CN110057918A - Damage of composite materials quantitative identification method and system under strong noise background - Google Patents
Damage of composite materials quantitative identification method and system under strong noise background Download PDFInfo
- Publication number
- CN110057918A CN110057918A CN201910458874.4A CN201910458874A CN110057918A CN 110057918 A CN110057918 A CN 110057918A CN 201910458874 A CN201910458874 A CN 201910458874A CN 110057918 A CN110057918 A CN 110057918A
- Authority
- CN
- China
- Prior art keywords
- damage
- signal
- strong noise
- composite materials
- noise background
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N29/00—Investigating or analysing materials by the use of ultrasonic, sonic or infrasonic waves; Visualisation of the interior of objects by transmitting ultrasonic or sonic waves through the object
- G01N29/04—Analysing solids
- G01N29/12—Analysing solids by measuring frequency or resonance of acoustic waves
Landscapes
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
- Investigating Or Analyzing Materials By The Use Of Ultrasonic Waves (AREA)
Abstract
Present disclose provides the damage of composite materials quantitative identification methods and system under a kind of strong noise background, simulate different degrees of damage on the composite, and change different positions, acquire different degrees of and different location Lamb wave response signal；The Lamb wave signal acquired under the very noisy signal imitation strong noise background of certain signal-to-noise ratio is added in the Lamb wave signal of acquisition；Very noisy signal is rejected, useful signal is obtained；Useful signal is divided into two parts, a portion is used as test data as training data, a part, and is carried out Fourier transformation and obtain frequency spectrum data realization damage feature extraction corresponding with different degrees of and different location damage；Training data substitution autocoder is trained, autocoder non-destructive tests model is obtained, test data is substituted into the non-destructive tests model after training, is exported to obtain damage reason location and quantitative judge information according to model.Realize reliable location and accurate quantitative analysis identification of the composite structure under strong noise environment.
Description
Technical field
The disclosure belongs to material damage information analysis field, and the damage of composite materials being related under a kind of strong noise background is quantitative
Recognition methods and system.
Background technique
Only there is provided background technical informations relevant to the disclosure for the statement of this part, it is not necessary to so constitute first skill
Art.
Carbon fibre reinforced composite (Carbon Fibre Reinforced Plastics, CFRP) is with light weight, strong
Degree is high, can designed capacity it is strong the features such as, important role is play in aerospace industry.For example, the carbon fiber of CR929 aircraft
Dimension composite material content is up to 50%.However, carbon fiber composite structure in manufacturing process or in-service application process, is easy
Invisible injury caused by being concentrated by external impact and stress, or even cause major accident.Therefore, compound for guarantee carbon fiber
The safety of material structure needs the method for a kind of damage reason location and quantification.
Lamb wave is long, at low cost with its propagation distance, various imperfection sensitivities are become well composite material detection and
The research focus of evaluation.To realize that the damage position of composite material determines that scholar has studied geometry location method, time-of-flight method etc.
Method.Geometry location method and time-of-flight method need that location determination could be carried out by velocity of wave, however, due to the frequency dispersion of Lamb wave
Characteristic, spread speed are the functions of frequency and material thickness, and leading to velocity of wave is not constant, it is difficult to realize reliable location.For
Amount damage identification, existing research extract damage criterion from the amplitude of Lamb wave signal, phase transformation and energy, big with quantization damage
It is small.However, being understood according to inventor, since the mechanism of transmission is unclear in composite panel for Lamb wave, so that using signal
It is relatively difficult that characteristic index directly quantifies degree of injury.In addition the signal of sensor acquisition inevitably contains noise signal,
Lu Shizeng realizes the rejecting of noise in signal using wavelet transformation, to realize that damage reason location provides using the method for positioning using TDOA
Condition.Boudraa is based on empirical mode decomposition and realizes signal noise silencing, is related to being filtered each mode intrinsic function or threshold value
Change, and mode intrinsic function rebuilds estimation signal using treated, the deficiency of this method is that generation is mixed between each mode
Folded de-noising effect is unobvious.In addition to this also divide shape denoising method and neural network denoising method or by fractional order differential side
Method is used for signal denoising, in the case where no signal priori knowledge, can more effectively remove the noise of signal, while more preferable
The minutia of ground reservation main signal.But these researchs are mostly carried out in laboratory environment, do not consider in practical application such as by
The very noisy of the aircraft wing structure vibration noise generated and random noise (data collection system noise, external environmental interference)
Interference problem.
To sum up, in the presence of very noisy, whether there is or not the minor differences between signal under faulted condition to be easily submerged, and utilizes mesh
Preceding quantitative analysis method cannot achieve lesion assessment, i.e., the lesion assessment of current composite panel can not by laboratory research
Turn to practical application, it is necessary to solve the problems, such as damage feature extraction under strong noise background.
Summary of the invention
The disclosure to solve the above-mentioned problems, proposes the damage of composite materials quantitative judge side under a kind of strong noise background
Method and system, the disclosure under big data quantity and strong noise environment, can quickly and accurately realize that the extraction of damage characteristic is multiple
Condensation material dash-board injury detection and localization and quantitative judge overcome traditional damage positioning method under strong noise environment based on Lamb wave
Velocity of wave can not reliably realize that damage of composite materials location determination, dependence signal characteristic can not accurate quantitative analysis identification of damage defects.
According to some embodiments, the disclosure is adopted the following technical scheme that
A kind of damage of composite materials quantitative identification method under strong noise background, comprising the following steps:
Different degrees of damage is simulated on the composite, and changes different positions, acquires different degrees of and different positions
The Lamb wave response signal set；
It is added in the Lamb wave signal of acquisition and acquires under the very noisy signal imitation strong noise background of certain signal-to-noise ratio
Lamb wave signal；
Very noisy signal is rejected, useful signal is obtained；
Useful signal is divided into two parts, for a portion as training data, a part is used as test data, and by its
It carries out Fourier transformation and obtains frequency spectrum data realization damage feature extraction corresponding with different degrees of and different location damage；
Training data substitution autocoder is trained, autocoder non-destructive tests model is obtained, number will be tested
According to the non-destructive tests model substituted into after training, exported to obtain damage reason location and quantitative judge information according to model.
As possible embodiment, changes structural strain field using mass block and simulate true damage, by changing not
The different degrees of damage of same quality simulating passes through the position for changing the setting position change damage of mass block.
As possible embodiment, the acquisition of damage data is carried out using data collection system, specifically includes any letter
Number generator, amplifier, multiple piezoelectric transducers and oscillograph, wherein the arbitrary-function generator hair lamb wave signal warp
In at least one piezoelectric transducer, remaining piezoelectric transducer acquires different quality by oscillograph for amplifier amplification load
Lamb wave signal of the mass block in different location.
It is limited as further, acquires multi-group data, every group of data acquisition is multiple.
As possible embodiment, very noisy signal is rejected using synchronous compression Wavelet Transformation Algorithm.
As possible embodiment, effective lamb wave signal is subjected to Fourier transformation, time-domain signal dress is changed to
Frequency domain extraction feature can embody the change of frequency response and the relationship of structural damage degree and position.
It is limited as further, the self-encoding encoder successively trains self-encoding encoder by the way of greediness study, by instructing
The self-encoding encoder perfected stacks.
It is limited as further, the training process of the self-encoding encoder was divided to including two stages:
First stage: being input to sample in first SAE network and is sufficiently trained, to obtain the ginseng of first layer
Number, then the input by the output of first layer as next SAE obtains the ginseng of this layer after model trains up again
Number, and this trained SAE model is stacked, and so on, until all SAE are trained to；
Second stage: adding one layer of neural network, and the parameter initialization neural network that the first stage is learned in top layer,
Then the fine tuning for having supervision is carried out to each parameter of training gained using back-propagation algorithm.
A kind of damage of composite materials quantitative judge system under strong noise background, comprising:
Acquisition system is configured as simulating different degrees of damage on the composite, and changes different positions, acquisition
Different degrees of and different location Lamb wave response signal；
Signal processing system is configured as that the very noisy signal mode of certain signal-to-noise ratio is added in the Lamb wave signal of acquisition
The Lamb wave signal acquired under quasi- strong noise background；
Very noisy signal is rejected, useful signal is obtained；
Useful signal is divided into two parts, for a portion as training data, a part is used as test data, and by its
It carries out Fourier transformation and obtains frequency spectrum data realization damage feature extraction corresponding with different degrees of and different location damage；
Training data substitution autocoder is trained, autocoder non-destructive tests model is obtained, number will be tested
According to the non-destructive tests model substituted into after training, exported to obtain damage reason location and quantitative judge information according to model.
A kind of computer readable storage medium, wherein being stored with a plurality of instruction, described instruction is suitable for by terminal device
Reason device loads and executes the damage of composite materials quantitative identification method under a kind of strong noise background.
A kind of terminal device, including processor and computer readable storage medium, processor is for realizing each instruction；It calculates
Machine readable storage medium storing program for executing is suitable for being loaded by processor and being executed a kind of very noisy for storing a plurality of instruction, described instruction
Damage of composite materials quantitative identification method under background.
Compared with prior art, the disclosure has the beneficial effect that
Disclosure effective solution because of the propagation in the composite of composite material itself anisotropic and wave still not
It is clear, it is difficult to reliably to realize asking for damage of composite materials location determination accurate quantitative analysis identification of damage using the characteristic index of signal
Topic.
The disclosure use with the strong synchronous compression Wavelet Transformation Algorithm of denoising strong noise ability eliminate in application environment because
The very noisy and establish non-destructive tests model using the SAE algorithm of strong nonlinearity capability of fitting that environment generates, realize compound
Reliable location and accurate quantitative analysis identification of the material structure under strong noise environment.
Detailed description of the invention
The Figure of description for constituting a part of this disclosure is used to provide further understanding of the disclosure, and the disclosure is shown
Meaning property embodiment and its explanation do not constitute the improper restriction to the disclosure for explaining the disclosure.
Fig. 1 is driver sensor layout schematic diagram；
Fig. 2 is the flow diagram of the method for the present embodiment；
Fig. 3 is the signal of Noise；
Fig. 4 is the later signal of denoising；
Fig. 5 is the spectrogram of mass block three sensor response signals at position 1 of 50g；
Fig. 6 is the spectrogram of mass block three sensor response signals at position 1 of 100g；
Fig. 7 is the spectrogram of mass block three sensor response signals at position 1 of 200g；
Fig. 8 is the spectrogram of mass block three sensor response signals at position 25 of 200g；
Fig. 9 is the spectrogram of mass block three sensor response signals at position 56 of 200g；
Figure 10 is self-encoding encoder network structure；
Figure 11 is that damage position determines and quantitative judge result figure；
Specific embodiment:
The disclosure is described further with embodiment with reference to the accompanying drawing.
It is noted that following detailed description is all illustrative, it is intended to provide further instruction to the disclosure.Unless another
It indicates, all technical and scientific terms used herein has usual with disclosure person of an ordinary skill in the technical field
The identical meanings of understanding.
It should be noted that term used herein above is merely to describe specific embodiment, and be not intended to restricted root
According to the illustrative embodiments of the disclosure.As used herein, unless the context clearly indicates otherwise, otherwise singular
Also it is intended to include plural form, additionally, it should be understood that, when in the present specification using term "comprising" and/or " packet
Include " when, indicate existing characteristics, step, operation, device, component and/or their combination.
Based on the positioning of the damage of composite materials of Lamb wave and autocoder and quantitative judge side under a kind of strong noise background
Method comprises the following steps:
(1) Lamb wave data collection system is built, it includes arbitrary-function generator, amplifier, piezoelectric transducer, oscillographys
Device and composite panel, and paste square shaped sensor device array.Wherein a sensor sends out lamb wave signal, and other sensors are adopted
Collect signal；
(2) simulation true damage in structural strain field is changed by mass block, it is different by changing different quality simulatings
The damage of degree, and change different positions.Sensor acquires different degrees of and different location Lamb wave response signal；
(3) it is added under the very noisy signal imitation strong noise background that signal-to-noise ratio is 3dB and adopts in the Lamb wave signal of acquisition
The Lamb wave signal of collection；
(4) synchronous compression Wavelet Transformation Algorithm realizes the noise eliminating of the signal containing very noisy, obtains useful signal；
(5) useful signal being divided into two parts, for a portion as training data, a part is used as test data, and
Carried out Fourier transformation obtain in various degree and different location damage corresponding frequency spectrum data realization damage characteristic mentions
It takes.
(6) training data substitution autocoder is trained, autocoder non-destructive tests model is obtained, test
Data substitute into non-destructive tests model and carry out damage reason location and quantitative judge.
The signal-to-noise ratio computation formula of step (3) are as follows:
The synchronous compression Wavelet Transformation Algorithm of step (4) are as follows:
According to wavelet function, for function x (t) ∈ L2(R) continuous wavelet transform are as follows:
Wherein, " * " is the conjugation of function, and W (a, b) is wavelet conversion coefficient.
Instantaneous frequency ω is sought using obtained wavelet coefficientx(a, b), is defined as:
This by when m- scale plane (b, a) is transformed into T/F plane (b, ω (a, b)), this can be by optional frequency
ωlSurrounding sectionValue be compressed to ωlOn, it can get the value T (ω of synchronous compression transformationl, b), from
And achieve the purpose that improve time frequency resolution.That is synchronous compression transformation may be expressed as:
Wherein N is representedakFor discrete scale, k is scale number.
Lamb wave signal is discrete signal, above formula mesoscale coordinate Δ akAre as follows: Δ ak=ak-ak-1, frequency coordinate Δ ω are as follows:
Δ ω=ωl-ωl-1。
Then synchronous compression wavelet transformation is inversely transformed into:
In formula,Take finite value, ψ*(ξ) is that basic d ξ wavelet function is conjugated Fourier transformation.
It can be in the hope of reconstruction signal by above formula.
It carries out in SAE model training and damage reason location and quantitative judge, training data is subjected to SAE training and obtains composite wood
Flitch damage position determines and timing identification model, and test data is substituted into model and carries out result test.
Self-encoding encoder model in step (6) are as follows:
Self-encoding encoder successively trains self-encoding encoder by the way of greediness study, is then stacked by trained self-encoding encoder
It forms.The training process of self-encoding encoder (SAE) is divided into two stages: unsupervised feature learning and the fine tuning for having supervision.
First stage: being input to sample in first SAE network and is sufficiently trained, to obtain the ginseng of first layer
Number θ1, then the input by the output of first layer as next SAE obtains this layer after model trains up again
Parameter θ2.And this trained SAE model is stacked, and so on, until all SAE are trained to.
Second stage: adding one layer of neural network, and the parameter initialization neural network that the first stage is learned in top layer,
Then the fine tuning for having supervision is carried out to each parameter of training gained using back-propagation algorithm.
And provide product embodiments as shown below:
A kind of damage of composite materials quantitative judge system under strong noise background, comprising:
Acquisition system is configured as simulating different degrees of damage on the composite, and changes different positions, acquisition
Different degrees of and different location Lamb wave response signal；
Signal processing system is configured as that the very noisy signal mode of certain signal-to-noise ratio is added in the Lamb wave signal of acquisition
The Lamb wave signal acquired under quasi- strong noise background；
Very noisy signal is rejected, useful signal is obtained；
Useful signal is divided into two parts, for a portion as training data, a part is used as test data, and by its
It carries out Fourier transformation and obtains frequency spectrum data realization damage feature extraction corresponding with different degrees of and different location damage；
Training data substitution autocoder is trained, autocoder non-destructive tests model is obtained, number will be tested
According to the non-destructive tests model substituted into after training, exported to obtain damage reason location and quantitative judge information according to model.
A kind of computer readable storage medium, wherein being stored with a plurality of instruction, described instruction is suitable for by terminal device
Reason device loads and executes the damage of composite materials quantitative identification method under a kind of strong noise background.
A kind of terminal device, including processor and computer readable storage medium, processor is for realizing each instruction；It calculates
Machine readable storage medium storing program for executing is suitable for being loaded by processor and being executed a kind of very noisy for storing a plurality of instruction, described instruction
Damage of composite materials quantitative identification method under background.
As typical embodiment, Fig. 1 show the carbon fibre composite plate of the present embodiment use, size 60cm
× 60cm, and plate center it is square it is uniform drawn 64 grids, the size of each grid is 3cm × 3cm.In order to realize damage
Being located in plate for wound arranges 4 piezoelectric transducers, wherein one is only considered as the Lamb wave signal that driver sends 50KHz, remains
3 sensors of remaininging receive response signal.Damage is the 50g used, and the mass block of 100g, 200g change answering for composite structure
What variable field was realized.
Fig. 2 is the flow diagram of the present embodiment method, first building data collection system, and it includes arbitrary function generations
Device, amplifier, piezoelectric transducer, oscillograph and composite panel, arbitrary-function generator hair lamb wave signal are put through amplifier
It is greatly loaded in piezoelectric transducer, remaining sensor acquires the mass block of different quality in different location by oscillograph
Lamb wave signal, altogether acquire 64 × 3=192 group, each group acquisition 150 times.Signal is added in these signals than for 3dB's
Noise simulation strong noise background, Fig. 3 are the signal containing very noisy.Picking for very noisy is realized using synchronous compression wavelet transformation
It removes, Fig. 4 is the signal for rejecting very noisy, obtains effective Lamb wave signal.
Because damage will lead to the changes of Structure dynamic characteristics, lamb wave signal is subjected to Fourier transformation, by when
Domain signal switch can embody the change of frequency response and the relationship of structural damage degree and position to frequency domain extraction feature.Fig. 5~
Fig. 9 be different quality mass block same position and same mass block different location spectrogram, it can be seen that damage journey
It is different to spend different spectral, damage position different spectral is also different, therefore can establish by SAE algorithm multiple between frequency spectrum and damage
Miscellaneous mapping relations.
For the training and test of implementation model, 140 groups of formation training datas are randomly selected in 150 groups of data for mould
Type training selects 1 group of formal testing data to carry out model measurement at random in remaining 10 groups.Training data is put into SAE algorithm
Model training is carried out, Figure 10 is SAE network structure, and network structure is set as [900 100 193] and obtains SAE damage in training
Hurt identification model.Test data substitution model is tested, test result is as shown in figure 11, it is known that in 192 kinds of degree of impairment
Under, position identifies mistake when only a kind of mass block is 200g, but also in its adjacent position, correct non-destructive tests rate is
99.48%, it is known that the method that the present embodiment proposes can be very good to solve composite structure damage position under strong noise background
Determine and degree of injury quantitative judge problem.
It should be understood by those skilled in the art that, embodiment of the disclosure can provide as method, system or computer program
Product.Therefore, complete hardware embodiment, complete software embodiment or reality combining software and hardware aspects can be used in the disclosure
Apply the form of example.Moreover, it wherein includes the computer of computer usable program code that the disclosure, which can be used in one or more,
The computer program implemented in usable storage medium (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.) produces
The form of product.
The disclosure is referring to method, the process of equipment (system) and computer program product according to the embodiment of the present disclosure
Figure and/or block diagram describe.It should be understood that every one stream in flowchart and/or the block diagram can be realized by computer program instructions
The combination of process and/or box in journey and/or box and flowchart and/or the block diagram.It can provide these computer programs
Instruct the processor of general purpose computer, special purpose computer, Embedded Processor or other programmable data processing devices to produce
A raw machine, so that being generated by the instruction that computer or the processor of other programmable data processing devices execute for real
The device for the function of being specified in present one or more flows of the flowchart and/or one or more blocks of the block diagram.
These computer program instructions, which may also be stored in, is able to guide computer or other programmable data processing devices with spy
Determine in the computer-readable memory that mode works, so that it includes referring to that instruction stored in the computer readable memory, which generates,
Enable the manufacture of device, the command device realize in one box of one or more flows of the flowchart and/or block diagram or
The function of being specified in multiple boxes.
These computer program instructions also can be loaded onto a computer or other programmable data processing device, so that counting
Series of operation steps are executed on calculation machine or other programmable devices to generate computer implemented processing, thus in computer or
The instruction executed on other programmable devices is provided for realizing in one or more flows of the flowchart and/or block diagram one
The step of function of being specified in a box or multiple boxes.
The foregoing is merely preferred embodiment of the present disclosure, are not limited to the disclosure, for the skill of this field
For art personnel, the disclosure can have various modifications and variations.It is all within the spirit and principle of the disclosure, it is made any to repair
Change, equivalent replacement, improvement etc., should be included within the protection scope of the disclosure.
Although above-mentioned be described in conjunction with specific embodiment of the attached drawing to the disclosure, model not is protected to the disclosure
The limitation enclosed, those skilled in the art should understand that, on the basis of the technical solution of the disclosure, those skilled in the art are not
Need to make the creative labor the various modifications or changes that can be made still within the protection scope of the disclosure.
Claims (10)
1. the damage of composite materials quantitative identification method under a kind of strong noise background, it is characterized in that: the following steps are included:
Different degrees of damage is simulated on the composite, and changes different positions, is acquired different degrees of and different location
Lamb wave response signal；
The Lamb acquired under the very noisy signal imitation strong noise background of certain signal-to-noise ratio is added in the Lamb wave signal of acquisition
Wave signal；
Very noisy signal is rejected, useful signal is obtained；
Useful signal is divided into two parts, for a portion as training data, a part is used as test data, and is carried out
Fourier transformation obtains frequency spectrum data corresponding with different degrees of and different location damage and realizes damage feature extraction；
Training data substitution autocoder is trained, autocoder non-destructive tests model is obtained, by test data generation
Non-destructive tests model after entering training, exports to obtain damage reason location and quantitative judge information according to model.
2. the damage of composite materials quantitative identification method under a kind of strong noise background as described in claim 1, it is characterized in that: sharp
Change the true damage of structural strain field simulation with mass block to lead to by changing the different degrees of damage of different quality simulatings
Cross the position for changing the setting position change damage of mass block.
3. the damage of composite materials quantitative identification method under a kind of strong noise background as described in claim 1, it is characterized in that: sharp
The acquisition that damage data is carried out with data collection system specifically includes arbitrary-function generator, amplifier, multiple piezoelectric transducers
And oscillograph, wherein the arbitrary-function generator hair lamb wave signal is passed through amplifier amplification load at least one piezoelectricity
In sensor, remaining piezoelectric transducer acquires Lamb wave signal of the mass block in different location of different quality by oscillograph.
4. the damage of composite materials quantitative identification method under a kind of strong noise background as described in claim 1, it is characterized in that: adopting
Collect multi-group data, every group of data acquisition is multiple.
5. the damage of composite materials quantitative identification method under a kind of strong noise background as described in claim 1, it is characterized in that: sharp
Very noisy signal is rejected with synchronous compression Wavelet Transformation Algorithm.
6. the damage of composite materials quantitative identification method under a kind of strong noise background as described in claim 1, it is characterized in that: will
Effective lamb wave signal carries out Fourier transformation, and time-domain signal dress, which is changed to frequency domain extraction feature, can embody changing for frequency response
Become the relationship with structural damage degree and position.
7. the damage of composite materials quantitative identification method under a kind of strong noise background as described in claim 1, it is characterized in that: institute
It states self-encoding encoder and successively trains self-encoding encoder by the way of greediness study, stacked by trained self-encoding encoder；
Or, the training process of the self-encoding encoder was divided to including two stages:
First stage: being input to sample in first SAE network and is sufficiently trained, so that the parameter of first layer is obtained,
Then the input by the output of first layer as next SAE obtains the parameter of this layer after model trains up again,
And this trained SAE model is stacked, and so on, until all SAE are trained to；
Second stage: one layer of neural network, and the parameter initialization neural network that the first stage is learned are added in top layer, then
The fine tuning for having supervision is carried out to each parameter of training gained using back-propagation algorithm.
8. the damage of composite materials quantitative judge system under a kind of strong noise background, it is characterized in that: including:
Acquisition system is configured as simulating different degrees of damage on the composite, and changes different positions, and acquisition is different
The Lamb wave response signal of degree and different location；
Signal processing system, the very noisy signal imitation for being configured as being added certain signal-to-noise ratio in the Lamb wave signal of acquisition are strong
The Lamb wave signal acquired under noise background；
Very noisy signal is rejected, useful signal is obtained；
Useful signal is divided into two parts, for a portion as training data, a part is used as test data, and is carried out
Fourier transformation obtains frequency spectrum data corresponding with different degrees of and different location damage and realizes damage feature extraction；
Training data substitution autocoder is trained, autocoder non-destructive tests model is obtained, by test data generation
Non-destructive tests model after entering training, exports to obtain damage reason location and quantitative judge information according to model.
9. a kind of computer readable storage medium, it is characterized in that: being wherein stored with a plurality of instruction, described instruction is suitable for being set by terminal
Standby processor load and perform claim requires the damage of composite materials under a kind of strong noise background described in any one of 1-7 fixed
Measure recognition methods.
10. a kind of terminal device, it is characterized in that: including processor and computer readable storage medium, processor is for realizing each
Instruction；Computer readable storage medium is for storing a plurality of instruction, and described instruction is suitable for by processor load and perform claim is wanted
Seek the damage of composite materials quantitative identification method under a kind of strong noise background described in any one of 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910458874.4A CN110057918B (en) | 2019-05-29 | 2019-05-29 | Method and system for quantitatively identifying damage of composite material under strong noise background |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910458874.4A CN110057918B (en) | 2019-05-29 | 2019-05-29 | Method and system for quantitatively identifying damage of composite material under strong noise background |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110057918A true CN110057918A (en) | 2019-07-26 |
| CN110057918B CN110057918B (en) | 2020-11-06 |
Family
ID=67325040
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910458874.4A Active CN110057918B (en) | 2019-05-29 | 2019-05-29 | Method and system for quantitatively identifying damage of composite material under strong noise background |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110057918B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110865123A (en) * | 2019-11-14 | 2020-03-06 | 天津大学 | Method for calculating laser surface acoustic wave frequency dispersion curve |
| CN112684012A (en) * | 2020-12-02 | 2021-04-20 | 青岛科技大学 | Equipment key force-bearing structural part fault diagnosis method based on multi-parameter information fusion |
| CN113740425A (en) * | 2021-07-12 | 2021-12-03 | 北京航空航天大学 | Composite material laminated structure anisotropic damage identification method |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101169390A (en) * | 2007-10-12 | 2008-04-30 | 南京航空航天大学 | Engineering structure damage active monitoring lamb wave time-reversal focusing method |
| CN101694484A (en) * | 2009-10-22 | 2010-04-14 | 中国第一重型机械股份公司 | Method for ultrasonic locating defect in austenitic stainless steel weld joint |
| CN203422355U (en) * | 2013-07-17 | 2014-02-05 | 浙江方圆金属材料检测有限公司 | Defect simulation and comparison test cube for ultrasonic detection |
| CN104297346A (en) * | 2014-09-11 | 2015-01-21 | 天津大学 | Nondestructive detection system of sheet metal by ultrasonic planar guided-wave and detection method thereof |
| CN106198551A (en) * | 2016-08-01 | 2016-12-07 | 南方电网科学研究院有限责任公司 | Method and device for detecting defects of power transmission line |
| CN106742057A (en) * | 2016-12-23 | 2017-05-31 | 湖南科技大学 | Aircraft skin damage monitoring device and method based on wireless piezoelectric sensing technology |
| CN107016241A (en) * | 2017-04-05 | 2017-08-04 | 重庆交通大学 | Based on the rotating machinery lifetime stage recognition methods for adding sample enhancing depth own coding learning network of making an uproar |
| CN107228942A (en) * | 2017-08-01 | 2017-10-03 | 福州大学 | Fluorescence immune chromatography detection method and device based on sparse own coding neutral net |
| CN108562709A (en) * | 2018-04-25 | 2018-09-21 | 重庆工商大学 | A kind of sewage disposal system water quality monitoring method for early warning based on convolution self-encoding encoder extreme learning machine |
| CN109406629A (en) * | 2018-10-15 | 2019-03-01 | 成都飞机工业（集团）有限责任公司 | A kind of test block of the angle R and production method for composite structure ultrasound detection |
| CN109490316A (en) * | 2018-11-30 | 2019-03-19 | 熵智科技(深圳)有限公司 | A kind of surface defects detection algorithm based on machine vision |
| CN109613178A (en) * | 2018-11-05 | 2019-04-12 | 广东奥博信息产业股份有限公司 | A kind of method and system based on recurrent neural networks prediction air pollution |
-
2019
- 2019-05-29 CN CN201910458874.4A patent/CN110057918B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101169390A (en) * | 2007-10-12 | 2008-04-30 | 南京航空航天大学 | Engineering structure damage active monitoring lamb wave time-reversal focusing method |
| CN101694484A (en) * | 2009-10-22 | 2010-04-14 | 中国第一重型机械股份公司 | Method for ultrasonic locating defect in austenitic stainless steel weld joint |
| CN203422355U (en) * | 2013-07-17 | 2014-02-05 | 浙江方圆金属材料检测有限公司 | Defect simulation and comparison test cube for ultrasonic detection |
| CN104297346A (en) * | 2014-09-11 | 2015-01-21 | 天津大学 | Nondestructive detection system of sheet metal by ultrasonic planar guided-wave and detection method thereof |
| CN106198551A (en) * | 2016-08-01 | 2016-12-07 | 南方电网科学研究院有限责任公司 | Method and device for detecting defects of power transmission line |
| CN106742057A (en) * | 2016-12-23 | 2017-05-31 | 湖南科技大学 | Aircraft skin damage monitoring device and method based on wireless piezoelectric sensing technology |
| CN107016241A (en) * | 2017-04-05 | 2017-08-04 | 重庆交通大学 | Based on the rotating machinery lifetime stage recognition methods for adding sample enhancing depth own coding learning network of making an uproar |
| CN107228942A (en) * | 2017-08-01 | 2017-10-03 | 福州大学 | Fluorescence immune chromatography detection method and device based on sparse own coding neutral net |
| CN108562709A (en) * | 2018-04-25 | 2018-09-21 | 重庆工商大学 | A kind of sewage disposal system water quality monitoring method for early warning based on convolution self-encoding encoder extreme learning machine |
| CN109406629A (en) * | 2018-10-15 | 2019-03-01 | 成都飞机工业（集团）有限责任公司 | A kind of test block of the angle R and production method for composite structure ultrasound detection |
| CN109613178A (en) * | 2018-11-05 | 2019-04-12 | 广东奥博信息产业股份有限公司 | A kind of method and system based on recurrent neural networks prediction air pollution |
| CN109490316A (en) * | 2018-11-30 | 2019-03-19 | 熵智科技(深圳)有限公司 | A kind of surface defects detection algorithm based on machine vision |
Non-Patent Citations (1)
| Title |
|---|
| 陈仁祥等: "栈式稀疏加噪自编码深度神经网络的滚动轴承损伤程度诊断", 《振动与冲击》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110865123A (en) * | 2019-11-14 | 2020-03-06 | 天津大学 | Method for calculating laser surface acoustic wave frequency dispersion curve |
| CN112684012A (en) * | 2020-12-02 | 2021-04-20 | 青岛科技大学 | Equipment key force-bearing structural part fault diagnosis method based on multi-parameter information fusion |
| CN113740425A (en) * | 2021-07-12 | 2021-12-03 | 北京航空航天大学 | Composite material laminated structure anisotropic damage identification method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110057918B (en) | 2020-11-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109682561B (en) | Method for automatically detecting free vibration response of high-speed railway bridge to identify mode | |
| CN105929024B (en) | Concrete defect intellectualized detection and quantitative identification method | |
| CN110057918A (en) | Damage of composite materials quantitative identification method and system under strong noise background | |
| CN106096562B (en) | Gearbox of wind turbine method for diagnosing faults based on vibration signal blind sources separation and sparse component analysis | |
| CN104483049A (en) | Fiber bragg grating sensing dynamic load identification method based on AR model and mahalanobis distance | |
| CN103245907B (en) | A kind of analog-circuit fault diagnosis method | |
| CN109033226B (en) | Vibration sensor arrangement optimization method based on complex network theory | |
| CN109000876B (en) | SNS optical fiber impact identification method based on automatic encoder deep learning | |
| CN101221213A (en) | Analogue circuit fault diagnosis neural network method based on particle swarm algorithm | |
| Yao et al. | Blind modal identification using limited sensors through modified sparse component analysis by time‐frequency method | |
| CN101900789A (en) | Tolerance analog circuit fault diagnosing method based on wavelet transform and fractal dimension | |
| CN104112072A (en) | Operating modal parameter identification method for principal component analysis on basis of wavelet threshold denoising | |
| CN101901209B (en) | Structural response analysis method based on improved EMD (Empirical Mode Decomposition) and ARMA (Autoregressive Moving-Average) model | |
| CN110132403A (en) | A kind of vacuum pump vibration signal noise-reduction method based on EEMD and wavelet threshold | |
| CN110298085A (en) | Analog-circuit fault diagnosis method based on XGBoost and random forests algorithm | |
| CN105424366A (en) | Bearing fault diagnosis method based on EEMD adaptive denoising | |
| CN109374119A (en) | Transformer vibration signal Characteristic Extraction method | |
| Mao et al. | The construction and comparison of damage detection index based on the nonlinear output frequency response function and experimental analysis | |
| CN104807534A (en) | Equipment natural vibration mode self-learning recognition method based on online vibration data | |
| CN105844055B (en) | It is fissioned-is polymerize the damage monitoring method of probabilistic model based on guided wave dynamic contract-enhanced | |
| CN105258789A (en) | Method and device for extracting vibration signal characteristic frequency band | |
| CN105572572A (en) | WKNN-LSSVM-based analog circuit fault diagnosis method | |
| CN106451498A (en) | Low frequency oscillation modal identification method based on improved generalized morphological filtering | |
| Paulraj et al. | Structural steel plate damage detection using non destructive testing, frame energy based statistical features and artificial neural networks | |
| CN106548031A (en) | A kind of Identification of Modal Parameter |
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 |