Wheel damage detection method, system, program, and storage medium

Abstract

The embodiment of the application provides a wheel damage detection method, system, program and storage medium, the method comprises the following steps: based on the vibration sensor arranged on the axle box of the wheel, the vibration signal of the wheel is continuously collected at a set sampling frequency, the vibration signal is subjected to envelope demodulation and frequency domain conversion processing to obtain the frequency domain feature map of the wheel. The rotation frequency value of the wheel is determined, if the frequency domain feature map contains the rotation frequency value, the motion state information of the wheel is determined according to the vibration signal collected in the current wheel moving window, and the damage information of the wheel is determined according to the motion state information of the wheel. Through the scheme, the accuracy of the wheel damage detection result can be improved.

Description

Technical Field

[0001] This application relates to the field of rail transit technology, and in particular to a wheel damage detection method, system, program and storage medium. Background Technology

[0002] During the actual operation of high-speed trains, the wheels are prone to accidental damage from the track, leading to rapid non-circular wear of the wheels, which results in the rapid formation of polygonal anomalies, seriously endangering driving safety.

[0003] One current method for detecting wheel damage utilizes the energy generated by the impact vibration waves produced after wheel damage. Specifically, it uses vehicle speed, average wheelset weight, wheel diameter, and vibration voltage at measuring points to quantify the depth of wheel abrasion, and uses the time difference in the propagation of mechanical waves vibrating at measuring points before and after the rail to locate the faulty wheel. However, this method of setting up test points on the track suffers from severe signal crosstalk, resulting in low accuracy of the detection results. Summary of the Invention

[0004] To address one of the aforementioned problems, this application provides a wheel damage detection method, system, program, and storage medium to achieve accurate detection of wheel damage.

[0005] According to a first aspect of the embodiments of this application, a wheel damage detection method is provided, wherein a vibration sensor is installed on the axle box of the wheel, the method comprising: Based on the vibration sensor, the vibration signal of the wheel is continuously acquired at a set sampling frequency; The vibration signal is subjected to envelope demodulation and frequency domain transformation to obtain the frequency domain feature map of the wheel; Determine the rotational frequency of the wheel; If the frequency domain feature map contains the rotational frequency value, then the motion state information of the wheel is determined based on the vibration signal collected within the current wheel movement window; The damage information of the wheel is determined based on the motion state information.

[0006] According to a second aspect of the embodiments of this application, a wheel damage detection device is provided, wherein a vibration sensor is disposed on the axle box of the wheel, the device comprising: The signal acquisition module is used to continuously acquire the vibration signal of the wheel based on the vibration sensor at a set sampling frequency; The signal processing module is used to perform envelope demodulation and frequency domain transformation on the vibration signal to obtain the frequency domain feature map of the wheel. The motion determination module is used to determine the rotational frequency value of the wheel. If the frequency domain feature map contains the rotational frequency value, the motion state information of the wheel is determined based on the vibration signal collected within the current wheel movement window. The damage determination module is used to determine the damage information of the wheel based on the motion state information.

[0007] According to a third aspect of the embodiments of this application, a wheel damage detection system is provided, comprising: Vibration sensors, signal acquisition devices, and processors are installed on the axle boxes of the wheels; The signal acquisition device is communicatively connected to the vibration sensor and the processor, respectively, and is used to continuously acquire the vibration signal of the wheel at a set sampling frequency and transmit it to the processor; The processor is configured to execute the method as described in the first aspect.

[0008] According to a fourth aspect of the embodiments of this application, a vehicle is provided, including: a wheel damage detection system as described in the third aspect.

[0009] According to a fifth aspect of the present application, a computer-readable storage medium is provided having a computer program stored thereon; the computer program is executed by a processor to implement the method as described in the first aspect.

[0010] According to a sixth aspect of the embodiments of this application, a computer program product is provided, comprising a computer program; the computer program is executed by a processor to implement the method as described in the first aspect.

[0011] The wheel damage detection scheme provided in this application embodiment uses a vibration sensor installed on the wheel's axle box to continuously collect wheel vibration signals at a set sampling frequency. Then, the vibration signals undergo envelope demodulation and frequency domain transformation to obtain a frequency domain feature map of the wheel, and the wheel's rotational frequency is determined. It is then determined whether the frequency domain feature map contains this rotational frequency value. If the frequency domain feature map contains the wheel's rotational frequency value, the wheel's motion state information, such as the effective value and maximum value of acceleration, is determined based on multiple vibration signals collected within the current wheel movement window. This motion state information is then combined with the wheel's motion state information to determine the specific damage information of the wheel. By simultaneously performing envelope demodulation and frequency domain transformation on the vibration signals, the frequency domain feature map can clearly reveal whether the wheel may have abnormal vibrations. After this initial judgment, a subsequent, more precise wheel damage degree identification process is triggered, thus ensuring the accuracy of the final wheel damage detection result. Attached Figure Description

[0012] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings: Figure 1 A flowchart of a wheel damage detection method provided in an embodiment of this application; Figure 2 This is a schematic diagram of a wheel damage detection system provided in an embodiment of this application; Figures 3a-3d A schematic diagram illustrating the wheel damage detection principle provided in an embodiment of this application; Figure 4 A flowchart of another wheel damage detection method provided in this application embodiment; Figures 5a-5b A schematic diagram of the impact vibration index provided in an embodiment of this application; Figure 6 A flowchart of another wheel damage detection method provided in this application embodiment; Figure 7 This is a schematic diagram of a wheel damage detection device provided in an embodiment of this application. Detailed Implementation

[0013] To make the technical solutions and advantages of the embodiments of this application clearer, the exemplary embodiments of this application will be described in further detail below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not an exhaustive list of all embodiments. It should be noted that, unless otherwise specified, the embodiments and features in the embodiments of this application can be combined with each other.

[0014] In developing this application, the inventors discovered that when two vibration measuring points are set on the track to detect faulty wheels (such as those with abrasions, peeling, or chipping), the results are easily affected by signal crosstalk, leading to unreliable detection. For example, two wheelsets on the same axle of the same vehicle or two wheelsets on the front and rear of the same bogie will inevitably have a difference in wheel diameter. During wheel rotation, there will definitely be a beat vibration phenomenon, meaning that the vibration energy of an undamaged wheel may be much larger than that of a damaged wheelset, resulting in inaccurate detection. Moreover, in actual operation, the impact vibration in the test section can also be affected by the condition of the rails, the condition of the rail foundation, and other issues, which may also cause impact vibration and lead to misjudgment.

[0015] To address the aforementioned issues and improve the accuracy of wheel damage detection results, this application provides a wheel damage detection method. The main idea is as follows: First, a vibration sensor is installed on the wheel's axle box to continuously detect vibration signals. By performing envelope demodulation and frequency domain analysis on the vibration signals, a preliminary judgment can be made as to whether the wheel may be damaged. When the wheel is preliminarily determined to be damaged, the wheel's movement status is then combined to accurately complete the detection of the wheel damage, thereby ensuring that the detection results are accurate and reliable.

[0016] Figure 1 A flowchart of a wheel damage detection method provided in an embodiment of this application is shown below. Figure 1 As shown, the method includes the following steps: 101. A vibration sensor installed on the axle box of the wheel continuously collects the vibration signal of the wheel at a set sampling frequency.

[0017] 102. Perform envelope demodulation and frequency domain transformation on the vibration signal to obtain the frequency domain feature map of the wheel.

[0018] 103. Determine the wheel's rotational frequency value. If the frequency domain feature map contains the wheel's rotational frequency value, then determine the wheel's motion state information based on the vibration signal collected within the current wheel movement window.

[0019] 104. Determine the damage information of the wheel based on the wheel's motion status information.

[0020] In this embodiment of the application, the vehicle being tested for wheel damage can be various rail transit trains, including but not limited to subways and high-speed trains.

[0021] The wheel damage detection method provided in this application embodiment can be executed by a wheel damage detection system, such as... Figure 2 As shown, the system includes a vibration sensor mounted on the wheel's axle box, a signal acquisition unit, and a processor. The signal acquisition unit is communicatively connected to both the vibration sensor and the processor; the communication connection can be wired or wireless, without specific limitation. The signal acquisition unit continuously acquires vibration signals from the wheel via the vibration sensor at a set sampling frequency and transmits them to the processor for further processing. The signal acquisition unit can amplify the acquired raw vibration signals by a set amplitude before transmitting them to the processor to meet its processing requirements.

[0022] In practical applications, the sampling frequency can be, for example, 5000Hz, without specific limitations. In the embodiments of this application, the collected vibration signal can be the vertical acceleration signal of the axle box.

[0023] In an optional embodiment, to avoid signal interference, the collected vibration signal can be filtered before subsequent processing, for example, by performing bandpass signal filtering of 1-5kHz.

[0024] In this embodiment, the collected vibration signal is first subjected to envelope demodulation and frequency domain conversion to obtain the frequency domain feature map of the wheel. Based on the frequency domain feature map, it is initially determined whether the wheel may be damaged. If it may be damaged, the subsequent processing continues; otherwise, the process ends. At this point, the acquisition of the vibration signal can be terminated.

[0025] Optionally, Hilbert envelope demodulation can be used to determine the envelope of the acquired vibration signal, without limitation. Frequency domain transformation can be performed by sampling short-time Fourier transform, without limitation. By combining envelope demodulation and frequency domain transformation, the presence of periodic signal energy impact phenomena can be clearly identified in the obtained frequency domain feature map. If this periodically occurring signal energy matches the wheel's rotational frequency, then it can be preliminarily determined that the wheel is damaged.

[0026] Therefore, it is also necessary to calculate the wheel's rotational frequency first. The specific formula is as follows: Where f is the wheel rotation frequency, V is the vehicle speed, D is the wheel diameter, and pi is 3.14. Therefore, if the obtained frequency domain feature map contains the above-mentioned rotation frequency value and multiple harmonics of that value (such as 2 times, 3 times, etc.), then it can be preliminarily determined that the wheel has suspected damage.

[0027] For ease of understanding, combined with Figures 3a-3d To illustrate the above processing procedure, assume the continuously acquired vibration signal is as follows: Figure 3a The time-domain signal shown is represented by the horizontal axis, where the horizontal axis represents the acquisition time (in seconds), and the vertical axis represents the signal amplitude. If a frequency domain transformation (such as a Fourier transform) is performed directly without envelope demodulation, the resulting frequency domain feature map is as follows. Figure 3b As shown, no obvious periodic signal energy resembling wheel impact damage can be observed in the frequency domain feature map. However, if envelope demodulation is performed first, such as... Figure 3c As shown, the envelope value of the vibration signal can be determined. Then, the vibration signal, after envelope demodulation, undergoes a short-time Fourier transform to obtain the following result: Figure 3d The frequency domain feature diagram shown shows periodic signal energy around multiple frequency points such as 10Hz and 20Hz, which happen to be multiples of the wheel's rotation frequency.

[0028] Therefore, by combining demodulation and frequency domain transformation, a more accurate frequency domain characteristic reflecting whether the wheel is damaged can be obtained. Based on this frequency domain characteristic, the presence or absence of wheel damage can be preliminarily determined. Specifically, if the frequency domain characteristic map contains the wheel's rotational frequency value (including multiple harmonics of the rotational frequency value), it is determined that the wheel may be damaged. The specific degree of damage can be determined according to subsequent processing.

[0029] Next, the motion state information of the wheel can be determined based on the vibration signal collected within the current wheel movement window, and the damage information of the wheel can be determined based on this motion state information.

[0030] In this embodiment, a wheel movement window of a fixed length (e.g., 3 meters) is pre-set. Multiple vibration signals collected within each wheel movement window can determine the wheel's motion state within that window, thus serving as a basis for judging wheel damage. It should be noted that the length of the wheel movement window can be determined based on the wheel's circumference, ensuring at least one complete rotation of the wheel.

[0031] The motion status information of a wheel can reflect the smoothness of its motion. For example, when the vibration signal is the vertical acceleration signal of the axle box, the degree of change in this acceleration signal can be statistically analyzed to determine the extent of wheel damage.

[0032] In this embodiment, by simultaneously performing envelope demodulation and frequency domain transformation on the vibration signal, it is possible to preliminarily determine whether there may be abnormal vibration in the wheel through the frequency domain feature map. After this preliminary judgment, the subsequent precise identification process of the wheel damage level is triggered, thereby ensuring the accuracy of the final wheel damage detection result.

[0033] Figure 4 A flowchart of another wheel damage detection method provided in the embodiments of this application is shown below. Figure 4 As shown, the method includes the following steps: 401. A vibration sensor installed on the axle box of a wheel continuously acquires the vertical acceleration signal of the axle box of the wheel at a set sampling frequency.

[0034] 402. The vertical acceleration signal of the axle box is envelope demodulated and frequency domain transformed to obtain the frequency domain feature map of the wheel.

[0035] 403. Determine the wheel's rotational frequency. If the frequency domain feature map contains the wheel's rotational frequency, then based on the axle box vertical acceleration signal collected within the current wheel movement window, determine the effective value and maximum value of the wheel's axle box vertical acceleration within the current wheel movement window.

[0036] 404. Based on the effective and maximum values ​​of the vertical acceleration of the axle box of the wheel within the current wheel movement window, determine the first impact vibration index of the wheel within the current wheel movement window.

[0037] 405. Based on the first impact vibration index corresponding to each wheel in multiple wheel movement windows, determine the second impact vibration index of the wheel in the current movement statistics window, where the current movement statistics window contains multiple wheel movement windows.

[0038] 406. Determine the damage level of the wheel based on the second impact vibration index corresponding to each wheel within multiple consecutive moving statistical windows and the preset index threshold range corresponding to different wheel damage levels.

[0039] In this embodiment, the execution of steps 401-402 can be referred to the relevant descriptions in the previous embodiments, and will not be repeated here.

[0040] In an optional embodiment, when the vibration signal is an axle box vertical acceleration signal, the effective value and maximum value of the wheel's axle box vertical acceleration within the current wheel movement window can be determined based on the axle box vertical acceleration signal collected within the current wheel movement window. Then, based on the effective value and maximum value of the wheel's axle box vertical acceleration within the current wheel movement window, a first impact vibration index of the wheel within the current wheel movement window is determined, and the wheel damage information is determined based on the first impact vibration index.

[0041] Assuming the current wheel movement window is the i-th wheel movement window, and assuming that a total of K vibration signal values ​​are collected within this window, the effective value of the vertical acceleration of the wheel's axle box within the current wheel movement window can be calculated using the following formula:

[0042] in, For the first Effective value of vertical acceleration of axle box within the movement window of each wheel. This represents the vertical acceleration value of the j-th axle box collected within the wheel movement window. This represents the total number of vertical accelerations of the axle box collected within the wheel movement window.

[0043] The maximum vertical acceleration of the wheel's axle box within the current wheel movement window can be calculated using the following formula: Where abs is the absolute value operator, and K is the number of absolute values. The total number of axle box vertical accelerations collected within each wheel movement window.

[0044] Thus, the first impact vibration index It can be represented as / That is, the first The quotient of the maximum and effective values ​​of the vertical acceleration of the axle box of each wheel moving in the window. For example... Figure 5a As shown, the first impact vibration index of the same wheel within multiple wheel movement windows is illustrated.

[0045] Optionally, different wheel damage levels and corresponding index threshold ranges for each wheel damage level can be preset. This allows the first impact vibration index to be compared with different index threshold ranges to determine the wheel damage level.

[0046] In another optional embodiment, to further improve the detection accuracy of wheel damage, the damage level of the wheel can be finally determined by statistically analyzing the first impact vibration index corresponding to each of multiple consecutive wheel movement windows.

[0047] Optionally, if the first impact vibration index corresponding to each of the N consecutive wheel movement windows all falls within a certain index threshold range, then the wheel damage level is finally determined as the damage level corresponding to that index threshold range, where N is greater than 1, such as N=3 or N=4.

[0048] Alternatively, the average value of the first impact vibration index corresponding to each of the N consecutive wheel movement windows can be calculated, and the wheel damage level can be determined based on this average value.

[0049] In other words, the second impact vibration index of the wheel in the current movement statistics window can be determined based on the first impact vibration index corresponding to each wheel within multiple wheel movement windows. The damage information of the wheel can then be determined based on the second impact vibration index, where the current movement statistics window contains multiple wheel movement windows. For example... Figure 5b As shown, the second impact vibration index of the wheel is illustrated within several different movement statistical windows.

[0050] Specifically, the second impact vibration index of the wheel within the current movement statistics window can be compared with the index threshold range corresponding to different damage levels to determine the wheel damage level.

[0051] Alternatively, to further improve the accuracy of determining the wheel damage level, the wheel damage level can be determined based on the second impact vibration index corresponding to each wheel within multiple consecutive moving statistical windows and the preset index threshold range corresponding to different wheel damage levels.

[0052] Specifically, for example, the average value of the second impact vibration index corresponding to each wheel within multiple consecutive moving statistical windows can be calculated. This average value can then be compared with the index threshold range corresponding to different damage levels of the wheel to determine the wheel's damage level. Alternatively, the second impact vibration index corresponding to each wheel within multiple consecutive moving statistical windows can be directly compared with the index threshold range corresponding to different damage levels of the wheel, and the statistical comparison results can be used to determine the wheel's damage level.

[0053] The number of moving statistical windows can be determined based on the length of a track used in the actual application. For example, if one moving statistical window is 10 meters and a 100-meter track is used, the second impact vibration index of the wheel can be counted within 10 consecutive moving statistical windows. For instance, if the second impact index corresponding to each of the 10 consecutive moving statistical windows is within the range of [3, 5], the wheel damage level is determined to be level 2; if the index exceeds 5 for all 10 consecutive windows, the wheel damage level is determined to be level 1. Level 2 indicates that the wheel can continue to run, while level 1 requires immediate repair.

[0054] By calculating the impact vibration index within different granular length ranges, such as wheel movement window and movement statistics window, the reliability of wheel damage detection results can be guaranteed.

[0055] Figure 6 A flowchart of another wheel damage detection method provided in the embodiments of this application is shown below. Figure 6 As shown, the method includes the following steps: 601. If the vehicle's speed is within the set speed range and the movement is uniform, the vertical acceleration signal of the wheel's axle box is continuously collected based on the vibration sensor installed on the wheel's axle box at a set sampling frequency.

[0056] 602. The vertical acceleration signal of the axle box is envelope demodulated and frequency domain transformed to obtain the frequency domain feature map of the wheel.

[0057] 603. Determine the wheel's rotational frequency. If the frequency domain feature map contains the wheel's rotational frequency, then based on the axle box vertical acceleration signal collected within the current wheel movement window, determine the effective value and maximum value of the wheel's axle box vertical acceleration within the current wheel movement window.

[0058] 604. Based on the effective and maximum values ​​of the vertical acceleration of the axle box of the wheel within the current wheel movement window, determine the first impact vibration index of the wheel within the current wheel movement window.

[0059] 605. Based on the first impact vibration index corresponding to each wheel in multiple wheel movement windows, determine the second impact vibration index of the wheel in the current movement statistics window, where the current movement statistics window contains multiple wheel movement windows.

[0060] 606. Determine the damage level of the wheel based on the second impact vibration index corresponding to each wheel within multiple consecutive moving statistical windows and the preset index threshold range corresponding to different damage levels of the wheel.

[0061] In this embodiment, the prerequisite for triggering wheel damage detection is that the vehicle's speed is within a set speed range and the movement is uniform. This speed range is, for example, V = 100-160 km / h. This range is chosen because: if the speed is too low, even if the wheel is damaged, vibration may not be generated, making wheel damage detection impossible; if the speed is too high, the vibration signal will be overwhelmed, also preventing accurate wheel damage detection. Under uniform motion, the vibration signal caused by wheel damage will better exhibit periodic characteristics.

[0062] The execution of other steps in this embodiment can be referred to the relevant descriptions in the foregoing embodiments, and will not be repeated here.

[0063] Figure 7 This is a schematic diagram of a wheel damage detection device provided in an embodiment of this application, as shown below. Figure 7 As shown, the device includes: a cut-off control module 11, a status latching module 12, and a detection control module 13.

[0064] The signal acquisition module 11 is used to continuously acquire the vibration signal of the wheel based on the vibration sensor at a set sampling frequency.

[0065] The signal processing module 12 is used to perform envelope demodulation and frequency domain conversion processing on the vibration signal to obtain the frequency domain feature map of the wheel.

[0066] The motion determination module 13 is used to determine the rotational frequency value of the wheel. If the frequency domain feature map contains the rotational frequency value, the motion state information of the wheel is determined based on the vibration signal collected within the current wheel movement window.

[0067] The damage determination module 14 is used to determine the damage information of the wheel based on the motion state information.

[0068] Optionally, the vibration signal includes an axle box vertical acceleration signal; the motion determination module 13 is specifically used to: determine the effective value and maximum value of the axle box vertical acceleration of the wheel within the current wheel movement window based on the axle box vertical acceleration signal collected within the current wheel movement window.

[0069] Optionally, the damage determination module 14 is specifically used to: determine the first impact vibration index of the wheel within the current wheel movement window based on the effective value and the maximum value of the vertical acceleration of the axle box of the wheel within the current wheel movement window; and determine the damage information of the wheel based on the first impact vibration index.

[0070] Optionally, the damage determination module 14 is specifically used to: determine the second impact vibration index of the wheel in the current movement statistics window based on the first impact vibration index corresponding to each of the multiple wheel movement windows, wherein the current movement statistics window includes the multiple wheel movement windows; and determine the damage information of the wheel based on the second impact vibration index.

[0071] Optionally, the damage determination module 14 is specifically used to: determine the damage level of the wheel based on the second impact vibration index corresponding to each wheel within a series of consecutive moving statistical windows and the preset index threshold range corresponding to different damage levels of the wheel.

[0072] Optionally, the signal acquisition module 11 is specifically used to: if the vehicle's moving speed is within a set speed range and the moving state is uniform motion, trigger continuous acquisition of the vibration signal of the wheel at a set sampling frequency.

[0073] Optionally, the device further includes a filtering module for filtering the vibration signal.

[0074] Figure 7 The control device shown in the embodiment can be used to execute the wheel damage detection method provided in the foregoing embodiment.

[0075] This application also provides a computer-readable storage medium having a computer program stored thereon; the computer program is executed by a processor to implement the control method as described in the foregoing embodiments.

[0076] This application also provides a computer program product comprising a computer program; the computer program is executed by a processor to implement the control method as described in the foregoing embodiments.

[0077] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can 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. The solutions in the embodiments of this application can be implemented in various computer languages, such as C, VHDL, Verilog, the object-oriented programming language Java, and the interpreted scripting language JavaScript.

[0078] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0079] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0080] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0081] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this application, "multiple" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0082] Although preferred embodiments of this application have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of this application.

[0083] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of the claims of this application and their equivalents, this application also intends to include such modifications and variations.

Claims

1. A method for detecting wheel damage, characterized in that, The method of installing a vibration sensor on the axle box of a wheel includes: Based on the vibration sensor, the vibration signal of the wheel is continuously acquired at a set sampling frequency; The vibration signal is subjected to envelope demodulation and frequency domain transformation to obtain the frequency domain feature map of the wheel; Determine the rotational frequency of the wheel; If the frequency domain feature map contains the rotational frequency value, then the motion state information of the wheel is determined based on the vibration signal collected within the current wheel movement window; The damage information of the wheel is determined based on the motion state information.

2. The method according to claim 1, characterized in that, The vibration signal includes the axle box vertical acceleration signal; determining the motion state information of the wheel based on the vibration signal collected within the current wheel movement window includes: Based on the vertical acceleration signal of the axle box collected within the current wheel movement window, determine the effective value and maximum value of the vertical acceleration of the wheel's axle box within the current wheel movement window.

3. The method according to claim 2, characterized in that, Determining the damage information of the wheel based on the motion state information includes: Based on the effective and maximum values ​​of the vertical acceleration of the axle box of the wheel within the current wheel movement window, determine the first impact vibration index of the wheel within the current wheel movement window; The damage information of the wheel is determined based on the first impact vibration index.

4. The method according to claim 3, characterized in that, The step of determining the damage information of the wheel based on the first impact vibration index includes: Based on the first impact vibration index corresponding to each wheel in multiple wheel movement windows, the second impact vibration index of the wheel in the current movement statistics window is determined, wherein the current movement statistics window includes the multiple wheel movement windows; The damage information of the wheel is determined based on the second impact vibration index.

5. The method according to claim 4, characterized in that, The step of determining the wheel damage information based on the second impact vibration index includes: The damage level of the wheel is determined based on the second impact vibration index corresponding to each wheel within multiple consecutive moving statistical windows and the preset index threshold range corresponding to different damage levels of the wheel.

6. The method according to any one of claims 1-5, characterized in that, The continuous acquisition of vibration signals from the wheel at a set sampling frequency includes: If the vehicle's speed is within the set speed range and the movement is uniform, then the vibration signal of the wheel will be continuously collected at the set sampling frequency.

7. The method according to any one of claims 1-5, characterized in that, Before performing envelope demodulation and frequency domain conversion on the vibration signal, the process further includes: The vibration signal is then filtered.

8. A wheel damage detection system, characterized in that, include: Vibration sensors, signal acquisition devices, and processors are installed on the axle boxes of the wheels; The signal acquisition device is communicatively connected to the vibration sensor and the processor, respectively, and is used to continuously acquire the vibration signal of the wheel at a set sampling frequency and transmit it to the processor; The processor is configured to execute the method as described in any one of claims 1-7.

9. A computer-readable storage medium, characterized in that, It stores a computer program thereon; the computer program is executed by a processor to implement the method as described in any one of claims 1-7.

10. A computer program product, characterized in that, It includes a computer program; the computer program is executed by a processor to implement the method as described in any one of claims 1-7.

Images