Railway track detection method, device, equipment and medium
By combining acoustic signal detection with adaptive filters and minimum variance unbiased estimation algorithms, the problem of damage detection in track sections without electrical circuits is solved, achieving efficient and accurate track damage detection in complex environments.
Patent Information
- Application Number
- CN202411174781.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-26
- Publication Date
- 2024-11-15
AI Technical Summary
Existing technologies are insufficient for effectively detecting track damage in sections of track without electrical circuits, especially in scenarios where track circuits are not installed. This makes it impossible to accurately assess the health condition of the track, thus affecting train operation safety.
An acoustic signal detection method is used to acquire signals from receiving nodes on the track. Then, an adaptive filter and a minimum variance unbiased estimation algorithm are used to perform spectral estimation, generate a power spectral density map of the track, and determine whether the track is damaged.
It improves the accuracy and efficiency of track damage detection, enables long-distance detection in complex track environments, reduces the impact on track bed conditions, reduces the amount of subsequent maintenance, and eliminates the need for long-distance cable laying.
Smart Images

Figure CN118961882A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of railway track detection, and in particular to a railway track detection method, device, equipment and medium. Background Art
[0002] Tracks are an important basic carrier of rail transit, and their health directly affects railway transportation and the safety of people's lives and property. Track status is easily affected by factors such as temperature changes, train load pressure, and geological changes, which can cause damage and breakage of the tracks, seriously affecting the safety of train operation. Track circuits are currently the main basic equipment that carries the function of broken track inspection, but there are still many scenarios where track circuits are not installed, and there is an urgent need to solve the problem of damage detection of track sections without circuit lines. Summary of the invention
[0003] The present invention provides a railway track detection method, device, equipment and medium to solve the problem of damage detection of track sections without circuit lines.
[0004] According to one aspect of the present invention, there is provided a railway track detection method, comprising:
[0005] Acquire a target mixed signal obtained by a first receiving node on the first track collecting the acoustic wave signal sent by the first sending node, and acquire a target reference signal obtained by a second receiving node on the second track collecting the acoustic wave signal sent by the first sending node;
[0006] According to a pre-trained adaptive filter, the target mixed signal and the target reference signal are processed to obtain a target prediction signal; wherein the adaptive filter is trained by using the mixed signal on the first track and the reference signal on the second track;
[0007] Using a minimum variance unbiased estimation algorithm to perform spectrum estimation on the target prediction signal to obtain a power spectrum density diagram of the target prediction signal;
[0008] Whether the first track is damaged is determined according to the power spectrum density diagram, and the first track is a track to be detected currently.
[0009] According to another aspect of the present invention, there is provided a railway track detection device, a data processing device deployed in a railway track detection system, comprising:
[0010] A signal acquisition module, used to acquire a target mixed signal obtained by a first receiving node on a first track collecting an acoustic wave signal sent by a first sending node, and to acquire a target reference signal obtained by a second receiving node on a second track collecting an acoustic wave signal sent by the first sending node;
[0011] A prediction module, used for processing the target mixed signal and the target reference signal according to a pre-trained adaptive filter to obtain a target prediction signal; wherein the adaptive filter is obtained by training the adaptive filter using the mixed signal on the first track and the reference signal on the second track;
[0012] A spectrum estimation module, used for performing spectrum estimation on the target prediction signal by using a minimum variance unbiased estimation algorithm to obtain a power spectrum density diagram of the target prediction signal;
[0013] The judgment module is used to judge whether the first track is damaged according to the power spectrum density diagram, and the first track is the current track to be detected.
[0014] According to another aspect of the present invention, a computer program product is provided, comprising a computer program, wherein when the computer program is executed by a processor, the railway track detection method according to any embodiment of the present invention is implemented.
[0015] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:
[0016] at least one processor; and
[0017] a memory communicatively connected to the at least one processor; wherein,
[0018] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the railway track detection method described in any embodiment of the present invention.
[0019] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the railway track detection method described in any embodiment of the present invention when executed.
[0020] The embodiment of the present invention realizes railway track damage detection based on the characteristic changes of the acoustic wave signal. Compared with the electrical signal detection method, the track damage inspection based on the acoustic wave method has a longer distance, is less affected by the roadbed conditions, has a small amount of later maintenance, can support damage positioning, does not require long-distance cable laying, and can better meet the needs of long-distance track damage inspection in complex line environment sections. The adaptive filtering technology is applied to the denoising of the railway track acoustic wave signal, and the adaptive filter is trained by combining the receiving node signals on the two tracks. According to the pre-trained adaptive filter, the receiving end signal on the current track to be detected is denoised, which can improve the signal-to-noise ratio of the receiving end signal and obtain a more accurate power spectrum density diagram of the target prediction signal. The embodiment of the present invention has a wide range of applicability to noise types in the railway environment, such as white noise, non-stationary noise, vehicle passing noise, burst interference noise, and power frequency interference, which have good denoising effects and improve the efficiency and accuracy of track damage detection.
[0021] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS
[0022] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.
[0023] Figure 1A is a first flow chart of a railway track detection method provided by an embodiment of the present invention;
[0024] Figure 1B is a schematic diagram of the structure of a railway track detection system provided by an embodiment of the present invention;
[0025] Figure 2 is a second flow chart of the railway track detection method provided by an embodiment of the present invention;
[0026] Figure 3 is a third flow chart of the railway track detection method provided by an embodiment of the present invention;
[0027] Figure 4 is a schematic structural diagram of a railway track detection device provided by an embodiment of the present invention;
[0028] Figure 5 It is a schematic diagram of the structure of an electronic device implementing an embodiment of the present invention. DETAILED DESCRIPTION
[0029] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.
[0030] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.
[0031] Figure 1A This is the first flow chart of the railway track detection method provided by the embodiment of the present invention. This embodiment is applicable to the case of detecting railway tracks. The method can be applied to data processing equipment in the railway track detection system, can be executed by a railway track detection device, can be implemented in the form of hardware and / or software, and the device can be configured in an electronic device with corresponding data processing capabilities. Figure 1A As shown, the method includes:
[0032] S110, obtaining a target mixed signal obtained by a first receiving node on a first track collecting an acoustic wave signal sent by a first sending node, and obtaining a target reference signal obtained by a second receiving node on a second track collecting an acoustic wave signal sent by the first sending node.
[0033] Railway tracks are usually composed of multiple tracks, for example, Figure 1BAs shown, a sending node 10 and a receiving node 20 are sequentially arranged on the track along the direction of the railway track, and the sending node on the track to be detected sends an acoustic wave signal, and the receiving node on the track to be detected collects the acoustic wave signal on the track to be detected as a target mixed signal, and the receiving nodes on other tracks collect the acoustic wave signal on the track as a target reference signal, which is used to detect the state of the track within the interval between the sending node and the receiving node. Taking two parallel tracks in the railway track as an example, the track on one side to be detected is recorded as the first track, and the track on the other side is recorded as the second track. The first sending node and the first receiving node are arranged on the first track. The second sending node and the second receiving node are arranged on the second track. When the first track is detected, the first sending node sends an acoustic wave signal, the first receiving node collects the acoustic wave signal on the first track as a target mixed signal, and the second receiving node collects the acoustic wave signal on the second track as a target reference signal. The target mixed signal includes the acoustic wave signal transmitted through the first track and the noise in the environment, and the target reference signal includes the acoustic wave signal transmitted through the second track and the noise in the environment.
[0034] In an optional embodiment, the railway track detection system also includes a sending end trackside node and a receiving end trackside node, and the acoustic wave signal is generated in the following manner: the sending end trackside node sends a source electrical signal to the first sending node; the first sending node converts the source electrical signal into an acoustic wave signal of a specific frequency.
[0035] Continue to refer Figure 1B The railway track detection system also includes a sending end trackside node 30 and a receiving end trackside node 40. The sending end trackside node 30 is connected to a power source 50 and each sending node, and the receiving end trackside node 40 is connected to a power source 50 and each receiving node. The sending end trackside node sends a source electrical signal to the first sending node, and the first sending node converts the acquired source electrical signal into an acoustic wave signal of a specific frequency. The track is used as a propagation medium for the acoustic wave signal, and the acoustic wave is used to detect the damage of the track. Compared with the electrical signal detection method, the acoustic wave-based track damage inspection has a longer distance, is less affected by the roadbed conditions, requires less maintenance in the later stage, can support damage location, does not require long-distance cable laying, and can better meet the needs of long-distance track damage inspection in complex line environment sections.
[0036] Correspondingly, the method of obtaining a target mixed signal obtained by collecting the acoustic wave signal sent by the first sending node by the first receiving node on the first track, and obtaining a target reference signal obtained by collecting the acoustic wave signal sent by the first sending node by the second receiving node on the second track, include: respectively obtaining the target mixed signal and the target reference signal from the trackside node at the receiving end; wherein, the target mixed signal is obtained by the trackside node at the receiving end from the first receiving node, and the target reference signal is obtained by the trackside node at the receiving end from the second receiving node.
[0037] Specifically, the first receiving node collects the acoustic wave signal on the first track and converts the acoustic wave signal into an electrical signal as a target mixed signal. The second receiving node collects the acoustic wave signal on the second track and converts the acoustic wave signal into an electrical signal as a target reference signal. The receiving end trackside node obtains the target mixed signal from the first receiving node, obtains the target reference signal from the second receiving node, and sends the target mixed signal and the target reference signal to the data processing device.
[0038] The present invention detects railway track damage based on the characteristic changes of acoustic wave signals. Compared with the electrical signal detection method, the track damage inspection based on the acoustic wave method has a longer distance, is less affected by the roadbed conditions, requires less subsequent maintenance, can support damage location, does not require long-distance cable laying, and can better meet the needs of long-distance track damage inspection in complex line environment sections.
[0039] S120. According to a pre-trained adaptive filter, the target mixed signal and the target reference signal are processed to obtain a target prediction signal; wherein the adaptive filter is obtained by training the adaptive filter using the mixed signal on the first track and the reference signal on the second track.
[0040] Specifically, the adaptive filter is trained in advance according to the mixed signal on the first track and the reference signal on the second track to obtain the optimal filter parameters of the adaptive filter. According to the optimal filter parameters of the adaptive filter, the target mixed signal and the target reference signal are processed to obtain the target prediction signal. The target prediction signal is the sound wave signal after the target mixed signal is denoised, that is, the sound wave signal sent by the first sending node is transmitted to the first receiving node via the first track. The state of the first track between the first sending node and the first receiving node is determined according to the target prediction signal.
[0041] S130, using a minimum variance unbiased estimation algorithm to perform spectrum estimation on the target prediction signal to obtain a power spectrum density diagram of the target prediction signal.
[0042] Specifically, the minimum variance unbiased estimation algorithm is used to predict the target signal X * Perform spectrum estimation to obtain the power spectrum density diagram of the target prediction signal. The formula is as follows:
[0043]
[0044] Among them, the target prediction signal X * The sequence is x * (m), m = 0, 1, 2, ..., N-1, N is the sequence length of the target prediction signal, ω is the angular frequency. *(m) is divided into L segments, each segment length is N / L rounded, denoted by T. * (m) can form a L×T matrix. Rx is x * (m) Correlation matrix, the matrix dimension is L×L. Rx -1 is the inverse matrix of Rx. a(ω) is the angle vector at frequency ω, a(ω)=[1,e -jω , e -2-jω ,...e -(L-1)-jω ] T ,a H (ω) is the transpose of a(ω).
[0045] P(ω) is the power spectrum density when the angular frequency is ω. By converting the angular frequency to the corresponding frequency (in Hertz), the power spectrum density of the target prediction signal at each frequency can be obtained.
[0046] By using the minimum variance unbiased estimation algorithm to perform spectrum estimation on the target prediction signal, the problem of low frequency resolution caused by main lobe broadening and side lobe leakage when using the periodogram method to perform spectrum estimation on the target prediction signal can be overcome. The resolution of power spectrum estimation and frequency positioning accuracy are improved.
[0047] S140. Determine whether the first track is damaged according to the power spectrum density diagram, the first track being a current track to be detected.
[0048] Specifically, in the power spectrum density diagram, observe the power distribution in different frequency bands. If the track is damaged, there will often be an abnormal increase or decrease in power in certain specific frequency bands. Extract characteristic indicators related to damage, such as the average power and maximum power in a specific frequency band. Compare the extracted characteristic indicators with the power spectrum density diagram characteristics of the normal track to determine whether there are significant differences. If there are significant differences, and this difference is consistent with the known track damage characteristics, it can be preliminarily determined that the track is damaged.
[0049] The embodiment of the present invention realizes railway track damage detection based on the characteristic changes of the acoustic wave signal. Compared with the electrical signal detection method, the track damage inspection based on the acoustic wave method has a longer distance, is less affected by the roadbed conditions, has a small amount of later maintenance, can support damage positioning, does not require long-distance cable laying, and can better meet the needs of long-distance track damage inspection in complex line environment sections. The adaptive filtering technology is applied to the denoising of the railway track acoustic wave signal, and the adaptive filter is trained by combining the receiving node signals on the two tracks. According to the pre-trained adaptive filter, the receiving end signal on the current track to be detected is denoised, which can improve the signal-to-noise ratio of the receiving end signal and obtain a more accurate power spectrum density diagram of the target prediction signal. The embodiment of the present invention has a wide range of applicability to noise types in the railway environment, such as white noise, non-stationary noise, vehicle passing noise, burst interference noise, and power frequency interference, which have good denoising effects and improve the efficiency and accuracy of track damage detection. By using the minimum variance unbiased estimation algorithm to perform spectrum estimation on the target prediction signal, the problem of low frequency resolution caused by main lobe broadening and side lobe leakage when using the periodogram method to perform spectrum estimation on the target prediction signal can be overcome. The resolution of power spectrum estimation and frequency positioning accuracy are improved.
[0050] Figure 2 2 is a second flow chart of the railway track detection method provided by an embodiment of the present invention. This embodiment is optimized and improved on the basis of the above embodiment. Figure 2 As shown, the method includes:
[0051] S210 , using the mixed signal on the first track and the reference signal on the second track to train the adaptive filter, inputting the reference signal into the adaptive filter to be trained, and obtaining a noise signal.
[0052] Specifically, when the first transmitting node on the first track transmits a sine wave with a frequency of f, the first receiving node on the first track continuously collects the acoustic wave signal as a mixed signal. The second receiving node on the second track continuously collects the acoustic wave signal as a reference signal. The adaptive filter can use a finite impulse response (FIR) filter. Set the length of the FIR filter to M, and initialize the filter parameter w(0) = [0,0,…0] T , set the learning rate μ and the number of iterations Iter. Input the reference signal into the adaptive filter to be trained to obtain the noise signal. The specific formula is as follows:
[0053] y(i)=w T (i)-x2(i) (2)
[0054] Among them, w T(i) is the parameter of the filter at the i-th iteration, x2(i) is the signal sequence of the reference signal X2 participating in the training at the i-th iteration, and y(i) is the noise signal at the i-th iteration.
[0055] Exemplarily, for training of the adaptive filter, in the i-th iteration round, the signal interval processed in the i-th iteration round is determined based on the tail signal identifier and processing window length processed in the i-1-th iteration round; the processing window length is the same as the length of the adaptive filter.
[0056] Correspondingly, x2(i) is the signal sequence in the signal interval processed by the reference signal X2 in the i-th iteration round, x2(i) = [x2 (0+i) ,x2 (1+i) ,…,x2 (M-1+i) ] T For example, if the length of the signal sequence is 1000 and the processing window length is 10, then in the first iteration, the signal data from the 1st to the 10th bit is intercepted for training, in the second iteration, the signal data from the 2nd to the 11th bit is intercepted for training, in the third iteration, the signal data from the 3rd to the 12th bit is intercepted for training, and so on. The processing window moves back one bit in each iteration.
[0057] S220: Compare and subtract the noise signal from the mixed signal to obtain a target signal.
[0058] S230: Update filter parameters according to the target signal and the reference signal, and stop training the adaptive filter until the target signal reaches a steady state.
[0059] Referring to the following formula (3), the noise signal in the mixed signal can be filtered out to obtain the target signal; and referring to the following formula (4), the filter parameters are updated according to the target signal and the reference signal:
[0060] e(i)=x1(i)-y(i) (3)
[0061] w(i+1)=w(i)+2μx2(i)e(i) (4)
[0062] Among them, x1(i) is the signal sequence of the mixed signal X1 participating in the training at the i-th iteration, x1(i) = [x1 (0+i) ,x1 (1+i) ,…,x1 (M-1+i) ] T , e(i) is the target signal at the i-th iteration. μ is the learning rate, which controls the learning speed of the filter parameters and can be set based on experience, for example, it can be set to 0.05, 0.1, etc.
[0063] Iteratively update the filter parameters w(i) until i = Iter, the training is completed, and the optimal filter parameters w are obtained * By applying adaptive filtering technology to the denoising of railway track acoustic signals, combining the receiving node signals on the two tracks, training the adaptive filter, and fully considering factors such as acoustic signal characteristics, real-time requirements, stability and convergence, and noise characteristics, the signal-to-noise ratio of the receiving end signal can be improved.
[0064] S240, obtaining a target mixed signal obtained by a first receiving node on the first track collecting the acoustic wave signal sent by the first sending node, and obtaining a target reference signal obtained by a second receiving node on the second track collecting the acoustic wave signal sent by the first sending node.
[0065] S250 . Process the target mixed signal and the target reference signal according to a pre-trained adaptive filter to obtain a target prediction signal.
[0066] S260 , performing spectrum estimation on the target prediction signal using a minimum variance unbiased estimation algorithm to obtain a power spectrum density diagram of the target prediction signal.
[0067] S270. Determine whether the first track is damaged according to the power spectrum density diagram, the first track being a current track to be detected.
[0068] The embodiment of the present invention applies adaptive filtering technology to the denoising of railway track acoustic wave signals, and trains an adaptive filter by combining the receiving node signals on the two tracks. The receiving end signal on the current track to be detected is denoised according to the pre-trained adaptive filter, and factors such as acoustic wave signal characteristics, real-time requirements, stability and convergence, and noise characteristics are fully considered. The signal-to-noise ratio of the receiving end signal can be improved. The embodiment of the present invention has a wide range of applicability to noise types in the railway environment, such as white noise, non-stationary noise, passing noise, burst interference noise, and power frequency interference, etc., all of which have good denoising effects, thereby improving the efficiency and accuracy of track damage detection.
[0069] Figure 3 is a third flow chart of the railway track detection method provided by an embodiment of the present invention. This embodiment is optimized and improved on the basis of the above embodiments. Figure 3 As shown, the method includes:
[0070] S310, obtaining a target mixed signal obtained by a first receiving node on a first track collecting an acoustic wave signal sent by a first sending node, and obtaining a target reference signal obtained by a second receiving node on a second track collecting an acoustic wave signal sent by the first sending node.
[0071] S320: Filter the target reference signal according to a pre-trained adaptive filter to obtain a target noise signal.
[0072] The adaptive filter is obtained by training the adaptive filter using the mixed signal on the first track and the reference signal on the second track.
[0073] Specifically, the optimal filter parameter w of the pre-trained adaptive filter is obtained * , filter the target reference signal to obtain the target noise signal. The specific formula is as follows:
[0074] y′=w* T X2′ (5)
[0075] Among them, w * is the optimal filter parameter, x2' is the target reference signal, and y' is the target noise signal.
[0076] S330 , denoising the target mixed signal according to the target noise signal to obtain a target prediction signal with noise interference removed.
[0077] Specifically, the target mixed signal is denoised according to the target noise signal to obtain a target prediction signal without noise interference. The specific formula is as follows:
[0078] X * =x1′-y′ (6)
[0079] Among them, x1' is the target mixed signal, y' is the target noise signal, X * Predict the target signal.
[0080] S340 , performing spectrum estimation on the target prediction signal using a minimum variance unbiased estimation algorithm to obtain a power spectrum density diagram of the target prediction signal.
[0081] S350: Determine whether the first track is damaged according to the power spectrum density diagram, the first track being the current track to be detected.
[0082] In an optional embodiment, the method also includes: obtaining a specific frequency of the sound wave signal sent by the first sending node as a positioning frequency; determining whether the power spectrum density at the positioning frequency in the power spectrum density diagram is within a preset range; if the power spectrum density is within the preset range, determining that the first track is not damaged between the first sending node and the first receiving node.
[0083] The power spectrum density diagram can clearly show how the signal power changes with frequency. By judging whether the power spectrum density at the positioning frequency is within the preset range, it is possible to accurately determine whether the track is damaged. Acoustic signals are not affected by electromagnetic effects, so they can maintain high detection accuracy even in complex electromagnetic environments. By adjusting the frequency and detection parameters of the acoustic signal, different types of track damage can be detected, such as cracks, fractures, and wear. The method of using the specific frequency and power spectrum density diagram of the acoustic signal for track damage detection has the advantages of high accuracy, strong anti-interference ability, strong real-time performance, wide application range, and low cost.
[0084] The embodiment of the present invention obtains a target noise signal by filtering a target reference signal according to a pre-trained adaptive filter. The target mixed signal is denoised according to the target noise signal to obtain a target prediction signal with noise interference removed. The target prediction signal is spectrally estimated using the minimum variance unbiased estimation algorithm to obtain a power spectrum density diagram of the target prediction signal, and whether the first track is damaged is determined according to the power spectrum density diagram. The adaptive filtering technology is applied to the denoising of the acoustic wave signal of the railway track, and the adaptive filter is trained by combining the receiving node signals on the two tracks. The receiving end signal on the current track to be detected is denoised according to the pre-trained adaptive filter, and factors such as acoustic wave signal characteristics, real-time requirements, stability and convergence, and noise characteristics are fully considered. The signal-to-noise ratio of the receiving end signal can be improved, and the embodiment of the present invention has a wide range of applicability to noise types in the railway environment, such as white noise, non-stationary noise, vehicle passing noise, burst interference noise, and power frequency interference, all of which have good denoising effects. At the same time, when extracting the spectral information of the target prediction signal, the minimum variance unbiased estimation algorithm is used instead of the traditional periodogram method, which makes the spectral resolution of the signal better, avoids the leakage of side lobes and the broadening of the main lobe, thereby improving the efficiency and accuracy of track damage detection.
[0085] Figure 4 Schematic diagram of the structure of the railway track detection device provided by the embodiment of the present invention. The device is deployed in the data processing equipment of the railway track detection system, such as Figure 4 As shown, the device comprises:
[0086] The signal acquisition module 410 is used to acquire a target mixed signal obtained by the first receiving node on the first track collecting the acoustic wave signal sent by the first sending node, and to acquire a target reference signal obtained by the second receiving node on the second track collecting the acoustic wave signal sent by the first sending node;
[0087] A prediction module 420 is used to process the target mixed signal and the target reference signal according to a pre-trained adaptive filter to obtain a target prediction signal; wherein the adaptive filter is trained by using the mixed signal on the first track and the reference signal on the second track;
[0088] A spectrum estimation module 430 is used to perform spectrum estimation on the target prediction signal using a minimum variance unbiased estimation algorithm to obtain a power spectrum density diagram of the target prediction signal;
[0089] The judgment module 440 is used to judge whether the first track is damaged according to the power spectrum density diagram, and the first track is the current track to be detected.
[0090] The railway track detection device provided in the embodiment of the present invention can execute the railway track detection method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.
[0091] Optionally, the prediction module includes:
[0092] The training unit is used to input the reference signal into the adaptive filter to be trained to obtain a noise signal; compare the noise signal with the mixed signal and perform a difference to obtain a target signal; update the filter parameters according to the target signal and the reference signal until the target signal reaches a steady state and stops training the adaptive filter.
[0093] Optionally, the training unit is also used to determine, in the i-th iteration round, the signal interval processed in the i-th iteration round based on the tail signal identifier and processing window length processed in the i-1-th iteration round; the processing window length is the same as the length of the adaptive filter.
[0094] Optionally, the prediction module further includes:
[0095] The prediction unit is used to filter the target reference signal according to a pre-trained adaptive filter to obtain a target noise signal; and denoise the target mixed signal according to the target noise signal to obtain a target prediction signal with noise interference removed.
[0096] Optionally, the judgment module is specifically used to: obtain the specific frequency of the sound wave signal sent by the first sending node as the positioning frequency; determine whether the power spectrum density at the positioning frequency in the power spectrum density diagram is within a preset range; if the power spectrum density is within the preset range, determine that the first track is not damaged in the interval between the first sending node and the first receiving node.
[0097] Optionally, the railway track detection system also includes a sending end trackside node and a receiving end trackside node, and the signal acquisition module is also used for: the sending end trackside node sends a source electrical signal to the first sending node; the first sending node converts the source electrical signal into an acoustic wave signal of a specific frequency.
[0098] Optionally, the signal acquisition module is specifically used to: respectively acquire the target mixed signal and the target reference signal from the receiving end trackside node; wherein, the target mixed signal is acquired by the receiving end trackside node from the first receiving node, and the target reference signal is acquired by the receiving end trackside node from the second receiving node.
[0099] The railway track detection device further described can also execute the railway track detection method provided by any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.
[0100] Figure 5 A schematic diagram of an electronic device 50 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.
[0101] like Figure 5 As shown, the electronic device 50 includes at least one processor 51, and a memory connected to the at least one processor 51 in communication, such as a read-only memory (ROM) 52, a random access memory (RAM) 53, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 51 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 52 or the computer program loaded from the storage unit 58 to the random access memory (RAM) 53. In the RAM 53, various programs and data required for the operation of the electronic device 50 can also be stored. The processor 51, the ROM 52, and the RAM 53 are connected to each other via a bus 54. An input / output (I / O) interface 55 is also connected to the bus 54.
[0102] A number of components in the electronic device 50 are connected to the I / O interface 55, including: an input unit 56, such as a keyboard, a mouse, etc.; an output unit 57, such as various types of displays, speakers, etc.; a storage unit 58, such as a disk, an optical disk, etc.; and a communication unit 59, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 59 allows the electronic device 50 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.
[0103] The processor 51 may be a variety of general and / or dedicated processing components with processing and computing capabilities. Some examples of the processor 51 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 51 executes the various methods and processes described above, such as a railway track detection method.
[0104] In some embodiments, the railway track detection method may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 58. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 50 via the ROM 52 and / or the communication unit 59. When the computer program is loaded into the RAM 53 and executed by the processor 51, one or more steps of the railway track detection method described above may be performed. Alternatively, in other embodiments, the processor 51 may be configured to execute the railway track detection method in any other appropriate manner (e.g., by means of firmware).
[0105] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.
[0106] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.
[0107] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
[0108] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).
[0109] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.
[0110] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.
[0111] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.
[0112] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims
1. A railway track detection method, characterized in that: The method is performed by a data processing device in a railway track detection system, and includes: Acquire a target mixed signal obtained by a first receiving node on the first track collecting the acoustic wave signal sent by the first sending node, and acquire a target reference signal obtained by a second receiving node on the second track collecting the acoustic wave signal sent by the first sending node; According to a pre-trained adaptive filter, the target mixed signal and the target reference signal are processed to obtain a target prediction signal; wherein the adaptive filter is trained by using the mixed signal on the first track and the reference signal on the second track; Using a minimum variance unbiased estimation algorithm to perform spectrum estimation on the target prediction signal to obtain a power spectrum density diagram of the target prediction signal; Whether the first track is damaged is determined according to the power spectrum density diagram, and the first track is a track to be detected currently.
2. The method according to claim 1, characterized in that: The adaptive filter is trained in the following way: Inputting the reference signal into an adaptive filter to be trained to obtain a noise signal; Compare the noise signal with the mixed signal and perform subtraction to obtain a target signal; The filter parameters are updated according to the target signal and the reference signal, and the training of the adaptive filter is stopped until the target signal reaches a steady state.
3. The method according to claim 2, characterized in that The method further comprises: In the i-th iteration round, the signal interval processed in the i-th iteration round is determined according to the tail signal identifier processed in the i-1-th iteration round and the processing window length; the processing window length is the same as the length of the adaptive filter.
4. The method according to claim 1, characterized in that: The step of processing the target mixed signal and the target reference signal according to the pre-trained adaptive filter to obtain a target prediction signal includes: Filtering the target reference signal according to a pre-trained adaptive filter to obtain a target noise signal; The target mixed signal is denoised according to the target noise signal to obtain a target prediction signal without noise interference.
5. The method according to claim 1, characterized in that The determining whether the first track is damaged according to the power spectrum density diagram includes: Acquire a specific frequency of the sound wave signal sent by the first sending node as a positioning frequency; Determine whether the power spectrum density at the positioning frequency in the power spectrum density graph is within a preset range; if the power spectrum density is within the preset range, determine that the first track is not damaged between the first sending node and the first receiving node.
6. The method according to claim 1, characterized in that The railway track detection system also includes a transmitting end trackside node and a receiving end trackside node, and the acoustic wave signal is generated in the following manner: The transmitting end trackside node transmits a source electrical signal to the first transmitting node; the first transmitting node converts the source electrical signal into a sound wave signal of a specific frequency.
7. The method according to claim 6, characterized in that The step of acquiring a target mixed signal obtained by a first receiving node on a first track collecting a sound wave signal sent by a first sending node, and acquiring a target reference signal obtained by a second receiving node on a second track collecting a sound wave signal sent by the first sending node, comprises: The target mixed signal and the target reference signal are respectively obtained from the trackside node at the receiving end; wherein the target mixed signal is obtained from the first receiving node by the trackside node at the receiving end, and the target reference signal is obtained from the second receiving node by the trackside node at the receiving end.
8. A railway track detection device, characterized in that: A data processing device deployed in a railway track detection system, the device comprising: A signal acquisition module, used to acquire a target mixed signal obtained by a first receiving node on a first track collecting an acoustic wave signal sent by a first sending node, and to acquire a target reference signal obtained by a second receiving node on a second track collecting an acoustic wave signal sent by the first sending node; A prediction module is used to process the target mixed signal and the target reference signal according to a pre-trained adaptive filter to obtain a target prediction signal; wherein the adaptive filter is obtained by training the adaptive filter using the mixed signal on the first track and the reference signal on the second track; A spectrum estimation module, used for performing spectrum estimation on the target prediction signal by using a minimum variance unbiased estimation algorithm to obtain a power spectrum density diagram of the target prediction signal; The judgment module is used to judge whether the first track is damaged according to the power spectrum density diagram, and the first track is the current track to be detected.
9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the railway track detection method according to any one of claims 1 to 7.
10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the railway track detection method according to any one of claims 1 to 7 when executed.
Citation Information
Cited By
Steel rail damage positioning method, device, equipment and medium
CN121656394A
