Method and system for estimating instantaneous speed of train

Abstract

The invention provides a train instantaneous speed estimation method and system, and belongs to the technical field of rail transit operation monitoring, and the method comprises the steps: collecting a vertical or transverse dynamic displacement signal of a steel rail, and dividing the time domain dynamic displacement data of a certain measurement channel into a plurality of sliding window subsequences according to a fixed length; smoothing each sliding window sub-sequence in sequence to obtain a de-noising smooth waveform of the complete signal; performing wave crest detection on the obtained smooth waveform, and determining the position of a signal wave crest; serialization processing is carried out according to the time sequence, and every two adjacent wave crests are paired so as to judge the bogie and the carriage; and reversely calculating the instantaneous speed of the train according to the identified wave crest time interval and the time difference when each bogie passes by in combination with the train marshalling number, the train fixed distance and the wheelbase information. The method can effectively estimate the instantaneous running speed of each compartment of the train, and has good self-adaptability to signals under the influence of various random parameters.

Description

Technical Field

[0001] This invention relates to the field of rail transit operation monitoring technology, specifically to a method and system for estimating instantaneous train speed based on adaptive threshold filtering. Background Technology

[0002] With the continuous development of urban rail transit, train condition monitoring and track and environmental vibration testing require extensive on-site testing. Besides obtaining target test indicators, it is also necessary to accurately acquire the actual operating speed of the train during testing for further data analysis and processing. However, it is difficult to accurately measure the actual operating speed of each train during testing. While existing train speed measurement methods such as onboard GNSS receivers, axle counters, Doppler radar, or laser velocimeters perform well in many scenarios, they also have limitations in certain specific environments. For example, these devices and their daily maintenance require significant investment, which may not be the optimal choice for users with limited funds; in areas with complex coverage conditions such as underground shield tunnels and deep foundation pits, GNSS signals may occasionally weaken or even be briefly interrupted; and in measurement points with complex track structures and limited space, such as switch areas, axle counters are insufficient for practical measurement applications. Furthermore, although the Train Control System (ATO) continuously monitors and records train speed, it is difficult for third-party testing personnel to obtain authorization from the operating company to share this data. The speeds publicly released by the operating department are usually the average or nominal operating speed of the train, and there is currently no accurate and convenient method for measuring the instantaneous operating speed of the train during actual measurement. Summary of the Invention

[0003] The purpose of this invention is to provide a method and system for estimating the instantaneous speed of a train, so as to solve at least one of the technical problems existing in the background art.

[0004] To achieve the above objectives, the present invention adopts the following technical solution:

[0005] In a first aspect, the present invention provides a method for estimating the instantaneous speed of a train, comprising:

[0006] The vertical or lateral dynamic displacement signals of the rail are collected using a strain gauge and a multi-channel data acquisition instrument, and the time-domain dynamic displacement data of a certain measurement channel is divided into multiple sliding window sub-sequences according to a fixed length.

[0007] Each sliding window subsequence is smoothed sequentially to obtain a denoised and smoothed waveform of the complete signal. The smoothing process for each sliding window subsequence includes: for each sliding window, taking the center point of the window as the processing object, selecting a preset number of data points before and after it, fitting the signal with a low-order polynomial within the window, solving the coefficients of the fitted polynomial using the least squares method, and then calculating and outputting the smoothing function value at the center of the window.

[0008] Peak detection is performed on the obtained smooth waveform to determine the location of the signal peak;

[0009] The signal waveform peaks whose positions have been determined are serialized in chronological order, and adjacent peaks are paired to identify bogies and cars. Based on the train formation number, vehicle spacing and wheelbase information, the instantaneous speed of the train is calculated in reverse according to the time difference when each bogie passes, based on the identified peak time interval.

[0010] As a further limitation of the first aspect of the present invention, peak detection is performed on the obtained smooth waveform to determine the position of the signal peak, including: calculating the median of the original complete signal sequence and the absolute deviation of each sampling point from the median, and using the median of the absolute deviation sequence as the absolute deviation of the median; estimating the signal standard deviation based on the Gaussian normal distribution theory and the conversion relationship between the absolute deviation of the median and the standard deviation; and combining significance judgment, adaptive height threshold and time interval restriction rules to perform adaptive threshold judgment on the smooth waveform to determine the position of the signal peak.

[0011] As a further limitation of the first aspect of the present invention, the time-domain data sequence of rail dynamic displacement is used as the raw signal for train speed estimation.

[0012] As a further limitation of the first aspect of the present invention, the number of points of the sliding window is selected based on the peak feature width and the sampling frequency.

[0013] As a further limitation of the first aspect of the present invention, the adaptive threshold parameter for peak determination is determined by using the median absolute deviation of the original time-domain signal sequence.

[0014] As a further limitation of the first aspect of the present invention, the peak value for significance judgment should be higher than a certain multiple of the background signal and selected according to the signal characteristics; the adaptive height threshold should be lower than a certain standard deviation of the overall median of the data; and the minimum peak interval protection value should be slightly greater than the time it takes for two adjacent axles to pass.

[0015] In a second aspect, the present invention provides a train instantaneous speed estimation system, comprising:

[0016] The preprocessing module is used to collect the vertical or lateral dynamic displacement signals of the rail using strain gauges in conjunction with a multi-channel data acquisition instrument, and to divide the time-domain dynamic displacement data of a certain measurement channel into multiple sliding window subsequences according to a fixed length.

[0017] The smoothing module is used to smooth each sliding window subsequence sequentially to obtain a denoised and smoothed waveform of the complete signal. The smoothing process for each sliding window subsequence sequentially includes: for each sliding window, taking the center point of the window as the processing object, selecting a preset number of data points before and after it, fitting the signal with a low-order polynomial within the window, solving the coefficients of the fitted polynomial by the least squares method, and then calculating and outputting the smoothing function value at the center of the window.

[0018] The peak detection module is used to detect the peaks of the obtained smooth waveform and determine the location of the signal peaks.

[0019] The calculation module is used to serialize the peak values ​​of the signal waveform whose positions have been determined according to time sequence, and pair adjacent peaks to identify bogies and cars; combined with the train formation number, vehicle spacing and wheelbase information, the instantaneous speed of the train is calculated in reverse according to the time difference when each bogie passes, based on the identified peak time interval.

[0020] Thirdly, the present invention provides a non-transitory computer-readable storage medium for storing computer instructions, which, when executed by a processor, implement the instantaneous train speed estimation method as described in the first aspect.

[0021] Fourthly, the present invention provides a computer device including a memory and a processor, wherein the processor and the memory communicate with each other, the memory stores program instructions that can be executed by the processor, and the processor calls the program instructions to execute the instantaneous train speed estimation method as described in the first aspect.

[0022] Fifthly, the present invention provides an electronic device, comprising: a processor, a memory, and a computer program; wherein the processor is connected to the memory, the computer program is stored in the memory, and when the electronic device is running, the processor executes the computer program stored in the memory to cause the electronic device to execute instructions for implementing the instantaneous train speed estimation method as described in the first aspect.

[0023] The beneficial effects of this invention are as follows: It employs strain gauges and a multi-channel data acquisition system to acquire time-domain data of the vertical or lateral dynamic displacement of the rails. Signal denoising and smoothing are achieved through a 51-point sliding window and third-order polynomial least-squares fitting. Subsequently, a peak detection threshold is adaptively determined based on the relationship between the median absolute deviation (MAD) and Gaussian distribution, and peaks are accurately identified by combining significance and minimum interval protection rules. Finally, a self-developed Python program, combined with vehicle distance and wheelbase parameters, maps the time difference between adjacent peaks to known distances, accurately calculating the instantaneous operating speed of each bogie and car. This method achieves an average error of less than 3% in instantaneous speed estimation in simulation experiments and field tests, possessing advantages such as high precision, high robustness, and high automation. It can be widely applied to operation monitoring and safety assessment of high-speed railways, subways, and urban rail transit.

[0024] The advantages of additional aspects of the invention will be set forth more clearly in the following description or will be learned by practice of the invention. Attached Figure Description

[0025] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0026] Figure 1 This is a flowchart of the train instantaneous speed estimation method according to an embodiment of the present invention.

[0027] Figure 2 This is a diagram showing the layout of strain gauge measuring points in a subway tunnel according to an embodiment of the present invention.

[0028] Figure 3 This is a schematic diagram of the original time-domain data sequence of rail dynamic displacement and the division of the sliding window according to an embodiment of the present invention.

[0029] Figure 4 This is a schematic diagram of the waveform after the original signal has been denoised and smoothed using the Savitzky-Golay method as described in an embodiment of the present invention.

[0030] Figure 5 This is a schematic diagram of all peak positions identified by the adaptive threshold determination method described in an embodiment of the present invention.

[0031] Figure 6 This is a block diagram illustrating the principle of train structural feature identification and calculation in the speed estimation system described in this embodiment of the invention.

[0032] Figure 7This is a verification result diagram of an example of using the method and program system described in this embodiment of the invention to calculate the speed of the simulation results. Detailed Implementation

[0033] Embodiments of the present invention are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and should not be construed as limiting the present invention.

[0034] It will be understood by those skilled in the art that, unless otherwise defined, all terms used herein (including technical and scientific terms) have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0035] It should also be understood that terms such as those defined in general dictionaries should be understood to have meanings consistent with their meanings in the context of the prior art, and should not be interpreted in an idealized or overly formal sense unless defined as here.

[0036] Those skilled in the art will understand that, unless specifically stated otherwise, the singular forms “a,” “an,” “the,” and “the” used herein may also include the plural forms. It should be further understood that the term “comprising” as used in this specification means the presence of the stated features, integers, steps, operations, elements, and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, and / or groups thereof.

[0037] In the description of this specification, references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the present invention. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of those different embodiments or examples.

[0038] To facilitate understanding of the present invention, the present invention will be further explained and described below with reference to the accompanying drawings and specific embodiments. However, the specific embodiments do not constitute a limitation on the embodiments of the present invention.

[0039] Those skilled in the art should understand that the accompanying drawings are merely schematic diagrams of embodiments, and the components in the drawings are not necessarily essential for implementing the present invention.

[0040] This invention proposes a method and system for estimating the instantaneous speed of a train. The method includes the following steps: First, using a strain gauge displacement sensor to measure the original time-domain signal sequence of the dynamic displacement of the train as it passes a measuring point. Based on the Savitzky-Golay principle, a sliding window of a certain length is used to process each sub-sequence of the time-domain signal sequentially. Within each sliding window, a low-order polynomial is used to perform least-squares fitting on the data, and the value of the fitted polynomial at the center point of the window is taken as the differential result at that point. This achieves smooth denoising of discrete signals containing high-frequency noise while preserving the local characteristics of the signal. Next, a judgment threshold is adaptively determined using the median absolute deviation method to accurately identify peaks caused by wheel-rail interaction in the denoised waveform, eliminating outliers or spurious peaks caused by noise. Finally, a self-developed program is used to intelligently estimate the instantaneous speed of each train carriage as it passes, combining parameters such as train distance and wheelbase. This invention can effectively estimate the instantaneous operating speed of each train carriage and has good adaptability to signals affected by various random parameters.

[0041] Example 1

[0042] In this embodiment 1, a method for estimating the instantaneous speed of a train is provided. The steps of this method include:

[0043] S1. Preprocess the raw signals measured on-site. This step includes:

[0044] S11. Use strain gauges in conjunction with a multi-channel data acquisition instrument to measure the vertical or lateral dynamic displacement of the rail.

[0045] S12. Divide the dynamic displacement time domain data sequence under a certain channel into subsequences using a sliding window of fixed length.

[0046] S13. Within each sliding window, with a certain processing point as the center, select a certain number of data points before and after it, and fit the signal using a low-order polynomial within that window.

[0047] S14. The least squares method is used to determine the polynomial coefficients. Based on the fitted polynomial, the function value at the center of the window is calculated as the smoothing result for that point.

[0048] S14. Process the data in each sliding window sequentially using the same method to obtain the entire signal denoising and smoothing waveform.

[0049] S2. Perform adaptive threshold determination of the peak of the processed waveform. This step includes:

[0050] S21. Calculate the median of the original complete signal sequence and the absolute deviation of each data point in the sequence from the median.

[0051] S22. Based on the above absolute deviation data sequence, calculate the median of the sequence, denoted as the median absolute deviation (MAD).

[0052] S23. Based on the Gaussian normal distribution theory, calculate the standard deviation according to the relationship between the median absolute deviation (MAD) and the standard deviation.

[0053] S24. Formulate rules such as significance judgment, adaptive height threshold, and time limit restriction to determine the location of the peak.

[0054] S3. Estimate the train speed using a self-developed program. This step includes:

[0055] S31. The peak values ​​of the waveform processed by the above steps are time-series processed, and the peak values ​​are paired according to the time between adjacent peaks to enable the program to judge the bogie and the car.

[0056] S32. Based on the vehicle's fixed distance and wheelbase information during on-site testing, and combined with the peak time interval identified by the program, the speed of each bogie passing through is estimated to achieve an approximation of the instantaneous speed.

[0057] In this embodiment, a custom-written program was developed to analyze the above process, allowing the system to output the instantaneous speed of each train car by inputting the train formation quantity, distance, and wheelbase information. The custom-written program system uses the train's distance and wheelbase parameters to estimate speed, and uses wheelbase intervals to estimate instantaneous speed.

[0058] In step S11, the rail dynamic displacement time-domain data sequence, rather than the easily disturbed vibration acceleration, is used as the original signal for train speed estimation. In step S12, the selection of the number of sliding window points is mainly based on the peak characteristic width and sampling frequency, requiring it to be slightly larger than the full width at half maximum (FWHM) of a peak in the time-domain signal to reasonably determine the denoising capability. In step S13, the order of the polynomial is selected as a 2nd to 4th order polynomial, and is smaller than the window length to maintain a balance between smoothing effect and waveform preservation capability. In step S22, the median absolute deviation is used to determine the adaptive threshold parameter for peak detection in the original time-domain signal sequence. In step S24, the peak value for significance judgment should be higher than a certain multiple of the background signal, mainly selected based on signal characteristics; the adaptive height threshold should be lower than a certain standard deviation of the overall data median; and the minimum peak interval protection value should be slightly larger than the time it takes for two adjacent axles to pass. This improves the system's adaptability to the signal and effectively prevents missed and false peak detections.

[0059] Example 2

[0060] In this embodiment 2, a train instantaneous speed estimation system is first provided, including: a preprocessing module, used to collect vertical or lateral dynamic displacement signals of the rail using a strain gauge and a multi-channel data acquisition instrument, and to divide the time-domain dynamic displacement data of a certain measurement channel into multiple sliding window sub-sequences according to a fixed length; a smoothing module, used to smooth each sliding window sub-sequence sequentially to obtain a denoised and smoothed waveform of the complete signal; the smoothing of each sliding window sub-sequence sequentially includes: for each sliding window, taking the center point of the window as the processing object, selecting a preset number of data points before and after it, fitting the signal with a low-order polynomial within the window, solving the coefficients of the fitted polynomial using the least squares method, and then calculating and outputting the smoothing function value at the center of the window; and a peak detection module, used to detect the peaks of the obtained smoothed waveform to determine the position of the signal peaks. The calculation module is used to serialize the peak values ​​of the signal waveform whose positions have been determined according to time sequence, and pair adjacent peaks to identify bogies and cars; combined with the train formation number, vehicle spacing and wheelbase information, the instantaneous speed of the train is calculated in reverse according to the time difference when each bogie passes, based on the identified peak time interval.

[0061] By using a self-developed program to process the aforementioned signal processing and speed calculation procedures, an analysis system was created that can automatically output the instantaneous operating speed of each carriage by inputting basic parameters such as the number of train formations, the fixed distance, and the wheelbase. This analysis system not only improves the automation level of data processing but also significantly enhances the efficiency and accuracy of instantaneous speed estimation.

[0062] In this embodiment, a method for estimating the instantaneous speed of a train is implemented using the aforementioned system. This includes: acquiring vertical or lateral dynamic displacement signals of the rails using a strain gauge and a multi-channel data acquisition instrument; dividing the time-domain dynamic displacement data of a measurement channel into multiple sliding window sub-sequences of fixed length; sequentially smoothing each sliding window sub-sequence to obtain a denoised and smoothed waveform of the complete signal; the sequential smoothing of each sliding window sub-sequence includes: for each sliding window, taking the center point of the window as the processing object, selecting a preset number of data points before and after it, fitting the signal with a low-order polynomial within the window, solving for the coefficients of the fitted polynomial using the least squares method, and then calculating and outputting the smoothing function value at the center of the window; performing peak detection on the obtained smoothed waveform to determine the position of the signal peaks; serializing the peak values ​​of the signal waveform with determined positions according to their chronological order, and pairing adjacent peaks to determine the bogies and carriages; combining the train formation number, vehicle spacing, and wheelbase information, and based on the identified peak time intervals, calculating the instantaneous speed of the train in reverse order according to the time difference when each bogie passes.

[0063] The process of detecting peaks in the obtained smooth waveform to determine the location of signal peaks includes: calculating the median of the original complete signal sequence and the absolute deviation of each sampling point from the median, and using the median of the absolute deviation sequence as the absolute deviation of the median; estimating the signal standard deviation based on the Gaussian normal distribution theory and the conversion relationship between the absolute deviation of the median and the standard deviation; and combining significance judgment, adaptive height threshold, and time interval restriction rules to perform adaptive threshold judgment on the smooth waveform to determine the location of signal peaks.

[0064] In this embodiment, the time-domain data sequence of dynamic displacement of the rail, rather than the easily disturbed vibration acceleration, is used as the raw signal for train speed estimation.

[0065] The sliding window is selected as an odd-numbered window with 51 points to balance noise reduction capability and temporal resolution.

[0066] The polynomial order is preferably 3 to balance the signal smoothing effect and waveform preservation capability.

[0067] The adaptive threshold parameter for peak determination is determined by calculating the median absolute deviation (MAD) of the original time-domain signal sequence. Significance is defined as a peak height exceeding four times that of its surrounding data, the adaptive height threshold is defined as being less than twice the standard deviation of the overall signal median, and a minimum peak interval protection of 0.1 seconds is set.

[0068] Example 3

[0069] This embodiment 3 provides a non-transitory computer-readable storage medium for storing computer instructions. When executed by a processor, the computer instructions implement the instantaneous train speed estimation method described above. The method includes:

[0070] The vertical or lateral dynamic displacement signals of the rail are collected using a strain gauge and a multi-channel data acquisition instrument, and the time-domain dynamic displacement data of a certain measurement channel is divided into multiple sliding window sub-sequences according to a fixed length.

[0071] Each sliding window subsequence is smoothed sequentially to obtain a denoised and smoothed waveform of the complete signal. The smoothing process for each sliding window subsequence includes: for each sliding window, taking the center point of the window as the processing object, selecting a preset number of data points before and after it, fitting the signal with a low-order polynomial within the window, solving the coefficients of the fitted polynomial using the least squares method, and then calculating and outputting the smoothing function value at the center of the window.

[0072] Peak detection is performed on the obtained smooth waveform to determine the location of the signal peak;

[0073] The signal waveform peaks whose positions have been determined are serialized in chronological order, and adjacent peaks are paired to identify bogies and cars. Based on the train formation number, vehicle spacing and wheelbase information, the instantaneous speed of the train is calculated in reverse according to the time difference when each bogie passes, based on the identified peak time interval.

[0074] Example 4

[0075] This embodiment 4 provides a computer device, including a memory and a processor, wherein the processor and the memory communicate with each other, and the memory stores program instructions that can be executed by the processor. The processor calls the program instructions to execute the instantaneous train speed estimation method described above, the method including:

[0076] The vertical or lateral dynamic displacement signals of the rail are collected using a strain gauge and a multi-channel data acquisition instrument, and the time-domain dynamic displacement data of a certain measurement channel is divided into multiple sliding window sub-sequences according to a fixed length.

[0077] Each sliding window subsequence is smoothed sequentially to obtain a denoised and smoothed waveform of the complete signal. The smoothing process for each sliding window subsequence includes: for each sliding window, taking the center point of the window as the processing object, selecting a preset number of data points before and after it, fitting the signal with a low-order polynomial within the window, solving the coefficients of the fitted polynomial using the least squares method, and then calculating and outputting the smoothing function value at the center of the window.

[0078] Peak detection is performed on the obtained smooth waveform to determine the location of the signal peak;

[0079] The signal waveform peaks whose positions have been determined are serialized in chronological order, and adjacent peaks are paired to identify bogies and cars. Based on the train formation number, vehicle spacing and wheelbase information, the instantaneous speed of the train is calculated in reverse according to the time difference when each bogie passes, based on the identified peak time interval.

[0080] Example 5

[0081] This embodiment 5 provides an electronic device, including: a processor, a memory, and a computer program; wherein, the processor is connected to the memory, and the computer program is stored in the memory. When the electronic device is running, the processor executes the computer program stored in the memory to cause the electronic device to execute instructions to implement the train instantaneous speed estimation method described above, the method including:

[0082] The vertical or lateral dynamic displacement signals of the rail are collected using a strain gauge and a multi-channel data acquisition instrument, and the time-domain dynamic displacement data of a certain measurement channel is divided into multiple sliding window sub-sequences according to a fixed length.

[0083] Each sliding window subsequence is smoothed sequentially to obtain a denoised and smoothed waveform of the complete signal. The smoothing process for each sliding window subsequence includes: for each sliding window, taking the center point of the window as the processing object, selecting a preset number of data points before and after it, fitting the signal with a low-order polynomial within the window, solving the coefficients of the fitted polynomial using the least squares method, and then calculating and outputting the smoothing function value at the center of the window.

[0084] Peak detection is performed on the obtained smooth waveform to determine the location of the signal peak;

[0085] The signal waveform peaks whose positions have been determined are serialized in chronological order, and adjacent peaks are paired to identify bogies and cars. Based on the train formation number, vehicle spacing and wheelbase information, the instantaneous speed of the train is calculated in reverse according to the time difference when each bogie passes, based on the identified peak time interval.

[0086] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0087] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0088] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0089] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment, whereby a series of operational steps are performed to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0090] While the specific embodiments of the present invention have been described above in conjunction with the accompanying drawings, this is not intended to limit the scope of protection of the present invention. Those skilled in the art should understand that, based on the technical solutions disclosed in the present invention, various modifications or variations that can be made by those skilled in the art without creative effort should be included within the scope of protection of the present invention.

Claims

1. A method for estimating the instantaneous speed of a train, characterized in that, include: The vertical or lateral dynamic displacement signals of the rail are collected using a strain gauge and a multi-channel data acquisition instrument, and the time-domain dynamic displacement data of a certain measurement channel is divided into multiple sliding window sub-sequences according to a fixed length. Each sliding window subsequence is smoothed sequentially to obtain a denoised and smoothed waveform of the complete signal; The smoothing process for each sliding window subsequence includes: for each sliding window, taking the center point of the window as the processing object, selecting a preset number of data points before and after it, fitting the signal with a low-order polynomial within the window, solving the coefficients of the fitted polynomial by the least squares method, and then calculating and outputting the smoothing function value at the center of the window. Peak detection is performed on the obtained smooth waveform to determine the location of the signal peak; The signal waveform peaks whose positions have been determined are serialized in chronological order, and adjacent peaks are paired to identify bogies and cars. Based on the train formation number, vehicle spacing and wheelbase information, the instantaneous speed of the train is calculated in reverse according to the time difference when each bogie passes, based on the identified peak time interval.

2. The method for estimating the instantaneous speed of a train according to claim 1, characterized in that, Peak detection is performed on the obtained smooth waveform to determine the location of the signal peak. This includes: calculating the median of the original complete signal sequence and the absolute deviation of each sampling point from the median, and using the median of the absolute deviation sequence as the median absolute deviation; estimating the signal standard deviation based on the Gaussian normal distribution theory and the conversion relationship between the median absolute deviation and the standard deviation; and combining significance judgment, adaptive height threshold, and time interval restriction rules to perform adaptive threshold judgment on the smooth waveform to determine the location of the signal peak.

3. The method for estimating the instantaneous speed of a train according to claim 1, characterized in that, The time-domain data sequence of rail dynamic displacement is used as the raw signal for train speed estimation.

4. The method for estimating the instantaneous speed of a train according to claim 1, characterized in that, The number of points in the sliding window is selected based on the peak characteristic width and the sampling frequency.

5. The method for estimating the instantaneous speed of a train according to claim 1, characterized in that, An adaptive threshold parameter for peak determination is determined by using the median absolute deviation of the original time-domain signal sequence.

6. The method for estimating the instantaneous speed of a train according to claim 1, characterized in that, The peak value for significance assessment should be a certain multiple higher than the background signal, and should be selected based on the signal characteristics; The adaptive height threshold should be lower than a certain standard deviation of the overall data median; the minimum peak interval protection value should be slightly greater than the time it takes for two adjacent axles to pass each other.

7. A train instantaneous speed estimation system, characterized in that, include: The preprocessing module is used to collect the vertical or lateral dynamic displacement signals of the rail using strain gauges in conjunction with a multi-channel data acquisition instrument, and to divide the time-domain dynamic displacement data of a certain measurement channel into multiple sliding window subsequences according to a fixed length. The smoothing module is used to smooth each sliding window subsequence sequentially to obtain a denoised and smoothed waveform of the complete signal. The smoothing process for each sliding window subsequence includes: for each sliding window, taking the center point of the window as the processing object, selecting a preset number of data points before and after it, fitting the signal with a low-order polynomial within the window, solving the coefficients of the fitted polynomial by the least squares method, and then calculating and outputting the smoothing function value at the center of the window. The peak detection module is used to detect the peaks of the obtained smooth waveform and determine the location of the signal peaks. The calculation module is used to serialize the peak values ​​of the signal waveform whose positions have been determined according to time sequence, and pair adjacent peaks to identify bogies and cars; combined with the train formation number, vehicle spacing and wheelbase information, the instantaneous speed of the train is calculated in reverse according to the time difference when each bogie passes, based on the identified peak time interval.

8. A non-transitory computer-readable storage medium, characterized in that, The non-transitory computer-readable storage medium is used to store computer instructions, which, when executed by a processor, implement the train instantaneous speed estimation method as described in any one of claims 1-6.

9. A computer device, characterized in that, The system includes a memory and a processor, which communicate with each other. The memory stores program instructions that can be executed by the processor, and the processor calls the program instructions to execute the instantaneous train speed estimation method as described in any one of claims 1-6.

10. An electronic device, characterized in that, include: The device includes a processor, a memory, and a computer program; wherein the processor is connected to the memory, the computer program is stored in the memory, and when the electronic device is running, the processor executes the computer program stored in the memory to cause the electronic device to execute instructions that implement the instantaneous train speed estimation method as described in any one of claims 1-6.

Images