A rail vibration reduction system and monitoring method based on electromagnetic induction

Through the track vibration damping system based on electromagnetic induction, adaptive damping force adjustment of train type and driving speed and real-time monitoring of electromagnetic damping devices is achieved, and the poor adaptability and insufficient monitoring methods of track vibration damping devices in the prior art are solved. The problem has improved the effect and reliability of track vibration damping.

CN118932797BActive Publication Date: 2024-12-06GUANGDONG UNIV OF TECH
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
CN202411418235.2
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-10-11
Publication Date
2024-12-06
Estimated Expiration
2044-10-11

AI Technical Summary

Technical Problem

The existing track vibration damping devices cannot adjust the adaptive damping force according to the train type and driving speed, and lack effective abnormal monitoring and maintenance methods, resulting in poor vibration damping effect and insufficient reliability.

Method used

Using a track vibration damping system based on electromagnetic induction, the speed receiving module, train type acquisition module, damping force configuration module, magnetic core data acquisition module and current prediction module can be used to collect and analyze the data of the train operating status and electromagnetic damping device in real time to realize the data of the train operation status and electromagnetic damping device. Adaptive adjustment and abnormal monitoring to generate maintenance signals for timely maintenance.

Benefits of technology

It realizes accurate damping force configuration based on train type and driving speed, monitors the status of the electromagnetic damping device in real time, detects abnormalities in a timely manner, and ensures the effect and safety of track vibration damping.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118932797B_ABST
    Figure CN118932797B_ABST
Patent Text Reader

Abstract

The present invention relates to a track vibration reduction system and monitoring method based on electromagnetic induction, which relates to the field of rail transit, and includes: a speed receiving module for receiving the train speed; a train type acquisition module for collecting timestamps according to the speed, and obtaining train type information based on the train schedule; a damping force configuration module for configuring the damping force according to the train type information and the train speed, and obtaining the target damping force; a magnetic core data acquisition module for receiving the magnetic core movement speed timing information and the magnetic core relative movement distance; a current prediction module for obtaining the target current magnitude timing information; a maintenance signal generation module for generating an electromagnetic damping floating plate structure maintenance signal and sending it to the management end. Through the electromagnetic damping floating plate structure, the adaptive damping force adjustment and real-time abnormality monitoring of the track vibration reduction device are realized, and the technical effect of improving the track vibration reduction effect and ensuring the reliable operation of the track vibration reduction is achieved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of rail transportation, and in particular to a rail vibration reduction system and a monitoring method based on electromagnetic induction. Background Art

[0002] Track vibration reduction is an important technology in the field of rail transportation. Its main purpose is to reduce the impact of vibration generated by train operation on the track structure and the surrounding environment, and to improve the stability and safety of train operation. Traditional track vibration reduction devices mainly include elastic elements (such as steel springs) and damping elements (liquid viscous dampers), etc., and the vibration reduction effect is achieved through the deformation of elastic elements and the energy consumption of damping elements. However, traditional track vibration reduction devices generally have problems such as unadjustable vibration reduction performance and poor adaptability. For example, different types of trains and different driving speeds have different requirements for the damping characteristics of the vibration reduction device, but the existing vibration reduction device is difficult to achieve adaptive adjustment, resulting in poor vibration reduction effect. In addition, traditional vibration reduction devices also lack effective monitoring and maintenance means. For example, the damping of the steel spring floating plate is basically provided by the liquid viscous damper. During long-term use, the liquid viscous damper is prone to leakage and other problems. Once a failure or performance degradation occurs, it is difficult to detect and deal with it in time, affecting the reliability and safety of track vibration reduction. Summary of the invention

[0003] The present invention aims to solve the technical problems that the existing track vibration reduction cannot adaptively adjust the damping force according to the train type and running speed, and lacks effective abnormality monitoring and maintenance means, resulting in poor track vibration reduction effect and insufficient reliability. A track vibration reduction system and a monitoring method based on electromagnetic induction are provided to solve the problems.

[0004] The technical solution of the present invention to solve the above technical problems is as follows:

[0005] In a first aspect, the present invention provides a track vibration reduction system based on electromagnetic induction, comprising: a speed receiving module for receiving a train speed, wherein the train speed has a speed acquisition timestamp; a train type acquisition module for acquiring train type information based on a train schedule according to the speed acquisition timestamp; a damping force configuration module for configuring damping force according to the train type information and the train speed to obtain a target damping force; a core data acquisition module for receiving core movement speed timing information and core relative movement distance through a displacement sensor; a current prediction module for performing electromagnetic induction analysis on the target damping force, core movement speed timing information and core relative movement distance through a current prediction channel to obtain target current magnitude time series information; a maintenance signal generation module for generating an electromagnetic damping floating plate structure maintenance signal when the monitored current magnitude time series information is inconsistent with the target current magnitude time series information, and sending the signal to a management end.

[0006] In the second aspect, the present invention provides a track monitoring method based on electromagnetic induction, including: receiving a train speed, wherein the train speed has a speed collection timestamp; obtaining train type information based on the speed collection timestamp and the train schedule; configuring damping force according to the train type information and the train speed to obtain a target damping force; receiving a magnetic core movement speed timing information and a magnetic core relative movement distance through a displacement sensor; performing electromagnetic induction analysis on the target damping force, the magnetic core movement speed timing information and the magnetic core relative movement distance through a current prediction channel to obtain a target current magnitude time series information; when the monitored current magnitude time series information is inconsistent with the target current magnitude time series information, generating an electromagnetic damping floating plate structure maintenance signal and sending it to the management end.

[0007] In a third aspect, the present application provides an electronic device, comprising: a processor; a memory for storing instructions executable by the processor; wherein the processor is used to execute a track vibration reduction system based on electromagnetic induction provided in the present application.

[0008] In a fourth aspect, the present application provides a computer-readable storage medium storing a computer program, and the computer program is used to execute a track vibration reduction system based on electromagnetic induction provided by the present application.

[0009] The beneficial effects of the present invention are:

[0010] The speed receiving module receives the train speed and obtains the current running status information of the train, which provides a basis for the subsequent damping force adjustment. At the same time, the train type acquisition module accurately obtains the train type information through the timestamp attached to the train speed. In this way, combined with the train type and speed, the damping force configuration module can accurately configure the target damping force according to the vibration characteristics and speed conditions of different trains, and realize adaptive vibration reduction control; the magnetic core data acquisition module receives the movement speed and relative movement distance data of the magnetic core in real time through the displacement sensor, and fully grasps the running status of the electromagnetic damping floating plate structure. On this basis, the current prediction module combines the target damping force and performs electromagnetic induction analysis on the magnetic core movement data, and obtains the target current size sequence information under the ideal state as the target current. By comparing the measured current and the target current, the abnormal situation of the electromagnetic damping floating plate structure can be discovered in time. Once the actual current is detected to be inconsistent with the target current, the maintenance signal generation module generates a maintenance signal of the electromagnetic damping floating plate structure and sends it to the management end, prompting relevant personnel to carry out maintenance work in time, eliminate potential faults, and ensure normal track vibration reduction work. By collecting the train running status and the working data of the electromagnetic damping device in real time, adaptively adjusting the damping force, predicting the ideal current and comparing it with the measured value, and promptly prompting maintenance when an abnormality is found, the problem of the electromagnetic damping floating plate structure in the prior art lacking effective abnormality monitoring means is effectively solved, thus ensuring the vibration reduction effect and operational safety of the track vibration reduction system. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] Figure 1 A schematic structural diagram of a track vibration reduction system based on electromagnetic induction provided by the present invention;

[0012] Figure 2 A schematic diagram of a flow chart of a track monitoring method based on electromagnetic induction provided by the present invention;

[0013] Figure 3 A schematic diagram of the structure of an electronic device provided by the present invention;

[0014] Figure 4 A schematic diagram of the structure of a computer-readable storage medium provided by the present invention.

[0015] In the accompanying drawings, the components represented by the reference numerals are described as follows:

[0016] Speed ​​receiving module 11, train type acquisition module 12, damping force configuration module 13, core data acquisition module 14, current prediction module 15, maintenance signal generation module 16, electronic device 200, memory 210, processor 220, computer program 211, computer readable storage medium 300, computer program 311. DETAILED DESCRIPTION

[0017] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions 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 those skilled in the art without creative work are within the scope of protection of the present invention.

[0018] In the description of the present invention, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0019] In the description of the present invention, the term "for example" is used to mean "used as an example, illustration or explanation". Any embodiment described as "for example" in the present invention is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is given to enable any technician in the field to implement and use the present invention. In the following description, details are listed for the purpose of explanation. It should be understood that a person of ordinary skill in the art can recognize that the present invention can be implemented without using these specific details. In other examples, well-known structures and processes will not be elaborated in detail to avoid obscuring the description of the present invention with unnecessary details. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the widest scope consistent with the principles and features disclosed in the present invention.

[0020] Embodiment 1:

[0021] like Figure 1As shown, an embodiment of the present invention provides a track vibration reduction system based on electromagnetic induction, wherein the track vibration reduction is performed by an electromagnetic damping floating plate structure. When the train passes through the structure, the wheel-rail pressure exerts positive pressure to cause the electromagnetic core to displace positively. A coil is surrounded by the electromagnetic core to form a closed conductor loop. When the electromagnetic core moves relative to the closed conductor around the coil, the core cuts the magnetic flux and penetrates the magnetic flux. According to the law of electromagnetic induction, an induced current is generated in the closed conductor around the coil. The induced current further forms an electromagnetic field in the closed conductor around the coil, generating an Ampere force in the opposite direction of the movement of the magnetic core. The magnitude of the Ampere force is proportional to physical quantities such as the magnetic induction intensity and relative movement speed of the magnet. The Ampere force generated by this electromagnetic induction can effectively offset the wheel-rail pressure and reduce the energy transmitted from the wheel-rail pressure to the track foundation, thereby achieving the effect of vibration reduction. Compared with the traditional liquid viscous damper, the electromagnetic damping floating plate structure avoids problems such as leakage and is more convenient to maintain. At the same time, by real-time monitoring of the changes in the induced current in the closed conductor around the coil, the state monitoring of the electromagnetic damping floating plate structure can also be achieved.

[0022] The track vibration reduction system includes:

[0023] The speed receiving module 11 is used to receive the train speed, wherein the train speed has a speed acquisition timestamp.

[0024] Specifically, the speed receiving module 11 periodically collects the train speed by establishing a communication connection with the speed sensor installed on the train. During the speed collection process, the speed receiving module 11 not only records the instantaneous speed value of the train, but also associates a speed collection timestamp for each collected speed data point. The timestamp is accurate to the millisecond level and is used to characterize the time point of the collection of the train speed. By recording the timestamp, the changing law of the train speed in the time dimension can be grasped, providing a time reference for subsequent data analysis.

[0025] The speed receiving module 11 continuously collects and records the train speed, providing data support for the adaptive control of the track vibration reduction system.

[0026] The train type acquisition module 12 is used to acquire the train type information based on the train schedule according to the travel speed acquisition timestamp.

[0027] Specifically, the train type acquisition module 12 first obtains the train speed and its corresponding speed acquisition timestamp from the speed receiving module 11. Then, based on the pre-stored train schedule, the train type acquisition module 12 matches the speed acquisition timestamp with the time information in the train schedule to determine the train schedule that should pass through the vibration reduction section at the current time. Further, based on the train schedule, the train type acquisition module 12 obtains detailed type information of the train from the train schedule, such as EMU, intercity train, subway train, etc.

[0028] The train type information obtained by the train type acquisition module 12 is used for subsequent wheel-rail pressure prediction and damping force adjustment, providing an important decision-making basis for the adaptive adjustment of track vibration reduction. Because different types of trains have significant differences in axle weight, suspension parameters, wheel-rail force characteristics, etc., different vibration reduction strategies need to be adopted. Mastering the train type information helps to reduce vibration according to the characteristics of the train and achieve more accurate and targeted vibration reduction control.

[0029] The damping force configuration module 13 is used to configure the damping force according to the train type information and the train running speed to obtain a target damping force.

[0030] Specifically, the damping force configuration module 13 receives the train type information provided by the train type acquisition module 12 and the train speed provided by the speed receiving module 11. Based on these two parameters, the damping force configuration module 13 uses the pre-established damping force configuration strategy to calculate the target damping force that the electromagnetic damper should provide under the current working condition.

[0031] In the process of establishing the damping force configuration strategy, through a large number of simulation analyses and field tests, the optimal damping force value rules for different train types at different speeds are summarized. These rules are stored in the configuration strategy library in the form of table lookup, curve fitting, etc. After receiving the train type information and the train speed, the damping force configuration module 13 can quickly retrieve and calculate to obtain the corresponding target damping force.

[0032] Through the damping force configuration module 13, the train type information and the train speed are comprehensively considered, and the pre-optimized configuration strategy is used to calculate the target damping force of the electromagnetic damper in real time, providing parameter support for the adaptive control of track vibration reduction.

[0033] The magnetic core data acquisition module 14 is used to receive the magnetic core movement speed timing information and the magnetic core relative movement distance through the displacement sensor.

[0034] Specifically, the magnetic core data acquisition module 14 establishes a communication connection with the displacement sensor inside the electromagnetic damper, and periodically receives the magnetic core movement speed timing information and the magnetic core relative movement distance data measured by the displacement sensor. Among them, the magnetic core movement speed timing information reflects the speed change law of the magnetic core's reciprocating motion inside the electromagnetic damper. By analyzing the magnetic core movement speed timing information, the movement state of the magnetic core at different times can be grasped, and then the change trend of the induced current during the electromagnetic induction process can be inferred; the magnetic core relative movement distance data records the displacement of the magnetic core relative to the fixed part of the electromagnetic damper (for example, around the coil). By monitoring the relative movement distance, it can be determined whether the magnetic core has excessive displacement, whether there is a risk of collision, and whether the electromagnetic damper has hidden dangers of failure. The magnetic core movement speed timing information and relative movement distance data collected by the magnetic core data acquisition module 14 are continuously recorded at a certain time interval (for example, 10 milliseconds).

[0035] The core data acquisition module 14 continuously acquires the core movement speed timing information and the core relative movement distance, providing key input for current prediction and data support for the electromagnetic damping floating plate structure status monitoring.

[0036] The current prediction module 15 is used to perform electromagnetic induction analysis on the target damping force, the timing information of the magnetic core movement speed and the relative movement distance of the magnetic core through a current prediction channel to obtain the timing information of the target current magnitude;

[0037] Specifically, the current prediction module 15 uses a pre-trained current prediction channel to comprehensively analyze the target damping force output by the damping force configuration module 13, the core movement speed timing information and the core relative movement distance data collected by the core data acquisition module 14, establish a corresponding relationship between the physical parameters of the electromagnetic damper and the excitation current, and then obtain the target current magnitude timing information required to achieve the target damping force.

[0038] In the process of establishing the current prediction channel, through a large amount of simulation analysis and test data, a nonlinear mapping model with target damping force, core movement speed, and core relative movement distance as input and excitation current size as output is constructed, which accurately reflects the dynamic relationship between excitation current and damping force under different working conditions. Among them, the current prediction channel is based on machine learning methods, such as neural networks, support vector machines, etc., and automatically learns and optimizes model parameters through training of a large amount of sample data in order to obtain the best prediction performance. Based on the current prediction channel, the current prediction module 15 receives the target damping force, core movement speed, and core relative movement distance, which reflect the instantaneous working conditions of the electromagnetic damper, in real time, and quickly obtains the target current size at the corresponding moment. Since the core movement speed and relative movement distance are dynamically changing during the process of the train passing through the vibration reduction section, the target current size given by the current prediction module 15 is also a time series signal, that is, the target current size time series information, which reflects the change law of the excitation current in the time dimension.

[0039] The target current magnitude time series information output by the current prediction module 15 can be directly used to guide the excitation control of the electromagnetic damper coil. According to the time series information, the coil current is adjusted in real time to track the change of the target damping force. At the same time, the target current magnitude time series information also provides a reference for subsequent excitation circuit fault diagnosis, coil working status monitoring, etc. By comparing the difference between the actual current and the target current, problems such as excitation circuit fault or coil performance degradation can be discovered in time.

[0040] Through the current prediction module 15, the operating conditions of the electromagnetic damper are comprehensively analyzed using the current prediction channel to obtain the target current magnitude time series information required to achieve the dynamically changing target damping force, which provides a key basis for the precise control of track vibration reduction, and takes into account the fault diagnosis and status monitoring of track vibration reduction, effectively improving the adaptability and reliability of track vibration reduction.

[0041] The maintenance signal generating module 16 is used to generate an electromagnetic damping floating plate structure maintenance signal and send it to the management end when the monitored current magnitude sequence information is inconsistent with the target current magnitude sequence information.

[0042] Specifically, the maintenance signal generation module 16 receives the target current magnitude time series information output by the current prediction module 15 in real time, and simultaneously obtains the monitoring current magnitude time series information actually flowing in the electromagnetic damper coil in the electromagnetic damping floating plate structure through monitoring equipment such as current sensors. By comparing and analyzing the monitoring current magnitude time series information and the target current magnitude time series information, the maintenance signal generation module 16 can evaluate the operating status of the electromagnetic damper in real time and determine whether it has a fault or performance abnormality.

[0043] Ideally, the actual current in the electromagnetic damper coil should be consistent with the target current magnitude time series information, that is, the actual damping force provided should match the target damping force. However, in the actual operation process, due to excitation circuit failure, coil performance degradation, mechanical structure wear and other reasons, the actual current may deviate from the target value, resulting in the damping force failing to meet the expected requirements, thereby affecting the vibration reduction effect. To this end, the maintenance signal generation module 16 performs a quantitative analysis of the deviation between the monitoring current and the target current. When the deviation exceeds the preset threshold and lasts for a certain period of time (for example, 3 consecutive sampling cycles), the maintenance signal generation module 16 will determine that the electromagnetic damping floating plate structure has a fault and generate a corresponding maintenance signal. The generated maintenance signal usually includes information such as the severity of the fault and the time of the fault. This information is sent to the management end of the track vibration reduction system, such as the station control center, maintenance dispatch center, etc., in real time through a wired or wireless communication network. After receiving the maintenance signal, the management end arranges the corresponding inspection and maintenance activities in a timely manner according to the maintenance signal, such as adjusting the train operation plan, dispatching maintenance personnel for on-site inspection, etc., to ensure the reliable operation of the track vibration reduction.

[0044] The maintenance signal generation module 16 monitors and analyzes the current state of the electromagnetic damper in real time, so that faults and performance abnormalities of the track vibration reduction can be discovered in time. By generating and sending maintenance signals, fault warnings and active maintenance of the track vibration reduction system can be achieved, thereby ensuring the safe and reliable operation of the track vibration reduction.

[0045] Furthermore, the damping force configuration module includes the following execution steps:

[0046] Predicting the wheel-rail pressure according to the train type information and the train running speed to obtain the predicted wheel-rail pressure;

[0047] The target damping force is obtained by configuring the damping force through the predicted wheel-rail pressure and the train type information.

[0048] In a feasible implementation, when the damping force is configured according to the train type information and the train speed to obtain the target damping force, first, the damping force configuration module 13 receives the train type information provided by the train type acquisition module 12 and the train speed provided by the speed receiving module 11. Then, the wheel-rail pressure prediction model established in advance is combined with the train type information and the train speed to calculate the predicted wheel-rail pressure when the train passes through the vibration reduction section. Among them, the wheel-rail pressure prediction model is constructed using a machine learning algorithm, such as a neural network, a support vector machine, etc. In the training process of the model, a large amount of historical operating data is used, including wheel-rail pressure test records of different types of trains at different speeds, and a mapping relationship between train type, speed and wheel-rail pressure is established through supervised learning. The wheel-rail pressure prediction model can receive the train type information and train speed information online in real time and quickly predict the corresponding wheel-rail pressure.

[0049] After obtaining the wheel-rail predicted pressure, the damping force configuration module 13 will further calculate the corresponding target damping force in combination with the train type information. The matching target damping force is calculated by combining the wheel-rail predicted pressure and the train type information through the pre-established damping force prediction model. Among them, the damping force prediction model establishes the relationship between the wheel-rail pressure, the train type and the target damping force through machine learning. When training the damping force prediction model, the wheel-rail pressure and the train type are used as input features, and the optimal damping force manually marked or experimentally measured is used as a label, and the model parameter optimization is completed through supervised learning. When applied, the damping force prediction model inputs the wheel-rail predicted pressure and the train type information to obtain the corresponding target damping force.

[0050] Through wheel-rail pressure prediction and damping force configuration, the damping force configuration module 13 adaptively adjusts the damping force of the electromagnetic damper according to the real-time operating conditions of the train, thereby achieving more accurate and efficient track vibration reduction control.

[0051] Furthermore, the damping force configuration module also includes the following execution steps:

[0052] Collecting sample data according to the train type information and the train running speed to obtain a wheel-rail pressure monitoring log, wherein the wheel-rail pressure monitoring log includes a plurality of wheel-rail pressure monitoring values;

[0053] performing centralized analysis based on the plurality of wheel-rail pressure monitoring values ​​to obtain a plurality of centralized weighted evaluation values;

[0054] The wheel-rail predicted pressure is obtained by performing weighted mean statistics on the plurality of wheel-rail pressure monitoring values ​​according to the plurality of concentrated weight evaluation values.

[0055] In a preferred embodiment,

[0056] In order to improve the accuracy and reliability of wheel-rail pressure prediction, firstly,

[0057] After receiving the train type information and the train speed, the damping force configuration module 13 first triggers the sample data collection process. Through monitoring equipment such as track pressure sensors, the wheel-rail pressure data within a certain time window is continuously collected during the process of the train passing through the vibration reduction section to form a wheel-rail pressure monitoring log. The wheel-rail pressure monitoring log contains several discrete wheel-rail pressure monitoring values, which reflect the dynamic changes of the wheel-rail pressure when the train passes through the vibration reduction section. After obtaining the wheel-rail pressure monitoring log, the damping force configuration module 13 will conduct a centralized analysis of several wheel-rail pressure monitoring values ​​in the log. The purpose of centralized analysis is to evaluate the representativeness and reliability of each monitoring value to determine its weight in subsequent predictions. Specifically, the centralized analysis process quantitatively evaluates the distribution characteristics of several wheel-rail pressure monitoring values, among which the centralized analysis indicators include mean, median, mode, variance, skewness, kurtosis, etc. These indicators reflect the characteristics of the central tendency, discreteness, distribution form, etc. of the monitoring values. Through centralized analysis, the damping force configuration module 13 assigns a centralized weight evaluation value to each wheel-rail pressure monitoring value to obtain a number of centralized weight evaluation values. The higher the value, the higher the credibility of the wheel-rail pressure monitoring value, and the greater the weight in the prediction.

[0058] After obtaining the concentrated weight evaluation value of each wheel-rail pressure monitoring value, the damping force configuration module 13 adopts the weighted average method to integrate several wheel-rail pressure monitoring values ​​to obtain the final wheel-rail predicted pressure. Specifically, first, each wheel-rail pressure monitoring value is multiplied by its corresponding concentrated weight evaluation value to obtain several weighted wheel-rail pressure monitoring values; then, all weighted wheel-rail pressure monitoring values ​​are summed to obtain the weighted wheel-rail pressure monitoring total value; then, the weighted wheel-rail pressure monitoring total value is divided by the sum of all concentrated weight evaluation values ​​to obtain the wheel-rail predicted pressure.

[0059] Through weighted mean statistics, the reliability information of each wheel-rail pressure monitoring value is fully utilized, and the monitoring values ​​with high credibility are given greater weights, while the influence of the monitoring values ​​with low credibility is reduced. The time-varying characteristics and uncertainty of the wheel-rail pressure monitoring data are fully considered, so as to obtain more accurate and robust wheel-rail pressure prediction results, thereby providing a more reliable input for the subsequent damping force configuration and improving the control performance of track vibration reduction.

[0060] On the basis of the above-mentioned wheel-rail pressure prediction process, the damping force configuration module 13 can also adopt steps such as sample data collection, centralized analysis and weighted mean statistics similar to wheel-rail pressure prediction when performing damping force configuration, so as to improve the accuracy and reliability of damping force configuration. Specifically, the damping force configuration module 13 obtains damping force sample data within a certain time window according to the train type information and the wheel-rail predicted pressure, and forms a damping force monitoring log; then the damping force monitoring values ​​in the damping force monitoring log are centralized analyzed to obtain the corresponding centralized weight evaluation value; then the damping force monitoring values ​​are weighted mean statistics according to the centralized weight evaluation value to obtain the optimized target damping force. By introducing improvement measures similar to wheel-rail pressure prediction, the damping force configuration module 13 can effectively improve the dynamic adaptability and robustness of the damping force configuration, thereby further improving the control performance of track vibration reduction.

[0061] Furthermore, the damping force configuration module also includes the following execution steps:

[0062] Obtaining a first wheel-rail pressure monitoring value of the plurality of wheel-rail pressure monitoring values;

[0063] Based on the first wheel-rail pressure monitoring value, traverse the plurality of wheel-rail pressure monitoring values ​​to perform pressure deviation modulus calculation to obtain a plurality of wheel-rail pressure deviation moduli;

[0064] Performing mean analysis on the plurality of wheel-rail pressure deviation moduli to obtain a first wheel-rail pressure dispersion factor, and adding the plurality of wheel-rail pressure dispersion factors;

[0065] Calculating the average of the plurality of wheel-rail pressure dispersion factors to obtain a global average dispersion factor;

[0066] Comparing the global average dispersion factor with the first wheel-rail pressure dispersion factor to obtain a first wheel-rail pressure concentration coefficient, and adding a plurality of wheel-rail pressure concentration coefficients;

[0067] Counting the sum of the plurality of wheel-rail pressure concentration coefficients to obtain a sum value of the wheel-rail pressure concentration coefficients;

[0068] The ratio of the first wheel-rail pressure concentration coefficient to the sum of the wheel-rail pressure concentration coefficients is calculated to obtain a first wheel-rail pressure concentration weight, which is added to the plurality of concentration weight evaluation values.

[0069] In a preferred embodiment, when performing concentrated wheel-rail pressure analysis, several wheel-rail pressure monitoring values ​​are traversed, and one wheel-rail pressure monitoring value is obtained each time as the first wheel-rail pressure monitoring value. Secondly, the damping force configuration module 13 takes the first wheel-rail pressure monitoring value as a reference, calculates the absolute value of the deviation between each other wheel-rail pressure monitoring value and the first wheel-rail pressure monitoring value one by one, and obtains several wheel-rail pressure deviation moduli, which are used to measure the degree of deviation of the remaining wheel-rail pressure monitoring values ​​relative to the first wheel-rail pressure monitoring value. Thirdly, the damping force configuration module 13 performs arithmetic average operation on several wheel-rail pressure deviation moduli to obtain the first wheel-rail pressure dispersion factor, which reflects the average dispersion degree of other wheel-rail pressure monitoring values ​​when the first wheel-rail pressure monitoring value is used as a reference. The damping force configuration module 13 adds the first wheel-rail pressure dispersion factor to several wheel-rail pressure dispersion factors for subsequent analysis. Repeat the calculation of the wheel-rail pressure dispersion factor until several wheel-rail pressure monitoring values ​​are traversed and several wheel-rail pressure dispersion factors are obtained.

[0070] Subsequently, the damping force configuration module 13 performs arithmetic averaging on several wheel-rail pressure dispersion factors to obtain a global average dispersion factor, which reflects the overall dispersion degree between all wheel-rail pressure monitoring values ​​and is a reference standard for measuring the discrete degree of a single monitoring value. Afterwards, the damping force configuration module 13 divides the global average dispersion factor by the first wheel-rail pressure dispersion factor to obtain the first wheel-rail pressure concentration coefficient, which reflects the relative concentration degree of other wheel-rail pressure monitoring values ​​when the first wheel-rail pressure monitoring value is used as a reference. The larger the wheel-rail pressure concentration coefficient, the closer the first wheel-rail pressure monitoring value is to the center of the overall monitoring value and the stronger its representativeness. The damping force configuration module 13 adds the first wheel-rail pressure concentration coefficient to several wheel-rail pressure concentration coefficients for subsequent analysis. Repeat the calculation of the wheel-rail pressure concentration coefficient until all wheel-rail pressure monitoring values ​​are traversed and several wheel-rail pressure concentration coefficients are obtained.

[0071] Afterwards, the damping force configuration module 13 performs a sum operation on several wheel-rail pressure concentration coefficients to obtain the sum of the wheel-rail pressure concentration coefficients, which reflects the comprehensive concentration degree of all monitoring values. Next, the damping force configuration module 13 divides the first wheel-rail pressure concentration coefficient by the sum of the wheel-rail pressure concentration coefficients to obtain the first wheel-rail pressure concentration weight as the concentration weight evaluation value corresponding to the first wheel-rail pressure monitoring value, which reflects the relative importance of the monitoring value among all monitoring values. The damping force configuration module 13 adds the first wheel-rail pressure concentration weight to several concentration weight evaluation values. Repeat the calculation of the concentration weight evaluation value until all wheel-rail pressure monitoring values ​​are traversed and a number of concentration weight evaluation values ​​equal to the number of wheel-rail pressure monitoring values ​​are obtained.

[0072] Through the centralized analysis method, the damping force configuration module 13 fully considers the representativeness and importance of each wheel-rail pressure monitoring value relative to the overall monitoring value distribution when calculating the centralized weight evaluation value, effectively avoiding the adverse effects of individual abnormal values ​​or extreme values ​​on the weighted results, making the final wheel-rail predicted pressure more reasonable and reliable, thus laying a good foundation for the subsequent damping force configuration.

[0073] Furthermore, the current prediction module includes the following execution steps:

[0074] Obtaining electromagnetic damping floating plate structure test data, wherein the electromagnetic damping floating plate structure test data includes damping force test data, magnetic core movement speed timing test data, magnetic core relative movement distance test data and current monitoring timing data;

[0075] Constructing a current prediction loss function, wherein the current prediction loss function includes a first current prediction loss function and a second current prediction loss function, wherein the first current prediction loss function represents a mean value of current prediction deviations at multiple moments, and the second current prediction loss function represents a variance of current prediction deviations at multiple moments;

[0076] Based on the first loss threshold and the second loss threshold, according to the first current prediction loss function and the second current prediction loss function, the current monitoring timing data is retrieved, the damping force test data, the magnetic core movement speed timing test data, and the magnetic core relative movement distance test data are supervised, and the BP neural network is trained to obtain the current prediction channel.

[0077] In a feasible implementation, in order to establish a current prediction channel, the current prediction module 15 first obtains a set of test data of the electromagnetic damping floating plate structure as a sample data set for subsequent current prediction model training. The test data is derived from offline tests or simulation analysis, and contains multiple physical quantities reflecting the operating state of the electromagnetic damper, including damping force test data, which characterizes the magnitude of the damping force provided by the electromagnetic damper; core movement speed time series test data, which characterizes the movement speed change process of the electromagnetic damper core; core relative movement distance test data, which characterizes the displacement of the electromagnetic damper core relative to the coil; current monitoring time series data, which characterizes the actual current size change process in the electromagnetic damper coil. At the same time, a current prediction loss function is defined to measure the deviation between the model prediction result and the true value, and to guide the optimization of the model parameters. Among them, the current prediction loss function is a composite loss function, which includes two sub-loss functions, namely the first current prediction loss function and the second current prediction loss function. Among them, the first current prediction loss function is used to measure the arithmetic mean of the difference between the current prediction value and the true value at multiple moments, reflecting the overall level of prediction deviation. By minimizing the first current prediction loss function, the prediction results of the current prediction model can be made as close to the true value as possible throughout the entire period. The second current prediction loss function is used to measure the discreteness of the current prediction deviation at multiple moments, reflecting the volatility of the prediction deviation. By minimizing the second current prediction loss function, the prediction results of the current prediction model at each moment are made as stable as possible, reducing the drastic fluctuations in the prediction value. By comprehensively considering the first current prediction loss function and the second current prediction loss function, the current prediction model can ensure the overall prediction accuracy while taking into account the stability of the prediction results, thereby obtaining more reliable and practical prediction results.

[0078] Afterwards, the BP neural network is selected as the basic framework of the current prediction model. During the model training process, the current prediction module 15 uses the damping force test data, the core movement speed timing test data, and the core relative movement distance test data as the input of the BP neural network, uses the current monitoring timing data as the supervision signal, and uses the first current prediction loss function and the second current prediction loss function to evaluate the model prediction performance. The current prediction module 15 sets the first loss threshold and the second loss threshold as the termination conditions of the model training. When the value of the first current prediction loss function is lower than the first loss threshold and the value of the second current prediction loss function is lower than the second loss threshold, it is considered that the model training has achieved the expected goal and the iteration is stopped. After multiple rounds of iterative training, the BP neural network can learn the physical characteristics of the electromagnetic damper contained in the test data, and establish a nonlinear correlation model between physical quantities such as damping force, core movement speed, and core relative movement distance and coil current. After the training is completed, the current prediction module 15 uses the trained BP neural network as a current prediction channel to receive the target damping force, core movement speed timing information, and core relative movement distance data output by the damping force configuration module in real time, and predict the corresponding target current magnitude timing information.

[0079] The current prediction module 15 obtains the electromagnetic damper test data, constructs a composite current prediction loss function, and uses it as a guide to train the BP neural network, and finally obtains a high-precision and highly robust current prediction channel, thereby achieving accurate prediction of the coil current and providing a reliable basis for the real-time control of the electromagnetic damper.

[0080] Furthermore, the current prediction module also includes the following execution steps:

[0081] Retrieving the current monitoring time series data, supervising the damping force test data, the magnetic core movement speed time series test data, and the magnetic core relative movement distance test data, training the BP neural network M times, obtaining M first loss parameters according to the first current prediction loss function, and obtaining M second loss parameters according to the second current prediction loss function;

[0082] Counting the proportion of the M first loss parameters that are less than or equal to the first loss threshold, to obtain a first convergence ratio;

[0083] Counting the proportion of the M second loss parameters that are less than or equal to the second loss threshold, to obtain a second convergence ratio;

[0084] When the first convergence ratio and the second convergence ratio are both greater than or equal to a convergence ratio threshold, the current prediction channel is obtained, wherein 1≥the convergence ratio threshold≥97%.

[0085] In a preferred embodiment, when training the BP neural network to obtain the current prediction channel, in order to fully evaluate the performance of the BP neural network and improve the reliability of the current prediction channel, a strategy of repeated training and cross-validation is adopted. Specifically, the current prediction module 15 uses the same training data set to repeatedly train the BP neural network M times, and each training records the corresponding first current prediction loss function value and the second current prediction loss function value, forming M first loss parameters and M second loss parameters respectively, for subsequent convergence judgment. Among them, M is a preset positive integer. The larger the M value, the more sufficient the evaluation of the BP neural network performance is, but it also means a greater computational overhead.

[0086] Subsequently, the current prediction module 15 counts the number of times the first loss parameter is less than or equal to the first loss threshold in M ​​training times, and calculates its proportion to the total training times M to obtain a first convergence ratio. The first convergence ratio reflects the degree of convergence of the BP neural network in the sense of the first current prediction loss function. The higher the first convergence ratio, the more stable the overall prediction accuracy of the BP neural network. At the same time, the current prediction module 15 counts the number of times the second loss parameter is less than or equal to the second loss threshold in M ​​training times, and calculates its proportion to the total training times M to obtain a second convergence ratio. The second convergence ratio reflects the degree of convergence of the BP neural network in the sense of the second current prediction loss function. The higher the second convergence ratio, the better the prediction stability of the BP neural network.

[0087] Next, the current prediction module 15 comprehensively considers the first convergence ratio and the second convergence ratio to determine whether the BP neural network has reached the expected convergence state. When the first convergence ratio and the second convergence ratio are both greater than or equal to the preset convergence ratio threshold, the current prediction module 15 believes that the BP neural network has reached a stable optimal state, and uses the currently trained BP neural network as a current prediction channel for subsequent online predictions. Among them, the convergence ratio threshold is a preset ratio value, for example, the value range is between 97% and 100%. The higher the convergence ratio threshold, the more stringent the requirements for the convergence of the BP neural network, and the higher the reliability of the current prediction channel, but it may also increase the training time.

[0088] The current prediction module 15 repeatedly trains the BP neural network and evaluates the convergence of each training according to the first current prediction loss function and the second current prediction loss function, and then determines the overall convergence state of the BP neural network, and finally obtains a highly reliable and stable current prediction channel, which can effectively reduce the randomness of a single training, improve the robustness of the current prediction channel, and ensure that it can continuously and stably provide high-precision current prediction results in practical applications.

[0089] Furthermore, the embodiment of the present application also includes an energy recovery module, and the energy recovery module includes the following execution steps:

[0090] When the electromagnetic damping floating plate structure is activated, the current output wire connected to the electromagnetic damping floating plate structure is connected to the energy storage device for energy recovery.

[0091] In a preferred embodiment, the track vibration reduction system based on electromagnetic induction further includes an energy recovery module for realizing the recovery and utilization of the electric energy generated in the electromagnetic damping floating plate structure.

[0092] Specifically, the energy recovery module is connected to the current output wire and the energy storage device of the electromagnetic damping floating plate structure. When the train passes through the track vibration reduction section and the wheel-rail pressure acts on the electromagnetic damping floating plate structure, the electromagnetic damping floating plate structure is activated. At this time, under the action of electromagnetic induction, an induced current is generated in the electromagnetic damper coil. The induced current flows to the energy recovery module through the current output wire and is then transmitted to the energy storage device. The energy storage device can be a device capable of storing electrical energy, such as a battery and a supercapacitor, which is used to temporarily store and manage the electrical energy recovered from the electromagnetic damping floating plate structure.

[0093] By connecting the current output wire and the energy storage device in time when the electromagnetic damping floating plate structure is activated, the energy recovery module effectively captures and recovers the induced current energy generated in the electromagnetic damper coil. This energy recovery mechanism can not only improve the energy utilization efficiency of the track vibration reduction system and save energy, but also provide power supply for other electrical equipment in the track vibration reduction system, such as powering low-power devices such as sensors and controllers, to achieve self-powered operation of the system and reduce dependence on external energy.

[0094] Among them, the energy recovery module needs to ensure that the recovery process does not interfere with the normal operation of the electromagnetic damper while realizing the energy recovery function. To this end, when designing the circuit, the energy recovery module adopts technical means such as isolation circuit or energy buffer circuit to realize the electrical isolation and energy smoothing between the electromagnetic damper coil and the energy storage device, so as to avoid the charging and discharging process of the energy storage device from having an adverse effect on the induced current of the electromagnetic damper coil. At the same time, the energy recovery module can also set up a current monitoring circuit and an overcurrent protection circuit to monitor the size of the recovery current in real time, and cut off the recovery circuit in time when the recovery current exceeds the safety range, so as to ensure the safety and reliability of the operation of the track vibration reduction system.

[0095] By introducing the energy recovery module, the energy of the induced current in the electromagnetic damping floating plate structure is recycled and utilized, effectively improving the energy utilization efficiency of the system. The energy recovery module uses the moment when the electromagnetic damping floating plate structure is activated to connect the current output wire with the energy storage device to store the induced current energy in the energy storage device for use by other components of the system, saving energy and improving the self-power supply capacity of the system.

[0096] The electromagnetic induction-based rail vibration reduction system provided by the embodiment of the present invention has at least the following technical effects:

[0097] The speed receiving module is used to receive the train speed, wherein the train speed has a speed acquisition timestamp, accurately grasps the running status of the train, and provides necessary data support for subsequent damping force adjustment and abnormal monitoring. The train type acquisition module is used to obtain the train type information based on the train schedule according to the speed acquisition timestamp, and can make corresponding damping force adjustments for different train types to achieve more accurate vibration reduction control. The damping force configuration module is used to configure the damping force according to the train type information and the train speed, obtain the target damping force, and dynamically adjust the damping force according to the actual operating conditions to achieve the best vibration reduction effect. The magnetic core data acquisition module is used to receive the magnetic core movement speed timing information and the relative movement distance of the magnetic core through the displacement sensor, which can reflect the actual working status of the electromagnetic damping device and provide an important basis for subsequent abnormal monitoring and fault diagnosis. The current prediction module is used to perform electromagnetic induction analysis on the target damping force, the timing information of the magnetic core movement speed and the relative movement distance of the magnetic core through the current prediction channel to obtain the target current magnitude timing information, which provides a standard reference for abnormal monitoring, so that the system can promptly detect abnormal conditions of the electromagnetic damping device. The maintenance signal generation module is used to generate an electromagnetic damping floating plate structure maintenance signal when the monitoring current magnitude timing information is inconsistent with the target current magnitude timing information, and send it to the management end. Through timely warning, maintenance personnel are prompted to inspect and maintain abnormal electromagnetic damping devices, eliminate potential faults, and ensure the normal operation of track vibration reduction.

[0098] Embodiment 2:

[0099] like Figure 2 As shown, based on the same inventive concept as the rail vibration reduction system based on electromagnetic induction provided in the first embodiment, the embodiment of the present invention further provides a rail monitoring method based on electromagnetic induction, comprising:

[0100] Receiving a train running speed, wherein the train running speed has a running speed acquisition timestamp;

[0101] Acquiring train type information based on the travel speed acquisition timestamp and the train schedule;

[0102] Performing damping force configuration according to the train type information and the train running speed to obtain a target damping force;

[0103] Receive the core movement speed timing information and the core relative movement distance through the displacement sensor;

[0104] Through the current prediction channel, electromagnetic induction analysis is performed on the target damping force, the timing information of the magnetic core movement speed, and the relative movement distance of the magnetic core to obtain the target current magnitude timing information;

[0105] When the monitored current magnitude sequence information is inconsistent with the target current magnitude sequence information, an electromagnetic damping floating plate structure maintenance signal is generated and sent to the management end.

[0106] Further, performing damping force configuration according to the train type information and the train running speed to obtain a target damping force includes:

[0107] Predicting the wheel-rail pressure according to the train type information and the train running speed to obtain the predicted wheel-rail pressure;

[0108] The target damping force is obtained by configuring the damping force through the predicted wheel-rail pressure and the train type information.

[0109] Further, predicting the wheel-rail pressure according to the train type information and the train running speed to obtain the predicted wheel-rail pressure includes:

[0110] Collecting sample data according to the train type information and the train running speed to obtain a wheel-rail pressure monitoring log, wherein the wheel-rail pressure monitoring log includes a plurality of wheel-rail pressure monitoring values;

[0111] performing centralized analysis based on the plurality of wheel-rail pressure monitoring values ​​to obtain a plurality of centralized weighted evaluation values;

[0112] The wheel-rail predicted pressure is obtained by performing weighted mean statistics on the plurality of wheel-rail pressure monitoring values ​​according to the plurality of concentrated weight evaluation values.

[0113] Furthermore, a centralized analysis is performed based on the plurality of wheel-rail pressure monitoring values ​​to obtain a plurality of centralized weight evaluation values, including:

[0114] Obtaining a first wheel-rail pressure monitoring value of the plurality of wheel-rail pressure monitoring values;

[0115] Based on the first wheel-rail pressure monitoring value, traverse the plurality of wheel-rail pressure monitoring values ​​to perform pressure deviation modulus calculation to obtain a plurality of wheel-rail pressure deviation moduli;

[0116] Performing mean analysis on the plurality of wheel-rail pressure deviation moduli to obtain a first wheel-rail pressure dispersion factor, and adding the plurality of wheel-rail pressure dispersion factors;

[0117] Calculating the average of the plurality of wheel-rail pressure dispersion factors to obtain a global average dispersion factor;

[0118] Comparing the global average dispersion factor with the first wheel-rail pressure dispersion factor to obtain a first wheel-rail pressure concentration coefficient, and adding a plurality of wheel-rail pressure concentration coefficients;

[0119] Counting the sum of the plurality of wheel-rail pressure concentration coefficients to obtain a sum value of the wheel-rail pressure concentration coefficients;

[0120] The ratio of the first wheel-rail pressure concentration coefficient to the sum of the wheel-rail pressure concentration coefficients is calculated to obtain a first wheel-rail pressure concentration weight, which is added to the plurality of concentration weight evaluation values.

[0121] Furthermore, electromagnetic induction analysis is performed on the target damping force, the timing information of the magnetic core movement speed, and the relative movement distance of the magnetic core through the current prediction channel to obtain the target current magnitude timing information, including:

[0122] Obtaining electromagnetic damping floating plate structure test data, wherein the electromagnetic damping floating plate structure test data includes damping force test data, magnetic core movement speed timing test data, magnetic core relative movement distance test data and current monitoring timing data;

[0123] Constructing a current prediction loss function, wherein the current prediction loss function includes a first current prediction loss function and a second current prediction loss function, wherein the first current prediction loss function represents a mean value of current prediction deviations at multiple moments, and the second current prediction loss function represents a variance of current prediction deviations at multiple moments;

[0124] Based on the first loss threshold and the second loss threshold, according to the first current prediction loss function and the second current prediction loss function, the current monitoring timing data is retrieved, the damping force test data, the magnetic core movement speed timing test data, and the magnetic core relative movement distance test data are supervised, and the BP neural network is trained to obtain the current prediction channel.

[0125] Further, based on the first loss threshold and the second loss threshold, according to the first current prediction loss function and the second current prediction loss function, the current monitoring time series data is retrieved, the damping force test data, the magnetic core movement speed time series test data, and the magnetic core relative movement distance test data are supervised, and the BP neural network is trained to obtain the current prediction channel, including:

[0126] Retrieving the current monitoring time series data, supervising the damping force test data, the magnetic core movement speed time series test data, and the magnetic core relative movement distance test data, training the BP neural network M times, obtaining M first loss parameters according to the first current prediction loss function, and obtaining M second loss parameters according to the second current prediction loss function;

[0127] Counting the proportion of the M first loss parameters that are less than or equal to the first loss threshold, to obtain a first convergence ratio;

[0128] Counting the proportion of the M second loss parameters that are less than or equal to the second loss threshold, to obtain a second convergence ratio;

[0129] When the first convergence ratio and the second convergence ratio are both greater than or equal to a convergence ratio threshold, the current prediction channel is obtained, wherein 1≥the convergence ratio threshold≥97%.

[0130] Furthermore, the embodiment of the present application also includes:

[0131] When the electromagnetic damping floating plate structure is activated, the current output wire connected to the electromagnetic damping floating plate structure is connected to the energy storage device for energy recovery.

[0132] Embodiment three:

[0133] See also Figure 3 , Figure 3 Schematic diagram of an electronic device provided by an embodiment of the present invention. Figure 3 As shown, an electronic device 200 provided by an embodiment of the present invention includes a memory 210, a processor 220, and a computer program 211 stored in the memory 210 and executable on the processor 220. When the processor 220 executes the computer program 211, a rail vibration reduction system based on electromagnetic induction is implemented.

[0134] Embodiment 4:

[0135] See also Figure 4 , Figure 4 A schematic diagram of an embodiment of a computer-readable storage medium provided in an embodiment of the present invention. Figure 4 As shown, this embodiment provides a computer-readable storage medium 300 on which a computer program 311 is stored. When the computer program 311 is executed by a processor, a rail vibration reduction system based on electromagnetic induction is implemented.

[0136] It should be noted that in the above embodiments, the description of each embodiment has its own emphasis, and for parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0137] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented 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.

[0138] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0139] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0140] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0141] Although preferred embodiments of the present invention have been described, additional changes and modifications may occur to these embodiments once those skilled in the art understand the basic inventive concepts.

[0142] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention belong to the scope of the present invention and its equivalent technology, the present invention is also intended to include these changes and variations.

Claims

1. A rail vibration reduction system based on electromagnetic induction, characterized in that: include: A speed receiving module, the speed receiving module is used to receive the train speed, wherein the train speed has a speed acquisition timestamp; A train type acquisition module, the train type acquisition module is used to acquire the train type information based on the travel speed acquisition timestamp and the train schedule; A damping force configuration module, the damping force configuration module is used to configure the damping force according to the train type information and the train running speed to obtain a target damping force; A magnetic core data acquisition module, wherein the magnetic core data acquisition module is used to receive the magnetic core movement speed timing information and the magnetic core relative movement distance through a displacement sensor; A current prediction module, the current prediction module is used to perform electromagnetic induction analysis on the target damping force, the timing information of the magnetic core movement speed and the relative movement distance of the magnetic core through a current prediction channel to obtain the timing information of the target current magnitude; A maintenance signal generation module, wherein the maintenance signal generation module is used to generate an electromagnetic damping floating plate structure maintenance signal when the monitoring current magnitude sequence information is inconsistent with the target current magnitude sequence information, and send the signal to the management end; The damping force configuration module includes the following execution steps: Predicting the wheel-rail pressure according to the train type information and the train running speed to obtain the predicted wheel-rail pressure; Perform damping force configuration according to the wheel-rail predicted pressure and the train type information to obtain the target damping force; The damping force configuration module further includes the following execution steps: Collecting sample data according to the train type information and the train running speed to obtain a wheel-rail pressure monitoring log, wherein the wheel-rail pressure monitoring log includes a plurality of wheel-rail pressure monitoring values; performing centralized analysis based on the plurality of wheel-rail pressure monitoring values ​​to obtain a plurality of centralized weighted evaluation values; The wheel-rail predicted pressure is obtained by performing weighted mean statistics on the plurality of wheel-rail pressure monitoring values ​​according to the plurality of concentrated weight evaluation values.

2. The system according to claim 1, characterized in that The damping force configuration module also includes the following execution steps: Obtaining a first wheel-rail pressure monitoring value of the plurality of wheel-rail pressure monitoring values; Based on the first wheel-rail pressure monitoring value, traverse the plurality of wheel-rail pressure monitoring values ​​to perform pressure deviation modulus calculation to obtain a plurality of wheel-rail pressure deviation moduli; Performing mean analysis on the plurality of wheel-rail pressure deviation moduli to obtain a first wheel-rail pressure dispersion factor, and adding the plurality of wheel-rail pressure dispersion factors; Calculating the average of the plurality of wheel-rail pressure dispersion factors to obtain a global average dispersion factor; Comparing the global average dispersion factor with the first wheel-rail pressure dispersion factor to obtain a first wheel-rail pressure concentration coefficient, and adding a plurality of wheel-rail pressure concentration coefficients; Counting the sum of the plurality of wheel-rail pressure concentration coefficients to obtain a sum value of the wheel-rail pressure concentration coefficients; The ratio of the first wheel-rail pressure concentration coefficient to the sum of the wheel-rail pressure concentration coefficients is calculated to obtain a first wheel-rail pressure concentration weight, which is added to the plurality of concentration weight evaluation values.

3. The system according to claim 1, characterized in that The current prediction module includes the following execution steps: Obtaining electromagnetic damping floating plate structure test data, wherein the electromagnetic damping floating plate structure test data includes damping force test data, magnetic core movement speed timing test data, magnetic core relative movement distance test data and current monitoring timing data; Constructing a current prediction loss function, wherein the current prediction loss function includes a first current prediction loss function and a second current prediction loss function, wherein the first current prediction loss function represents a mean value of current prediction deviations at multiple moments, and the second current prediction loss function represents a variance of current prediction deviations at multiple moments; Based on the first loss threshold and the second loss threshold, according to the first current prediction loss function and the second current prediction loss function, the current monitoring timing data is retrieved, the damping force test data, the magnetic core movement speed timing test data, and the magnetic core relative movement distance test data are supervised, and the BP neural network is trained to obtain the current prediction channel.

4. The system according to claim 3, characterized in that The current prediction module also includes the following execution steps: Retrieving the current monitoring time series data, supervising the damping force test data, the magnetic core movement speed time series test data, and the magnetic core relative movement distance test data, training the BP neural network M times, obtaining M first loss parameters according to the first current prediction loss function, and obtaining M second loss parameters according to the second current prediction loss function; Counting the proportion of the M first loss parameters that are less than or equal to the first loss threshold, to obtain a first convergence ratio; Counting the proportion of the M second loss parameters that are less than or equal to the second loss threshold, to obtain a second convergence ratio; When the first convergence ratio and the second convergence ratio are both greater than or equal to a convergence ratio threshold, the current prediction channel is obtained, wherein 1≥the convergence ratio threshold≥97%.

5. The system according to claim 1, wherein: It also includes an energy recovery module, which includes the following execution steps: When the electromagnetic damping floating plate structure is activated, the current output wire connected to the electromagnetic damping floating plate structure is connected to the energy storage device for energy recovery.

6. A track monitoring method based on electromagnetic induction, characterized in that: include: Receiving a train running speed, wherein the train running speed has a running speed acquisition timestamp; Acquiring train type information based on the travel speed acquisition timestamp and the train schedule; Performing damping force configuration according to the train type information and the train running speed to obtain a target damping force; Receive the core movement speed timing information and the core relative movement distance through the displacement sensor; Through the current prediction channel, electromagnetic induction analysis is performed on the target damping force, the timing information of the magnetic core movement speed, and the relative movement distance of the magnetic core to obtain the target current magnitude timing information; When the monitored current magnitude sequence information is inconsistent with the target current magnitude sequence information, an electromagnetic damping floating plate structure maintenance signal is generated and sent to the management end.

7. An electronic device, characterized in that: include: Memory for storing computer software programs; A processor is used to read and execute the computer software program, thereby implementing a rail vibration reduction system based on electromagnetic induction as described in any one of claims 1-5.

8. A non-transitory computer-readable storage medium, characterized in that: The storage medium stores a computer software program, and when the computer software program is executed by the processor, it implements a rail vibration reduction system based on electromagnetic induction as described in any one of claims 1 to 5.

Citation Information

Patent Citations

  • Adjustable damping feedback energy suspension system with driving behavior prediction model and control method of adjustable damping feedback energy suspension system

    CN106114111A

  • Magneto-rheological semi-active suspension control method, device and system

    CN113619346A