High-speed train meeting working condition mark elimination method based on train vibration characteristics

Abstract

The invention discloses a high-speed train meeting working condition mark elimination method based on train vibration characteristics, and relates to the technical field of automatic recognition of high-speed railway locomotive meeting. The method comprises the following steps: acquiring a train transverse vibration acceleration signal acquired based on a vehicle-mounted vibration sensor, and screening; setting positive and negative peak point thresholds and a screening range to screen a target vibration peak point; according to a fixed interval between vibration peak point pairs in two directions in a single vibration in a meeting state, the characteristic that the interval between the first transverse vibration and the second transverse vibration of a vehicle body in the meeting state is relatively stable, and the characteristic that the vibration directions of two middle peak points in adjacent peak point pairs in the meeting state are the same, the transverse vibration of the vehicle body in the meeting state is obtained. And screening positive and negative peak point pairs meeting conditions, and returning the positions of the positive and negative peak point pairs as vehicle meeting identification points. The natural vibration characteristics of the vehicle body are introduced for vehicle meeting state analysis, and the vehicle meeting state can be effectively identified.

Description

Technical Field

[0001] The present invention relates to the technical field of automatic recognition of passing of high - speed railway locomotives, and particularly to a method for eliminating the marking of passing conditions of high - speed trains based on the vibration characteristics of trains. Background Art

[0002] Currently, vertical and lateral vibration acceleration acquisition sensors of the car body are equipped on high - speed trains. These sensors can monitor the vibration of the train at different vehicle speeds and track sections at any time, and the collected vibration data can be used to assist in evaluating the state of the track line. When the sensors detect large - amplitude lateral or vertical vibrations, the system will trigger an alarm and record the relevant data, which is convenient for subsequent maintenance and repair of the track, and thus ensures the safe operation of the EMU.

[0003] During high - speed driving, a train (EMU) may meet another EMU traveling in the same or opposite direction, and this phenomenon is called passing. Due to the change in the aerodynamic characteristics of the EMU during passing, the lateral vibration acceleration of the train will increase sharply, thus generating alarm signals similar to track diseases. These signals may interfere with the judgment of maintenance personnel. If this influence is not recognized and processed in time, it may reduce the accuracy and reliability of the track state evaluation results. Therefore, it is necessary to effectively mark the passing state that appears during the operation of the EMU.

[0004] After retrieval, the existing patent "CN117565930 A method for identifying passing of high - speed trains for on - vehicle line inspection instruments" provides a method for identifying railway passing. First, select the original data of the on - vehicle sensors of a certain train for a period of time, screen out the passing waveforms to form a passing data set, and calculate the average driving speed of the train during each passing; filter the original data to obtain the filtered passing data set; divide the driving speed range, and train the passing waveform recognition parameters for different speed ranges respectively; use the speed data to train the passing correlation threshold in the passing recognition algorithm to analyze the lateral vibration acceleration data of the train and perform passing recognition.

[0005] The technical method of the above - mentioned patent application trains different passing waveform recognition parameters by dividing different train driving speed ranges. This method needs to first determine the driving speed of the train, but it will be found in the actual measurement of the train operation state that the driving speed of the train is not constant. In addition, this patent application locates the passing peak points based on the monitored train mileage data, which requires the format of the monitored data to conform to the specification of this patent application.

[0006] Based on this, the present invention proposes a method for eliminating the marking of passing conditions of high - speed trains based on the vibration characteristics of trains, which is no longer limited by vehicle speed and standardized mileage record data and is more universal. Summary of the Invention

[0007] The present invention provides a method for eliminating the marking of the passing condition of high-speed trains based on the vibration characteristics of trains, including: Obtaining the lateral vibration acceleration signal of the train collected by on-vehicle vibration sensors, and preprocessing the lateral vibration acceleration signal of the train; Performing the following peak screening on the preprocessed lateral vibration acceleration signal of the train: Setting the positive and negative peak point thresholds and the screening range as global screening conditions, and screening the target vibration peak points that meet the global screening conditions; According to the characteristics of the positive and negative peak point pairs where the single vibration always presents positive and negative two-direction vibrations under the passing condition, and the fixed interval between the positive and negative peak point pairs, performing the first local screening on the screened target vibration peak points to obtain the first positive and negative peak point pairs that meet the first local screening conditions; According to the characteristic that the interval between the first lateral vibration of the car body and the second lateral vibration under the passing condition is relatively stable, setting a local screening window between the peak point pairs, and performing the second local screening on the first positive and negative peak point pairs according to the local screening window to screen out the second positive and negative peak point pairs that meet the second local screening conditions; According to the characteristic that the vibration directions of the middle two peak points in the adjacent peak point pairs under the passing condition are the same, performing the third local screening on the second positive and negative peak point pairs to screen out the third positive and negative peak point pairs that meet the third local screening conditions; According to the position information of the third positive and negative peak point pairs, screening out the positive and negative peak point pairs that meet the continuous peak screening conditions, and returning the position of the positive and negative peak point pairs as the passing identification point.

[0008] For the method for eliminating the marking of the passing condition of high-speed trains based on the vibration characteristics of trains as described above, after obtaining the lateral vibration acceleration signal of the train, a time-domain waveform diagram of the original data of the lateral vibration acceleration of the train during the monitoring period is drawn, the time data corresponding to the acceleration is converted into a linearly equally spaced time interpolation array in milliseconds, and the lateral vibration acceleration signal of the train is band-pass filtered.

[0009] For the method for eliminating the marking of the passing condition of high-speed trains based on the vibration characteristics of trains as described above, setting the positive and negative peak point thresholds and the screening range as global screening conditions, and screening the target vibration peak points that meet the global screening conditions specifically means: setting the minimum peak threshold of the positive and negative peak points and the peak point screening range, screening out all positive and negative peak points greater than the minimum peak threshold of the peak points, and finding their corresponding position sequences.

[0010] For the method for eliminating the marking of the passing condition of high-speed trains based on the vibration characteristics of trains as described above, the fixed interval between the two-direction vibration peak point pairs in a single vibration is analyzed and determined by the following method: Statistical analysis of the interval between the positive and negative peak point pairs of the single vibration in the oncoming vehicle state based on measured data; Analysis based on the inherent vibration characteristics of the car body; Determination of the interval between the positive and negative peak point pairs of the single vibration in the oncoming vehicle state based on the train vibration characteristics.

[0011] A method for eliminating the oncoming vehicle condition marks of a high-speed train based on the train vibration characteristics as described above, wherein, screening the second positive and negative peak point pairs, specifically: defining a peak point search threshold, searching for positive peak points that meet the peak point search threshold, and formulating a first local screening window according to the relatively stable characteristic of the interval between the first lateral vibration of the train and the second lateral vibration of the train in the oncoming vehicle state; judging whether the number of negative peak points within the first local screening window is greater than two, if it is greater than two, then retain the peak points that meet the conditions, otherwise, eliminate the peak point pairs including the positive peak point.

[0012] A method for eliminating the oncoming vehicle condition marks of a high-speed train based on the train vibration characteristics as described above, wherein, screening the third positive and negative peak point pairs, specifically: formulating a second local screening window according to the characteristic that the vibration directions of the middle two peak points in the adjacent peak point pairs in the oncoming vehicle state are the same; judging the directions of the latest peak point and the negative peak point found through the second local screening window, if the directions are the same, then take the latest peak point as the target peak point, that is, the third positive and negative peak point pair; otherwise, eliminate the latest peak point until there are no peak points in the local screening window to judge.

[0013] A method for eliminating the oncoming vehicle condition marks of a high-speed train based on the train vibration characteristics as described above, wherein, screening out the positive and negative peak point pairs that meet the continuous peak screening conditions, specifically: continuing to introduce a screening window according to the position information of the third positive and negative peak point pair, if there are more than 3 consecutive peak points in the local screening window, then eliminate them; if the found peak point does not meet the condition that the amplitude of the first vibration is greater than the peak value of the second vibration, then eliminate it; taking the positions of the remaining positive and negative peak point pairs after elimination as the oncoming vehicle identification points.

[0014] The present invention also provides a computer storage medium, including: at least one memory and at least one processor; The memory is used to store one or more program instructions; The processor is used to run one or more program instructions to execute a method for eliminating the oncoming vehicle condition marks of a high-speed train based on the train vibration characteristics described in any one of the above.

[0015] The beneficial effects achieved by the present invention are as follows: The present invention takes the train lateral vibration acceleration data collected by the train on-vehicle vibration monitoring equipment as the research object, and based on the waveform and frequency spectrum characteristics of the train lateral vibration under the train meeting condition, a method for eliminating the meeting condition marks applicable to high-speed trains is developed. Different from the existing research, this method no longer relies on the train running speed to identify the key peak points during meeting, but introduces the inherent vibration characteristics of the car body to analyze the train lateral vibration characteristics during the meeting state, locates and searches for the key peak points based on the sampling frequency of the monitoring data, and thus can effectively identify the meeting state based on the vibration characteristics of the train car body. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required to be used in the description of the embodiments or the prior art. Obviously, the drawings described below are only some embodiments recorded in the present invention, and those of ordinary skill in the art can also obtain other drawings based on these drawings.

[0017] Figure 1 It is a flowchart of a method for eliminating the meeting condition marks of high-speed trains based on the train vibration characteristics provided in Embodiment 1 of the present invention; Figure 2 It shows the time-domain waveform diagram of the train lateral vibration acceleration and the comparison diagram of the screening results after the first peak screening; Figure 3 It is the lateral vibration curve diagram under the meeting condition of the measured train group; Figure 4 It is the cumulative distribution diagram of the lateral acceleration amplitude of the car body at different peak points; Figure 5 It is the comparison diagram of the local peak screening results; Figure 6 It is the final obtained meeting state identification result diagram. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0018] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts fall within the protection scope of the present invention.

[0019] Embodiment 1 As Figure 1 shown, Embodiment 1 of the present invention provides a method for eliminating the meeting condition marks of high-speed trains based on the train vibration characteristics, including: Step 110: Obtain the train lateral vibration acceleration signal collected by the on-vehicle vibration sensor, and preprocess the train lateral vibration acceleration signal; Specifically, after obtaining the train lateral vibration acceleration signal, plot the time-domain waveform of the original data of the train lateral vibration acceleration during the monitoring period, convert the time data corresponding to the acceleration into a linearly equally spaced time interpolation array in milliseconds, and perform band-pass filtering on the train lateral vibration acceleration signal, with the passband range being 2 Hz to 20 Hz.

[0020] Perform the following peak screening operation on the preprocessed train lateral vibration acceleration signal: Step 120: Set the positive and negative peak point thresholds and the screening range as global screening conditions, screen the target vibration peak points that meet the global screening conditions, and remove the invalid points that do not meet the global screening conditions; In the embodiment of the present application, screening the first pair of peak points is specifically: set the minimum peak threshold of the positive and negative peak points and the peak point screening range, screen out all positive and negative peak points greater than the minimum peak threshold of the peak points, and find their corresponding position sequences; The default positive peak point is in the positive direction, and the negative peak point is in the negative direction; set the minimum peak threshold of the positive and negative peak points and the peak point screening range, where the minimum amplitude threshold of the positive and negative peak points is set to 0.013g; screen out all positive peak points greater than the minimum peak threshold of the peak points, and find their corresponding position sequences , then: Wherein, is the position information corresponding to the i-th positive peak point; is the train lateral acceleration amplitude corresponding to the i-th positive peak point; g is the acceleration due to gravity; M is the total length of the positive peak point sequence.

[0021] Figure 2 Shows the comparison diagram of the time-domain waveform of the train lateral vibration acceleration and the screening result after the first peak screening.

[0022] Step 130: According to the characteristics of the positive and negative peak point pairs where the single vibration always presents positive and negative two-direction vibrations during the meeting state, and the fixed interval between the positive and negative peak point pairs, perform the first local screening on the screened target vibration peak points to obtain the first positive and negative peak point pairs that meet the first local screening conditions, and remove the invalid points that do not meet the first local screening conditions; Define the peak point search threshold, search for the positive peak points that meet the peak point search threshold, and formulate the first local screening window according to the relatively stable characteristic of the interval between the first train lateral vibration and the second train lateral vibration during the meeting state; judge whether the number of negative peak points within the first local screening window is greater than two. If it is greater than two, retain the peak points that meet the conditions. Otherwise, remove the peak point pair including the positive peak point.

[0023] Specifically, according to the relatively stable characteristics of the interval between the lateral vibration of the first train and the lateral vibration of the second train in the oncoming state (substituting the vehicle speed of 243 km / h into the calculation and analysis of the time interval between two lateral vibrations during oncoming, the interval between the two vibrations is about 100 m, that is, about half of the vehicle length), a local screening window is formulated, and the window length is , that is: In the formula, the window length is measured by the number of data points; coef is the compensation coefficient, which is taken as 1.1 here; and are the minimum vehicle speed and the maximum vehicle speed, which are taken as 100 km / h and 380 km / h respectively here.

[0024] For example, define the peak point search threshold as 0.007 g, and the selection of this value is determined through data statistical analysis.

[0025] Return to see Figure 1 , step 140: According to the relatively stable characteristics of the interval between the first lateral vibration of the car body and the second lateral vibration in the oncoming state, set a local screening window for the pair of peak points, and perform a second local screening on the first pair of positive and negative peak points according to the local screening window, screen out the second pair of positive and negative peak points that meet the second local screening conditions, and remove the invalid points that do not meet the local screening situation; Figure 3 The figure shows the lateral vibration curve of the measured train group in the oncoming state. The position marked by the dashed box in the figure is the oncoming section.

[0026] It can be seen from the figure that before oncoming, the lateral vibration of the train is relatively stable. The amplitude range of the lateral acceleration of the train is 0 - 0.003 g, and the maximum position is much smaller than the Class I daily maintenance standard of 0.06 g for high-speed railway maintenance management, which indicates that the lateral vibration of the EMU train is stable. When the train travels to 14:57:06, it meets an oncoming train on the adjacent line. At this time, the amplitude of the lateral vibration acceleration of the train increases rapidly and reaches 0.045 g.

[0027] After that, the car body of the train continues to vibrate, and the lateral vibration of the train continues to show an increasing trend, with an amplitude of 0.048 g, which is still much larger than the lateral vibration in the non-oncoming section (amplitude less than 0.003 g). In this vibration, the amplitude of the lateral vibration acceleration of the rear peak point of the train is slightly smaller than that of the front peak point. After that, the vibration of the car body of the train quickly returns to stability. Subsequently, the second lateral vibration occurs. At this time, the time from the occurrence of the first lateral vibration is about 1.5 s, and the peak value of the second lateral vibration is smaller than that of the first lateral vibration.

[0028] From Figure 3It can be seen that when a passing train occurs, the body of the passing train will experience two lateral vibrations with opposite vibration directions, and there are a total of 4 obvious peak points within a certain length range. Moreover, the signs of the 1st and 4th peak points are the same. Through the above research on the passing peak points, the characteristics of the four-peak points under the passing condition are determined.

[0029] Analyze the cumulative distribution of the lateral vibration acceleration amplitudes of the train at different peak points, create a threshold array `thresholds` from 0.005 to 0.1 with a step size of 0.001. This array is used to calculate the percentage of acceleration data less than each threshold in the subsequent calculation. Extract the lateral vibration acceleration amplitudes of the train at all the 1st, 2nd, 3rd, and 4th peak points in the body vibration monitoring data and plot the corresponding cumulative distribution curves. The results are as Figure 4 shown.

[0030] From Figure 4 it can be seen that for almost more than 90% of the peak points among the four vibration peak points under the passing condition, the peak point amplitudes are higher than 0.013g, and there are a few 3rd and 4th peak point amplitudes between 0.007g and 0.013g. Therefore, in the present invention, the global screening threshold is set to 0.013g and the local screening threshold is set to 0.007g.

[0031] Specifically, according to the fixed interval between the vibration peak point pairs in two directions during a single vibration, based on the position of any positive peak point, and then find and determine the position of the negative peak point in its corresponding peak point pair; The fixed interval between the vibration peak point pairs in two directions during a single vibration is specifically analyzed and determined by the following method: ① Statistical analysis of the interval between positive and negative peak point pairs of a single vibration in the passing state based on measured data Statistically analyze the time interval information between the positive and negative peak points of a single vibration in the monitoring data. The results are shown in Table 1. The statistical results show that for the monitoring data, 56.25% of the data shows that the interval time between the peak points of a single vibration is 0.101s, 18.75% of the data shows that the interval time between the peak points of a single vibration is 0.102s, 21.88% of the data shows that the interval time between the peak points of a single vibration is 0.106s, and the remaining 3.12% of the data shows that the interval time between the peak points of a single vibration is 0.121s. Therefore, it can be considered that about 97% of the data shows that the interval time between the peak points of a single vibration in the passing state is 0.1s. Considering the simple harmonic characteristics of the body vibration during passing, it can be considered that when the running train meets the oncoming train, the body of the passing train is affected by the impact force of the passing air flow and then generates a periodic vibration response, and the vibration period is about 0.1s. Further conversion gives the corresponding vibration frequency f as 10Hz.

[0032] Table 1 Statistical distribution of the interval time between peak points of a single vibration in the passing state

[0033] ②Analysis based on the inherent vibration characteristics of the car body For example, introducing the finite element analysis of the vibration characteristics of a certain high-speed rail car body, the research results show that the 7th-order inherent vibration frequency of this model is about 9.7052 Hz. Therefore, it can be considered that when the monitored high-speed rail train meets an oncoming train during operation, the impact air flow between the two trains exactly excites the 7th-order inherent vibration of the car body, thereby triggering a significant increase in the lateral vibration of the car body during meeting.

[0034] ③Determination of the positive and negative peak point pairs of the meeting state based on the vibration characteristics of the train Based on the above-mentioned inherent vibration characteristics of the car body, the present invention proposes that the interval between the positive and negative peak points in a single vibration can be obtained by converting the sampling frequency of the monitoring data, and is no longer limited by the train speed and the monitoring data format. The inherent resonance frequency of the car body is introduced and the sampling frequency of the monitoring data , and a screening range for finding the peak point in the opposite direction corresponding to a certain peak point is formulated, that is In the formula is the range of the number of interval points for finding the negative peak point before and after any positive peak point is the lower limit of the range is the upper limit of the range; is the sampling frequency of this monitoring data, which is taken as 200 Hz here; is the inherent resonance frequency of the car body caused by the meeting of oncoming trains. Through statistical analysis, here is taken as 9.7 Hz; ceil() is the ceiling function.

[0035] Step 150: According to the characteristic that the vibration directions of the middle two peak points in the adjacent peak point pairs of the meeting state are the same, perform a third local screening on the second positive and negative peak point pairs, screen out the third positive and negative peak point pairs that meet the third local screening conditions, and remove the peak points that do not meet the third local screening conditions; According to the characteristic that the vibration directions of the middle two peak points in the adjacent peak point pairs in the meeting state are the same, formulate a second local screening window; judge the direction of the latest peak point found through the second local screening window and the negative peak point. If the directions are the same, take the latest peak point as the third positive and negative peak point pair; otherwise, remove the latest peak point until there are no peak points to judge in this local screening window.

[0036] Step 160: According to the position information of the third positive and negative peak point pairs, screen out the positive and negative peak point pairs that meet the continuous peak screening conditions, and return the position of the positive and negative peak point pairs as the meeting identification point.

[0037] Based on the above steps, all peak points that meet the conditions such as peak threshold, single vibration peak interval, and interval between two vibrations can be found. However, there are still single-point vibration peaks and multi-point continuous vibration peak interferences caused by passing through turnouts. Therefore, based on the vibration characteristics during passing, the present invention further designs and introduces local screening conditions on the basis of the above screening, that is: Condition 1: If there are more than 3 consecutive peak points in the local screening window, they are excluded. Condition 2: If the found peak point does not satisfy that the amplitude of the first vibration is greater than the peak value of the second vibration, it is excluded.

[0038] For example, based on the position and amplitude information of 4 peak points in the third group of peak point pairs, according to the characteristics that the amplitudes of the 1st and 2nd peak points are greater than those of the 3rd and 4th peak points under the passing condition, the information of the above 4 peak points is finally determined, named the 1st, 2nd, 3rd, and 4th peak points respectively, and the position of the 1st peak point is returned as the passing identification point.

[0039] The following is a specific implementation example of the present invention: Taking the operation of a train on a certain line under the jurisdiction of a certain railway bureau as an example for analysis and research, using the original lateral vibration acceleration data of on-vehicle sensors, the time-domain waveform diagram of its lateral vibration acceleration is obtained by using MATLAB software, and the number of passing times of this train and oncoming trains can be obtained through the monitoring data of the train lateral vibration acceleration curve; One day, about 1.8 million pieces of on-vehicle vibration acquisition signals (sampling frequency is 200Hz, and the total sampling time is 150 minutes) are analyzed, and the lateral vibration curve of the train during the monitoring period from 13:38 to 16:07 is monitored. According to the monitoring data, it can be known that the train had a total of 16 passing times with oncoming trains during this period.

[0040] The first group of passing peak point pairs that meet the conditions obtained after the initial screening of the filtered lateral vibration acceleration of the train Figure 2 It can be seen that there are 24 pairs of peak point pairs that meet the conditions screened out by the first peak point, and the number is significantly more than the number of passing times of the train. Therefore, further screening of the peak points is required. Figure 5 This is a comparison diagram of the results of local peak screening. It can be seen from the figure that there are 18 pairs of peak point pairs that meet the conditions after screening. Compared with the results of the first screening, the number of peak point pairs that meet the conditions after this screening is significantly reduced. Figure 6 This is the identification result diagram of the passing state finally obtained. For the 16 passing records in the data, 14 passing conditions are accurately captured by applying the method proposed in the present invention, and the accuracy rate is 87.5%. It basically meets the requirements of the automatic identification technology for passing of high-speed railway locomotives. Subsequently, it is planned to optimize and adjust the screening parameters in the invention based on the big data of train operation monitoring in order to improve the passing identification accuracy. The present invention is simple to implement, has a wide application range, and a high accuracy rate.

[0041] Corresponding to the above embodiments, an embodiment of the present invention provides a computer storage medium, including: at least one memory and at least one processor; The memory is used to store one or more program instructions; The processor is used to run one or more program instructions to execute a method for eliminating the marking of the meeting condition of high-speed trains based on the vibration characteristics of trains.

[0042] Corresponding to the above embodiments, an embodiment of the present invention provides a computer-readable storage medium. The computer storage medium contains one or more program instructions, and the one or more program instructions are used to be executed by a processor to execute a method for eliminating the marking of the meeting condition of high-speed trains based on the vibration characteristics of trains.

[0043] An embodiment disclosed by the present invention provides a computer-readable storage medium. Computer program instructions are stored in the computer-readable storage medium. When the computer program instructions run on a computer, the computer is enabled to execute the above-mentioned method for eliminating the marking of the meeting condition of high-speed trains based on the vibration characteristics of trains.

[0044] In the embodiment of the present invention, the processor may be an integrated circuit chip with signal processing capabilities. The processor may be a general-purpose processor, a digital signal processor (DSP for short), an application-specific integrated circuit (ASIC for short), a field-programmable gate array (FPGA for short), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0045] It can implement or execute the various methods, steps and logic block diagrams disclosed in the embodiments of the present invention. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The steps of the method disclosed in combination with the embodiments of the present invention may be directly embodied as being executed by a hardware decoding processor, or executed by a combination of hardware and software modules in the decoding processor. The software module may be located in a mature storage medium in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. The processor reads the information in the storage medium and combines its hardware to complete the steps of the above method.

[0046] The storage medium may be a memory, for example, it may be a volatile memory or a non-volatile memory, or may include both a volatile memory and a non-volatile memory.

[0047] Among them, the non-volatile memory can be a Read-Only Memory (ROM), a Programmable ROM (PROM), an Erasable PROM (EPROM), an Electrically Erasable PROM (EEPROM), or a flash memory.

[0048] The volatile memory can be a Random Access Memory (RAM), which is used as an external cache. By way of example but not limitation, many forms of RAM are available, such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDR SDRAM), Enhanced SDRAM (ESDRAM), Synchlink DRAM (SLDRAM), and Direct Rambus RAM (DRRAM).

[0049] The storage media described in the embodiments of the present invention are intended to include, but are not limited to, these and any other suitable types of memories.

[0050] Those skilled in the art should be able to realize that in one or more of the above examples, the functions described in the present invention can be implemented by a combination of hardware and software. When applying software, the corresponding functions can be stored in a computer-readable medium or transmitted as one or more instructions or codes on a computer-readable medium. The computer-readable medium includes computer storage media and communication media, where the communication media includes any medium that facilitates the transmission of a computer program from one place to another. The storage media can be any available medium that can be accessed by a general-purpose or special-purpose computer.

[0051] The specific embodiments described above further elaborate on the objectives, technical solutions, and beneficial effects of the present invention. It should be understood that the above are only specific embodiments of the present invention and are not used to limit the protection scope of the present invention. Any modifications, equivalent replacements, improvements, etc. made on the basis of the technical solutions of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for eliminating the marking of the passing condition of high-speed trains based on the vibration characteristics of trains, characterized in that, Including: Obtain the train lateral vibration acceleration signal collected by the on-vehicle vibration sensor, and preprocess the train lateral vibration acceleration signal; Perform the following peak screening on the preprocessed train lateral vibration acceleration signal: Set the positive and negative peak point thresholds and the screening range as the global screening conditions, and screen the target vibration peak points that meet the global screening conditions; According to the characteristics of the positive and negative peak point pairs where the single vibration always presents positive and negative vibrations in both directions during the meeting state, and the fixed interval between the positive and negative peak point pairs, perform the first local screening on the screened target vibration peak points to obtain the first positive and negative peak point pairs that meet the first local screening conditions; According to the characteristic that the interval between the first lateral vibration of the car body and the second lateral vibration is relatively stable during the meeting state, set the local screening window between the peak point pairs, and perform the second local screening on the first positive and negative peak point pairs according to the local screening window to screen out the second positive and negative peak point pairs that meet the second local screening conditions; According to the characteristic that the vibration directions of the middle two peak points in the adjacent peak point pairs are the same during the meeting state, perform the third local screening on the second positive and negative peak point pairs to screen out the third positive and negative peak point pairs that meet the third local screening conditions; According to the position information of the third positive and negative peak point pairs, screen out the positive and negative peak point pairs that meet the continuous peak screening conditions, and return the position of the positive and negative peak point pairs as the meeting recognition point.

2. The method for eliminating the marking of the passing condition of a high-speed train based on the vibration characteristics of the train according to claim 1, characterized in that, After obtaining the train lateral vibration acceleration signal, draw the time-domain waveform diagram of the original data of the train lateral vibration acceleration during the monitoring period, convert the time data corresponding to the acceleration into a linearly equally spaced time interpolation array in milliseconds, and perform band-pass filtering on the train lateral vibration acceleration signal.

3. The high-speed train passing condition marking elimination method based on train vibration characteristics according to claim 1, characterized in that Set the positive and negative peak point thresholds and the screening range as the global screening conditions, and screen the target vibration peak points that meet the global screening conditions. Specifically: set the minimum peak threshold of the positive and negative peak points and the peak point screening range, screen out all positive and negative peak points greater than the minimum peak threshold of the peak points, and find their corresponding position sequences.

4. The method for eliminating the marking of the passing condition of a high-speed train based on the vibration characteristics of the train according to claim 3, wherein, The fixed interval between the two-direction vibration peak point pairs in a single vibration is determined by the following method: Statistical analysis of the interval between the positive and negative peak point pairs of the single vibration in the meeting state based on the measured data; Analysis based on the inherent vibration characteristics of the car body; Determination of the interval between the positive and negative peak point pairs of the single vibration in the meeting state based on the train vibration characteristics.

5. The method for eliminating the marking of the passing condition of a high-speed train based on the vibration characteristics of the train according to claim 4, characterized in that Screen the second positive and negative peak point pairs. Specifically: define the peak point search threshold, search for the positive peak points that meet the peak point search threshold, and formulate the first local screening window according to the characteristic that the interval between the first train lateral vibration and the second train lateral vibration is relatively stable during the meeting state; judge whether the number of negative peak points within the first local screening window is greater than two. If it is greater than two, retain the peak points that meet the conditions. Otherwise, remove the peak point pairs including the positive peak point.

6. The method for eliminating the marking of the passing condition of a high-speed train based on the vibration characteristics of the train according to claim 5, characterized in that, Screen the third pair of positive and negative peak points, specifically: according to the feature that the vibration directions of the middle two peak points in the adjacent peak point pairs of the meeting state are the same, formulate a second local screening window; judge the directions of the latest peak point and the negative peak point found through the second local screening window. If the directions are the same, take the latest peak point as the target peak point, that is, the third pair of positive and negative peak points; otherwise, eliminate the latest peak point until there are no peak points in this local screening window to judge.

7. The method for eliminating the marking of the passing condition of a high-speed train based on the vibration characteristics of the train according to claim 6, wherein, Screen out the pairs of positive and negative peak points that meet the continuous peak screening conditions, specifically: according to the position information of the third pair of positive and negative peak points, continue to introduce a screening window. If there are more than 3 consecutive peak points in the local screening window, eliminate them; if the found peak point does not satisfy that the first vibration amplitude is greater than the second vibration peak, eliminate it; take the positions of the remaining pairs of positive and negative peak points after elimination as the meeting recognition points.

8. A computer storage medium, characterized in that, Including: At least one memory and at least one processor; The memory is used to store one or more program instructions; The processor is used to run one or more program instructions to execute a method for eliminating the marking of the meeting condition of a high-speed train based on the vibration characteristics of the train as described in any one of claims 1-7.

Images