spectrum comparison under the condition of over-reinforcement and over-reinforcement respectively at the same distance d The upper frequency limit is f u At the same time, f can also be obtained d -f u Attenuation β (f) of this band.
In summary, the leak identification method of the reinforcement sealing structure of the spacecraft provided by the embodiment can effectively improve the leak occurrence and leak characteristic identification capability, and can also control the feature quantity required to be brought into training.
The previous description of the embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims (2)

1. The method for identifying the leak hole of the reinforced sealing structure of the spacecraft is characterized by comprising the following steps of:
s1, establishing an identification model library: leakage simulation experiments of leakage holes with different shapes and sizes are performed in advance, leakage sound signals are collected, characteristic values are extracted, and learning and training are performed to form an identification model;
the method for establishing the identification model library in the step S1 comprises the following steps:
A1. the following leakage signal extraction is performed in the internal and external air pressure and vacuum degree of the simulated spacecraft: no leakage of distribution extraction,
Figure FDA0004139072700000011
Leakage of round hole>
Figure FDA0004139072700000012
Leakage of round hole>
Figure FDA0004139072700000013
Seven signals of round hole leakage, 1mm multiplied by 1mm square hole leakage, three-side 1mm triangular hole leakage and 0.5mm multiplied by 2mm rectangular hole leakage are simultaneously extracted by two identical A signals each time 1 Sensor and A 2 The sensors are used for extracting each group of acoustic signals for 3s, and the distance between the sensors and the center of the leak hole is 10cm during signal extraction;
A2. cutting each extracted signal into 200 groups of 0.015s each, wherein A 1 The sensor is used as test group data for testing the accuracy of the classification model, A 2 The sensor data is used as training set data of a classification algorithm model;
A3. the method comprises the steps of carrying out digital filtering on all original signal data, wherein an effective frequency band of an acoustic sensor is selected to comprise 30kHz-500kHz, and filtering is carried out by a band-pass FIR filter to obtain signal components between 30kHz and 500kHz in consideration of background noise influence and the general need of filtering components below 30 kHz;
A4. processing the data by an EMD algorithm and a WPD algorithm respectively, wherein an interpolation function of the EMD adopts cubic spline interpolation, a wavelet mother function of the WPD adopts dmey wavelet, and the two algorithms respectively obtain IMF_1-IMF_n 1 Hezi (Hezi)With signals 1-n 2 Taking the intermediate 4 groups of IMF obtained by EMD and the first 4 groups of subband signals obtained by WPD, extracting 9 characteristic values by using the 8 groups of signals respectively, and enabling the two methods of EMD and WPD to obtain 36 characteristics respectively, wherein the 9 characteristic values are respectively a time domain kurtosis factor, a skewness factor and a waveform factor, and meanwhile, the frequency domain kurtosis factor, the skewness factor, the waveform factor, a peak frequency, a spectrum bandwidth and a bandwidth centroid frequency, and the algorithm of 9 characteristic parameters is as follows:
[1]time domain kurtosis factor:
Figure FDA0004139072700000014
(x n is a time domain signal value);
[2]time domain skewness factor:
Figure FDA0004139072700000015
(x n for signal time domain values, +.>
Figure FDA0004139072700000016
Is the time domain mean value of the signal);
[3]time domain form factor:
Figure FDA0004139072700000021
(x rms is the signal time domain root mean square value, x avr Is the time domain mean value of the signal);
[4]frequency domain kurtosis factor:
Figure FDA0004139072700000022
(y n is a frequency domain value);
[5]frequency domain skewness factor:
Figure FDA0004139072700000023
(y n for signal frequency domain values, +.>
Figure FDA0004139072700000024
Is the mean value of the signal frequency domain values);
[6]frequency domain form factor:
Figure FDA0004139072700000025
(y rms is the root mean square value of the frequency domain, y avr Is the frequency domain mean value);
[7]peak frequency: f (f) max ＝max(y(f))| f The method comprises the steps of carrying out a first treatment on the surface of the (y (f) is a signal frequency domain function, the value of y (f) is called frequency domain amplitude, f max Representing a frequency point corresponding to the maximum amplitude of the frequency domain);
[8]spectrum bandwidth: f (f) dB ＝f up -f down (f up For the frequency domain amplitude y (f) is at the maximum frequency point corresponding to the maximum amplitude of 0.3 times, f down The frequency domain amplitude y (f) is at the lowest frequency point corresponding to the maximum amplitude of 0.3 times);
[9]bandwidth centroid frequency:
Figure FDA0004139072700000026
A5. the two groups of 36 features are respectively applied to a ReliefF feature evaluation algorithm to obtain respective weight values, the weight values are equivalent to the distinguishing capability of the features, and the higher the weight values are, the higher the distinguishing capability of the features to different leakage holes is, so that the application of the ReliefF algorithm is: randomly selecting one sample R from a certain leak leakage characteristic set A, searching k nearest neighbor sample sets H from samples of the same type of R, searching k nearest neighbor sample sets M from samples of different types of R, and updating the weight of each leakage characteristic according to the following two formulas (1) (2):
Figure FDA0004139072700000027
Figure FDA0004139072700000031
obtaining the weight of 36 multiplied by 2 features corresponding to each leak hole from the above steps;
A6. the weights of the same features of each leak hole are all summed and calculated to be average, so that new weights of 36 features of EMD and WPD are obtained, then new weights of 36 features of two groups are ordered, features of 2 before each weight in the two groups are selected to be brought into SVM classification training, a Radial Basis Function (RBF) is adopted as a kernel function of the SVM, a leak hole identification model library after training is tested by test group data, how the leak hole identification model library is distinguished in accuracy is seen, if the accuracy is insufficient, the number of features with high weights can be gradually increased, and experimental results show that the number of the features with high weight is increased, but the training amount is definitely increased, so that the number of the features with high weight is finally determined according to the required requirements;
A7. finally, determining the characteristics selected in the next simulation test and an identification model library of the trained SVM;
s2, collecting leakage sound signals: collecting leakage sound signals, filtering and preprocessing at 30kHz-500kHz to remove background noise, observing attenuation condition of sound signals before and after passing through reinforcing ribs, and selecting sound signal frequency band f with weaker attenuation d -f u ；
S3, positioning the leak holes: establishing a coordinate system by adopting S 1 ，S 2 ，S 3 3 sensor data, and FIR filter is used to obtain these sensors f d -f u Band energy signal, S 1 The sensor is exemplified by a sensor such as a sensor,
Figure FDA0004139072700000032
y (f) is the signal amplitude at different frequencies, sensor S 2 、S 3 The same calculation method is used for establishing an equation set:
Figure FDA0004139072700000033
(x 1 ,y 1 )(x 2 ,y 2 )(x 3 ,y 3 ) Knowing coordinates for three sensors, using a linear iterative algorithm, the equation set can be solved for leak coordinates (x, y);
S4.and (3) signal bar-crossing compensation: after the coordinates of the leak hole are obtained, the original data of the signal of the sensor closest to the leak hole is applied, the number alpha of the reinforcing ribs passing through in the linear propagation process between the leak hole and the sensor can be known, the signal is compensated by the reinforcing ribs, and each reinforcing rib pair f d -f u The attenuation coefficient of this band range is β (f), so multiplying this band of y (f) by the compensation coefficient α×β (f), α being the number of over-tendons, β (f) being the attenuation coefficient;
s5, identifying leakage holes: and extracting leakage sound signal characteristics, and comparing the leakage sound signal characteristics with an identification model library to obtain leakage hole characteristics.
2. The method for identifying leakage holes of reinforcement seal structure of spacecraft according to claim 1, wherein f in the step S2 d And f u The frequency lower limit of the part of the over-reinforcement spectrum, which is larger than 80% of the over-reinforcement spectrum energy, is f only by using the same drain hole to collect signals and make spectrum comparison under the condition of over-reinforcement and over-reinforcement respectively at the same distance d The upper frequency limit is f u At the same time, f can also be obtained d -f u Attenuation β (f) of this band.
CN202111370023.8A 2021-11-18 2021-11-18 Method for identifying leak hole of reinforced sealing structure of spacecraft Active CN114061848B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111370023.8A CN114061848B (en) 2021-11-18 2021-11-18 Method for identifying leak hole of reinforced sealing structure of spacecraft

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111370023.8A CN114061848B (en) 2021-11-18 2021-11-18 Method for identifying leak hole of reinforced sealing structure of spacecraft

Publications (2)

Publication Number Publication Date
CN114061848A CN114061848A (en) 2022-02-18
CN114061848B true CN114061848B (en) 2023-05-26

Family

ID=80277879

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111370023.8A Active CN114061848B (en) 2021-11-18 2021-11-18 Method for identifying leak hole of reinforced sealing structure of spacecraft

Country Status (1)

Country Link
CN (1) CN114061848B (en)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115420247B (en) * 2022-11-03 2023-01-06 核工业北京地质研究院 Method for determining shape and area of vacuum leakage hole and experimental system
CN117968971B (en) * 2024-03-28 2024-06-04 杭州微影软件有限公司 Gas leakage amount detection method and device and electronic equipment

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2010002264A (en) * 2008-06-19 2010-01-07 Honda Motor Co Ltd Gas leakage diagnosis device and gas leakage diagnosis method
CN103471784A (en) * 2013-09-26 2013-12-25 北京卫星环境工程研究所 Method for judging size of non-contact type ultrasonic quantitative leakage hole of spacecraft on-orbit leakage
CN106764451A (en) * 2016-12-08 2017-05-31 重庆科技学院 The modeling method of gas pipeline tiny leakage is detected based on sound wave signals
CN108195525A (en) * 2018-01-29 2018-06-22 清华大学合肥公共安全研究院 A kind of pipeline of simulated leakage noise signal and its noise signal online acquisition device
CN109870276A (en) * 2018-11-28 2019-06-11 中国人民解放军国防科技大学 Spacecraft on-orbit leakage positioning method and system
CN112254891A (en) * 2020-10-22 2021-01-22 北京卫星环境工程研究所 Spacecraft reinforcing rib structure leakage positioning method

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8955383B2 (en) * 2012-06-27 2015-02-17 General Monitors, Inc. Ultrasonic gas leak detector with false alarm discrimination
US9091613B2 (en) * 2012-06-27 2015-07-28 General Monitors, Inc. Multi-spectral ultrasonic gas leak detector

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2010002264A (en) * 2008-06-19 2010-01-07 Honda Motor Co Ltd Gas leakage diagnosis device and gas leakage diagnosis method
CN103471784A (en) * 2013-09-26 2013-12-25 北京卫星环境工程研究所 Method for judging size of non-contact type ultrasonic quantitative leakage hole of spacecraft on-orbit leakage
CN106764451A (en) * 2016-12-08 2017-05-31 重庆科技学院 The modeling method of gas pipeline tiny leakage is detected based on sound wave signals
CN108195525A (en) * 2018-01-29 2018-06-22 清华大学合肥公共安全研究院 A kind of pipeline of simulated leakage noise signal and its noise signal online acquisition device
CN109870276A (en) * 2018-11-28 2019-06-11 中国人民解放军国防科技大学 Spacecraft on-orbit leakage positioning method and system
CN112254891A (en) * 2020-10-22 2021-01-22 北京卫星环境工程研究所 Spacecraft reinforcing rib structure leakage positioning method

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
一种航天器舱壁加筋结构泄漏定位方法;綦磊;岳桂轩;孙立臣;邵容平;芮小博;张宇;;航天器工程(第02期);全文 *

Also Published As

Publication number Publication date
CN114061848A (en) 2022-02-18

Similar Documents

Publication Publication Date Title
CN114061848B (en) Method for identifying leak hole of reinforced sealing structure of spacecraft
CN112232400B (en) Stainless steel weld ultrasonic defect detection method based on depth feature fusion
RU2750516C1 (en) Method for multi-positional determination of leaks position in pipeline based on improved amd
CN109782274B (en) Water damage identification method based on time-frequency statistical characteristics of ground penetrating radar signals
CN111563893B (en) Grading ring defect detection method, device, medium and equipment based on aerial image
CN110333285B (en) Ultrasonic lamb wave defect signal identification method based on variational modal decomposition
CN106841403A (en) A kind of acoustics glass defect detection method based on neutral net
CN109003275B (en) Segmentation method of weld defect image
CN112603334B (en) Spike detection method based on time sequence characteristics and stacked Bi-LSTM network
CN109085244A (en) A kind of non-linear Lamb wave structure fatigue damage chromatography imaging method based on piezoelectric-array
CN107328868A (en) A kind of Analysis of Acoustic Emission Signal method of quick identification ceramic coating failure type
CN107121501A (en) A kind of turbine rotor defect classification method
CN113763986B (en) Abnormal sound detection method for air conditioner indoor unit based on sound classification model
CN116229380A (en) Method for identifying bird species related to bird-related faults of transformer substation
CN113960171B (en) Damage identification method and system based on ultrasonic guided waves
CN112070788B (en) Image processing method for rapidly counting deformation twin crystal based on block gradient segmentation
CN115034271A (en) Pressure vessel gas leakage acoustic identification method capable of automatically extracting features
CN110057918B (en) Method and system for quantitatively identifying damage of composite material under strong noise background
CN112857730B (en) Method for analyzing and processing hypersonic pulse pressure test data
CN114486260A (en) Bearing fault diagnosis method based on self-adaptive variational modal decomposition
CN104749249B (en) A kind of method of the detection physical purity of seed based on ultrasonic technology
CN114324580A (en) Intelligent knocking detection method and system for structural defects
CN107192892B (en) Thunder positioning system automatic trigger method based on lightning electromagnetic signal identification technology
Palakal et al. Intelligent computational methods for corrosion damage assessment
Liu et al. Speech enhancement based on Hilbert-Huang transform

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant