CN116359341A - Method and device for monitoring damage condition of expansion joint based on noise - Google Patents
Method and device for monitoring damage condition of expansion joint based on noise Download PDFInfo
- Publication number
- CN116359341A CN116359341A CN202310284248.4A CN202310284248A CN116359341A CN 116359341 A CN116359341 A CN 116359341A CN 202310284248 A CN202310284248 A CN 202310284248A CN 116359341 A CN116359341 A CN 116359341A
- Authority
- CN
- China
- Prior art keywords
- expansion joint
- signal
- noise
- characteristic
- signals
- 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.)
- Pending
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 25
- 238000000034 method Methods 0.000 title claims abstract description 24
- 230000037231 joint health Effects 0.000 claims abstract description 20
- 238000012549 training Methods 0.000 claims abstract description 17
- 238000001228 spectrum Methods 0.000 claims abstract description 9
- 210000001503 joint Anatomy 0.000 claims description 22
- 238000012545 processing Methods 0.000 claims description 20
- 238000000605 extraction Methods 0.000 claims description 10
- 238000011176 pooling Methods 0.000 claims description 10
- 230000009466 transformation Effects 0.000 claims description 10
- 229910000831 Steel Inorganic materials 0.000 claims description 6
- 230000005236 sound signal Effects 0.000 claims description 6
- 239000010959 steel Substances 0.000 claims description 6
- 238000004458 analytical method Methods 0.000 claims description 5
- 238000013519 translation Methods 0.000 claims description 5
- 238000001514 detection method Methods 0.000 abstract description 8
- 230000036541 health Effects 0.000 abstract description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000009434 installation Methods 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 230000003139 buffering effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 238000006073 displacement reaction Methods 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 239000002184 metal Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 239000004576 sand Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
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
-
- 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
- G01N29/44—Processing the detected response signal, e.g. electronic circuits specially adapted therefor
-
- 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
- G01N29/44—Processing the detected response signal, e.g. electronic circuits specially adapted therefor
- G01N29/4472—Mathematical theories or simulation
-
- 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
- G01N29/44—Processing the detected response signal, e.g. electronic circuits specially adapted therefor
- G01N29/4481—Neural networks
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N2291/00—Indexing codes associated with group G01N29/00
- G01N2291/02—Indexing codes associated with the analysed material
- G01N2291/023—Solids
-
- 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
Abstract
The invention provides a noise-based method and a device for monitoring damage condition of an expansion joint, wherein the method comprises the following steps: acquiring an original noise signal when a vehicle passes through an expansion joint; acquiring a characteristic signal of the expansion joint according to the original noise signal; inputting the characteristic signals of the expansion joint into a preset expansion joint health signal reconstruction model to obtain model output signals; and obtaining the damage result of the expansion joint according to the characteristic signals of the expansion joint and the model output signals. Because the expansion joint health signal reconstruction model is obtained by training the health noise signal, after the frequency spectrum enters the expansion joint health signal reconstruction model when the expansion joint noise signal is damaged, the error between the input signal and the output signal is increased due to the deviation from the health noise signal distribution, so that whether the expansion joint is damaged can be judged easily, and further the damage detection of the fault expansion joint is realized.
Description
Technical Field
The invention relates to the technical field of bridge expansion joint damage detection, in particular to a noise-based method and device for monitoring expansion joint damage conditions.
Background
The bridge expansion joint is a device which is arranged between beam ends and between the beam ends and the bridge abutment and can deform freely in order to adapt to bridge deformation. Due to the long-term dynamic load effect of heavy vehicles and the influence of various complex factors such as abutment subsidence, installation errors, sand and sundry accumulation and the like, the diseases of the expansion joints are common. The damage monitoring of the bridge expansion joints at home and abroad is still mainly carried out by a method of periodic manual investigation, and the method is time-consuming and labor-consuming and affects the traffic. Other monitoring means, such as installation of a displacement sensor, can conveniently acquire data related to the service condition of the bridge expansion joint, but the acquired data in engineering cannot directly reflect the damage condition of the modular expansion joint. Meanwhile, physical quantities such as deflection and strain are greatly influenced by temperature, and correlation correction of the physical quantities and the temperature is often required to be carried out, so that the method is complex and inaccurate.
In recent years, related studies have attempted to analyze the health state of an expansion joint by utilizing noise generated when a vehicle runs through the expansion joint. The method has the advantages that the sound wave acquisition equipment is additionally arranged on the automobile by Nishikawa (staff of Kokusai Shinon Keiso limited company of Osaka, japan) and the like, the sound wave signals when the automobile passes through the expansion joints are recorded, the automobile is required to travel through all the expansion joints in the flaw detection process, and the applicability of the method to other automobile types cannot be proved, so that the method has larger limitation. Guerreiro (a student of the electric engineering system of new Litsbook university of Bougueka Paeri) and the like obtain an identification method of an expansion joint bolt loosening damage form characterized by metal reverberation through Fourier transformation of a 'jump' sound wave signal, but a sound acquisition device of the research is too huge, is not beneficial to actual installation, and has too simple algorithm and poor applicability to actual engineering problems.
Disclosure of Invention
Aiming at the defects in the prior art, the invention provides a noise-based method and device for monitoring the damage condition of an expansion joint so as to improve the practicability.
In a first aspect, the invention provides a noise-based method for monitoring damage conditions of an expansion joint.
In a first implementation manner, a method for monitoring damage condition of an expansion joint based on noise comprises the following steps: acquiring an original noise signal when a vehicle passes through an expansion joint;
acquiring a characteristic signal of the expansion joint according to the original noise signal;
inputting the characteristic signals of the expansion joint into a preset expansion joint health signal reconstruction model to obtain model output signals;
and obtaining the damage result of the expansion joint according to the characteristic signals of the expansion joint and the model output signals.
In combination with the first implementation manner, in a second implementation manner, acquiring the characteristic signal of the expansion joint according to the original noise signal includes:
and analyzing the original noise signal by adopting a wavelet transformation algorithm to obtain a signal time spectrum of the expansion joint.
In combination with the second implementation manner, in a third implementation manner, the analysis of the original noise signal by using the wavelet transform algorithm is implemented by the following formula:
in the above formula, WT f (a, τ) is a wavelet transform coefficient, a is a scale parameter, a > 0, τ is a translation parameter, a, τ e R, and the function f (t) is the original noise signal.
With reference to the first implementation manner, in a fourth implementation manner, the expansion joint health signal reconstruction model is constructed by the following manner:
acquiring a training set, wherein the training set comprises healthy noise signals of a plurality of expansion joints; the healthy noise signal is noise when the vehicle passes through the expansion joint in the state that the expansion joint is not damaged;
and simultaneously taking the healthy noise signals as the input and the output of the model, and training the initial model to obtain the expansion joint healthy signal reconstruction model.
In combination with the fourth implementation manner, in a fifth implementation manner, the initial model includes an input layer, a signal feature extraction module, a signal reconstruction module, and an output layer; the signal characteristic extraction module comprises a first convolution layer, a pooling layer and a second convolution layer which are sequentially connected; the signal reconstruction module comprises a first deconvolution layer, a pooling layer and a second deconvolution layer which are sequentially connected.
In combination with the first implementation manner, in a sixth implementation manner, obtaining a damage result of the expansion joint according to the characteristic signal and the model output signal of the expansion joint includes:
judging whether the characteristic signals of the expansion joint are the same as the model output signals; under the same condition, the expansion joint is determined to be undamaged, and under the different condition, the expansion joint is determined to be damaged.
In a second aspect, the invention provides a noise-based device for monitoring damage conditions of an expansion joint.
In a seventh implementation manner, a device for monitoring damage condition of an expansion joint based on noise includes:
the original noise signal acquisition module is configured to acquire an original noise signal when the vehicle passes through the expansion joint;
the characteristic signal acquisition module is configured to acquire characteristic signals of the expansion joint according to the original noise signals;
the model output signal acquisition module is configured to input the characteristic signals of the expansion joints into a preset expansion joint health signal reconstruction model to obtain model output signals;
the damage result acquisition module is configured to acquire a damage result of the expansion joint according to the characteristic signals and the model output signals of the expansion joint.
In a third aspect, the invention provides another noise-based device for monitoring damage to an expansion joint.
In an eighth implementation manner, a device for monitoring damage condition of an expansion joint based on noise is characterized by comprising:
the sound collection card is used for collecting an original noise signal when the vehicle passes through the expansion joint and transmitting the original noise signal to the edge server;
the edge server is used for receiving the original noise signal and acquiring a characteristic signal of the expansion joint according to the original noise signal; inputting the characteristic signals of the expansion joint into a preset expansion joint health signal reconstruction model to obtain model output signals; obtaining the damage result of the expansion joint according to the characteristic signal and the model output signal of the expansion joint; and sending the damage result of the expansion joint to a preset terminal.
In combination with the eighth implementation manner, in a ninth implementation manner, the sound collecting card is highly integrated by a chip and a device, and the sound collecting card is attached to the expansion joint section steel of the road surface.
With reference to the eighth implementation manner, in a tenth implementation manner, the sound collection card includes:
the audio processing module is used for collecting noise when the vehicle passes through the expansion joint, converting the noise into an electric signal and sending the electric signal to the edge server through Bluetooth; the audio processing module comprises an audio receiving unit, an audio signal unit, a high-speed ADC, a Buffer data Buffer unit, flash firmware, a control and data processing unit and a Bluetooth unit;
and a battery for powering the audio processing microphone unit.
According to the technical scheme, the beneficial technical effects of the invention are as follows:
1. because the expansion joint health signal reconstruction model is obtained by training the health noise signal, after the characteristic signal of the expansion joint under the damage state enters the expansion joint health signal reconstruction model, the error between the input signal and the output signal is increased due to the deviation of the health noise signal distribution, so that whether the expansion joint is damaged can be judged easily, and further the damage detection of the fault expansion joint is realized.
2. The expansion joint noise signals are analyzed through the wavelet transformation algorithm, compared with Fourier transformation, the wavelet transformation algorithm overcomes the defects that the window size does not change along with frequency and the like, can keep the detail characteristics of more expansion joint noise signals, and improves the detection accuracy.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below. Like elements or portions are generally identified by like reference numerals throughout the several figures. In the drawings, elements or portions thereof are not necessarily drawn to scale.
Fig. 1 is a schematic structural diagram of a method for monitoring damage condition of an expansion joint based on noise provided in this embodiment;
fig. 2 is a schematic structural diagram of a device for monitoring damage of an expansion joint based on noise provided in this embodiment;
fig. 3 is a schematic structural diagram of another device for monitoring damage of an expansion joint based on noise provided in this embodiment;
fig. 4 is a schematic structural diagram of an audio processing unit according to the present embodiment;
reference numerals:
the system comprises a 1-sound acquisition card, a 2-expansion joint, a 3-bridge plate, a 4-edge server, a 5-user terminal, a 5-audio receiving unit, a 6-audio signal unit, a 7-high-speed ADC,8-flash firmware, a 9-Buffer data Buffer unit, a 10-control and data processing unit and an 11-Bluetooth unit.
Detailed Description
Embodiments of the technical scheme of the present invention will be described in detail below with reference to the accompanying drawings. The following examples are only for more clearly illustrating the technical aspects of the present invention, and thus are merely examples, and are not intended to limit the scope of the present invention.
It is noted that unless otherwise indicated, technical or scientific terms used herein should be given the ordinary meaning as understood by one of ordinary skill in the art to which this invention pertains. The terms first, second and the like in the description and in the claims of the embodiments of the disclosure and in the above-described figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate in order to implement the embodiments of the disclosure described herein. Furthermore, the terms "comprise" and "have," as well as any variations thereof, are intended to cover a non-exclusive inclusion. The term "plurality" means two or more, unless otherwise indicated. In the embodiment of the present disclosure, the character "/" indicates that the front and rear objects are an or relationship. For example, A/B represents: a or B. The term "and/or" is an associative relationship that describes an object, meaning that there may be three relationships. For example, a and/or B, represent: a or B, or, A and B. The term "corresponding" may refer to an association or binding relationship, and the correspondence between a and B refers to an association or binding relationship between a and B.
Referring to fig. 1, this embodiment provides a method for monitoring damage condition of an expansion joint based on noise, including:
step S01, acquiring an original noise signal when a vehicle passes through an expansion joint;
step S02, obtaining a characteristic signal of the expansion joint according to the original noise signal;
s03, inputting the characteristic signals of the expansion joints into a preset expansion joint health signal reconstruction model to obtain model output signals;
and S04, obtaining a damage result of the expansion joint according to the characteristic signal and the model output signal of the expansion joint.
Optionally, acquiring the characteristic signal of the expansion joint according to the original noise signal includes: and analyzing the original noise signal by adopting a wavelet transformation algorithm to obtain a signal time spectrum of the expansion joint.
Optionally, the analysis of the original noise signal using a wavelet transform algorithm is achieved by the following formula:
in the above formula, WT f (a, τ) is a wavelet transform coefficient, a is a scale parameter, a > 0, τ is a translation parameter, a, τ e R, and the function f (t) is the original noise signal.
Optionally, the wavelet basis function ψ a,b (t) is:
a,τ∈R；a＞0；ψ a,b (t) a set of function sequences obtained by scaling and translation of the wavelet mother function ψ (t).
Optionally, the expansion joint health signal reconstruction model is constructed by: acquiring a training set, wherein the training set comprises healthy noise signals of a plurality of expansion joints; the healthy noise signal is noise when the vehicle passes through the expansion joint in the state that the expansion joint is not damaged; and simultaneously taking the healthy noise signals as the input and the output of the model, and training the initial model to obtain the expansion joint healthy signal reconstruction model.
In some embodiments, when the expansion joint is not damaged, noise when a vehicle passes through the expansion joint is acquired through a sound acquisition card, a plurality of healthy noise signals are obtained, the plurality of healthy noise signals are analyzed through a wavelet transformation algorithm to obtain characteristic signals of the plurality of healthy noise signals, a training set is formed to train an initial model, model parameters of an expansion joint healthy signal reconstruction model are obtained, the expansion joint healthy signal reconstruction model is output as a healthy noise signal, and the model parameters are model parameters for obtaining the noise characteristic signals in an undamaged state of the expansion joint. Thus, after any signal is input into the expansion joint health signal reconstruction model, the signal output by the model is the characteristic signal of the expansion joint in an undamaged state.
Optionally, the initial model includes an input layer, a signal feature extraction module, a signal reconstruction module, and an output layer; the signal characteristic extraction module comprises a first convolution layer, a pooling layer and a second convolution layer which are sequentially connected; the signal reconstruction module comprises a first deconvolution layer, a pooling layer and a second deconvolution layer which are sequentially connected.
In some embodiments, the signal time spectrum of the expansion joint is input through the input layer, and then the characteristic extraction is performed through the first convolution layer, the pooling layer and the second convolution layer of the signal characteristic extraction module, so as to obtain the state characteristic information of the input signal. And then, carrying out signal reconstruction on the state characteristic information through a first deconvolution layer, a reverse pooling layer and a second deconvolution layer of the signal reconstruction module, wherein the parameters of the model are obtained by training healthy noise signals in an undamaged state of the expansion joint, so that the signal reconstructed by the signal reconstruction module according to the state characteristic information is the noise signals in the undamaged state of the expansion joint, namely the healthy noise signals. And outputs the healthy noise signal through the output layer. The time spectrum of the expansion joint noise signal essentially belongs to the image signal, the self-encoder is combined with the convolutional neural network, the processing capacity of the image signal is effectively improved, the spectrum damage detection performance of the expansion joint noise signal is improved, and the monitoring accuracy is improved.
Optionally, obtaining the damage result of the expansion joint according to the characteristic signal and the model output signal of the expansion joint includes: judging whether the characteristic signals of the expansion joint are the same as the model output signals; under the same condition, the expansion joint is determined to be undamaged, and under the different condition, the expansion joint is determined to be damaged.
In some embodiments, since the output signal of the model is a characteristic signal in an undamaged state of the expansion joint, when the signal output by the model is the same as the signal input by the model, the characteristic signal input by the model is also a characteristic signal in an undamaged state of the expansion joint, and the expansion joint damage result corresponding to the input characteristic signal is undamaged. When the signals output by the model are different from the signals input by the model, the characteristic signals input by the model are characteristic signals in the expansion joint damage state, and the expansion joint damage result corresponding to the input characteristic signals is damaged. Because the model is obtained by training the characteristic signals of the healthy noise, after the frequency spectrum enters the model when the noise signals of the expansion joint are damaged, the error between the output signals and the input signals is increased because of the deviation from the characteristic signal distribution of the healthy noise, so that whether the expansion joint is damaged can be easily judged, and further the damage detection of the fault expansion joint is realized.
Referring to fig. 2, this embodiment provides a device for monitoring damage condition of an expansion joint based on noise, including: an original noise signal acquisition module 101 configured to acquire an original noise signal when a vehicle passes through an expansion joint; the characteristic signal acquisition module 102 is configured to acquire a characteristic signal of the expansion joint according to the original noise signal; the model output signal obtaining module 103 is configured to input the characteristic signals of the expansion joints into a preset expansion joint health signal reconstruction model to obtain model output signals; the damage result obtaining module 104 is configured to obtain a damage result of the expansion joint according to the characteristic signal and the model output signal of the expansion joint.
The embodiment provides a device of monitoring expansion joint damage condition based on noise, includes: the sound collection card is used for collecting an original noise signal when the vehicle passes through the expansion joint and transmitting the original noise signal to the edge server; the edge server is used for receiving the original noise signal and acquiring a characteristic signal of the expansion joint according to the original noise signal; inputting the characteristic signals of the expansion joint into a preset expansion joint health signal reconstruction model to obtain model output signals; obtaining the damage result of the expansion joint according to the characteristic signal and the model output signal of the expansion joint; and sending the damage result of the expansion joint to a preset terminal.
As shown in fig. 3, the expansion joint section steel is installed at the expansion joint 2 of the bridge plate 3, and the sound collecting card 1 is attached to the expansion joint section steel. When the vehicle runs through the expansion joint, the sound collecting card collects an original noise signal generated when the vehicle runs through the expansion joint, and the sound collecting card transmits the original noise signal to the edge server 4 through Bluetooth. The edge server 4 performs damage detection on the obtained original noise signal by using the written wavelet transformation algorithm and model, and registers the damage result of the expansion joint in the edge server 4 or sends the damage result to the user terminal 5.
In some embodiments, the edge server is an edge computing module and relay.
Optionally, the sound collecting card is highly integrated by the chip and the device, and the sound collecting card is attached to the expansion joint section steel of the road surface.
Optionally, the sound collection card includes: the audio processing module is used for collecting noise when the vehicle passes through the expansion joint, converting the noise into an electric signal and sending the electric signal to the edge server through Bluetooth; the audio processing module comprises an audio receiving unit, an audio signal unit, a high-speed ADC, flash firmware, a Buffer data Buffer unit, a control and data processing unit and a Bluetooth unit; and a battery for powering the audio processing microphone unit.
As shown in fig. 4, the audio processing module includes an audio receiving unit 5, an audio signal unit 6, a high-speed ADC7, flash firmware 8, a Buffer data Buffer unit 9, a control and data processing unit 10, and a bluetooth unit 11. The audio receiving unit 5 collects sounds of the vehicle passing through the expansion joint and transmits the sounds to the audio signal unit 6, and the audio signal unit 6 converts the sounds into Analog signals and transmits the Analog signals to the high-speed ADC (Analog-to-digital converter) 7. The flash firmware 8 stores a command of the control and data processing unit 10 to the flash ADC configuration file, the flash firmware 8 sends the stored configuration file command to the flash ADC7, and the flash ADC7 converts the analog signal into the digital signal in response to the command and sends the digital signal to the Buffer data Buffer unit 9 for buffering. The Buffer data Buffer unit 9 then sends the buffered digital signal to the control and data processing unit 10, the control and data processing unit 10 sends the digital signal, i.e. the original noise signal, to the bluetooth unit 11, and the bluetooth unit 11 transmits the original noise signal to the edge server.
In the prior art, damage is identified by utilizing noise generated when a vehicle runs through an expansion joint, and Guerreiro et al propose a sound acquisition device: two microphones are placed below the expansion joint, sound is transmitted to the XLR adapter, and then the voice is transmitted to a computer for analysis through USB. However, the installation position required by the sound collection device is oversized compared with the reserved size of the expansion joint, and the device cannot be installed on a real bridge in practical application. The sound collecting card of the scheme integrates the chip and the device highly, so that the size of the sound collecting card can be made small, the sound collecting card can be printed on a flexible FPC, the sound collecting card can be attached to two expansion joint section steels, and the sound collecting card is applicable to the situation that any type of expansion joint is strictly attached.
Optionally, the edge server obtains the characteristic signal of the expansion joint according to the original noise signal by the following manner: and analyzing the original noise signal by adopting a wavelet transformation algorithm to obtain a signal time spectrum of the expansion joint.
Optionally, the edge server implements the analysis of the original noise signal using a wavelet transform algorithm by:
in the above formula, WT f (a, τ) is a wavelet transform coefficient, a is a scale parameter, a > 0, τ is a translation parameter, a, τ e R, and the function f (t) is the original noise signal.
Optionally, the edge server is implemented to construct an expansion joint health signal reconstruction model by:
acquiring a training set, wherein the training set comprises healthy noise signals of a plurality of expansion joints; the healthy noise signal is noise when the vehicle passes through the expansion joint in the state that the expansion joint is not damaged;
and simultaneously taking the healthy noise signals as the input and the output of the model, and training the initial model to obtain the expansion joint healthy signal reconstruction model.
Optionally, the edge server builds an initial model in the expansion joint health signal reconstruction model, wherein the initial model comprises an input layer, a signal characteristic extraction module, a signal reconstruction module and an output layer; the signal characteristic extraction module comprises a first convolution layer, a pooling layer and a second convolution layer which are sequentially connected; the signal reconstruction module comprises a first deconvolution layer, a pooling layer and a second deconvolution layer which are sequentially connected.
Optionally, the edge server obtains the damage result of the expansion joint according to the characteristic signal and the model output signal of the expansion joint by the following modes:
judging whether the characteristic signals of the expansion joint are the same as the model output signals; under the same condition, the expansion joint is determined to be undamaged, and under the different condition, the expansion joint is determined to be damaged.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some or all of the technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit of the invention, and are intended to be included within the scope of the appended claims and description.
Claims (10)
1. A noise-based method for monitoring damage to an expansion joint, comprising:
acquiring an original noise signal when a vehicle passes through an expansion joint;
acquiring a characteristic signal of the expansion joint according to the original noise signal;
inputting the characteristic signals of the expansion joints into a preset expansion joint health signal reconstruction model to obtain model output signals;
and obtaining the damage result of the expansion joint according to the characteristic signals of the expansion joint and the model output signals.
2. The method of claim 1, wherein obtaining a characteristic signal of an expansion joint from the original noise signal comprises:
and analyzing the original noise signal by adopting a wavelet transformation algorithm to obtain a signal time spectrum of the expansion joint.
3. The method of claim 2, wherein the analysis of the original noise signal using a wavelet transform algorithm is accomplished by:
in the above formula, WT f (a, τ) is a wavelet transform coefficient, a is a scale parameter, a > 0, τ is a translation parameter, a, τ e R, and the function f (t) is the original noise signal.
4. The method of claim 1, wherein the expansion joint health signal reconstruction model is constructed by:
acquiring a training set, wherein the training set comprises healthy noise signals of a plurality of expansion joints; the healthy noise signal is a noise signal when a vehicle passes through the expansion joint in an undamaged state of the expansion joint;
and simultaneously taking the healthy noise signals as the input and the output of the model, and training the initial model to obtain the expansion joint healthy signal reconstruction model.
5. The method of claim 4, wherein the initial model comprises an input layer, a signal feature extraction module, a signal reconstruction module, and an output layer; the signal characteristic extraction module comprises a first convolution layer, a pooling layer and a second convolution layer which are sequentially connected; the signal reconstruction module comprises a first deconvolution layer, a pooling layer and a second deconvolution layer which are sequentially connected.
6. The method of claim 1, wherein obtaining the damage result of the expansion joint based on the characteristic signal and the model output signal of the expansion joint comprises:
judging whether the characteristic signals of the expansion joint are the same as the model output signals; under the same condition, the expansion joint is determined to be undamaged, and under the different condition, the expansion joint is determined to be damaged.
7. Device of monitoring expansion joint damage condition based on noise, characterized in that includes:
the original noise signal acquisition module is configured to acquire an original noise signal when the vehicle passes through the expansion joint;
the characteristic signal acquisition module is configured to acquire characteristic signals of the expansion joint according to the original noise signals;
the model output signal acquisition module is configured to input the characteristic signals of the expansion joints into a preset expansion joint health signal reconstruction model to obtain model output signals;
the damage result acquisition module is configured to acquire a damage result of the expansion joint according to the characteristic signals and the model output signals of the expansion joint.
8. Device of monitoring expansion joint damage condition based on noise, characterized in that includes:
the sound collection card is used for collecting an original noise signal when the vehicle passes through the expansion joint and transmitting the original noise signal to the edge server;
the edge server is used for receiving the original noise signal and acquiring a characteristic signal of the expansion joint according to the original noise signal; inputting the characteristic signals of the expansion joints into a preset expansion joint health signal reconstruction model to obtain model output signals; obtaining the damage result of the expansion joint according to the characteristic signal and the model output signal of the expansion joint; and sending the damage result of the expansion joint to a preset terminal.
9. The noise-based device for monitoring the damage condition of an expansion joint according to claim 8, wherein the sound collection card is highly integrated by a chip and a device, and the sound collection card is attached to expansion joint section steel of a road surface.
10. The noise-based device for monitoring damage to an expansion joint of claim 8, wherein the sound collection card comprises:
the audio processing module is used for collecting noise when the vehicle passes through the expansion joint, converting the noise into an electric signal and sending the electric signal to the edge server through Bluetooth; the audio processing module comprises an audio receiving unit, an audio signal unit, a high-speed ADC, a Buffer data Buffer unit, flash firmware, a control and data processing unit and a Bluetooth unit;
and a battery for powering the audio processing microphone unit.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310284248.4A CN116359341A (en) | 2023-03-22 | 2023-03-22 | Method and device for monitoring damage condition of expansion joint based on noise |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310284248.4A CN116359341A (en) | 2023-03-22 | 2023-03-22 | Method and device for monitoring damage condition of expansion joint based on noise |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116359341A true CN116359341A (en) | 2023-06-30 |
Family
ID=86935262
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310284248.4A Pending CN116359341A (en) | 2023-03-22 | 2023-03-22 | Method and device for monitoring damage condition of expansion joint based on noise |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116359341A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117554007A (en) * | 2024-01-12 | 2024-02-13 | 陕西炬烽建筑劳务有限公司 | Bridge expansion joint measuring device |
-
2023
- 2023-03-22 CN CN202310284248.4A patent/CN116359341A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117554007A (en) * | 2024-01-12 | 2024-02-13 | 陕西炬烽建筑劳务有限公司 | Bridge expansion joint measuring device |
| CN117554007B (en) * | 2024-01-12 | 2024-03-26 | 陕西炬烽建筑劳务有限公司 | Bridge expansion joint measuring device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Liu et al. | Advances of research on high-speed railway catenary | |
| JP5145417B2 (en) | Signal determination method, signal determination apparatus, program, and signal determination system | |
| CN116359341A (en) | Method and device for monitoring damage condition of expansion joint based on noise | |
| CN110398647B (en) | Transformer state monitoring method | |
| CN113029327B (en) | Tunnel fan embedded foundation damage identification method based on metric attention convolutional neural network | |
| CN109341848B (en) | Safety monitoring system in tunnel operation stage | |
| CN113314144A (en) | Voice recognition and power equipment fault early warning method, system, terminal and medium | |
| CN105882687A (en) | Method for analyzing categories of faults of point machines | |
| CN108241024A (en) | A kind of hollowing detection method and system based on wall | |
| CN117540174B (en) | Building structure multi-source heterogeneous data intelligent analysis system and method based on neural network | |
| CN110568082A (en) | cable wire breakage distinguishing method based on acoustic emission signals | |
| CN113392874B (en) | Abnormal state diagnosis method and device for rail vehicle and terminal equipment | |
| CN115290133A (en) | Method and system for monitoring track structure at joint of light rail platform | |
| CN114492146B (en) | Bolt group loosening positioning and quantitative analysis method and system based on transfer learning | |
| CN115481669A (en) | Method and system for quickly separating live load strain monitoring signals of highway and railway dual-purpose bridge | |
| CN116092519A (en) | Vehicle fault detection method and system | |
| CN109800382B (en) | Rail breakage detection method and device | |
| CN109993211B (en) | Damage identification method based on structural acceleration AR model coefficient | |
| CN113672859A (en) | Switch point machine fault acoustic diagnosis system | |
| CN105651526A (en) | Vibration signal analysis-based vehicle working condition identification method | |
| CN114323512B (en) | Heavy-load vehicle identification method and system | |
| CN114543717B (en) | Deformation identification method and device for ballastless track plate, terminal and storage medium | |
| CN113823317B (en) | Transformer substation noise separation method, device and medium based on spectrum structured recognition | |
| CN114358071A (en) | Method and device for detecting diseases in lining structure body and storage medium | |
| CN117912494A (en) | Rail transit multidimensional falling object analysis method and system based on voice recognition |
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 |