Steel rail corrugation detection and identification method, device, equipment, medium and program

Abstract

The invention relates to a rail corrugation detection and identification method, device, equipment, medium and program, and the method comprises the steps: obtaining an original vibration response signal, decomposing the original vibration response signal, and obtaining a modal function component; screening out a target component from the modal function components according to a preset correlation coefficient criterion, and reconstructing the target component to obtain a preprocessed signal; performing time-frequency analysis on the preprocessed signal to obtain a time-frequency ridge line, and intercepting a corrugation section according to a vibration response signal positioned by the time-frequency ridge line; and extracting time domain features of the corrugation section, and generating a wave depth grade result according to the time domain features.

Description

Technical Field

[0001] The present disclosure relates to the field of data analysis technology, and in particular to a rail corrugation detection and identification method, device, equipment, medium and program. Background Art

[0002] Rail corrugation, or corrugation for short, refers to the periodic wave-like unevenness on the surface of the rail. This phenomenon is not only widespread but also rapidly developing in the context of heavy-duty trains with large total weight, large transportation volume, and high driving frequency. The presence of rail corrugation complicates the dynamics between the wheel and rail, and produces violent vibrations between the wheel and rail, greatly reducing the service life of the vehicle and track structural components, and increasing maintenance costs. When corrugation is severe, it may even cause train derailment, overturning, and other accidents. Therefore, the detection and identification of rail corrugation is crucial.

[0003] In the existing technology, the identification of rail corrugation mostly relies on the time domain vibration response exceeding limit standard. However, this method ignores the periodic characteristics of the corrugation vibration response and is easily disturbed by other factors such as rail peeling, weld defects, etc., which causes frequent misjudgments and has obvious limitations. In addition, existing research focuses on high-speed rail and subway lines. Due to the uniqueness of heavy-load railways in axle weight and operating conditions, these research results are difficult to directly transfer to heavy-load lines. There is a certain gap between the detection results and the actual dynamic response when heavy-loaded trucks pass by, which leads to the failure to improve the efficiency of corrugation detection. Therefore, how to improve the efficiency and accuracy of rail corrugation detection has become an urgent problem to be solved. Summary of the invention

[0004] The present invention provides a rail corrugation detection and identification method, device, equipment, medium and program, the main purpose of which is to solve the problems of low efficiency and inaccurate detection of rail corrugation on heavy-load railways.

[0005] In a first aspect, the present disclosure provides a rail corrugation detection and identification method, comprising:

[0006] Acquire an original vibration response signal, and decompose the original vibration response signal to obtain a modal function component;

[0007] Filtering out a target component from the modal function components according to a preset correlation coefficient criterion, and reconstructing the target component to obtain a preprocessed signal;

[0008] Performing time-frequency analysis on the preprocessed signal to obtain a time-frequency ridge line, and cutting out a corrugation section according to a vibration response signal located by the time-frequency ridge line;

[0009] The time domain characteristics of the corrugation section are extracted, and the wave depth level results are generated according to the time domain characteristics.

[0010] In some embodiments, decomposing the original vibration response signal to obtain modal function components includes:

[0011] Using a preset sliding window to intercept the original vibration response signal to obtain a window intercept signal;

[0012] Performing empirical mode decomposition on the window intercepted signals to obtain the modal function components corresponding to each window intercepted signal.

[0013] In an embodiment of the present invention, the step of selecting a target component from the modal function components according to a preset correlation coefficient criterion includes:

[0014] The Pearson correlation coefficient is used to calculate the correlation coefficient between each modal function component and the original vibration response signal;

[0015] The corresponding modal function component whose correlation coefficient is greater than or equal to a preset correlation coefficient threshold is taken as the target component.

[0016] In the embodiment of the present invention, reconstructing the target component to obtain a preprocessed signal includes:

[0017] Obtain all local maximum and minimum points of the target component;

[0018] Using an interpolation method to create a smooth curve between all the local maximum and minimum points to obtain an envelope;

[0019] The envelope is multiplied by the target component and then summed to obtain a preprocessed signal.

[0020] In an embodiment of the present invention, the step of extracting the corrugation section according to the vibration response signal located by the time-frequency ridge line includes:

[0021] Selecting the vibration response signal position where the time-frequency ridge exceeds a preset positioning threshold;

[0022] The corrugation section is cut out according to the position of the vibration response signal to obtain wavelength information.

[0023] In the embodiment of the present invention, generating a wave depth level result according to the time domain feature includes:

[0024] Acquire wave depth information according to the time domain characteristics;

[0025] Calculate the correlation coefficient between each waveform index and the wave depth information;

[0026] The time domain feature whose correlation coefficient is greater than or equal to a preset correlation coefficient threshold is used as a sensitive feature;

[0027] The sensitive features are input into a vector machine classifier to generate a wave depth level result.

[0028] In a second aspect, the present disclosure provides a rail corrugation detection and identification device, comprising:

[0029] A signal decomposition module, which acquires an original vibration response signal and decomposes the original vibration response signal to obtain a modal function component;

[0030] A signal reconstruction module, which selects a target component from the modal function components according to a preset correlation coefficient criterion, and reconstructs the target component to obtain a preprocessed signal;

[0031] A time-frequency analysis module performs time-frequency analysis on the preprocessed signal to obtain a time-frequency ridge line, and cuts out a corrugation section according to a vibration response signal located by the time-frequency ridge line;

[0032] The detection and identification module extracts the time domain characteristics of the corrugation section and generates a corrugation depth level result according to the time domain characteristics.

[0033] In a third aspect, the present disclosure provides a computer device, including a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of the method described in the above aspects.

[0034] In a fourth aspect, the present disclosure provides a computer-readable storage medium having a computer program stored thereon, which implements the steps of the method described in the above aspects when executed by a processor.

[0035] In a fifth aspect, the present disclosure provides a computer program product, including a computer program, which implements the steps of the method described in the above aspects when executed by a processor.

[0036] The embodiment of the present invention decomposes the original vibration response signal to obtain the modal function components, which can more easily identify and remove the noise and interference components in the signal and reduce the complexity of subsequent calculations; selects the target components from the modal function components according to a preset correlation coefficient criterion, and reconstructs them to obtain the preprocessed signal, thereby realizing data compression and accelerating the signal processing speed; performs time-frequency analysis on the preprocessed signal to obtain the time-frequency ridge line, and cuts out the corrugation section according to the vibration response signal located by the time-frequency ridge line, thereby improving the accuracy of signal analysis and processing efficiency; extracts the time domain characteristics of the corrugation section and generates the wave depth level result, which can comprehensively analyze the time domain characteristics of the signal and improve the accuracy of wave depth level recognition, thereby realizing the recognition of the level of corrugation degradation. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] The present disclosure will be described in more detail below based on embodiments and with reference to the accompanying drawings:

[0038] Figure 1A schematic flow chart of a rail corrugation detection and identification method provided in an embodiment of the present disclosure.

[0039] Figure 2 A schematic diagram of the structure of a rail corrugation detection and identification device provided in an embodiment of the present disclosure.

[0040] In the drawings, the same reference numerals are used for the same components, and the drawings are not drawn to scale. DETAILED DESCRIPTION

[0041] In order to enable those skilled in the art to better understand the technical solution of the present disclosure, and to fully understand and implement how the present disclosure applies technical means to solve technical problems and achieve the corresponding technical effects, the technical solution in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only embodiments of a part of the present disclosure, not all of the embodiments. The embodiments of the present disclosure and the various features in the embodiments can be combined with each other without conflict, and the technical solutions formed are all within the scope of protection of the present disclosure. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in this field without making creative work should fall within the scope of protection of the present disclosure.

[0042] The embodiment of the present application provides a rail corrugation detection and identification method. The execution subject of the rail corrugation detection and identification method includes but is not limited to at least one of the electronic devices such as a server and a terminal that can be configured to execute the system provided by the embodiment of the present application. In other words, the rail corrugation detection and identification method can be executed by software or hardware installed in a terminal device or a server device. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, etc. The server can be an independent server, or it can be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (Content Delivery Network, CDN), and big data and artificial intelligence platforms.

[0043] Reference Figure 1 , which is a schematic flow chart of a rail corrugation detection and identification method provided by an embodiment of the present invention.

[0044] In this embodiment, the rail corrugation detection and identification method includes:

[0045] S1. Acquire an original vibration response signal, and decompose the original vibration response signal to obtain modal function components.

[0046] In the embodiment of the present invention, the modal function component, ie, the IMF component, is an oscillation function with a time-varying frequency, which can reflect the local characteristics of the signal. The present invention decomposes the original vibration response signal into a number of intrinsic mode functions by using an empirical mode decomposition method.

[0047] In an embodiment of the present invention, the original vibration response signal can be obtained by a vibration acceleration sensor at the train axle box. During the acquisition process, the electrical signal collected by the sensor exists in a continuous form, and the electrical signal is converted into a digital signal form, namely the original vibration response signal, to obtain it.

[0048] In the embodiment of the present invention, decomposing the original vibration response signal to obtain modal function components includes:

[0049] Using a preset sliding window to intercept the original vibration response signal to obtain a window intercept signal;

[0050] Performing empirical mode decomposition on the window intercepted signals to obtain the modal function components corresponding to each window intercepted signal.

[0051] Specifically, the original vibration response signal is intercepted by sliding the window by setting a fixed size window (such as 200m as the evaluation unit), and the original vibration response signal is analyzed in detail within the window, such as frequency analysis, feature extraction, etc. It is also possible to perform spatial analysis based on the specific positioning information of the original vibration response signal, which helps to understand the distribution and impact range of the signal in space.

[0052] The present invention performs empirical mode decomposition (EMD) on the vibration response signal in each window intercepted, and decomposes the original vibration response signal into a plurality of modal function components through EMD decomposition. The modal function components represent the components of the signal at different frequencies, which facilitates the subsequent calculation of the correlation coefficient with the original vibration response signal and determines the importance of each modal function component in the original vibration response signal.

[0053] In the embodiment of the present invention, by acquiring the original vibration response signal and decomposing the original vibration response signal, it is easier to identify and remove noise and interference components in the signal, and the modal function components are obtained by decomposition, which simplifies the subsequent signal processing and analysis process and reduces the computational complexity.

[0054] S2. Filter out target components from the modal function components according to a preset correlation coefficient criterion, and reconstruct the target components to obtain a preprocessed signal.

[0055] In the embodiment of the present invention, the correlation coefficient criterion refers to using the Pearson correlation coefficient to calculate the correlation coefficient between each modal function component, i.e., the IMF component, and the original vibration response signal. The target component refers to the IMF component related to the corrugation characteristics obtained by screening by comparing the correlation coefficients. The reconstruction refers to sequentially adding the screened IMF components and adding the residual component to form a preprocessed signal.

[0056] In the embodiment of the present invention, the step of selecting the target component from the modal function components according to a preset correlation coefficient criterion includes:

[0057] The Pearson correlation coefficient is used to calculate the correlation coefficient between each modal function component and the original vibration response signal;

[0058] The corresponding modal function component whose correlation coefficient is greater than or equal to a preset correlation coefficient threshold is taken as the target component.

[0059] In detail, the calculation of the correlation coefficient between each modal function component and the original vibration response signal using the Pearson correlation coefficient includes:

[0060] The correlation coefficient between each modal function component and the original vibration response signal is calculated using the following formula:

[0061]

[0062] Where r represents the correlation coefficient, n represents the sum of the modal function components, σx represents the standard score, mean value and standard deviation of the i-th modal function component, X i It is represented as the function vector obtained by transforming the i-th modal function component. σy represents the standard score, mean value and standard deviation of the original vibration response signal, and Y represents the signal vector obtained by transforming the original vibration response signal.

[0063] In detail, the modal function components and the original vibration response signal can be converted into a vector form using a word embedding method such as a one-hot model, a bag-of-words model, etc., to facilitate subsequent correlation coefficient calculation.

[0064] In the embodiment of the present invention, the preset correlation coefficient criterion is used to more clearly understand the degree of explanation of the IMF component to the original vibration response signal and the strength of the linear relationship between the two. The IMF component with a high correlation coefficient screened out by the present invention contains most of the information in the original signal, determines the importance of each frequency component, and facilitates the subsequent extraction of signal components related to the corrugation characteristics.

[0065] In the embodiment of the present invention, reconstructing the target component to obtain a preprocessed signal includes:

[0066] Obtain all local maximum and minimum points of the target component;

[0067] Using an interpolation method to create a smooth curve between all the local maximum and minimum points to obtain an envelope;

[0068] The envelope is multiplied by the target component and then summed to obtain a preprocessed signal.

[0069] In detail, the envelope refers to a smoothed version of the modal function component, which can be used to estimate the local amplitude of the signal. The present invention utilizes each modal function component and the corresponding envelope to reconstruct the signal, and any features of the original signal will not be lost during the reconstruction process.

[0070] The present invention effectively reconstructs the target component to obtain a preprocessed signal that meets the expectations. During the reconstruction process, noise and interference are eliminated to improve signal quality. At the same time, the target component is selected to achieve effective data compression, thereby improving signal processing efficiency.

[0071] In the embodiment of the present invention, the target component is screened out from the modal function components according to a preset correlation coefficient criterion, data compression is achieved, and the signal processing speed is accelerated; at the same time, the vibration response signal related to the corrugation characteristics can be effectively extracted, providing an accurate and reliable signal processing basis for further analysis; and the target component is reconstructed to eliminate noise interference, ensure the integrity of the signal to improve the signal quality, thereby obtaining a preprocessed signal.

[0072] S3. Perform time-frequency analysis on the preprocessed signal to obtain a time-frequency ridge line, and cut out a corrugation section according to the vibration response signal located by the time-frequency ridge line.

[0073] In the embodiment of the present invention, the time-frequency analysis refers to performing a short-time Fourier transform on the preprocessed signal to convert the signal into the time-frequency domain for operation. The time-frequency ridge line refers to the line connecting the points with the highest power in the time-frequency diagram obtained from the short-time Fourier transform, which is used as the time-frequency ridge line.

[0074] In the embodiment of the present invention, reconstructing the target component to obtain a preprocessed signal includes:

[0075] Obtain all local maximum and minimum points of the target component;

[0076] Using an interpolation method to create a smooth curve between all the local maximum and minimum points to obtain an envelope;

[0077] The envelope is multiplied by the target component and then summed to obtain a preprocessed signal.

[0078] In detail, the short-time Fourier transform is performed using the following formula:

[0079]

[0080] Where x(τ) represents the preprocessed signal, h(τ-t) represents the analysis window function, and e -j2πτ represents the kernel function of the Fourier short-time transform, f is the frequency, t is the time, and j is the imaginary unit. The analysis window function is used to divide the preprocessed signal into shorter time periods, including a rectangular window, a Hanning window, and the like.

[0081] The present invention calculates the power spectrum by short-time Fourier transform, plots the power spectrum as a function of time and frequency to form a time-frequency diagram, forms a frequency ridge line by connecting the points with the highest power in the time-frequency diagram, and superimposes the frequency ridge line on the time-frequency diagram to obtain the time-frequency ridge line. The extraction of the time-frequency ridge line helps to accurately identify corrugation and facilitates the subsequent precise positioning of the corrugation position.

[0082] In an embodiment of the present invention, the step of extracting the corrugation section according to the vibration response signal located by the time-frequency ridge line includes:

[0083] Selecting the vibration response signal position where the time-frequency ridge exceeds a preset positioning threshold;

[0084] The corrugation section is cut out according to the position of the vibration response signal to obtain wavelength information.

[0085] In detail, the present invention determines the position where the frequency exceeds the threshold in the time-frequency ridge by presetting the positioning threshold, cuts out the corrugation section of the vibration response signal after positioning, and uses fast Fourier transform FFT to extract the main frequency, thereby calculating the wavelength.

[0086] In the embodiment of the present invention, the corrugation positioning method based on short-time Fourier transform can accurately locate the position of corrugation in the vibration response signal. The present invention utilizes the periodicity of corrugation to filter out the influence of stripping blocks and weld defects, and completes the calculation of wavelength by extracting frequency.

[0087] In an embodiment of the present invention, time-frequency analysis is performed on the preprocessed signal to accurately capture the change of frequency in the signal over time, thereby improving the accuracy of signal analysis; the obtained time-frequency ridge positioning vibration response signal is intercepted from the wave grinding section, which can make the wave grinding positioning fast and intuitive, thereby improving processing efficiency and automation, and accelerating response and decision support.

[0088] S4. Extracting the time domain features of the corrugation section, and generating a corrugation depth level result according to the time domain features.

[0089] In an embodiment of the present invention, the time domain characteristics refer to the characteristics of a signal changing over time, including the maximum value, minimum value, average value, peak-to-peak value, root mean square amplitude, variance, standard deviation, effective value, degree of sharpness, skewness, waveform factor, peak factor, pulse factor, margin factor, and clearance factor of the vibration response signal.

[0090] In the embodiment of the present invention, generating a wave depth level result according to the time domain characteristics includes:

[0091] Acquire wave depth information according to the time domain characteristics;

[0092] Calculate the correlation coefficient between each waveform index and the wave depth information;

[0093] The time domain feature whose correlation coefficient is greater than or equal to a preset correlation coefficient threshold is used as a sensitive feature;

[0094] The sensitive features are input into a vector machine classifier to generate a wave depth level result.

[0095] In detail, the waveform index refers to a series of parameters that describe the waveform characteristics, including amplitude, frequency, period, etc. The present invention calculates the correlation coefficient between each waveform index and the wave depth to better analyze the relationship between the time domain characteristics and the wave depth, thereby performing more accurate wave grinding analysis and identification.

[0096] In detail, the sensitive feature refers to the time domain feature whose correlation coefficient is greater than or equal to the predetermined correlation coefficient threshold, including absolute mean, variance, degree of sharpness, waveform factor, clearance factor, and information entropy. The sensitive feature is used as a combined feature, and the vehicle speed information and wavelength information are added as additional features to input into the vector machine classifier SVM to generate the wavelength depth level result.

[0097] In the embodiment of the present invention, the wave depth information is obtained by measuring the peak-to-peak value and effective value of the time domain characteristics, wherein the peak-to-peak value refers to the difference between the maximum value and the minimum value of the signal, reflecting the amplitude of the signal fluctuation; the effective value refers to the statistic of the signal fluctuation, indicating the strength or power of the signal. The present invention understands the fluctuation amplitude and strength of the signal by measuring the peak-to-peak value and effective value, thereby obtaining the signal wave depth information.

[0098] In an embodiment of the present invention, time domain features in a signal are extracted by using zero-crossing rate or statistical values. After all time domain features are extracted, the Pearson correlation coefficient method is used to calculate all correlation coefficients with the wave depth. The correlation coefficients are compared with preset correlation coefficient thresholds one by one to obtain sensitive features. The vehicle speed information and the extracted wavelength information are then input as additional features into a vector machine classifier to complete the evaluation of the degree of wave wear degradation, thereby generating a wave depth level result.

[0099] In the embodiment of the present invention, by extracting the time domain characteristics of the corrugation section, the time domain characteristics of the signal such as amplitude, distribution, and morphology can be fully reflected, which is helpful to evaluate and classify the wave depth level from the time domain perspective. The present invention takes into account the influence of vehicle speed and wavelength on the change of the signal in the time domain, and inputs the vehicle speed information and the extracted wavelength information as additional features into the vector machine classifier to improve the accuracy of wave depth level recognition.

[0100] The embodiment of the present invention decomposes the original vibration response signal to obtain the modal function components, which can more easily identify and remove the noise and interference components in the signal and reduce the complexity of subsequent calculations; selects the target components from the modal function components according to a preset correlation coefficient criterion, and reconstructs them to obtain the preprocessed signal, thereby realizing data compression and accelerating the signal processing speed; performs time-frequency analysis on the preprocessed signal to obtain the time-frequency ridge line, and cuts out the corrugation section according to the vibration response signal located by the time-frequency ridge line, thereby improving the accuracy of signal analysis and processing efficiency; extracts the time domain characteristics of the corrugation section and generates the wave depth level result, which can comprehensively analyze the time domain characteristics of the signal and improve the accuracy of wave depth level recognition, thereby realizing the recognition of the level of corrugation degradation.

[0101] In some implementations of this embodiment, a computer-readable storage medium is provided, on which a computer program is stored, characterized in that when the computer program is executed by a processor, the steps of the method described in the above embodiment are implemented.

[0102] In some implementations of this embodiment, a computer program product is provided, including a computer program / instructions, characterized in that when the computer program is executed by a processor, the steps of the method described in the above embodiment are implemented.

[0103] The processor may include, but is not limited to, one or more processors or microprocessors, etc. Each processor may be an application specific integrated circuit (ASIC), a digital signal processor (DSP), a digital signal processing device (DSPD), a programmable logic device (PLD), a field programmable gate array (FPGA), a controller, a microcontroller, a microprocessor or other electronic components to execute the methods in the above embodiments.

[0104] The computer-readable storage medium may be implemented by any type of volatile or non-volatile storage device or a combination thereof. The computer-readable storage medium may include, but is not limited to, for example, random access memory (RAM), read-only memory (ROM), flash memory, EPROM memory, EEPROM memory, registers, computer storage media (e.g., hard disk, floppy disk, solid-state drive, removable disk, CDROM, DVDROM, Blu-ray disc, etc.).

[0105] The computer-readable storage medium may also store at least one computer executable program / instruction, which may be, for example, a computer-readable instruction. The computer-readable storage medium includes, but is not limited to, for example, a volatile memory and / or a non-volatile memory. The volatile memory may include, for example, a random access memory (RAM) and / or a cache memory (cache), etc. The computer-readable storage medium may include, for example, a read-only memory (ROM), a hard disk, a flash memory, etc. For example, a non-transitory computer-readable storage medium may be connected to a computing device such as a computer, and then, when the computing device runs the computer-readable instructions stored on the computer-readable storage medium, the various methods described above may be performed.

[0106] In one embodiment, the at least one computer executable instruction may also be compiled into or constitute a software product / computer program product, wherein one or more computer executable instructions are executed by a processor to perform the various functions and / or method steps in the embodiments described in the present technology.

[0107] In the embodiments provided in the present disclosure, it should be understood that the disclosed devices and methods can also be implemented in other ways. The device embodiments described above are merely schematic. For example, the flowcharts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the devices, methods and computer program products according to multiple embodiments of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of a code, and the above-mentioned module, program segment or a part of the code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart can be implemented with a dedicated hardware-based system that performs a specified function or action, or can be implemented with a combination of dedicated hardware and computer instructions.

[0108] It should be noted that in the present disclosure, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element limited by the sentence "includes a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element.

[0109] Although the embodiments disclosed in the present disclosure are as above, the above contents are only embodiments adopted for facilitating the understanding of the present disclosure and are not intended to limit the present disclosure. Any technician in the technical field to which the present disclosure belongs can make any modifications and changes in the form and details of the implementation without departing from the spirit and scope disclosed in the present disclosure, but the scope of patent protection of the present disclosure shall still be subject to the scope defined in the attached claims.

Claims

1. A rail corrugation detection and identification method, characterized in that: The method comprises: Acquire an original vibration response signal, and decompose the original vibration response signal to obtain a modal function component; Filtering out a target component from the modal function components according to a preset correlation coefficient criterion, and reconstructing the target component to obtain a preprocessed signal; Performing time-frequency analysis on the preprocessed signal to obtain a time-frequency ridge line, and cutting out a corrugation section according to a vibration response signal located by the time-frequency ridge line; The time domain characteristics of the corrugation section are extracted, and the wave depth level results are generated according to the time domain characteristics.

2. The method according to claim 1, characterized in that Decomposing the original vibration response signal to obtain modal function components includes: Using a preset sliding window to intercept the original vibration response signal to obtain a window intercept signal; Performing empirical mode decomposition on the window intercepted signals to obtain the modal function components corresponding to each window intercepted signal.

3. The method according to claim 1, characterized in that The step of selecting the target component from the modal function components according to a preset correlation coefficient criterion includes: The Pearson correlation coefficient is used to calculate the correlation coefficient between each modal function component and the original vibration response signal; The corresponding modal function component whose correlation coefficient is greater than or equal to a preset correlation coefficient threshold is taken as the target component.

4. The method according to claim 1, characterized in that: The step of reconstructing the target component to obtain a preprocessed signal includes: Obtain all local maximum and minimum points of the target component; Using an interpolation method, a smooth curve is created between all the local maximum and minimum points to obtain an envelope; The envelope is multiplied by the target component and then summed to obtain a preprocessed signal.

5. The method according to claim 1, characterized in that The performing time-frequency analysis on the preprocessed signal to obtain a time-frequency ridge line includes: The preprocessed signal is converted into the time-frequency domain using short-time Fourier transform to obtain a time-frequency diagram; A frequency ridge line is extracted from the time-frequency diagram, and the frequency ridge line is superimposed on the time-frequency diagram to obtain a visualized time-frequency ridge line.

6. The method according to claim 1, characterized in that Generating a wave depth level result according to the time domain characteristics includes: Acquire wave depth information according to the time domain characteristics; Calculate the correlation coefficient between each waveform index and the wave depth information; The time domain feature whose correlation coefficient is greater than or equal to a preset correlation coefficient threshold is used as a sensitive feature; The sensitive features are input into a vector machine classifier to generate a wave depth level result.

7. A rail corrugation detection and identification device, characterized in that: include: A signal decomposition module, which acquires an original vibration response signal and decomposes the original vibration response signal to obtain a modal function component; A signal reconstruction module, which selects a target component from the modal function components according to a preset correlation coefficient criterion, and reconstructs the target component to obtain a preprocessed signal; A time-frequency analysis module performs time-frequency analysis on the preprocessed signal to obtain a time-frequency ridge line, and cuts out a corrugation section according to a vibration response signal located by the time-frequency ridge line; The detection and identification module extracts the time domain characteristics of the corrugation section and generates a corrugation depth level result according to the time domain characteristics.

8. A computer device comprising a memory, a processor and a computer program stored in the memory, characterized in that: The processor executes the computer program to implement the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images