A method and system for measuring the instantaneous rotation speed of train wheelsets through vibration signals

By combining vibration signal processing with the Mamba model, the problem of inaccurate instantaneous speed measurement of train wheels was solved, high-precision fault diagnosis was achieved, and the accuracy of the train fault diagnosis system was improved.

CN119044527BActive Publication Date: 2025-09-23ZHEJIANG UNIV
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
CN202410965085.0
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-07-18
Publication Date
2025-09-23
Estimated Expiration
2044-07-18

AI Technical Summary

Technical Problem

In the existing technology, the instantaneous rotational speed of train wheels is difficult to measure accurately, resulting in a decrease in the accuracy of the fault diagnosis system. This is especially true in electrified and intelligent trains such as high-speed trains and subways, where errors occur when converting the travel speed using the train control system.

Method used

Through variational modal decomposition, time domain stationary division and fast Fourier transform of vibration signals, combined with deep learning of the Mamba model, a vibration-speed prediction model is established, the instantaneous speed of the train wheels is inversely calculated, and corrections are made based on the speed signal sent by the train control.

Benefits of technology

It greatly improves the accuracy of fault diagnosis, provides relatively accurate real-time speed measurement, and improves the accuracy of the fault diagnosis system.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119044527B_ABST
    Figure CN119044527B_ABST
Patent Text Reader

Abstract

The present invention discloses a method and system for calculating the instantaneous rotational speed of a train wheelset using vibration signals, belonging to the field of diagnostic technology. The method includes the following steps: obtaining a vibration signal and a rotational speed sequence within a continuous time window; performing data processing on each obtained vibration signal to obtain a corresponding vibration signal sequence for each vibration signal, and using the rotational speed sequence as a rotational speed label for each period of stable rotational speed in the vibration signal sequence; inputting the obtained vibration signal sequence and rotational speed sequence into a Mamba model for training to obtain a Mamba vibration-rotational speed prediction model; obtaining a vibration signal to be detected and performing data processing, inputting the obtained vibration signal sequence to be detected into the Mamba vibration-rotational speed prediction model, and outputting a predicted rotational speed sequence. The present invention can obtain relatively accurate real-time rotational speed, significantly improving the accuracy of fault diagnosis.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention belongs to the field of diagnostic technology, and in particular relates to a method and system for measuring the instantaneous rotation speed of a train wheelset through vibration signals. Background Art

[0002] With the electrification and intelligent advancements in high-speed rail, subway, and other rail-based trains, running gear fault diagnosis systems have become widely used in these systems, including intercity and intercity trains. They diagnose faults in running gear bearings, gears, and motors, ensuring safe train operation. These systems typically collect temperature, vibration, and impact signals, and determine the fault location based on the fault's characteristic frequency. This determination requires the instantaneous rotational speed as input.

[0003] At present, it is difficult to obtain the instantaneous speed of the on-board system. Usually, only the speed sensor of the braking system of the lead car can be borrowed. If a speed sensor is added to each axle, it will increase the operation and maintenance costs significantly. Therefore, in most cases, the travel speed of the train control system is still used, which requires converting the speed through the wheel diameter parameters. However, the wheel diameter of each wheel will be different due to the loss during the operation process, and the speed of the train has been filtered and delayed. The obtained speed signal is no longer a real-time and accurate signal, which has a great impact on fault diagnosis.

[0004] At present, for the running gear fault diagnosis system where the rotational speed cannot be directly measured, the rotational speed can only be converted through the train speed information and wheel diameter information transmitted by TCMS. However, the train speed is data after measurement, filtering, averaging, etc., and the wheel diameter information cannot be updated in real time to prevent errors caused by wear, wheel turning, etc. in the later stage. Therefore, the converted rotational speed is not accurate enough, resulting in a decrease in the accuracy of fault feature extraction of vibration signals. Summary of the Invention

[0005] The present invention aims to address the existing problems and provide a method and system for calculating the instantaneous rotational speed of a train wheel set using vibration signals. This method uses the vibration signal to reversely calculate the rotational speed, and then references the speed signal transmitted by the train control system to obtain a relatively accurate real-time rotational speed, significantly improving the accuracy of fault diagnosis.

[0006] In order to achieve the above-mentioned object of the invention, the present invention specifically adopts the following technical solutions:

[0007] In a first aspect, the present invention provides a method for calculating the instantaneous rotational speed of a train wheelset using a vibration signal, the specific steps of which are as follows:

[0008] S1. Obtain the vibration signal and speed sequence within a continuous time window;

[0009] S2. Data processing is performed on each vibration signal obtained, and each vibration signal corresponds to a vibration signal sequence, and the speed sequence is used as a speed label for each stable speed period of the vibration signal sequence;

[0010] In step S2, the data processing is specifically performed as follows:

[0011] S21. Perform variational modal decomposition on each vibration signal, generating n IMF components for each vibration signal;

[0012] S22. The ultra-high frequency signal is filtered out from the n IMF components of each vibration signal, and each IMF component corresponds to a filtered IMF component;

[0013] S23. The time domain segmentation of each filtered IMF component is performed according to the moment when the rate of change of the vibration signal speed signal is not 0, and each filtered IMF component is divided into m vibration signals at steady-state speed;

[0014] S24. Perform a fast Fourier transform on each steady-state vibration signal to obtain a spectrum. In each spectrum, the frequency value at which the gain is maximum is taken as the frequency eigenvalue. The frequency eigenvalues ​​corresponding to each vibration signal are combined into a one-dimensional sequence according to the order and time sequence of IMF component generation as a vibration signal sequence.

[0015] S3. Input the obtained vibration signal sequence and speed sequence into the Mamba model for training, and use the trained Mamba model as the vibration-speed Mamba prediction model;

[0016] S4. Obtain the vibration signal to be detected, perform data processing on the vibration signal to be detected, obtain a vibration signal sequence to be detected, input the vibration signal sequence to be detected into the vibration-speed Mamba prediction model, and output a predicted speed sequence.

[0017] In a second aspect, the present invention provides a system for measuring the instantaneous rotational speed of a train wheel set using a vibration signal, comprising: a data acquisition module, a data processing module, and a data monitoring module, wherein the data acquisition module interacts with the data processing module, and the data processing module interacts with the data monitoring module;

[0018] Data acquisition module, used to obtain vibration signals and speed sequences within a continuous time window;

[0019] The data processing module is used to perform data processing on each acquired vibration signal, obtain a vibration signal sequence corresponding to each vibration signal, and use the speed sequence as the speed label of each speed stable period of the vibration signal sequence; wherein, the specific process of the data processing is as follows: each vibration signal is subjected to variational mode decomposition, and each vibration signal generates n IMF components; the ultra-high frequency signal in the n IMF components of each vibration signal is filtered out, and each IMF component corresponds to a filtered IMF component; each filtered IMF component is subjected to time domain segmentation according to the moment when the rate of change of the vibration signal speed signal is not 0, and each filtered IMF component is segmented into m vibration signals at steady-state speed; each vibration signal at steady-state speed is subjected to fast Fourier transform to obtain a spectrum, and the frequency value at the maximum gain in each spectrum is taken as the frequency eigenvalue, and the frequency eigenvalues ​​corresponding to each vibration signal are combined into a one-dimensional sequence according to the order of generation of the IMF components and the time order as a vibration signal sequence;

[0020] The data monitoring module is used to input the obtained vibration signal sequence and speed sequence into the Mamba model for training, and use the trained Mamba model as the vibration-speed Mamba prediction model; obtain the vibration signal to be detected, and perform data processing on the vibration signal to be detected to obtain the vibration signal sequence to be detected, input the vibration signal sequence to be detected into the vibration-speed Mamba prediction model, and output the predicted speed sequence.

[0021] As a preferred embodiment of the above-mentioned second aspect, the data acquisition module includes a vibration sensor, a sensor data preprocessing module, a controller module, a power supply module, a clock module, a memory module and a data transmission module. The vibration sensor is connected to the controller module through the sensor data preprocessing module, and the clock module, the memory module, the data transmission module and the power supply module are all directly connected to the controller module.

[0022] As a preferred embodiment of the second aspect, the sensor data preprocessing module includes a first resistor, a second resistor, a third resistor, a fourth resistor, a fifth resistor, a sixth resistor, a seventh resistor, an eighth resistor, a ninth resistor, a first capacitor, a second capacitor, a third capacitor, a fourth capacitor, a first operational amplifier, a second operational amplifier, and a third operational amplifier;

[0023] Among them, the signal input -IN terminal is connected to one end of the first resistor, the other end of the first resistor is respectively connected to one end of the first capacitor, one end of the third resistor and the negative power supply pin of the first operational amplifier, the other end of the first capacitor and the other end of the third resistor are both connected to the output pin of the first operational amplifier, the signal input +IN terminal is connected to one end of the second resistor, the other end of the second resistor is respectively connected to one end of the fourth resistor, one end of the second capacitor and the positive power supply pin of the first operational amplifier, the other end of the second capacitor is connected to the other end of the fourth resistor and grounded, the other end of the second capacitor is connected to the other end of the fourth resistor and grounded, the output pin of the first operational amplifier is connected to one end of the fifth resistor, the positive pole of the power supply end of the first operational amplifier is connected to the DC power supply, the negative pole of the power supply end of the first operational amplifier is grounded, and the other end of the fifth resistor is connected The positive power supply pin of the second operational amplifier and the negative power supply pin of the second operational amplifier are connected to the negative power supply pin of the third operational amplifier, the positive power supply pin of the second operational amplifier is connected to the DC power supply, the negative power supply pin of the second operational amplifier is grounded, the positive power supply pin of the third operational amplifier is respectively connected to one end of the eighth resistor and one end of the ninth resistor, the other end of the ninth resistor is grounded, the positive power supply pin of the third operational amplifier is connected to the DC power supply, the negative power supply pin of the third operational amplifier is grounded, the other end of the eighth resistor and one end of the seventh resistor are both connected to the output pin of the second operational amplifier, the other end of the seventh resistor is connected to one end of the fourth capacitor, the other end of the fourth capacitor and one end of the sixth resistor are both connected to the output pin of the third operational amplifier, the other end of the sixth resistor is connected to one end of the third capacitor, and the other end of the third capacitor is grounded.

[0024] As a preferred embodiment of the above-mentioned second aspect, the clock module includes a clock chip, a fifth capacitor, a tenth resistor, an eleventh resistor, a twelfth resistor and a thirteenth resistor, the first DC power supply end is respectively connected to one end of the tenth resistor and one end of the eleventh resistor, the other end of the tenth resistor is connected to the SDA end of the clock chip, the other end of the eleventh resistor is connected to the SCL end of the clock chip, the second DC power supply end is respectively connected to one end of the twelfth resistor, one end of the thirteenth resistor, one end of the fifth capacitor and port 2 of the clock chip, the other end of the fifth capacitor is grounded, the other end of the twelfth resistor is connected to port 1 of the clock chip, the other end of the thirteenth resistor is connected to port 3 of the clock chip, port 4 of the clock chip is connected to the controller module, port 5, port 6, port 7, port 8, port 13, port 12, port 11, port 10 and port 9 of the clock chip are all grounded, and port 14 of the clock chip is connected to an external battery.

[0025] As a preferred embodiment of the second aspect, the power module includes an auxiliary power supply circuit and an isolation circuit connected to the auxiliary power supply circuit, the auxiliary power supply circuit includes a 24V voltage input terminal, a 12V voltage output terminal, a first diode, a second diode, a sixth capacitor, a seventh capacitor, an eighth capacitor, a ninth capacitor, a tenth capacitor, a fourteenth resistor, a fifteenth resistor, a sixteenth resistor, a first chip, and a first inductor, and the isolation circuit includes a second chip, a seventeenth resistor, an eighteenth resistor, a nineteenth resistor, a twentieth resistor, a twenty-first resistor, and a transistor;

[0026] Among them, the 24V voltage input end is connected to the positive electrode of the first diode, the negative electrode of the first diode is respectively connected to one end of the sixth capacitor, the positive electrode of the seventh capacitor, one end of the fourteenth resistor, and pin 6 of the first chip, the other end of the fourteenth resistor is respectively connected to pin 7, pin 8 and pin 1 of the first chip, pin 2 of the first chip is respectively connected to the negative electrode of the second diode and one end of the first inductor, the other end of the first inductor is respectively connected to the positive electrode of the ninth capacitor, one end of the tenth capacitor and the 12V voltage output end, the other end of the tenth capacitor is respectively connected to the negative electrode of the ninth capacitor, the positive electrode of the second diode, one end of the eighth capacitor, pin 4 of the first chip, one end of the fifteenth resistor, the negative electrode of the seventh capacitor and the pin of the sixth capacitor The other end, the other end of the eighth capacitor is connected to pin 3 of the first chip, the other end of the fifteenth resistor is respectively connected to pin 5 of the first chip and one end of the sixteenth resistor, the other end of the sixteenth resistor is connected to the 12V voltage output end, the IN1 input end of the second chip is connected to one end of the eighteenth resistor through the seventeenth resistor, the 12V voltage output end is connected to the other end of the eighteenth resistor and the +12V voltage end of the second chip, the positive output end of the second chip is connected to the collector of the transistor through the nineteenth resistor, the negative output end of the second chip is connected to one end of the twentieth resistor and one end of the twenty-first resistor, the other end of the twentieth resistor is connected to the base of the transistor, and the other end of the twenty-first resistor is connected to the emitter of the transistor.

[0027] Compared with the prior art, the present invention has the following beneficial effects:

[0028] The method of the present invention uses VMD, time domain stationary division and a data processing method of obtaining a strong signal spectrum after FFT, and uses the Mamba model for deep learning to obtain a relatively accurate Mamba prediction model of vibration-speed. The Mamba prediction model of vibration-speed can obtain a relatively accurate real-time speed, greatly improving the accuracy of fault diagnosis. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without paying any creative work.

[0030] Figure 1 is a flow chart of the method of the present invention;

[0031] Figure 2 It is a schematic diagram of the system structure of the present invention;

[0032] Figure 3 It is a structural diagram of the data acquisition module of the present invention;

[0033] Figure 4 is a circuit diagram of the sensor data preprocessing module of the present invention;

[0034] Figure 5 is a circuit diagram of a clock module of the present invention;

[0035] Figure 6 is a circuit diagram of an auxiliary power supply circuit in a power supply module of the present invention;

[0036] In the figure: signal input -IN terminal -IN, signal input +IN terminal +IN, DC power supply +VCC, clock chip DS3231, first DC power supply terminal VEE, second DC power supply terminal VDD, external battery BAT1 Battery, 24V voltage input terminal Uin, first resistor R4, second resistor R5, third resistor R6, fourth resistor R7, fifth resistor R8, sixth resistor R9, seventh resistor R10, eighth resistor R11, ninth resistor R12, tenth resistor R25, eleventh resistor R26, twelfth resistor R27, thirteenth resistor R28, fourteenth resistor R61, fifteenth resistor R62, sixteenth resistor R63, first capacitor C3, second capacitor C4, third capacitor C5, fourth capacitor C6, fifth capacitor C7, sixth capacitor C8, seventh capacitor E3, eighth capacitor C9, ninth capacitor E1, tenth capacitor C10, first diode D1, second diode D2, first chip U1, first inductor L1. DETAILED DESCRIPTION

[0037] In order to make the above-mentioned objects, features and advantages of the present invention more clearly understood, the specific embodiments of the present invention are described in detail below with reference to the accompanying drawings. In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention can be implemented in many other ways than those described herein, and those skilled in the art can make similar improvements without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below. The technical features in the various embodiments of the present invention can be combined accordingly without conflicting with each other.

[0038] In the description of the present invention, it should be understood that when an element is considered to be "connected" to another element, it can be directly connected to the other element or indirectly connected, that is, there are intermediate elements. On the contrary, when an element is said to be "directly" connected to another element, there are no intermediate elements.

[0039] In the description of the present invention, it should be understood that the terms "first" and "second" are used solely for descriptive purposes and are not to be construed as indicating or implying relative importance or implicitly specifying the number of technical features being described. Therefore, features defined as "first" or "second" may explicitly or implicitly include at least one of such features.

[0040] like Figure 1 As shown, in a preferred implementation of the present invention, the above method for measuring the instantaneous rotation speed of a train wheel set by using a vibration signal includes the following steps S1 to S4. The specific implementation process is described in detail below.

[0041] S1. Data acquisition: Acquire the vibration signal and speed sequence within a continuous time window (Δt time).

[0042] S2. Data processing: Perform data processing on each acquired vibration signal. Each vibration signal corresponds to a vibration signal sequence, and the speed sequence is used as the speed label of each stable speed period in the vibration signal sequence.

[0043] In step S2, the data processing is specifically performed as follows:

[0044] S21. Perform variational mode decomposition (VMD) on each vibration signal, and generate n IMF components for each vibration signal.

[0045] S22. Filter out the ultra-high frequency signal from the n IMF components of each vibration signal, and obtain a filtered IMF component corresponding to each IMF component.

[0046] It should be noted that, in the present invention, the signal with a frequency above 900kHz is used as an ultra-high frequency signal, and the IMF component is low-pass filtered to filter the ultra-high frequency signal therein to obtain the filtered IMF component for subsequent processing.

[0047] S23. Perform time domain segmentation on each filtered IMF component according to the moment when the rate of change of the vibration signal and the speed signal is not 0, and segment each filtered IMF component into m vibration signals at steady-state speeds.

[0048] It should be noted that, in step S23 of the present invention, for one vibration signal, n×m vibration signals at steady-state speeds are obtained.

[0049] S24. Perform fast Fourier transform (FFT) on the vibration signal at each steady-state speed to obtain a spectrum. In each spectrum, take the frequency value when the gain is maximum as the frequency eigenvalue. The frequency eigenvalues ​​corresponding to each vibration signal are combined into a one-dimensional sequence x[n×m] according to the order of IMF component generation and the time order as a vibration signal sequence.

[0050] It should be noted that in step S24 of the present invention, a fast Fourier transform FFT is performed on the vibration signal at each steady-state speed, and each vibration signal corresponds to n×m frequency spectra. The frequency value at the maximum gain in each spectrum obtained for each vibration signal is taken as the frequency eigenvalue, and these n×m frequency eigenvalues ​​are combined into a one-dimensional sequence x[n×m] as a vibration signal sequence in the order of IMF component generation and time sequence, and the corresponding output m speed sequences y[m] are used as the speed label of each speed stable period of the vibration signal sequence.

[0051] S3. Model training: The obtained vibration signal sequence x[n×m] and speed sequence y[m] are input into the Mamba model for training, and the trained Mamba model is used as the vibration-speed Mamba prediction model.

[0052] S4. Model prediction: Obtain the vibration signal to be detected, perform data processing on the vibration signal to be detected, obtain the vibration signal sequence to be detected, input the vibration signal sequence to be detected into the vibration-speed Mamba prediction model, and output the predicted speed sequence.

[0053] In the present invention, the rotational speed sequence is inversely calculated by the vibration signal, and the predicted rotational speed sequence can be subsequently corrected with reference to the speed signal sent by the train control system to obtain a relatively accurate real-time rotational speed sequence.

[0054] The present invention uses variational mode decomposition (VMD), time-domain stationary partitioning, and a data processing method of obtaining the strong signal spectrum after fast Fourier transform (FFT). It uses the Mamba model for deep learning to obtain a relatively accurate Mamba prediction model of vibration-speed. The speed is inversely calculated from the vibration signal, and then reference is made to the speed signal sent by the train control to obtain a relatively accurate real-time speed, thereby completing train monitoring and greatly improving the accuracy of fault diagnosis.

[0055] like Figure 2 As shown, the present invention provides a system for measuring the instantaneous rotational speed of a train wheelset through vibration signals, which includes: a data acquisition module, a data processing module and a data monitoring module, the data acquisition module interacts with the data processing module, and the data processing module interacts with the data monitoring module.

[0056] Data acquisition module, used to obtain vibration signals and speed sequences within a continuous time window;

[0057] The data processing module is used to perform data processing on each acquired vibration signal, obtain a vibration signal sequence corresponding to each vibration signal, and use the speed sequence as the speed label of each speed stable period of the vibration signal sequence; wherein, the specific process of the data processing is as follows: each vibration signal is subjected to variational mode decomposition, and each vibration signal generates n IMF components; the ultra-high frequency signal in the n IMF components of each vibration signal is filtered out, and each IMF component corresponds to a filtered IMF component; each filtered IMF component is subjected to time domain segmentation according to the moment when the rate of change of the vibration signal speed signal is not 0, and each filtered IMF component is segmented into m vibration signals at steady-state speed; each vibration signal at steady-state speed is subjected to fast Fourier transform to obtain a spectrum, and the frequency value at the maximum gain in each spectrum is taken as the frequency eigenvalue, and the frequency eigenvalues ​​corresponding to each vibration signal are combined into a one-dimensional sequence according to the order of generation of the IMF components and the time order as a vibration signal sequence;

[0058] The data monitoring module is used to input the obtained vibration signal sequence and speed sequence into the Mamba model for training, and use the trained Mamba model as the vibration-speed Mamba prediction model; obtain the vibration signal to be detected, and perform data processing on the vibration signal to be detected to obtain the vibration signal sequence to be detected, input the vibration signal sequence to be detected into the vibration-speed Mamba prediction model, and output the predicted speed sequence.

[0059] It should be noted that using existing technologies to acquire vibration signals and speed sequences within a continuous time window can lead to unstable data. To address this issue, the present invention improves the existing data acquisition module and adds a sensor data preprocessing module, along with an improved power supply module and clock module. Compared to the existing data acquisition module, the improved data acquisition module of the present invention has the advantage of amplifying and filtering the data collected by the vibration sensor before inputting it into the sensor data preprocessing module, a signal conversion circuit that can significantly reduce signal noise and signal loss during measurement.

[0060] The following describes in detail the structure of the data acquisition module of the present invention. Figure 3 As shown, the data acquisition module includes a vibration sensor, a sensor data preprocessing module, a controller module, a power module, a clock module, a memory module, and a data transmission module. The vibration sensor is connected to the controller module via the sensor data preprocessing module, while the clock module, memory module, data transmission module, and power module are all directly connected to the controller module.

[0061] It should be noted that in the above-mentioned data acquisition module, based on the consideration of signal noise and signal loss in measurement, the present invention connects the vibration sensor to the controller module through the sensor data preprocessing module, which can greatly reduce the signal noise and signal loss in measurement. Based on the consideration of data acquisition, data analysis, data transmission, and data storage, the present invention directly connects the clock module, memory module, data transmission module, and power supply module to the controller module, so that the instantaneous rotational speed of the train wheels can be measured by the vibration signal and analyzed, processed, and transmitted in a timely manner. Among them, the sensor data preprocessing module is used to reduce the signal noise and signal loss in measurement, the power supply module is used to provide the required electrical energy, and the clock module is used to record time so that the memory module can store data according to the time recorded by the clock module. In order to facilitate those skilled in the art to better understand the essence of the present invention, the implementation methods of the sensor data preprocessing module, the power supply module, and the clock module are respectively explained below.

[0062] like Figure 4As shown, the above-mentioned sensor data preprocessing module includes a first resistor R4, a second resistor R5, a third resistor R6, a fourth resistor R7, a fifth resistor R8, a sixth resistor R9, a seventh resistor R10, an eighth resistor R11, a ninth resistor R12, a first capacitor C3, a second capacitor C4, a third capacitor C5, a fourth capacitor C6, a first operational amplifier, a second operational amplifier and a third operational amplifier. Among them, the signal input -IN terminal -IN is connected to one end of the first resistor R4, the other end of the first resistor R4 is respectively connected to one end of the first capacitor C3, one end of the third resistor R6 and the negative power supply pin of the first operational amplifier, the other end of the first capacitor C3 and the other end of the third resistor R6 are both connected to the output pin of the first operational amplifier, the signal input +IN terminal +IN is connected to one end of the second resistor R5, the other end of the second resistor R5 is respectively connected to one end of the fourth resistor R7, one end of the second capacitor C4 and the positive power supply pin of the first operational amplifier, the other end of the second capacitor C4 is connected to the other end of the fourth resistor R7 and grounded, the other end of the second capacitor C4 is connected to the other end of the fourth resistor R7 and grounded, the output pin of the first operational amplifier is connected to one end of the fifth resistor R8, the positive pole of the power supply end of the first operational amplifier is connected to the DC power supply +VCC, the negative pole of the power supply end of the first operational amplifier is grounded, and the other end of the fifth resistor R8 The positive power supply pin of the second operational amplifier is connected, the negative power supply pin of the second operational amplifier is connected to the negative power supply pin of the third operational amplifier, the positive power supply pin of the second operational amplifier is connected to the DC power supply +VCC, the negative power supply pin of the second operational amplifier is grounded, the positive power supply pin of the third operational amplifier is respectively connected to one end of the eighth resistor R11 and one end of the ninth resistor R12, the other end of the ninth resistor R12 is grounded, the positive power supply pin of the third operational amplifier is connected to the DC power supply +VCC, the negative power supply pin of the third operational amplifier is grounded, the other end of the eighth resistor R11 and one end of the seventh resistor R10 are both connected to the output pin of the second operational amplifier, the other end of the seventh resistor R10 is connected to one end of the fourth capacitor C6, the other end of the fourth capacitor C6 and one end of the sixth resistor R9 are both connected to the output pin of the third operational amplifier, the other end of the sixth resistor R9 is connected to one end of the third capacitor C5, and the other end of the third capacitor C5 is grounded.

[0063] The present invention amplifies and filters the data collected by the vibration sensor and then inputs it into the sensor data preprocessing module. The sensor data preprocessing module is a signal conversion circuit that can greatly reduce signal noise and signal loss during measurement. Among them, the amplification circuit part is an amplification circuit composed of an OPA277 operational amplifier and resistors and capacitors. This circuit is a typical differential amplifier circuit. At the same time, the first capacitor C3 and the third resistor R6, the second capacitor C4 and the fourth resistor R7 form a low-pass filter. The dual op amp bandpass filter designed by the present invention is composed of two OPA277 operational amplifiers. The Q value and center frequency of the dual op amp bandpass filter are adjustable. Adjusting the sixth resistor R9 can adjust the resonant frequency of the circuit, and adjusting the fifth resistor R8 can adjust the Q value of the circuit.

[0064] It is worth noting that the vibration sensor collects signals at various points, selects and outputs them to the signal processing circuit, and then inputs them into the AD7794 for digital-to-analog conversion, converting the analog signal into a digital signal, which is conducive to long-distance wireless transmission of the signal. It is also worth noting that the 24-bit Σ-Δ analog-to-digital converter AD7794 has a noise of only 40nV and a power consumption of only 400μA, making it particularly suitable for applications requiring low power consumption and high-precision measurement.

[0065] like Figure 5 As shown, the clock module includes a clock chip DS3231, a fifth capacitor C7, a tenth resistor R25, an eleventh resistor R26, a twelfth resistor R27, and a thirteenth resistor R28. The first DC power supply terminal VEE is connected to one end of the tenth resistor R25 and one end of the eleventh resistor R26, respectively. The other end of the tenth resistor R25 is connected to the SDA end of the clock chip DS3231, and the other end of the eleventh resistor R26 is connected to the SCL end of the clock chip DS3231. The second DC power supply terminal VDD is connected to one end of the twelfth resistor R27 and one end of the thirteenth resistor R28, respectively. , one end of the fifth capacitor C7 and port 2 of the clock chip DS3231, the other end of the fifth capacitor C7 is grounded, the other end of the twelfth resistor R27 is connected to port 1 of the clock chip DS3231, the other end of the thirteenth resistor R28 is connected to port 3 of the clock chip DS3231, port 4 of the clock chip DS3231 is connected to the controller module, port 5, port 6, port 7, port 8, port 13, port 12, port 11, port 10, and port 9 of the clock chip DS3231 are all grounded, and port 14 of the clock chip DS3231 is connected to the external battery BAT1 Battery.

[0066] In the present invention, the clock module circuit is designed and implemented using the low-cost, high-precision real-time clock chip DS3231. The register addresses of the DS3231 are 00h to 12h. The clock module obtains clock and calendar information by reading the appropriate register bytes. The clock and calendar information are obtained by writing the appropriate register bytes. The clock and calendar data are set or initialized by writing the appropriate register bytes.

[0067] The power module includes an auxiliary power circuit and an isolation circuit connected to the auxiliary power circuit. Figure 6 As shown, the auxiliary power supply circuit includes a 24V voltage input terminal Uin, a 12V voltage output terminal, a first diode D1, a second diode D2, a sixth capacitor C8, a seventh capacitor E3, an eighth capacitor C9, a ninth capacitor E1, a tenth capacitor C10, a fourteenth resistor R61, a fifteenth resistor R62, a sixteenth resistor R63, a first chip U1, and a first inductor L1. The isolation circuit includes a second chip, a seventeenth resistor, an eighteenth resistor, a nineteenth resistor, a twentieth resistor, a twenty-first resistor, and a transistor. This circuit is not only compact, efficient, accurately regulated, and has minimal interference, but it can also convert a 24V input power supply into 12V DC power, providing a 12V DC voltage.

[0068] Among them, the 24V voltage input terminal Uin is connected to the positive electrode of the first diode D1, the negative electrode of the first diode D1 is respectively connected to one end of the sixth capacitor C8, the positive electrode of the seventh capacitor E3, one end of the fourteenth resistor R61, and the 6th pin of the first chip U1, the other end of the fourteenth resistor R61 is respectively connected to the 7th pin, the 8th pin and the 1st pin of the first chip U1, the pin 2 of the first chip U1 is respectively connected to the negative electrode of the second diode D2 and one end of the first inductor L1, the other end of the first inductor L1 is respectively connected to the positive electrode of the ninth capacitor E1, one end of the tenth capacitor C10 and the 12V voltage output terminal, the other end of the tenth capacitor C10 is respectively connected to the negative electrode of the ninth capacitor E1, the positive electrode of the second diode D2, one end of the eighth capacitor C9, the 4th pin of the first chip U1, one end of the fifteenth resistor R62, the seventh capacitor E3 The negative electrode of the second chip U2 is connected to the negative electrode of the first chip U1 and the other end of the sixth capacitor C8, the other end of the eighth capacitor C9 is connected to the 3 pin of the first chip U1, the other end of the fifteenth resistor R62 is respectively connected to the 5 pin of the first chip U1 and one end of the sixteenth resistor R63, the other end of the sixteenth resistor R63 is connected to the 12V voltage output end, the IN1 input end of the second chip U2 is connected to one end of the eighteenth resistor through the seventeenth resistor, the 12V voltage output end is connected to the other end of the eighteenth resistor and the +12V voltage end of the second chip U2, the positive output end of the second chip U2 is connected to the collector of the transistor V1 through the nineteenth resistor, the negative output end of the second chip U2 is connected to one end of the twentieth resistor and one end of the twenty-first resistor, the other end of the twentieth resistor is connected to the base of the transistor V1, and the other end of the twenty-first resistor is connected to the emitter of the transistor V1.

[0069] It should be noted that in industrial control equipment, power ground isolation between two systems is sometimes required, for example, to isolate ground noise or high common-mode voltage. This is achieved by using a DC converter with a transformer to separate the two power supplies, making them independent. Each isolated circuit is powered independently, preventing damage to one module due to high-voltage discharge or other factors from affecting other modules. This ensures that each module operates independently and without interference.

[0070] The embodiment described above is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Persons skilled in the art may make various changes and modifications without departing from the spirit and scope of the present invention. Therefore, any technical solution obtained by equivalent substitution or equivalent transformation falls within the scope of protection of the present invention.

Claims

1. A method for calculating the instantaneous rotational speed of a train wheel set by using a vibration signal, characterized in that: The following steps are involved: S1. Obtain the vibration signal and speed sequence within a continuous time window; S2. Data processing is performed on each vibration signal obtained, and each vibration signal corresponds to a vibration signal sequence, and the speed sequence is used as a speed label for each stable speed period of the vibration signal sequence; In step S2, the data processing is specifically performed as follows: S21. Perform variational modal decomposition on each vibration signal, generating n IMF components for each vibration signal; S22. The ultra-high frequency signal is filtered out from the n IMF components of each vibration signal, and each IMF component corresponds to a filtered IMF component; S23. The time domain segmentation of each filtered IMF component is performed according to the moment when the rate of change of the vibration signal speed signal is not 0, and each filtered IMF component is divided into m vibration signals at steady-state speed; S24. Perform a fast Fourier transform on each steady-state vibration signal to obtain a spectrum. In each spectrum, the frequency value at which the gain is maximum is taken as the frequency eigenvalue. The frequency eigenvalues ​​corresponding to each vibration signal are combined into a one-dimensional sequence according to the order and time sequence of IMF component generation as a vibration signal sequence. S3. Input the obtained vibration signal sequence and speed sequence into the Mamba model for training, and use the trained Mamba model as the vibration-speed Mamba prediction model; S4. Obtain the vibration signal to be detected, perform data processing on the vibration signal to be detected, obtain a vibration signal sequence to be detected, input the vibration signal sequence to be detected into the vibration-speed Mamba prediction model, and output a predicted speed sequence.

2. A system for measuring the instantaneous rotational speed of a train wheel set using vibration signals, characterized in that: include: A data acquisition module, a data processing module and a data monitoring module, wherein the data acquisition module exchanges information with the data processing module, and the data processing module exchanges information with the data monitoring module; Data acquisition module, used to obtain vibration signals and speed sequences within a continuous time window; The data processing module is used to perform data processing on each acquired vibration signal, obtain a vibration signal sequence corresponding to each vibration signal, and use the speed sequence as the speed label of each speed stable period of the vibration signal sequence; wherein, the specific process of the data processing is as follows: each vibration signal is subjected to variational mode decomposition, and each vibration signal generates n IMF components; the ultra-high frequency signal in the n IMF components of each vibration signal is filtered out, and each IMF component corresponds to a filtered IMF component; each filtered IMF component is subjected to time domain segmentation according to the moment when the rate of change of the vibration signal speed signal is not 0, and each filtered IMF component is segmented into m vibration signals at steady-state speed; each vibration signal at steady-state speed is subjected to fast Fourier transform to obtain a spectrum, and the frequency value at the maximum gain in each spectrum is taken as the frequency eigenvalue, and the frequency eigenvalues ​​corresponding to each vibration signal are combined into a one-dimensional sequence according to the order of generation of the IMF components and the time order as a vibration signal sequence; The data monitoring module is used to input the obtained vibration signal sequence and speed sequence into the Mamba model for training, and use the trained Mamba model as the vibration-speed Mamba prediction model; obtain the vibration signal to be detected, and perform data processing on the vibration signal to be detected to obtain the vibration signal sequence to be detected, input the vibration signal sequence to be detected into the vibration-speed Mamba prediction model, and output the predicted speed sequence.

3. The system for measuring the instantaneous rotation speed of a train wheel set by using a vibration signal according to claim 2, characterized in that: The data acquisition module includes a vibration sensor, a sensor data preprocessing module, a controller module, a power module, a clock module, a memory module and a data transmission module. The vibration sensor is connected to the controller module through the sensor data preprocessing module, and the clock module, the memory module, the data transmission module and the power module are all directly connected to the controller module.

4. The system for measuring the instantaneous rotation speed of a train wheel set by using a vibration signal according to claim 3, characterized in that: The sensor data preprocessing module includes a first resistor (R4), a second resistor (R5), a third resistor (R6), a fourth resistor (R7), a fifth resistor (R8), a sixth resistor (R9), a seventh resistor (R10), an eighth resistor (R11), a ninth resistor (R12), a first capacitor (C3), a second capacitor (C4), a third capacitor (C5), a fourth capacitor (C6), a first operational amplifier, a second operational amplifier, and a third operational amplifier; Wherein, the signal input -IN terminal (-IN) is connected to one end of the first resistor (R4), the other end of the first resistor (R4) is respectively connected to one end of the first capacitor (C3), one end of the third resistor (R6) and the negative power supply pin of the first operational amplifier, the other end of the first capacitor (C3) and the other end of the third resistor (R6) are both connected to the output pin of the first operational amplifier, the signal input +IN terminal (+IN) is connected to one end of the second resistor (R5), the other end of the second resistor (R5) is respectively connected to one end of the fourth resistor (R7), one end of the second capacitor (C4) and the positive power supply pin of the first operational amplifier, the other end of the second capacitor (C4) is connected to the other end of the fourth resistor (R7) and grounded, the other end of the second capacitor (C4) is connected to the other end of the fourth resistor (R7) and grounded, the output pin of the first operational amplifier is connected to one end of the fifth resistor (R8), the positive pole of the power supply terminal of the first operational amplifier is connected to the DC power supply (+VCC), the negative pole of the power supply terminal of the first operational amplifier is grounded, and the fifth resistor (R8 ) is connected to the positive power supply pin of the second operational amplifier, the negative power supply pin of the second operational amplifier is connected to the negative power supply pin of the third operational amplifier, the positive power supply pin of the second operational amplifier is connected to the DC power supply (+VCC), the negative power supply pin of the second operational amplifier is grounded, the positive power supply pin of the third operational amplifier is respectively connected to one end of the eighth resistor (R11) and one end of the ninth resistor (R12), the other end of the ninth resistor (R12) is grounded, the positive power supply pin of the third operational amplifier is connected to the DC power supply (+VCC), the negative power supply pin of the third operational amplifier is grounded, the other end of the eighth resistor (R11) and one end of the seventh resistor (R10) are both connected to the output pin of the second operational amplifier, the other end of the seventh resistor (R10) is connected to one end of the fourth capacitor (C6), the other end of the fourth capacitor (C6) and one end of the sixth resistor (R9) are both connected to the output pin of the third operational amplifier, the other end of the sixth resistor (R9) is connected to one end of the third capacitor (C5), and the other end of the third capacitor (C5) is grounded.

5. The system for measuring the instantaneous rotation speed of a train wheel set by using a vibration signal according to claim 3, characterized in that: The clock module includes a clock chip (DS3231), a fifth capacitor (C7), a tenth resistor (R25), an eleventh resistor (R26), a twelfth resistor (R27) and a thirteenth resistor (R28), a first DC power supply terminal (VEE) is respectively connected to one end of the tenth resistor (R25) and one end of the eleventh resistor (R26), the other end of the tenth resistor (R25) is connected to the SDA end of the clock chip (DS3231), the other end of the eleventh resistor (R26) is connected to the SCL end of the clock chip (DS3231), and a second DC power supply terminal (VDD) is respectively connected to one end of the twelfth resistor (R27), the thirteenth resistor (R28) and the second DC power supply terminal (VDD). ), one end of the fifth capacitor (C7) and port 2 of the clock chip (DS3231), the other end of the fifth capacitor (C7) is grounded, the other end of the twelfth resistor (R27) is connected to port 1 of the clock chip (DS3231), the other end of the thirteenth resistor (R28) is connected to port 3 of the clock chip (DS3231), port 4 of the clock chip (DS3231) is connected to the controller module, ports 5, 6, 7, 8, 13, 12, 11, 10 and 9 of the clock chip (DS3231) are all grounded, and port 14 of the clock chip (DS3231) is connected to an external battery (BAT1 Battery).

6. The system for measuring the instantaneous rotation speed of a train wheel set by using a vibration signal according to claim 3, characterized in that: The power module comprises an auxiliary power circuit and an isolation circuit connected to the auxiliary power circuit, wherein the auxiliary power circuit comprises a 24V voltage input terminal (Uin), a 12V voltage output terminal, a first diode (D1), a second diode (D2), a sixth capacitor (C8), a seventh capacitor (E3), an eighth capacitor (C9), a ninth capacitor (E1), a tenth capacitor (C10), a fourteenth resistor (R61), a fifteenth resistor (R62), a sixteenth resistor (R63), a first chip (U1) and a first inductor (L1), and the isolation circuit comprises a second chip, a seventeenth resistor, an eighteenth resistor, a nineteenth resistor, a twentieth resistor, a twenty-first resistor and a transistor; The 24V voltage input terminal (Uin) is connected to the positive electrode of the first diode (D1), the negative electrode of the first diode (D1) is respectively connected to one end of the sixth capacitor (C8), the positive electrode of the seventh capacitor (E3), one end of the fourteenth resistor (R61), and pin 6 of the first chip (U1), the other end of the fourteenth resistor (R61) is respectively connected to pins 7, 8 and 1 of the first chip (U1), pin 2 of the first chip (U1) is respectively connected to the negative electrode of the second diode (D2) and one end of the first inductor (L1), the other end of the first inductor (L1) is respectively connected to the positive electrode of the ninth capacitor (E1), one end of the tenth capacitor (C10) and the 12V voltage output terminal, the other end of the tenth capacitor (C10) is respectively connected to the negative electrode of the ninth capacitor (E1), the positive electrode of the second diode (D2), one end of the eighth capacitor (C9), pins 4 and 6 of the first chip (U1), One end of the fifteenth resistor (R62), the negative electrode of the seventh capacitor (E3) and the other end of the sixth capacitor (C8), and the other end of the eighth capacitor (C9) are connected to pin 3 of the first chip (U1), the other end of the fifteenth resistor (R62) are respectively connected to pin 5 of the first chip (U1) and one end of the sixteenth resistor (R63), the other end of the sixteenth resistor (R63) is connected to the 12V voltage output end, the IN1 input end of the second chip is connected to one end of the eighteenth resistor through the seventeenth resistor, the 12V voltage output end is connected to the other end of the eighteenth resistor and the +12V voltage end of the second chip, the positive output end of the second chip is connected to the collector of the transistor through the nineteenth resistor, the negative output end of the second chip is connected to one end of the twentieth resistor and one end of the twenty-first resistor, the other end of the twentieth resistor is connected to the base of the transistor, and the other end of the twenty-first resistor is connected to the emitter of the transistor.

Citation Information

Patent Citations

  • Method and device for acquiring and analyzing rotor vibration signal of variable-rotation wind generation set

    CN102661786A

  • Method for precisely extracting rotation speed signal using vibration signal

    CN106092524A