CN115881079B - Noise early warning method, system, equipment and storage medium in railway track construction - Google Patents
Noise early warning method, system, equipment and storage medium in railway track construction Download PDFInfo
- Publication number
- CN115881079B CN115881079B CN202310120150.5A CN202310120150A CN115881079B CN 115881079 B CN115881079 B CN 115881079B CN 202310120150 A CN202310120150 A CN 202310120150A CN 115881079 B CN115881079 B CN 115881079B
- Authority
- CN
- China
- Prior art keywords
- information
- acoustic
- noise
- acoustic wave
- sound wave
- 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
Links
Images
Classifications
-
- 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
- Train Traffic Observation, Control, And Security (AREA)
Abstract
The invention provides a noise early warning method, a system, equipment and a storage medium in railway track construction, and relates to the technical field of railway track construction, wherein the method comprises the steps of obtaining first information and second information, wherein the first information is acoustic wave information acquired by an acoustic wave acquisition device positioned at the bottom of a track laying machine, and the second information is constant value acoustic wave information transmitted by a plurality of acoustic wave transmitters; preprocessing the first information to obtain preprocessed first information; transforming the sound wave fixed value in the second information and the preprocessed first information to obtain a spectrogram corresponding to each sound wave fixed value; inputting a spectrogram corresponding to each sound wave constant value into a trained spectrum model to obtain a noise early warning characteristic value output by the spectrum model; and carrying out noise early warning based on the noise early warning characteristic value. The invention can fully know the noise source generation condition of the newly built track in early stage, and further effectively prevent the noise source generation condition.
Description
Technical Field
The invention relates to the technical field of railway track construction, in particular to a noise early warning method, a system, equipment and a storage medium in railway track construction.
Background
In the railway track construction, when the geometric shape, the size and the space position of the track deviate relative to the set position, the problem of track irregularity is generated, wherein the shortwave irregularity in the track irregularity can cause obvious noise, in the prior art, the noise early warning of the shortwave irregularity in the newly built railway track construction is absent, and after the newly built track is put into use, the noise problem of the newly built track is further aggravated; in addition, for newly built tracks, the noise generating source of short wave irregularity is in the early stage, and the noise generating source is not easily known sufficiently in the existing construction, so that effective prevention is not easy to perform. Therefore, a noise early warning method in railway track construction is needed to perform noise early warning on shortwave irregularity in railway track construction, and the problem that noise is aggravated after a new track is put into use is prevented.
Disclosure of Invention
The invention aims to provide a noise early warning method, a system, equipment and a storage medium in railway track construction so as to solve the problems. In order to achieve the above purpose, the technical scheme adopted by the invention is as follows:
in a first aspect, the present application provides a noise early warning method in railway track construction, the method comprising:
acquiring first information and second information, wherein the first information is acoustic information acquired by an acoustic collector at the bottom of the track laying machine, the second information is fixed value acoustic information transmitted by a plurality of acoustic transmitters, the fixed value acoustic information at least comprises two groups of different acoustic fixed values, and the acoustic transmitters are arranged on a track along the line;
preprocessing the first information to obtain preprocessed first information;
transforming the sound wave fixed value in the second information and the preprocessed first information to obtain a spectrogram corresponding to each sound wave fixed value;
inputting a spectrogram corresponding to each sound wave constant value into a trained spectral model to obtain a noise early warning characteristic value output by the spectral model, wherein the spectral model is a mapping relation neural network established by extracting all characteristics in the spectrogram;
and carrying out noise early warning based on the noise early warning characteristic value.
In a second aspect, the present application further provides a noise warning system in railway track construction, the system comprising:
the system comprises an acquisition module, a track laying machine and a track laying machine, wherein the acquisition module is used for acquiring first information and second information, the first information is acoustic information acquired by an acoustic acquisition device positioned at the bottom of the track laying machine, the second information is fixed value acoustic information transmitted by a plurality of acoustic transmitters, the fixed value acoustic information at least comprises two groups of different acoustic fixed values, and the acoustic transmitters are arranged on a track along the track;
the preprocessing module is used for preprocessing the first information to obtain preprocessed first information;
the first processing module is used for converting the sound wave fixed value in the second information and the preprocessed first information to obtain a spectrogram corresponding to each sound wave fixed value;
the third processing module is used for inputting the spectrogram corresponding to each sound wave constant value into the trained frequency spectrum model to obtain a noise early warning characteristic value output by the frequency spectrum model, wherein the frequency spectrum model is a mapping relation neural network established by extracting all characteristics in the spectrogram;
and the fourth processing module is used for carrying out noise early warning based on the noise early warning characteristic value.
In a third aspect, the present application further provides a noise warning device in railway track construction, including:
a memory for storing a computer program;
and the processor is used for realizing the noise early warning method in the railway track construction when executing the computer program.
In a fourth aspect, the present application further provides a storage medium, where a computer program is stored, where the computer program, when executed by a processor, implements the steps of the noise early warning method in railway track-based construction.
The beneficial effects of the invention are as follows:
the noise early warning method for the railway track construction is introduced, the noise source in the initial stage is amplified through the fixed value acoustic information transmitted by the plurality of acoustic transmitters, then the noise early warning characteristic value is obtained through calculation, and the noise early warning of the newly built track is realized.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be apparent from the description, or may be learned by practice of the embodiments of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims thereof as well as the appended drawings.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the embodiments will be briefly described below, it being understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and other related drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic flow chart of a noise early warning method in railway track construction according to an embodiment of the invention;
FIG. 2 is a schematic diagram of a noise warning system in railway track construction according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of a first processing module according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of a noise warning device in railway track construction according to an embodiment of the present invention;
FIG. 5 is a schematic diagram of first information before preprocessing according to an embodiment of the present invention;
FIG. 6 is a schematic diagram of the first information after preprocessing according to an embodiment of the present invention;
the marks in the figure:
901. an acquisition module; 902. a preprocessing module; 9021. a first calculation unit; 9022. a second calculation unit; 9023. a third calculation unit; 9024. a fourth calculation unit; 903. a first processing module; 9031. a first computing module; 90311. a first acquisition unit; 90312. a fifth calculation unit; 90313. a sixth calculation unit; 90314. a seventh calculation unit; 90315. an eighth calculation unit; 9032. a second computing module; 90321. a second acquisition unit; 90322. a first processing unit; 90323. a second processing unit; 90324. a third processing unit; 90325. a fourth processing unit; 90326. a fifth processing unit; 90327. a sixth processing unit; 9033. a third calculation module; 90331. a third acquisition unit; 90332. a seventh processing unit; 90333. an eighth processing unit; 90334. a ninth processing unit; 904. a second processing module; 9041. a fourth acquisition unit; 9042. a ninth calculation unit; 9043. a tenth calculation unit; 9044. a tenth processing unit; 905. a third processing module; 906. a fourth processing module; 800. noise early warning equipment in railway track construction; 801. a processor; 802. a memory; 803. a multimedia component; 804. an I/O interface; 805. a communication component.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention. The components of the embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the invention, as presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. 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.
It should be noted that: like reference numerals and letters denote like items in the following figures, and thus once an item is defined in one figure, no further definition or explanation thereof is necessary in the following figures. Meanwhile, in the description of the present invention, the terms "first", "second", and the like are used only to distinguish the description, and are not to be construed as indicating or implying relative importance.
Example 1:
the embodiment provides a noise early warning method in railway track construction.
Referring to fig. 1, the method is shown to include S1 to S6, specifically:
s1, acquiring first information and second information, wherein the first information is acoustic information acquired by an acoustic collector at the bottom of a track laying machine, the second information is fixed value acoustic information transmitted by a plurality of acoustic transmitters, the fixed value acoustic information at least comprises two groups of different acoustic fixed values, and the acoustic transmitters are arranged on a track along the line;
the rail surface irregularity with the wavelength below 1m is short wave irregularity, the amplitude is smaller and is mostly 0.1-2mm, if a new track is built, the factor source for causing the noise source is still in an initial stage, and the determination is not easy to carry out. In step S1, the fixed value acoustic wave information emitted by a plurality of acoustic wave emitters is introduced to amplify the noise source in the initial stage, namely the fixed value acoustic wave information emitted by the plurality of acoustic wave emitters and waves generated by the defect of the newly built track act together to obtain first information, wherein the first information is mixed waves; the second information can be preset with any short wave value, and then the set value of the short wave value is adjusted according to the feedback of the first information so as to acquire the effective first information.
S2, preprocessing the first information to obtain preprocessed first information;
as shown in fig. 5 and fig. 6, the preprocessed first information separates the fixed value acoustic information from the mixed wave to obtain a single wave after separating the fixed value acoustic, and the number of principal components in the first information is determined by analyzing the change of the single wave, where the number of principal components is a corresponding factor source causing a noise source.
In step S2, S21 to S24 are included, specifically:
step S21, carrying out centering calculation on the first information to obtain a centering sound wave signal, wherein the centering sound wave signal is a signal with zero average value of the sound wave signals corresponding to the sound wave information in the first information;
s22, spheroidizing the centralized acoustic wave signal to obtain an independent component source;
in step S22, the spheroidization may be performed by using a covariance matrix, and the calculation formula is as follows:
in the above-mentioned method, the step of,Prepresents the ith signal sourcePThe value of the individual signals can be regarded as lengthPIs used for the vector of (a),
is a vector of centered acoustic signals, k being the mean value of each signal. />
S23, judging the number of independent component sources, and respectively calculating the accumulated contribution rate of each independent component source;
in step S23, the cumulative contribution rate calculation formula of each independent component source is:
in the above-mentioned method, the step of,
representing the cumulative contribution rate of the ith independent component source,/->
Is->
Characteristic value of>
Represents the iteration number (number of initialization iterations +.>
）。
And step S24, determining the number of principal components in the first information according to the accumulated contribution rate of each independent component source, and obtaining the preprocessed first information based on the number of principal components in the first information, wherein the number of principal components is the corresponding factor source for causing the noise source.
In step S24, the cumulative contribution rate of each independent component source indicates the intensity of the source signal, and when the contribution rate is greater than the preset contribution rate high threshold, the position indicates that the more noise sources are generated, the composite noise source is generated, and when the contribution rate is between the preset contribution rate high threshold and the preset contribution rate low threshold, the position indicates that the noise sources are single, and the single noise source is generated.
S3, converting the sound wave fixed values in the second information and the preprocessed first information to obtain a spectrogram corresponding to each sound wave fixed value;
after step S3, to avoid mutual interference of waves emitted by adjacent acoustic wave emitters, step S4 is further included, where step S4: and calculating the setting distance of the adjacent sound wave emitters in the track along the line, and updating the spectrogram corresponding to each sound wave constant value according to the calculation result.
Step S4 includes S41 to S44, specifically:
step 41, obtaining third information and fourth information, wherein the third information is distance information corresponding to adjacent acoustic wave transmitters in the acoustic wave transmitters, the acoustic wave transmitters are equidistantly arranged, the fourth information is distance information corresponding to the adjacent acoustic wave transmitters in the acoustic wave transmitters, the acoustic wave transmitters are arranged in a variable distance mode, and the distances among the acoustic wave transmitters are calculated by a preset distance formula;
in the fourth information of step S41, for convenience in distance determination, the distances between the plurality of acoustic wave transmitters are calculated by a preset distance formula, specifically:
in the above-mentioned method, the step of,
represents the set distance of the (i+1) th track section, < ->
The set distance of the ith track section is represented, f (i) represents a linear function, f (i) can be fitted according to the track form of the new track, f (i) can be selected as a unitary linear function if the new track is a linear track, and f (i) can be selected as an arc function if the new track is a curve track.
Step S42, transforming according to the third information and the second information to obtain a first spectrogram corresponding to the equidistant sound wave emitter;
s43, converting according to the fourth information and the second information to obtain a second spectrogram corresponding to the variable-pitch acoustic transmitter;
and S44, determining the setting distance of the adjacent acoustic wave emitters in the track line according to the first spectrogram and the second spectrogram, and updating the spectrogram corresponding to each acoustic wave constant value according to the calculation result.
In step S44, determining a distance between each track according to the first spectrogram and the second spectrogram, so as to avoid mutual interference of waves emitted by adjacent acoustic wave emitters; and when the setting distance of the adjacent sound wave emitters in the track along the line is determined, updating the spectrogram corresponding to each sound wave constant value according to the calculation result.
S5, inputting a spectrogram corresponding to each sound wave constant value into a trained spectral model to obtain a noise early warning characteristic value output by the spectral model, wherein the spectral model is a mapping relation neural network established by extracting all characteristics in the spectrogram;
and S6, carrying out noise early warning based on the noise early warning characteristic value.
In step S6, noise warning is performed based on the noise warning feature value, specifically including: partitioning the noise early warning, namely partitioning the noise early warning into a low noise domain, a medium noise domain and a high noise domain, matching the noise early warning characteristic value with partition information, determining the noise domain corresponding to the sound wave information with the fixed value, and if the noise early warning characteristic value corresponds to the low noise domain, indicating that the newly built track has less noise sources and meets the long-term use requirement; if the noise early warning characteristic value corresponds to the middle noise region, the noise early warning characteristic value indicates that the newly built track has more noise sources and partial composite defects, and only meets the short-term use requirement; if the noise early warning characteristic value corresponds to a high noise area, the noise early warning characteristic value indicates that the newly built track has more noise sources and a large number of composite defects, and the defect rechecking is carried out to meet the design requirement.
In order to determine the influence of the train running speed on the sound wave constant value, in step S3, a step S31 is specifically included, and the step S31 includes steps S311 to S315, specifically including:
step S311, acquiring third information and acceleration information, wherein the third information is distance information corresponding to adjacent acoustic wave transmitters in a plurality of acoustic wave transmitters, the acoustic wave transmitters are equidistantly arranged, and the acceleration information is information acquired by an acceleration sensor on the track laying machine;
the relationship between the resonance frequency f, the vehicle speed v, and the wavelength λ can be expressed as:
therefore, the invention provides the research of controlling the acceleration to determine the influence of different train running speeds on the sound wave constant value, such as constant speed-speed change and the like.
Step S312, dividing the acceleration information into units according to the equidistant distance of the third information;
in step S312, in order to simplify the control of the acceleration information, the track pitch distances are set at equal intervals, and then each equal distance is subjected to unit division, so that the track laying machine realizes different acceleration fitting states in the corresponding unit intervals, and various conditions of train operation are fully simulated.
Step S313, obtaining fifth information based on the divided third information, wherein the fifth information is the maximum value, the minimum value, the peak-to-peak value and the effective value of the vehicle body acceleration of each unit section corresponding to the third information;
in step S313, the maximum value and the minimum value of the vehicle body acceleration of each unit section can reflect the speed simulation boundary of each unit section; the peak-to-peak value is used to reflect the range of variation of the signal; the effective value is used for measuring the index of information energy, the effective value is the index for judging the health state of the system in fault diagnosis, and the calculation formula is as follows:
in the above-mentioned method, the step of,
representing the effective value of the vehicle body acceleration in the cell section, i indicating the number of acceleration data points in the cell section from 1 to N, +.>
Indicating the acceleration control function relationship selected.
Step S314, the preprocessed first information is updated once according to the fifth information;
and step 315, transforming the sound wave fixed value in the second information and the first information updated at one time to obtain a spectrogram corresponding to each sound wave fixed value.
In order to recheck the influence of the track surface defects (such as scratches and stripping off blocks) on the sound wave constant value, after the step S31, the method further comprises a step S32, wherein the step S32 comprises steps S321 to S327, specifically comprises:
s321, acquiring image information, wherein the image information is an image of the track surface vertically or obliquely irradiated by laser acquired by an image acquisition device positioned at the bottom of the track laying machine;
step S322, performing image binarization processing on the image information, and extracting laser lines from the image information subjected to the image binarization processing;
in step S322, the image binarization process sets a global threshold T, and divides the image data into two parts by T: the pixel values of the pixel groups larger than T and the pixel groups smaller than T are set to white (or black), and the pixel values of the pixel groups smaller than T are set to black (or white).
Step S323, performing expansion and corrosion operation on the extracted laser line image to obtain a processed laser line image;
in step S323, the expansion operation is a process of combining all the background points in contact with the object into the object to expand the boundary to the outside, and expanding the laser line image by one turn after the expansion operation; the erosion operation is a process that causes the boundary to shrink inward, which can be used to eliminate small and meaningless image points.
Step S324, extracting pixel points from the processed laser line image;
step S325, performing Fourier transform on the extracted pixel points to obtain sixth information, wherein the sixth information is a spectrogram corresponding to the extracted pixel points;
step S326, the preprocessed first information is updated for the second time according to the sixth information;
step S327, transforming the sound wave constant value in the second information and the second updated first information, and updating the spectrogram corresponding to each sound wave constant value.
The influence of the defect inside the track on the sound wave constant value is determined for the recheck, and after the step S32, the method further comprises a step S33, wherein the step S33 comprises steps S331 to S334, specifically comprises:
s331, acquiring seventh information, wherein the seventh information is acoustic information corresponding to ultrasonic flaw detection, and the seventh information comprises rail top flaw detection acoustic information, rail waist flaw detection acoustic information and rail bottom flaw detection acoustic information;
in step S331, an ultrasonic flaw detector is arranged at the bottom of the rail laying machine, the rail is divided into a first flaw detection area, a second flaw detection area and a third flaw detection area according to positions, the first flaw detection area corresponds to the rail top of the rail, the second flaw detection area corresponds to the rail web of the rail, and the third flaw detection area corresponds to the rail bottom of the rail; adopting a K2.5 single probe on an ultrasonic flaw detector to carry out flaw detection on the first flaw detection area and the third flaw detection area; and flaw detection is carried out on the second flaw detection area by adopting a front-back tandem type probe on the ultrasonic flaw detector.
Step S332, transforming the seventh information to obtain eighth information, wherein the eighth information is a spectrogram of acoustic wave information at different positions of the track;
step S333, updating the preprocessed first information for three times according to the eighth information;
and step 334, transforming the sound wave fixed values in the second information and the third updated first information, and updating the spectrogram corresponding to each sound wave fixed value.
The introduction of the step S33 can fully understand the damage condition of the newly built track in early stage, and further effectively prevent the defect growth problem in the running process.
Step S33 may also be used to inspect the welding defect, such as the air hole generated by welding, where the single air hole has a low echo height and a single slit waveform, so that the method is stable. The reflected waves are detected from all directions approximately the same, but when the probe is moved slightly, a cluster of reflected waves can appear in the dense air holes, the wave height is different along with the size of the air holes, and when the probe rotates at a fixed point, the phenomenon of falling off can appear. The reason for generating the defects is mainly that the welding material is not dried according to the specified temperature, the current is overlarge during manual welding, and the arc is overlong; the voltage is too high or the network voltage fluctuation is too large during submerged arc welding; the purity of the shielding gas is low during gas shielded welding, and the like.
Example 2:
as shown in fig. 2, the present embodiment provides a noise early warning system in railway track construction, where the system includes an acquisition module 901, a preprocessing module 902, a first processing module 903, a third processing module 905, and a fourth processing module 906, specifically:
the acquiring module 901 is configured to acquire first information and second information, where the first information is acoustic information acquired by an acoustic collector located at the bottom of the track laying machine, the second information is fixed value acoustic information transmitted by a plurality of acoustic transmitters, the fixed value acoustic information at least includes two different fixed values of acoustic waves, and the plurality of acoustic transmitters are disposed on a track along the track;
a preprocessing module 902, configured to preprocess the first information to obtain preprocessed first information;
the first processing module 903 is configured to transform the acoustic fixed value in the second information and the preprocessed first information to obtain a spectrogram corresponding to each acoustic fixed value;
the third processing module 905 is configured to input a spectrogram corresponding to each acoustic constant value to a trained spectral model, so as to obtain a noise early warning feature value output by the spectral model, where the spectral model is a mapping relation neural network established by extracting all features in the spectrogram;
and a fourth processing module 906, configured to perform noise early warning based on the noise early warning feature value.
In a specific embodiment of the disclosure, the preprocessing module 902 includes a first computing unit 9021, a second computing unit 9022, a third computing unit 9023, and a fourth computing unit 9024, and specifically includes:
the first calculating unit 9021 is configured to perform a centering calculation on the first information to obtain a centered acoustic signal, where the centered acoustic signal is a signal with an average value of acoustic signals corresponding to acoustic information in the first information being zero;
the second calculating unit 9022 is configured to spheroidize the centered acoustic signal to obtain an independent component source;
a third calculating unit 9023, configured to determine the number of independent component sources, and calculate an accumulated contribution rate of each independent component source;
and a fourth calculating unit 9024, configured to determine, according to the cumulative contribution rate of each independent component source, the number of principal components in the first information, and obtain, based on the number of principal components in the first information, the preprocessed first information, where the number of principal components is a corresponding factor source that causes a noise source.
As shown in fig. 3, in a specific embodiment of the disclosure, a first processing module 903 includes a first computing module 9031, where the first computing module 9031 includes a first acquiring unit 90311, a fifth computing unit 90312, a sixth computing unit 90313, a seventh computing unit 90314, and an eighth computing unit 90315, specifically includes:
the first acquiring unit 90311 is configured to acquire third information and acceleration information, where the third information is distance information corresponding to adjacent acoustic wave transmitters among the plurality of acoustic wave transmitters, the plurality of acoustic wave transmitters are equidistantly arranged, and the acceleration information is information acquired by an acceleration sensor on the track laying machine;
a fifth calculation unit 90312 for performing unit division on the acceleration information according to the equidistant distance of the third information;
a sixth calculating unit 90313, configured to obtain fifth information based on the divided third information, where the fifth information is a maximum value, a minimum value, a peak-to-peak value, and an effective value of the vehicle body acceleration of each unit section corresponding to the third information;
a seventh calculating unit 90314 for updating the preprocessed first information once according to the fifth information;
and an eighth calculating unit 90315, configured to transform the acoustic constant value in the second information and the first information after one update to obtain a spectrogram corresponding to each acoustic constant value.
In a specific embodiment of the disclosure, after the first computing module 9031, a second computing module 9032 is further included, where the second computing module 9032 includes a second obtaining unit 90321, a first processing unit 90322, a second processing unit 90323, a third processing unit 90324, a fourth processing unit 90325, a fifth processing unit 90326, and a sixth processing unit 90327, and specifically includes:
the second acquiring unit 90321 is used for acquiring image information, wherein the image information is an image of the track surface vertically or obliquely irradiated by laser acquired by an image acquisition device positioned at the bottom of the track laying machine;
a first processing unit 90322, configured to perform image binarization processing on the image information, and extract laser lines from the image information after the image binarization processing;
a second processing unit 90323, configured to perform expansion and corrosion operations on the extracted laser line image, to obtain a processed laser line image;
a third processing unit 90324, configured to extract pixel points from the processed laser line image;
a fourth processing unit 90325, configured to perform fourier transform on the extracted pixel points to obtain sixth information, where the sixth information is a spectrogram corresponding to the extracted pixel points;
a fifth processing unit 90326, configured to update the preprocessed first information for a second time according to the sixth information;
and a sixth processing unit 90327, configured to transform the acoustic constant value in the second information and the second updated first information, and update a spectrogram corresponding to each acoustic constant value.
In a specific embodiment of the disclosure, after the second computing module 9032, a third computing module 9033 is further included, where the third computing module 9033 includes: the third acquiring unit 90331, the seventh processing unit 90332, the eighth processing unit 90333, and the ninth processing unit 90334 specifically include:
the third obtaining unit 90331 is configured to obtain seventh information, where the seventh information is acoustic information corresponding to ultrasonic flaw detection, and the seventh information includes rail top flaw detection acoustic information, rail waist flaw detection acoustic information, and rail bottom flaw detection acoustic information;
a seventh processing unit 90332, configured to transform the seventh information to obtain eighth information, where the eighth information is a spectrogram of acoustic wave information at different positions of the track;
an eighth processing unit 90333 configured to update the preprocessed first information three times according to the eighth information;
and a ninth processing unit 90334, configured to transform the acoustic constant value in the second information and the third updated first information, and update a spectrogram corresponding to each acoustic constant value.
In a specific embodiment of the disclosure, after the first processing module 903, a second processing module 904 is further included, where the second processing module 904 includes a fourth obtaining unit 9041, a ninth calculating unit 9042, a tenth calculating unit 9043, and a tenth processing unit 9044, and specifically includes:
a fourth obtaining unit 9041, configured to obtain third information and fourth information, where the third information is distance information corresponding to adjacent acoustic wave emitters in the plurality of acoustic wave emitters, the plurality of acoustic wave emitters are equidistantly arranged, the fourth information is distance information corresponding to adjacent acoustic wave emitters in the plurality of acoustic wave emitters, the plurality of acoustic wave emitters are set in a variable distance manner, and distances between the plurality of acoustic wave emitters are calculated by a preset distance formula;
a ninth calculating unit 9042, configured to perform transformation according to the third information and the second information, to obtain a first spectrogram corresponding to the equidistant acoustic transmitter;
a tenth calculation unit 9043, configured to perform transformation according to the fourth information and the second information, to obtain a second spectrogram corresponding to the variable-pitch acoustic transmitter;
and a tenth processing unit 9044, configured to determine a setting distance of adjacent acoustic wave transmitters along the line track according to the first spectrogram and the second spectrogram, and update the spectrogram corresponding to each acoustic wave constant value according to a calculation result.
It should be noted that, regarding the system in the above embodiment, the specific manner in which the respective modules perform the operations has been described in detail in the embodiment regarding the method, and will not be described in detail herein.
Example 3:
corresponding to the above method embodiment, a noise pre-warning device in railway track construction is further provided in this embodiment, and a noise pre-warning device in railway track construction described below and a noise pre-warning method in railway track construction described above may be referred to correspondingly with each other.
Fig. 4 is a block diagram illustrating a noise pre-warning apparatus 800 in railway track construction according to an exemplary embodiment. As shown in fig. 4, the noise pre-warning apparatus 800 in the construction of the railway track may include: a processor 801, a memory 802. The noise pre-warning device 800 in the construction of a railway track may further include one or more of a multimedia component 803, an I/O interface 804, and a communication component 805.
The processor 801 is configured to control the overall operation of the noise pre-warning device 800 in the railway track construction, so as to complete all or part of the steps in the noise pre-warning method in the railway track construction. The memory 802 is used to store various types of data to support the operation of the noise warning device 800 in the railway track construction, which may include, for example, instructions for any application or method operating on the noise warning device 800 in the railway track construction, as well as application related data, such as contact data, messages, pictures, audio, video, and the like. The Memory 802 may be implemented by any type or combination of volatile or non-volatile Memory devices, such as static random access Memory (Static Random Access Memory, SRAM for short), electrically erasable programmable Read-Only Memory (Electrically Erasable Programmable Read-Only Memory, EEPROM for short), erasable programmable Read-Only Memory (Erasable Programmable Read-Only Memory, EPROM for short), programmable Read-Only Memory (Programmable Read-Only Memory, PROM for short), read-Only Memory (ROM for short), magnetic Memory, flash Memory, magnetic disk, or optical disk. The multimedia component 803 may include a screen and an audio component. Wherein the screen may be, for example, a touch screen, the audio component being for outputting and/or inputting audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signals may be further stored in the memory 802 or transmitted through the communication component 805. The audio assembly further comprises at least one speaker for outputting audio signals. The I/O interface 804 provides an interface between the processor 801 and other interface modules, which may be a keyboard, mouse, buttons, etc. These buttons may be virtual buttons or physical buttons. The communication component 805 is used for wired or wireless communication between the noise warning device 800 and other devices in the railway track construction. Wireless communication, such as Wi-Fi, bluetooth, near field communication (Near FieldCommunication, NFC for short), 2G, 3G or 4G, or a combination of one or more thereof, the respective communication component 805 may thus comprise: wi-Fi module, bluetooth module, NFC module.
In an exemplary embodiment, the noise pre-warning device 800 in railway track construction may be implemented by one or more application specific integrated circuits (Application Specific Integrated Circuit, abbreviated as ASIC), digital signal processor (DigitalSignal Processor, abbreviated as DSP), digital signal processing device (Digital Signal Processing Device, abbreviated as DSPD), programmable logic device (Programmable Logic Device, abbreviated as PLD), field programmable gate array (Field Programmable Gate Array, abbreviated as FPGA), controller, microcontroller, microprocessor, or other electronic component for performing the noise pre-warning method in railway track construction described above.
In another exemplary embodiment, a computer readable storage medium is also provided that includes program instructions that when executed by a processor implement the steps of the noise warning method in railway track construction described above. For example, the computer readable storage medium may be the memory 802 described above including program instructions executable by the processor 801 of the noise warning apparatus 800 in railway track construction to perform the noise warning method in railway track construction described above.
Example 4:
corresponding to the above method embodiment, a storage medium is further provided in this embodiment, and a storage medium described below and a noise early warning method in railway track construction described above may be referred to correspondingly.
A storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of the noise warning method in the construction of a railway track of the above-described method embodiment.
The storage medium may be a flash disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), a magnetic disk, or an optical disk, and the like.
The above description is only of the preferred embodiments of the present invention and is not intended to limit the present invention, but various modifications and variations can be made to the present invention by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
The foregoing is merely illustrative of the present invention, and the present invention is not limited thereto, and any person skilled in the art will readily recognize that variations or substitutions are within the scope of the present invention. Therefore, the protection scope of the invention is subject to the protection scope of the claims.
Claims (8)
1. A noise early warning method in railway track construction is characterized by comprising the following steps:
acquiring first information and second information, wherein the first information is acoustic information acquired by an acoustic collector at the bottom of the track laying machine, the second information is fixed value acoustic information transmitted by a plurality of acoustic transmitters, the fixed value acoustic information at least comprises two groups of different acoustic fixed values, and the acoustic transmitters are arranged on a track along the line;
preprocessing the first information to obtain preprocessed first information;
transforming the sound wave fixed value in the second information and the preprocessed first information to obtain a spectrogram corresponding to each sound wave fixed value;
acquiring third information and fourth information, wherein the third information is distance information corresponding to adjacent acoustic wave transmitters in the acoustic wave transmitters, the acoustic wave transmitters are equidistantly arranged, the fourth information is distance information corresponding to the adjacent acoustic wave transmitters in the acoustic wave transmitters, the acoustic wave transmitters are arranged in a variable distance mode, and the distances among the acoustic wave transmitters are calculated by a preset distance formula;
transforming according to the third information and the second information to obtain a first spectrogram corresponding to the equidistant sound wave emitter;
transforming according to the fourth information and the second information to obtain a second spectrogram corresponding to the variable-pitch acoustic transmitter;
determining the setting distance of adjacent acoustic wave transmitters in a line track according to the first spectrogram and the second spectrogram, and updating the spectrogram corresponding to each acoustic wave constant value according to a calculation result;
inputting a spectrogram corresponding to each sound wave constant value into a trained spectral model to obtain a noise early warning characteristic value output by the spectral model, wherein the spectral model is a mapping relation neural network established by extracting all characteristics in the spectrogram;
and carrying out noise early warning based on the noise early warning characteristic value, wherein the noise is generated by the newly-built track.
2. The noise pre-warning method in railway track construction according to claim 1, wherein the preprocessing the first information to obtain preprocessed first information includes:
carrying out centralized calculation on the first information to obtain a centralized sound wave signal, wherein the centralized sound wave signal is a signal with zero average value of the sound wave signals corresponding to the sound wave information in the first information;
spheroidizing the centralized acoustic wave signal to obtain an independent component source;
judging the number of independent component sources, and respectively calculating the accumulated contribution rate of each independent component source;
and determining the number of principal components in the first information according to the accumulated contribution rate of each independent component source, and obtaining the preprocessed first information based on the number of principal components in the first information, wherein the number of principal components is a corresponding factor source for causing a noise source.
3. The noise pre-warning method in railway track construction according to claim 1 or 2, wherein the transforming the sound wave fixed value in the second information and the preprocessed first information to obtain the spectrogram corresponding to each sound wave fixed value comprises:
acquiring third information and acceleration information, wherein the third information is distance information corresponding to adjacent acoustic wave transmitters in a plurality of acoustic wave transmitters, the acoustic wave transmitters are equidistantly arranged, and the acceleration information is information acquired by an acceleration sensor on the track laying machine;
dividing the acceleration information into units according to the equidistant distance of the third information;
obtaining fifth information based on the divided third information, wherein the fifth information is the maximum value, the minimum value, the peak-to-peak value and the effective value of the vehicle body acceleration of each unit section corresponding to the third information;
updating the preprocessed first information for one time according to the fifth information;
and transforming the sound wave constant value in the second information and the first information updated once to obtain a spectrogram corresponding to each sound wave constant value.
4. Noise early warning system in railway track construction, characterized by comprising:
the system comprises an acquisition module, a track laying machine and a track laying machine, wherein the acquisition module is used for acquiring first information and second information, the first information is acoustic information acquired by an acoustic acquisition device positioned at the bottom of the track laying machine, the second information is fixed value acoustic information transmitted by a plurality of acoustic transmitters, the fixed value acoustic information at least comprises two groups of different acoustic fixed values, and the acoustic transmitters are arranged on a track along the track;
the preprocessing module is used for preprocessing the first information to obtain preprocessed first information;
the first processing module is used for converting the sound wave fixed value in the second information and the preprocessed first information to obtain a spectrogram corresponding to each sound wave fixed value;
after the first processing module, a second processing module is further included, the second processing module including:
a fourth obtaining unit, configured to obtain third information and fourth information, where the third information is distance information corresponding to adjacent acoustic wave emitters in the plurality of acoustic wave emitters, the plurality of acoustic wave emitters are equidistantly arranged, the fourth information is distance information corresponding to adjacent acoustic wave emitters in the plurality of acoustic wave emitters, the plurality of acoustic wave emitters are set in a variable distance manner, and distances between the plurality of acoustic wave emitters are calculated by a preset distance formula;
a ninth calculation unit, configured to perform transformation according to the third information and the second information, to obtain a first spectrogram corresponding to the equidistant acoustic transmitter;
a tenth calculation unit, configured to perform transformation according to the fourth information and the second information, to obtain a second spectrogram corresponding to the variable-pitch acoustic transmitter;
a tenth processing unit, configured to determine a setting distance between adjacent acoustic wave transmitters in a line track according to the first spectrogram and the second spectrogram, and update a spectrogram corresponding to each acoustic wave constant value according to a calculation result;
the third processing module is used for inputting the spectrogram corresponding to each sound wave constant value into the trained frequency spectrum model to obtain a noise early warning characteristic value output by the frequency spectrum model, wherein the frequency spectrum model is a mapping relation neural network established by extracting all characteristics in the spectrogram;
and the fourth processing module is used for carrying out noise early warning based on the noise early warning characteristic value, and the noise is generated by the newly-built track.
5. The noise pre-warning system in railway track construction according to claim 4, wherein the pre-processing module comprises:
the first calculation unit is used for carrying out centering calculation on the first information to obtain a centering sound wave signal, wherein the centering sound wave signal is a signal with zero average value of sound wave signals corresponding to the sound wave information in the first information;
the second calculation unit is used for spheroidizing the centralized acoustic wave signal to obtain an independent component source;
the third calculation unit is used for judging the number of the independent component sources and respectively calculating the accumulated contribution rate of each independent component source;
and the fourth calculation unit is used for determining the number of principal components in the first information according to the accumulated contribution rate of each independent component source, and obtaining the preprocessed first information based on the number of principal components in the first information, wherein the number of principal components is the corresponding factor source for causing the noise source.
6. The noise warning system in railway track construction of claim 4 or 5, comprising a first computing module in a first processing module, the first computing module comprising:
the first acquisition unit is used for acquiring third information and acceleration information, wherein the third information is distance information corresponding to adjacent acoustic wave transmitters in the acoustic wave transmitters, the acoustic wave transmitters are equidistantly arranged, and the acceleration information is information acquired by an acceleration sensor on the track laying machine;
a fifth calculation unit, configured to divide the acceleration information into units according to equidistant distances of the third information;
the sixth calculation unit is used for obtaining fifth information based on the divided third information, wherein the fifth information is the maximum value, the minimum value, the peak-to-peak value and the effective value of the vehicle body acceleration of each unit section corresponding to the third information;
a seventh calculation unit, configured to update the preprocessed first information once according to the fifth information;
and the eighth calculation unit is used for transforming the sound wave fixed value in the second information and the first information updated once to obtain a spectrogram corresponding to each sound wave fixed value.
7. Noise early warning equipment in railway track construction, characterized by, include:
a memory for storing a computer program;
a processor for implementing the steps of the noise warning method in railway track construction according to any one of claims 1 to 3 when executing the computer program.
8. A storage medium, characterized by: the storage medium has stored thereon a computer program which, when executed by a processor, implements the steps of the noise warning method in railway track construction as claimed in any one of claims 1 to 3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310120150.5A CN115881079B (en) | 2023-02-16 | 2023-02-16 | Noise early warning method, system, equipment and storage medium in railway track construction |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310120150.5A CN115881079B (en) | 2023-02-16 | 2023-02-16 | Noise early warning method, system, equipment and storage medium in railway track construction |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115881079A CN115881079A (en) | 2023-03-31 |
| CN115881079B true CN115881079B (en) | 2023-05-23 |
Family
ID=85761201
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310120150.5A Active CN115881079B (en) | 2023-02-16 | 2023-02-16 | Noise early warning method, system, equipment and storage medium in railway track construction |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115881079B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH10332647A (en) * | 1997-05-27 | 1998-12-18 | Tokimec Inc | Method and device for judging scratch of body to be inspected |
| RU2645818C1 (en) * | 2016-12-19 | 2018-02-28 | Открытое акционерное общество "Радиоавионика" | Method for ultrasonic inspection of rail bases |
| CN108663435A (en) * | 2018-04-12 | 2018-10-16 | 武汉光谷航天三江激光产业技术研究院有限公司 | A kind of distributed acoustic wave train wheel rail detection device and method |
| CN110672718A (en) * | 2019-07-08 | 2020-01-10 | 南昌航空大学 | Electromagnetic ultrasonic point focusing/diverging surface wave method and device for steel rail tread detection |
| CN115200695A (en) * | 2022-07-14 | 2022-10-18 | 扬州大学 | Abnormal sound wave characteristic identification-based safety early warning method and system for truck band-type brake |
Family Cites Families (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| PL69347B1 (en) * | 1970-06-20 | 1973-02-28 | ||
| DE19826230C2 (en) * | 1997-12-12 | 2002-03-28 | Siemens Ag | Method and device for assessing the condition of a railway track |
| GB2383413B (en) * | 2001-12-21 | 2005-10-26 | Peter Robert Armitage | Apparatus and method for detecting rail defects, using the velocity, attenuation, scattering and frequency absorbing properties of surface acoustic waves |
| RU2437090C1 (en) * | 2010-09-28 | 2011-12-20 | Общество с ограниченной ответственностью "Научно-Технический Центр Информационные Технологии" | Method of assessing state of railway track |
| RU2511644C1 (en) * | 2012-08-27 | 2014-04-10 | Федеральное государственное бюджетное образовательное учреждение высшего профессионального образования "Самарский государственный университет путей сообщения" (СамГУПС) | Acoustic method of rail track failure detection |
| CN107436326B (en) * | 2017-08-29 | 2023-04-25 | 中铁第四勘察设计院集团有限公司 | Rapid nondestructive detection device and method for structural defects under high-speed railway track |
| CN109212038A (en) * | 2018-11-14 | 2019-01-15 | 北京主导时代科技有限公司 | A kind of rail detector car and its layout system of popping one's head in |
| CN110059631B (en) * | 2019-04-19 | 2020-04-03 | 中铁第一勘察设计院集团有限公司 | Contact net non-contact type monitoring defect identification method |
| FR3105148B1 (en) * | 2019-12-23 | 2023-10-06 | Commissariat Energie Atomique | SYSTEM AND METHOD FOR DETECTING A DEFECT IN A RAIL OF A RAILWAY |
| CN111497902A (en) * | 2019-12-31 | 2020-08-07 | 南京大学 | phi-OTDR (optical time Domain reflectometer) -based high-speed rail health online monitoring method |
| CN114475678A (en) * | 2022-03-01 | 2022-05-13 | 柳州铁道职业技术学院 | Based on ultrasonic wave suspension type track robot of detecting a flaw |
| CN115629127B (en) * | 2022-12-16 | 2023-04-14 | 北京中海兴达建设有限公司 | Container defect analysis method, device and equipment and readable storage medium |
-
2023
- 2023-02-16 CN CN202310120150.5A patent/CN115881079B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH10332647A (en) * | 1997-05-27 | 1998-12-18 | Tokimec Inc | Method and device for judging scratch of body to be inspected |
| RU2645818C1 (en) * | 2016-12-19 | 2018-02-28 | Открытое акционерное общество "Радиоавионика" | Method for ultrasonic inspection of rail bases |
| CN108663435A (en) * | 2018-04-12 | 2018-10-16 | 武汉光谷航天三江激光产业技术研究院有限公司 | A kind of distributed acoustic wave train wheel rail detection device and method |
| CN110672718A (en) * | 2019-07-08 | 2020-01-10 | 南昌航空大学 | Electromagnetic ultrasonic point focusing/diverging surface wave method and device for steel rail tread detection |
| CN115200695A (en) * | 2022-07-14 | 2022-10-18 | 扬州大学 | Abnormal sound wave characteristic identification-based safety early warning method and system for truck band-type brake |
Non-Patent Citations (1)
| Title |
|---|
| 基于电磁超声表面波的钢轨在线探伤装置;邱玉;许霁;汪开灿;翟国富;;无损检测(第05期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115881079A (en) | 2023-03-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Yang et al. | Quantitative measurement of pass-by noise radiated by vehicles running at high speeds | |
| CN110307994A (en) | Allophone detection device and allophone detection method | |
| Park et al. | Visualization of pass-by noise by means of moving frame acoustic holography | |
| JP6270330B2 (en) | Engine sound output device and engine sound output method | |
| CN111985494A (en) | Road disease detection and classification method based on lightweight vehicle-mounted terminal | |
| JP6371516B2 (en) | Acoustic signal processing apparatus and method | |
| CN109754815A (en) | Systems, devices and methods for unmanned plane audio defeat | |
| JPH0627680B2 (en) | Tire noise simulating method and simulator | |
| JP2020077186A (en) | Monitoring system, program, and storage medium | |
| US20240046953A1 (en) | Sound data processing method, sound data processing device, and program | |
| CN107566969A (en) | A kind of enclosed environment internal low-frequency Reconstruction of Sound Field method | |
| CN115881079B (en) | Noise early warning method, system, equipment and storage medium in railway track construction | |
| Meng et al. | Signal reconstruction of fast moving sound sources using compressive beamforming | |
| Murovec et al. | Automated identification and assessment of environmental noise sources | |
| CN113358742B (en) | Roadbed compaction evaluation method, device and equipment and readable storage medium | |
| Meng et al. | A synthesis model for a moving sound source based on beamforming | |
| JP2008140222A (en) | Abnormality detection device and abnormality detection method | |
| US10717387B2 (en) | Engine sound control device, engine sound control method, and non-transitory computer-readable medium | |
| CN108594163B (en) | Method for identifying sound source by using single microphone movement and inner product operation | |
| Yan et al. | Experimental Study of Sound Travel-Time Estimation Method in Stored Grain. | |
| JP6956913B1 (en) | Feature extraction device, time series inference device, time series learning system, time series feature extraction method, time series inference method, and time series learning method | |
| Deowan et al. | A Warning and Detection System for Elephant Intrusions utilizing Signal Processing and IoT | |
| Talotte et al. | Simulations of the noise radiation of high speed trains | |
| JP4747323B2 (en) | Acoustic monitoring support device and acoustic monitoring support method | |
| CN116561563B (en) | Slope displacement prediction method and related device based on residual prediction model |
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 |