Wheel inspection methods, devices, computer equipment and storage media

Abstract

This application relates to a wheel detection method, apparatus, computer equipment, and storage medium. The method includes: acquiring noise time-domain data of the target wheel at a preset acquisition frequency using a noise acquisition component corresponding to the target wheel; determining the dominant noise frequency data of the target noise time-domain data in a preset frequency band based on the target noise time-domain data, and determining the target wear order of the target wheel based on the dominant noise frequency data; determining the target sound pressure level density threshold corresponding to the target wear order based on the target wear order and a preset first correspondence between the wear order and a sound pressure level density threshold; and generating detection information indicating wheel abnormality if the dominant frequency sound pressure level density in the noise frequency data is greater than or equal to the target sound pressure level density threshold. This solution allows for real-time detection of the target wheel.

Description

Technical Field

[0001] This application relates to the field of detection technology, and in particular to a wheel detection method, apparatus, computer equipment, and storage medium. Background Technology

[0002] With the development of detection technology, wheel detection technology has emerged. This technology can detect the wheels of rail transit vehicles to check whether the wheels have malfunctioned (i.e., abnormal).

[0003] Traditional vehicle inspection technology involves manually acquiring the wheel contour data of a rail transit vehicle when it is stopped, and then performing fault detection based on the contour data.

[0004] However, current wheel detection technology can only detect faults when the rail transit vehicle is stopped. If a fault occurs while the rail transit vehicle is in operation, it is impossible to detect wheel abnormalities in a timely manner. Therefore, current wheel detection technology cannot achieve real-time detection. Summary of the Invention

[0005] Therefore, it is necessary to provide a wheel detection method, apparatus, computer equipment, computer-readable storage medium, and computer program product that can perform real-time detection of target wheels to address the aforementioned technical problems.

[0006] Firstly, this application provides a wheel detection method. The method includes:

[0007] The noise time-domain data of the target wheel is collected by the noise acquisition component corresponding to the target wheel at a preset acquisition frequency.

[0008] Based on the target noise time domain data in the noise time domain data, determine the noise dominant frequency data of the target noise time domain data in the preset frequency band, and based on the noise dominant frequency data, determine the target wear order of the target wheel.

[0009] Based on the target wear order and the first correspondence between the preset wear order and the sound pressure level density threshold, the target sound pressure level density threshold corresponding to the target wear order is determined.

[0010] If the dominant frequency sound pressure level density in the noise dominant frequency data is greater than or equal to the target sound pressure level density threshold, detection information indicating wheel abnormality is generated.

[0011] In one embodiment, the noise time-domain data includes each acquisition time and the sound pressure level corresponding to each acquisition time; after acquiring the noise time-domain data of the target wheel according to a preset acquisition frequency, the method further includes:

[0012] The target sound pressure level is obtained by filtering the sound pressure levels that are less than or equal to a preset sound pressure level threshold.

[0013] The noise time-domain data, which is based on the target sound pressure level and the target acquisition time corresponding to the target sound pressure level, is used as the target noise time-domain data.

[0014] In one embodiment, determining the dominant noise frequency data of the target noise time-domain data in a preset frequency band based on the target noise time-domain data in the noise time-domain data, and determining the target wear order of the target wheel based on the dominant noise frequency data, includes:

[0015] In the noise frequency domain data corresponding to the target noise time domain data, determine the target noise frequency domain data corresponding to the preset frequency band;

[0016] In the target noise frequency domain data that includes the target noise frequency and the target sound pressure level density corresponding to the target noise frequency, the peak value of the target sound pressure level density and the target noise frequency corresponding to the peak value of the target sound pressure level density are determined to obtain the noise main frequency data.

[0017] The target wear level is determined based on the main frequency of the noise main frequency data, the preset target wheel diameter, and the target vehicle speed.

[0018] In one embodiment, the method further includes:

[0019] Based on the historical wear levels of the sample wheels and the second correspondence between the preset wear levels and wear degree thresholds, the reference wear degree threshold corresponding to the historical wear levels is determined.

[0020] If the wear level of the sample wheel is greater than or equal to the reference wear level threshold, the historical main frequency data of the sample wheel to which the wear level belongs shall be used as the reference data;

[0021] Based on the sound pressure level density in the reference data and the preset density threshold, a third correspondence between the sound pressure level density threshold and the wear degree threshold is determined.

[0022] For each wear degree threshold, the wear order corresponding to the wear degree threshold is determined in the second correspondence, and the sound pressure level density threshold corresponding to the wear degree threshold is determined in the third correspondence, thereby determining the sound pressure level density threshold corresponding to the wear order, and thus obtaining the first correspondence.

[0023] In one embodiment, determining the third correspondence between the sound pressure level density threshold and the wear degree threshold based on the sound pressure level density in the reference data and a preset density threshold determination strategy includes:

[0024] For the reference data of the sample wheel belonging to the same wear degree threshold, among the sound pressure level densities contained in each of the reference data, the sound pressure level density that meets the preset selection conditions is determined, and the sound pressure level density corresponding to the wear degree threshold is obtained.

[0025] Based on the sound pressure level density corresponding to each wear degree threshold, a third correspondence between the sound pressure level density threshold and the wear degree threshold is determined.

[0026] In one embodiment, determining the sound pressure level density that satisfies the preset selection criteria includes:

[0027] Determine the sound pressure level density corresponding to the preset quantile; or,

[0028] Determine the sound pressure level density belonging to a preset first sound pressure level density range, and among the sound pressure level densities belonging to the preset first sound pressure level density range, determine the sound pressure level density corresponding to the mode; or,

[0029] Determine the sound pressure level density that belongs to the preset second sound pressure level density range, and determine the sound pressure level density corresponding to the average value among the sound pressure level densities that belong to the preset second sound pressure level density range.

[0030] In one embodiment, before determining the wear degree threshold corresponding to the historical wear level based on the historical wear level of the sample wheel and a preset second correspondence between the wear level and the wear degree threshold, the method further includes:

[0031] The historical noise time-domain data of the sample wheel is collected by the noise acquisition component corresponding to the sample wheel according to the preset acquisition frequency.

[0032] Based on the target historical time-domain data in the historical noise time-domain data, determine the historical dominant frequency data of the target historical time-domain data in the preset frequency band, and determine the historical wear order of the sample wheel based on the historical dominant frequency data.

[0033] In one embodiment, the historical noise time-domain data includes each historical acquisition time and the historical sound pressure level corresponding to each historical acquisition time; after acquiring the historical noise time-domain data of the sample wheels according to the preset acquisition frequency, the method further includes:

[0034] The historical sound pressure levels that are less than or equal to a preset sound pressure level threshold are filtered to obtain the target historical sound pressure level; the historical noise time-domain data based on the target historical sound pressure level and the target historical acquisition time corresponding to the historical target sound pressure level is used as the target historical noise time-domain data.

[0035] In one embodiment, determining the historical dominant frequency data of the target historical time-domain data in the preset frequency band based on the target historical time-domain data in the historical noise time-domain data, and determining the historical wear order of the sample wheel based on the historical dominant frequency data includes:

[0036] In the historical frequency domain data corresponding to the target historical time domain data, the target historical frequency domain data corresponding to the preset frequency band is determined; in the target historical frequency domain data containing historical noise frequencies and historical sound pressure level densities corresponding to the historical noise frequencies, the historical sound pressure level density peak value and the historical noise frequency corresponding to the historical sound pressure level density peak value are determined to obtain the historical dominant frequency data; based on the historical dominant frequency of the historical dominant frequency data, the preset sample wheel diameter, and the sample vehicle speed, the historical wear order is determined.

[0037] Secondly, this application also provides a wheel detection device. The wheel detection device includes:

[0038] The first acquisition module is used to acquire the noise time-domain data of the target wheel through the noise acquisition component corresponding to the target wheel at a preset acquisition frequency;

[0039] The first determining module is used to determine the noise dominant frequency data of the target noise time domain data in a preset frequency band based on the target noise time domain data in the noise time domain data, and to determine the target wear order of the target wheel based on the noise dominant frequency data.

[0040] The second determining module is used to determine the target sound pressure level density threshold corresponding to the target wear order based on the target wear order and the first correspondence between the preset wear order and the sound pressure level density threshold.

[0041] The third determining module is used to generate detection information indicating wheel abnormality when the main frequency sound pressure level density in the noise main frequency data is greater than or equal to the target sound pressure level density threshold.

[0042] In one embodiment, the wheel detection device further includes:

[0043] The first filtering module is used to filter the sound pressure levels that are less than or equal to a preset sound pressure level threshold to obtain the target sound pressure level;

[0044] The first construction module is used to take the noise time-domain data based on the target sound pressure level and the target acquisition time corresponding to the target sound pressure level as the target noise time-domain data.

[0045] In one embodiment, the first determining module is specifically used for:

[0046] In the noise frequency domain data corresponding to the target noise time domain data, determine the target noise frequency domain data corresponding to the preset frequency band;

[0047] In the target noise frequency domain data that includes the target noise frequency and the target sound pressure level density corresponding to the target noise frequency, the peak value of the target sound pressure level density and the target noise frequency corresponding to the peak value of the target sound pressure level density are determined to obtain the noise main frequency data.

[0048] The target wear level is determined based on the main frequency of the noise main frequency data, the preset target wheel diameter, and the target vehicle speed.

[0049] In one embodiment, the wheel detection device further includes:

[0050] The fourth determining module is used to determine the reference wear degree threshold corresponding to the historical wear level based on the historical wear level of the sample wheel and the second correspondence between the preset wear level and the wear degree threshold.

[0051] The fifth determining module is used to use the historical main frequency data of the sample wheel to which the wear degree belongs as reference data when the wear degree of the sample wheel is greater than or equal to the reference wear degree threshold.

[0052] The sixth determining module is used to determine the third correspondence between the sound pressure level density threshold and the wear degree threshold based on the sound pressure level density in the reference data and the preset density threshold determination strategy.

[0053] The seventh determining module is used to determine the wear level corresponding to each wear level threshold in the second correspondence relationship, determine the sound pressure level density threshold corresponding to the wear level threshold in the third correspondence relationship, and then determine the sound pressure level density threshold corresponding to the wear level threshold to obtain the first correspondence relationship.

[0054] In one embodiment, the sixth determining module is specifically used for:

[0055] For the reference data of the sample wheel belonging to the same wear degree threshold, among the sound pressure level densities contained in each of the reference data, the sound pressure level density that meets the preset selection conditions is determined, and the sound pressure level density corresponding to the wear degree threshold is obtained.

[0056] Based on the sound pressure level density corresponding to each wear degree threshold, a third correspondence between the sound pressure level density threshold and the wear degree threshold is determined.

[0057] In one embodiment, the sixth determining module is specifically used for:

[0058] Determine the sound pressure level density corresponding to the preset quantile; or,

[0059] Determine the sound pressure level density belonging to a preset first sound pressure level density range, and among the sound pressure level densities belonging to the preset first sound pressure level density range, determine the sound pressure level density corresponding to the mode; or,

[0060] Determine the sound pressure level density that belongs to the preset second sound pressure level density range, and determine the sound pressure level density corresponding to the average value among the sound pressure level densities that belong to the preset second sound pressure level density range.

[0061] In one embodiment, the wheel detection device further includes:

[0062] The second acquisition module is used to acquire historical noise time-domain data of the sample wheel according to the preset acquisition frequency through the noise acquisition component corresponding to the sample wheel;

[0063] The eighth determining module is used to determine the historical dominant frequency data of the target historical time domain data in the preset frequency band based on the target historical time domain data in the historical noise time domain data, and to determine the historical wear order of the sample wheel based on the historical dominant frequency data.

[0064] In one embodiment, the historical noise time-domain data includes each historical acquisition time and the historical sound pressure level corresponding to each historical acquisition time; the wheel detection device further includes:

[0065] The second filtering module is used to filter the historical sound pressure levels that are less than or equal to a preset sound pressure level threshold to obtain the target historical sound pressure level.

[0066] The second construction module is used to take the historical noise time-domain data based on the target historical sound pressure level and the target historical acquisition time corresponding to the historical target sound pressure level as the target historical noise time-domain data.

[0067] In one embodiment, the eighth determining module is specifically used for:

[0068] In the historical frequency domain data corresponding to the target historical time domain data, the target historical frequency domain data corresponding to the preset frequency band is determined; in the target historical frequency domain data containing historical noise frequencies and historical sound pressure level densities corresponding to the historical noise frequencies, the historical sound pressure level density peak value and the historical noise frequency corresponding to the historical sound pressure level density peak value are determined to obtain the historical dominant frequency data; based on the historical dominant frequency of the historical dominant frequency data, the preset sample wheel diameter, and the sample vehicle speed, the historical wear order is determined.

[0069] Thirdly, this application also provides a computer device. The computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the steps described in the first aspect.

[0070] Fourthly, this application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program thereon, which, when executed by a processor, implements the steps described in the first aspect.

[0071] Fifthly, this application also provides a computer program product. The computer program product includes a computer program that, when executed by a processor, performs the steps described in the first aspect.

[0072] The aforementioned wheel detection method, apparatus, computer equipment, storage medium, and computer program product acquire noise time-domain data of the target wheel at a preset acquisition frequency through a noise acquisition component corresponding to the target wheel; determine the dominant noise frequency data of the target noise time-domain data in a preset frequency band based on the target noise time-domain data, and determine the target wear order of the target wheel based on the dominant noise frequency data; determine the target sound pressure level density threshold corresponding to the target wear order based on the target wear order and a preset first correspondence between the wear order and the sound pressure level density threshold; and generate detection information indicating wheel abnormality when the dominant frequency sound pressure level density in the dominant noise frequency data is greater than or equal to the target sound pressure level density threshold. In the above scheme, by determining the dominant noise frequency data of the target noise time-domain data in a preset frequency band based on the target noise time-domain data, and generating detection information indicating wheel abnormality when the dominant frequency sound pressure level density in the dominant noise frequency data is greater than or equal to the target sound pressure level density threshold, it can be understood that the target noise time-domain data is the noise data generated by the target wheel during operation. Therefore, by adopting this solution, the wheels can be inspected on-vehicle during the operation of the target wheels, thereby achieving real-time wheel inspection. Attached Figure Description

[0073] Figure 1 This is a flowchart illustrating a wheel detection method in one embodiment;

[0074] Figure 2 This is a flowchart illustrating a method for determining target noise time-domain data in one embodiment;

[0075] Figure 3 This is a flowchart illustrating a method for determining noise frequency data and target wear order in one embodiment;

[0076] Figure 4 This is a flowchart illustrating a method for determining the first correspondence in one embodiment;

[0077] Figure 5 This is a structural block diagram of a wheel detection device in one embodiment;

[0078] Figure 6 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0079] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0080] In one embodiment, such as Figure 1 As shown, a wheel detection method is provided. This embodiment illustrates the application of this method to a terminal. It is understood that this method can also be applied to a server, and further to a system including both a terminal and a server, and implemented through interaction between the terminal and the server. In this embodiment, the method includes the following steps:

[0081] Step 102: Collect the time-domain noise data of the target wheel using the noise acquisition component corresponding to the target wheel at a preset acquisition frequency.

[0082] In this embodiment, during the operation of the target vehicle, the terminal collects the time-domain noise data of the target wheel through a noise collection component corresponding to the target wheel of the target vehicle at a preset collection frequency. In one embodiment, the noise collection component is a sound level meter. Optionally, the noise collection component can be installed near the bogie of the target vehicle, or it can be installed at a distance not exceeding a preset distance from the bottom of the vehicle body. In one embodiment, the preset distance is 50 centimeters. The preset collection frequency is greater than or equal to 2000 Hz.

[0083] Step 104: Based on the target noise time domain data in the noise time domain data, determine the noise master frequency data of the target noise time domain data in the preset frequency band, and based on the noise master frequency data, determine the target wear order of the target wheel.

[0084] The noise time-domain data includes the sound pressure level at each acquisition time. The target noise time-domain data includes the target acquisition time and the target sound pressure level at each acquisition time.

[0085] In this embodiment, the terminal filters out target noise time-domain data from the noise time-domain data according to preset filtering conditions. The terminal performs frequency domain transformation processing on the target noise time-domain data to obtain the corresponding noise frequency-domain data. Specifically, the terminal performs a Fourier transform on the target noise time-domain data to obtain the corresponding noise frequency-domain data. Here, noise frequency-domain data refers to noise data containing noise frequency-domain information. Optionally, the noise frequency-domain data can be a noise spectrum or a noise time-frequency signal.

[0086] In one embodiment, the Fourier transform is a short-time Fourier transform, specifically as shown in formula (1) below.

[0087]

[0088] Where X(n, ω) is the noise time-frequency signal, x(n) is the noise time-domain data (target noise time-domain data or target historical time-domain data), ω(n-mR) is the window function, n is time, ω is frequency, m is window number, R is window length, and j is the imaginary unit.

[0089] The terminal uses the noise frequency domain data corresponding to the preset frequency band as the target noise frequency domain data, and obtains the noise main frequency data from the target noise frequency domain data. The noise main frequency data includes the main frequency and the corresponding main frequency sound pressure level density. Based on the main frequency in the noise main frequency data and the preset correspondence between frequency and wear order, the terminal calculates the target wear order of the target wheel. In one embodiment, the preset correspondence between frequency and wear order is shown in formula (2).

[0090]

[0091] Where, n order is the wear level, v is the vehicle speed of the vehicle in the wear level, f is the main noise frequency of the vehicle in the wear level, and d is the wheel diameter of the vehicle in the wear level.

[0092] Step 106: Determine the target sound pressure level density threshold corresponding to the target wear level based on the target wear level and the first correspondence between the preset wear level and the sound pressure level density threshold.

[0093] In this embodiment, the terminal matches the target sound pressure level density threshold corresponding to the target wear order with a preset first correspondence between wear orders and sound pressure level density thresholds. In one embodiment, the first correspondence can be stored in list form, such as a first correspondence table. The first correspondence table includes multiple key-value pairs, each consisting of a wear order and the corresponding sound pressure level density threshold. Specifically, the terminal searches the first correspondence table based on the target wear order to obtain key-value pairs containing the target wear order, and uses the sound pressure level density threshold in the key-value pair as the target sound pressure level density threshold corresponding to the target wear order.

[0094] Step 108: If the main frequency sound pressure level density in the noise main frequency data is greater than or equal to the target sound pressure level density threshold, generate detection information indicating wheel abnormality.

[0095] In this embodiment, the terminal compares the dominant frequency sound pressure level density in the noise dominant frequency data with the target sound pressure level density threshold corresponding to the target wear order. If the dominant frequency sound pressure level density in the noise dominant frequency data is greater than or equal to the target sound pressure level density threshold corresponding to the target wear order, the terminal generates detection information indicating wheel abnormality. If the dominant frequency sound pressure level density in the noise dominant frequency data is less than the target sound pressure level density threshold corresponding to the target wear order, the terminal generates detection information indicating wheel normality. The detection information includes, but is not limited to, the detection result, the detection time, and the wheel identifier of the target wheel of the target vehicle.

[0096] In the aforementioned wheel detection method, the dominant frequency data of the target noise in a preset frequency band is determined based on the target noise time-domain data. If the dominant frequency sound pressure level density in this noise time-domain data is greater than or equal to a target sound pressure level density threshold, detection information indicating a wheel anomaly is generated. The target sound pressure level density threshold is determined based on a preset first correspondence between the noise dominant frequency data and the target wheel. It can be understood that the target noise time-domain data is the noise data generated by the target wheel during operation. Therefore, this scheme allows for on-vehicle detection of the target wheel during its operation, thereby achieving real-time wheel detection.

[0097] In one embodiment, such as Figure 2 As shown, the noise time-domain data includes each acquisition time and the corresponding sound pressure level at each acquisition time; after acquiring the noise time-domain data of the target wheel according to the preset acquisition frequency, it also includes:

[0098] Step 202: Filter out sound pressure levels that are less than or equal to the preset sound pressure level threshold to obtain the target sound pressure level.

[0099] The noise time-domain data includes each acquisition time and the corresponding sound pressure level at each acquisition time.

[0100] In this embodiment, the terminal filters out sound pressure levels less than or equal to a preset sound pressure level threshold from the various sound pressure levels in the noise time-domain data, and uses these sound pressure levels as target sound pressure levels. For example, assuming the preset sound pressure level threshold is A dB, and there is a 3-hour period of noise time-domain data, where only the sound pressure level in the second hour of the noise time-domain data is greater than A dB. Therefore, the target sound pressure levels for this 3-hour period of noise time-domain data are the sound pressure levels in the first hour and the sound pressure levels in the third hour.

[0101] Step 204: The noise time-domain data based on the target sound pressure level and the target acquisition time corresponding to the target sound pressure level is used as the target noise time-domain data.

[0102] The target noise time-domain data includes the acquisition time of each target and the target sound pressure level corresponding to each acquisition time.

[0103] In this embodiment, the terminal uses noise time-domain data based on the target sound pressure level and the target acquisition time corresponding to the target sound pressure level as the target noise time-domain data. Referring to the example of step 202, the target noise time-domain data for this 3-hour period of noise time-domain data consists of the noise time-domain data for the first hour and the noise time-domain data for the third hour.

[0104] In this embodiment, the target noise time-domain data is determined based on a preset sound pressure level threshold. The target sound pressure level in the target noise time-domain data is all less than or equal to the sound pressure level threshold. Therefore, interference data with higher sound pressure levels can be filtered out, resulting in more accurate target noise time-domain data and thus improving the detection accuracy of wheel detection based on the target noise time-domain data.

[0105] In one embodiment, such as Figure 3 As shown, based on the target noise time-domain data in the noise time-domain data, the dominant noise frequency data of the target noise time-domain data in the preset frequency band is determined, and based on the dominant noise frequency data, the target wear order of the target wheel is determined, including:

[0106] Step 302: Determine the target noise frequency domain data corresponding to the preset frequency band from the noise frequency domain data corresponding to the target noise time domain data.

[0107] In this embodiment, the terminal matches the noise frequency domain data corresponding to the preset frequency band in the noise frequency domain data corresponding to the target noise time domain data according to the preset frequency band, and uses the noise frequency domain data corresponding to the preset frequency band as the target noise frequency domain data.

[0108] Step 304: In the target noise frequency domain data containing the target noise frequency and the target sound pressure level density corresponding to the target noise frequency, determine the peak value of the target sound pressure level density and the target noise frequency corresponding to the peak value of the target sound pressure level density to obtain the noise main frequency data.

[0109] The target noise frequency domain data includes the target noise frequency and the target sound pressure level density corresponding to that frequency. The noise dominant frequency data includes the dominant frequency and the dominant frequency sound pressure level density corresponding to that frequency.

[0110] In this embodiment, the terminal determines the target sound pressure level density peak and the target noise frequency corresponding to the target sound pressure level density from the target noise frequency domain data, which includes the target noise frequency and the target sound pressure level density corresponding to the target noise frequency. The terminal then uses the target noise frequency domain data based on the target sound pressure level density peak and the target noise frequency corresponding to the target sound pressure level density peak as the noise master frequency data. It can be understood that the target sound pressure level density peak is the master frequency sound pressure level density of the noise master frequency data, and the target noise frequency corresponding to the target sound pressure level density peak is the master frequency of the noise master frequency data.

[0111] Step 306: Determine the target wear level based on the main frequency of the noise main frequency data, the preset target wheel diameter, and the target vehicle speed.

[0112] In this embodiment, the terminal acquires the target vehicle speed. Optionally, the target vehicle speed can be a preset speed or the real-time speed acquired during the vehicle's operation. The terminal calculates the target wear order of the target wheel based on the main frequency of the noise main frequency data, the preset target wheel diameter, the target vehicle speed, and the preset correspondence between frequency and wear order. In one embodiment, the preset correspondence between frequency and wear order is as shown in formula (2) above.

[0113] In this embodiment, the dominant noise frequency data is determined from the noise frequency domain data corresponding to the preset frequency band, and the target wear order of the target wheel is calculated based on the dominant frequency of the noise frequency data. Therefore, this solution can perform real-time detection of the target vehicle's wheels based on the collected dominant noise frequency data during the target vehicle's operation.

[0114] In one embodiment, such as Figure 4 As shown, the wheel detection method also includes:

[0115] Step 402: Based on the historical wear levels of the sample wheels and the second correspondence between the preset wear levels and wear degree thresholds, determine the reference wear degree threshold corresponding to the historical wear levels.

[0116] In this embodiment, the terminal matches the historical wear order of the sample wheel with a reference wear level threshold from a preset second correspondence between wear order and wear level threshold. In one embodiment, the second correspondence can be stored in list form, such as a second correspondence table. The second correspondence table includes multiple key-value pairs, each consisting of a wear order and the corresponding wear level threshold. Specifically, the terminal searches the first correspondence table based on the historical wear order to obtain key-value pairs containing the historical wear order, and uses the wear level threshold in the key-value pair as the reference wear level threshold corresponding to the historical wear order.

[0117] Step 404: If the wear level of the sample wheel is greater than or equal to the reference wear level threshold, the historical frequency data of the sample wheel to which the wear level belongs is used as the reference data.

[0118] In this embodiment, the terminal compares the wear level of the sample wheel with a reference wear level threshold. If the wear level of the sample wheel is greater than or equal to the reference wear level threshold, the terminal uses the historical main frequency data of the sample wheel to which the wear level belongs as reference data.

[0119] Step 406: Based on the sound pressure level density in the reference data and the preset density threshold determination strategy, determine the third correspondence between the sound pressure level density threshold and the wear degree threshold.

[0120] In this embodiment, the terminal determines a third correspondence between the sound pressure level density threshold and the wear level threshold based on the sound pressure level density in the reference data and a preset density threshold. In one embodiment, the third correspondence can be stored in list form, such as a third correspondence table. The third correspondence table includes multiple key-value pairs, each consisting of a sound pressure level density threshold and the wear level threshold corresponding to that sound pressure level density threshold.

[0121] Step 408: For each wear degree threshold, determine the wear order corresponding to the wear degree threshold in the second correspondence relationship, determine the sound pressure level density threshold corresponding to the wear degree threshold in the third correspondence relationship, and then determine the sound pressure level density threshold corresponding to the wear order to obtain the first correspondence relationship.

[0122] In this embodiment, for each wear level threshold, the terminal matches the wear level corresponding to that wear level threshold in a second correspondence relationship; the terminal matches the sound pressure level density threshold corresponding to that wear level threshold in a third correspondence relationship; then, based on the same wear level threshold, the terminal matches the sound pressure level density threshold corresponding to the wear level, and constructs a first correspondence relationship based on the sound pressure level density thresholds corresponding to each wear level. For example, assuming the second correspondence relationship includes {(wear level threshold 1, wear level 1), (wear level threshold 2, wear level 2)}, and the third correspondence relationship includes {(wear level threshold 1, sound pressure level density threshold 1), (wear level threshold 2, sound pressure level density threshold 2)}, then the first correspondence relationship includes {(wear level 1, sound pressure level density threshold 1), (wear level 2, sound pressure level density threshold 2)}. It is understood that the above examples are only for illustrative purposes and do not constitute a limitation on step 408 of this application. Optionally, in the second correspondence, the correspondence between the wear degree threshold and the wear order can be one-to-one or one-to-many. That is, the wear degree thresholds corresponding to different wear orders may be different or the same. For example, in the second correspondence of the example above, wear order 1 is not equal to wear order 2, but wear degree threshold 1 is equal to wear degree threshold 2. Optionally, in the third correspondence, the correspondence between the wear degree threshold and the sound pressure level density threshold can be one-to-one or one-to-many. That is, the sound pressure level density thresholds corresponding to different wear degree thresholds may be different or the same. For example, in the third correspondence of the example above, wear degree threshold 1 is not equal to wear degree threshold 2, but sound pressure level density threshold 1 is equal to sound pressure level density threshold 2.

[0123] In this embodiment, a first correspondence between wear order and sound pressure level density threshold is constructed through a preset second correspondence between wear order and wear degree threshold, and a third correspondence between sound pressure level density threshold and wear degree threshold. Therefore, this solution can determine the sound pressure level density threshold corresponding to the target wear order during the operation of the target vehicle. Then, by comparing the magnitude of the dominant frequency sound pressure level density in the noise dominant frequency data with the sound pressure level density threshold, it can determine whether the target wheel is abnormal, thus achieving real-time detection of the target wheel.

[0124] In one embodiment, determining the third correspondence between the sound pressure level density threshold and the wear degree threshold based on the sound pressure level density in the reference data and a preset density threshold determination strategy includes:

[0125] For the reference data of sample wheels belonging to the same wear degree threshold, among the sound pressure level densities included in each reference data, the sound pressure level density that meets the preset selection conditions is determined, and the sound pressure level density corresponding to the wear degree threshold is obtained; based on the sound pressure level density corresponding to each wear degree threshold, the third correspondence between the sound pressure level density threshold and the wear degree threshold is determined.

[0126] The reference data includes historical dominant frequencies and the corresponding sound pressure level density.

[0127] In this embodiment, for each reference data point of a sample wheel belonging to the same wear level threshold, the sound pressure level density that meets the preset selection criteria is selected from the sound pressure level densities included in each reference data point, and the sound pressure level density that meets the preset selection criteria is taken as the sound pressure level density corresponding to the wear level threshold. After the terminal selects the sound pressure level density corresponding to each wear level threshold, the terminal constructs a third correspondence between the sound pressure level density threshold and the wear level threshold based on the sound pressure level density corresponding to each wear level threshold.

[0128] In this embodiment, the sound pressure level density corresponding to the wear level threshold is determined based on reference data of sample wheels belonging to the same wear level threshold, and a third correspondence is constructed based on the sound pressure level density corresponding to each wear level threshold. Therefore, this scheme can construct a third correspondence between the sound pressure level density threshold and the wear level threshold, providing a prerequisite for subsequently determining the first correspondence based on the third correspondence.

[0129] In one embodiment, determining the sound pressure level density that satisfies the preset selection criteria includes:

[0130] Determine the sound pressure level density corresponding to a preset quantile; or, determine the sound pressure level density belonging to a preset first sound pressure level density interval, and determine the sound pressure level density corresponding to the mode among the sound pressure level densities belonging to the preset first sound pressure level density interval; or, determine the sound pressure level density belonging to a preset second sound pressure level density interval, and determine the sound pressure level density corresponding to the mean among the sound pressure level densities belonging to the preset second sound pressure level density interval.

[0131] In this embodiment, the terminal calculates the sound pressure level density corresponding to a preset quantile. The preset quantile is the i% quantile, where i is a positive number less than 100. Optionally, i can be 1 or 1.5. Alternatively, the terminal filters sound pressure level densities belonging to a preset first sound pressure level density interval, calculates the mode of each sound pressure level density within the preset first sound pressure level density interval, and determines the sound pressure level density corresponding to the mode. Alternatively, the terminal filters sound pressure level densities belonging to a preset second sound pressure level density interval, calculates the average of each sound pressure level density within the preset second sound pressure level density interval, and determines the sound pressure level density corresponding to the average. The sound pressure level density interval (including the first and second sound pressure level density intervals) is determined based on a reference wear threshold. It is understood that the first and second sound pressure level density intervals can be the same or different. In one embodiment, the lower limit of the sound pressure level density range is a reference wear level threshold, and the upper limit of the preset sound pressure level density range is the sum of the reference wear level threshold and the allowable error. Optionally, the allowable error can be 0.1, 0.5, or 1. The allowable error is preset based on human experience.

[0132] In this embodiment, the sound pressure level density that satisfies the preset selection conditions includes at least three types: the first type is the sound pressure level density corresponding to a preset quantile; the second type is the sound pressure level density corresponding to the mode of each sound pressure level density belonging to a preset first sound pressure level density interval; and the third type is the sound pressure level density corresponding to the average of each sound pressure level density belonging to a preset second sound pressure level density interval. Therefore, this method can determine the sound pressure level density corresponding to the wear degree threshold from the reference data, thus providing a prerequisite for subsequently constructing a third correspondence between the sound pressure level density threshold and the wear degree threshold.

[0133] In one embodiment, before determining the wear degree threshold corresponding to the historical wear level based on the historical wear level of the sample wheel and a preset second correspondence between the wear level and the wear degree threshold, the method further includes:

[0134] The historical noise time-domain data of the sample wheel is collected by the noise acquisition component corresponding to the sample wheel according to the preset acquisition frequency; based on the target historical time-domain data in the historical noise time-domain data, the historical dominant frequency data of the target historical time-domain data in the preset frequency band is determined, and based on the historical dominant frequency data, the historical wear order of the sample wheel is determined.

[0135] In this embodiment, during the operation of the sample vehicle, the terminal collects historical noise time-domain data of the sample wheel through the noise collection component corresponding to the sample wheel of the sample vehicle at a preset collection frequency. In one embodiment, the noise collection component is a sound level meter. Optionally, the noise collection component can be installed near the bogie of the sample vehicle or at a distance not exceeding a preset distance from the bottom of the carriage. In one embodiment, the preset distance is 50 centimeters. The preset collection frequency is greater than or equal to 2000 Hz. The terminal filters the historical noise time-domain data to obtain target historical time-domain data according to preset filtering conditions. The terminal performs frequency domain transformation processing on the target historical time-domain data to obtain historical frequency-domain data corresponding to the target historical time-domain data. Specifically, the terminal performs Fourier transform on the target historical time-domain data to obtain historical frequency-domain data corresponding to the target historical time-domain data. The historical frequency-domain data refers to noise data containing historical noise frequency-domain information. Optionally, the historical frequency-domain data can be a noise spectrum or a noise time-frequency signal. In one embodiment, the Fourier transform is a short-time Fourier transform, specifically as shown in the above formula (1). The terminal uses the historical frequency domain data corresponding to the preset frequency band as the target historical frequency domain data, and obtains the historical dominant frequency data from the target historical frequency domain data. The historical dominant frequency data includes the historical dominant frequency and the sound pressure level density corresponding to that historical dominant frequency. Based on the historical dominant frequency in the historical dominant frequency data and the preset correspondence between frequency and wear order, the terminal calculates the historical wear order of the sample wheel. In one embodiment, the preset correspondence between frequency and wear order is as shown in formula (2) above.

[0136] In this embodiment, the historical dominant frequency data is determined based on the target historical time-domain data in the historical noise time-domain data, and then the historical wear order is determined. Therefore, this scheme can determine the historical wear order based on the historical noise time-domain data of the sample wheel, thus providing a basis for subsequently determining the wear degree threshold corresponding to the historical wear order based on the historical wear order and the preset second correspondence.

[0137] In one embodiment, the historical noise time-domain data includes each historical acquisition time and the historical sound pressure level corresponding to each historical acquisition time; after acquiring the historical noise time-domain data of the sample wheels according to a preset acquisition frequency, it also includes:

[0138] Historical sound pressure levels that are less than or equal to a preset sound pressure level threshold are filtered to obtain the target historical sound pressure level; historical noise time-domain data based on the target historical sound pressure level and the target historical acquisition time corresponding to the historical target sound pressure level are used as the target historical noise time-domain data.

[0139] The historical noise time-domain data includes each historical acquisition time and the corresponding historical sound pressure level. The target historical noise time-domain data includes each target historical acquisition time and the corresponding target historical sound pressure level.

[0140] In this embodiment, the terminal filters historical sound pressure levels that are less than or equal to a preset sound pressure level threshold from all historical sound pressure levels in the historical noise time-domain data, and uses the historical sound pressure levels that are less than or equal to the preset sound pressure level threshold as the target historical sound pressure level. The terminal uses the historical noise time-domain data based on the target historical sound pressure level and the target historical acquisition time corresponding to the target historical sound pressure level as the target historical noise time-domain data.

[0141] In this embodiment, the target historical noise time-domain data is determined based on a preset sound pressure level threshold. The target historical sound pressure level in the target historical noise time-domain data is all less than or equal to the sound pressure level threshold. Therefore, interference data with higher sound pressure levels can be filtered out, resulting in more accurate target historical noise time-domain data.

[0142] In one embodiment, determining the historical dominant frequency data of the target historical time-domain data in a preset frequency band based on the target historical time-domain data in the historical noise time-domain data, and determining the historical wear order of the sample wheel based on the historical dominant frequency data includes:

[0143] In the historical frequency domain data corresponding to the target historical time domain data, the target historical frequency domain data corresponding to the preset frequency band is determined; in the target historical frequency domain data containing historical noise frequencies and historical sound pressure level densities corresponding to historical noise frequencies, the historical sound pressure level density peak value and the historical noise frequency corresponding to the historical sound pressure level density peak value are determined to obtain the historical dominant frequency data; based on the historical dominant frequency of the historical dominant frequency data, the preset sample wheel diameter, and the sample vehicle speed, the historical wear order is determined.

[0144] The target historical frequency domain data includes historical noise frequencies and the corresponding historical sound pressure level density. The historical dominant frequency data includes the historical dominant frequency and the corresponding sound pressure level density.

[0145] In this embodiment, the terminal matches historical frequency domain data corresponding to the target historical time domain data with a preset frequency band, and uses the historical frequency domain data corresponding to the preset frequency band as the target historical frequency domain data. The terminal determines the historical sound pressure level density peak and the historical noise frequency corresponding to the historical sound pressure level density peak from the target historical frequency domain data containing historical noise frequencies and the historical sound pressure level density corresponding to those historical noise frequencies, and uses the target historical frequency domain data based on the historical sound pressure level density peak and the historical noise frequency corresponding to that peak as the historical dominant frequency data. It can be understood that the historical sound pressure level density peak is the historical dominant frequency sound pressure level density of the historical dominant frequency data, and the historical noise frequency corresponding to the historical sound pressure level density peak is the historical dominant frequency frequency of the historical dominant frequency data. The terminal obtains the sample vehicle speed of the sample vehicle. Optionally, the sample vehicle speed can be a preset speed or the real-time speed obtained by the sample vehicle during operation. The terminal calculates the historical wear order of the sample wheel based on the historical main frequency data, the preset sample wheel diameter, the sample vehicle speed, and the preset correspondence between frequency and wear order. In one embodiment, the preset correspondence between frequency and wear order is as shown in formula (2) above.

[0146] In this embodiment, historical dominant frequency data is determined from the historical frequency domain data corresponding to the preset frequency band, and the historical wear order of the sample wheel is calculated based on the historical dominant frequency of the historical dominant frequency data. Therefore, this solution can determine the historical wear order of the sample wheel based on the collected historical dominant frequency data during the operation of the sample vehicle.

[0147] In one embodiment, an example of a wheel detection method is also provided, which includes the following steps:

[0148] S1: The historical noise time-domain data of the sample wheel is collected by the noise acquisition component corresponding to the sample wheel at a preset acquisition frequency. The historical noise time-domain data includes each historical acquisition time and the historical sound pressure level corresponding to each historical acquisition time.

[0149] S2, filter historical sound pressure levels that are less than or equal to a preset sound pressure level threshold to obtain the target historical sound pressure level.

[0150] S3 uses the historical noise time-domain data, which is based on the target historical sound pressure level and the target historical acquisition time corresponding to the historical target sound pressure level, as the target historical noise time-domain data.

[0151] S4. Based on the target historical time domain data in the historical noise time domain data, determine the historical main frequency data of the target historical time domain data in the preset frequency band, and determine the historical wear order of the sample wheel based on the historical main frequency data.

[0152] S5. Based on the historical wear levels of the sample wheels and the second correspondence between the preset wear levels and wear degree thresholds, determine the reference wear degree threshold corresponding to the historical wear levels.

[0153] S6. If the wear level of the sample wheel is greater than or equal to the reference wear level threshold, the historical frequency data of the sample wheel to which the wear level belongs is used as the reference data.

[0154] S7. Based on the sound pressure level density in the reference data and the preset density threshold determination strategy, determine the third correspondence between the sound pressure level density threshold and the wear degree threshold.

[0155] S8. For each wear degree threshold, determine the wear order corresponding to the wear degree threshold in the second correspondence relationship, determine the sound pressure level density threshold corresponding to the wear degree threshold in the third correspondence relationship, and then determine the sound pressure level density threshold corresponding to the wear order to obtain the first correspondence relationship.

[0156] S9 collects the time-domain noise data of the target wheel using the noise acquisition component corresponding to the target wheel at a preset acquisition frequency.

[0157] S10: Filter out sound pressure levels that are less than or equal to the preset sound pressure level threshold to obtain the target sound pressure level.

[0158] S11, the noise time-domain data based on the target sound pressure level and the target acquisition time corresponding to the target sound pressure level is used as the target noise time-domain data.

[0159] S12, based on the target noise time domain data in the noise time domain data, determine the noise main frequency data of the target noise time domain data in the preset frequency band, and based on the noise main frequency data, determine the target wear order of the target wheel.

[0160] S13, based on the target wear order and the first correspondence between the preset wear order and the sound pressure level density threshold, determine the target sound pressure level density threshold corresponding to the target wear order.

[0161] S14: If the main frequency sound pressure level density in the noise main frequency data is greater than or equal to the target sound pressure level density threshold, generate detection information indicating wheel abnormality.

[0162] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0163] Based on the same inventive concept, this application also provides a wheel detection device for implementing the wheel detection method described above. The solution provided by this device is similar to the solution described in the above method; therefore, the specific limitations in one or more wheel detection device embodiments provided below can be found in the limitations of the wheel detection method described above, and will not be repeated here.

[0164] In one embodiment, such as Figure 5 As shown, a wheel detection device is provided, which includes:

[0165] The first acquisition module 502 is used to acquire the noise time domain data of the target wheel through the noise acquisition component corresponding to the target wheel at a preset acquisition frequency.

[0166] The first determining module 504 is used to determine the noise main frequency data of the target noise time domain data in a preset frequency band based on the target noise time domain data in the noise time domain data, and to determine the target wear order of the target wheel based on the noise main frequency data.

[0167] The second determining module 506 is used to determine the target sound pressure level density threshold corresponding to the target wear order based on the target wear order and the first correspondence between the preset wear order and the sound pressure level density threshold.

[0168] The third determining module 508 is used to generate detection information indicating wheel abnormality when the main frequency sound pressure level density in the noise main frequency data is greater than or equal to the target sound pressure level density threshold.

[0169] In one embodiment, the wheel detection device further includes:

[0170] The first filtering module is used to filter sound pressure levels that are less than or equal to a preset sound pressure level threshold to obtain the target sound pressure level.

[0171] The first construction module is used to take the noise time-domain data based on the target sound pressure level and the target acquisition time corresponding to the target sound pressure level as the target noise time-domain data.

[0172] In one embodiment, the first determining module 504 is specifically used for:

[0173] In the noise frequency domain data corresponding to the target noise time domain data, determine the target noise frequency domain data corresponding to the preset frequency band;

[0174] In the target noise frequency domain data that includes the target noise frequency and the target sound pressure level density corresponding to the target noise frequency, the peak value of the target sound pressure level density and the target noise frequency corresponding to the peak value of the target sound pressure level density are determined to obtain the noise main frequency data.

[0175] The target wear level is determined based on the main frequency of the noise main frequency data, the preset target wheel diameter, and the target vehicle speed.

[0176] In one embodiment, the wheel detection device further includes:

[0177] The fourth determining module is used to determine the reference wear degree threshold corresponding to the historical wear level based on the historical wear level of the sample wheel and the second correspondence between the preset wear level and the wear degree threshold.

[0178] The fifth determination module is used to use the historical frequency data of the sample wheel to which the wear level belongs as reference data when the wear level of the sample wheel is greater than or equal to the reference wear level threshold.

[0179] The sixth determination module is used to determine the third correspondence between the sound pressure level density threshold and the wear degree threshold based on the sound pressure level density in the reference data and the preset density threshold determination strategy.

[0180] The seventh determining module is used to determine the wear level corresponding to each wear level threshold in the second correspondence relationship, determine the sound pressure level density threshold corresponding to the wear level threshold in the third correspondence relationship, and then determine the sound pressure level density threshold corresponding to the wear level threshold to obtain the first correspondence relationship.

[0181] In one embodiment, the sixth determining module is specifically used for:

[0182] For the reference data of sample wheels belonging to the same wear degree threshold, among the sound pressure level densities contained in each reference data, the sound pressure level density that meets the preset selection conditions is determined, and the sound pressure level density corresponding to the wear degree threshold is obtained.

[0183] Based on the sound pressure level density corresponding to each wear degree threshold, a third correspondence between the sound pressure level density threshold and the wear degree threshold is determined.

[0184] In one embodiment, the sixth determining module is specifically used for:

[0185] Determine the sound pressure level density corresponding to the preset quantile; or,

[0186] Determine the sound pressure level density belonging to a preset first sound pressure level density range, and among the sound pressure level densities belonging to the preset first sound pressure level density range, determine the sound pressure level density corresponding to the mode; or,

[0187] Determine the sound pressure level density that belongs to the preset second sound pressure level density range, and determine the sound pressure level density corresponding to the average value among the sound pressure level densities that belong to the preset second sound pressure level density range.

[0188] In one embodiment, the wheel detection device further includes:

[0189] The second acquisition module is used to acquire historical noise time-domain data of the sample wheel through the noise acquisition component corresponding to the sample wheel at a preset acquisition frequency.

[0190] The eighth determination module is used to determine the historical main frequency data of the target historical time domain data in the preset frequency band based on the target historical time domain data in the historical noise time domain data, and to determine the historical wear order of the sample wheel based on the historical main frequency data.

[0191] In one embodiment, the historical noise time-domain data includes each historical acquisition time and the historical sound pressure level corresponding to each historical acquisition time; the wheel detection device further includes:

[0192] The second filtering module is used to filter historical sound pressure levels that are less than or equal to a preset sound pressure level threshold to obtain the target historical sound pressure level.

[0193] The second construction module is used to take the historical noise time-domain data, which is based on the target historical sound pressure level and the target historical acquisition time corresponding to the historical target sound pressure level, as the target historical noise time-domain data.

[0194] In one embodiment, the eighth determining module is specifically used for:

[0195] In the historical frequency domain data corresponding to the target historical time domain data, the target historical frequency domain data corresponding to the preset frequency band is determined; in the target historical frequency domain data containing historical noise frequencies and historical sound pressure level densities corresponding to historical noise frequencies, the historical sound pressure level density peak value and the historical noise frequency corresponding to the historical sound pressure level density peak value are determined to obtain the historical dominant frequency data; based on the historical dominant frequency of the historical dominant frequency data, the preset sample wheel diameter, and the sample vehicle speed, the historical wear order is determined.

[0196] Each module in the aforementioned wheel detection device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the corresponding operations of each module.

[0197] In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 6 As shown, the computer device includes a processor, memory, input / output interface, communication interface, display unit, and input device. The processor, memory, and input / output interface are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interface. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The input / output interface is used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, NFC (Near Field Communication), or other technologies. When executed by the processor, the computer program implements a wheel detection method. The display unit is used to form a visually visible image and can be a display screen, projection device, or virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device of the computer device can be a touch layer covering the display screen, or buttons, trackballs, or touchpads set on the casing of the computer device, or external keyboards, touchpads, or mice, etc.

[0198] Those skilled in the art will understand that Figure 6 The structures shown are merely block diagrams of some structures related to the present application and do not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than shown in the figures, or combine certain components, or have different component arrangements. In one embodiment, a computer device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described method embodiments.

[0199] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements the steps in the above method embodiments.

[0200] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above method embodiments.

[0201] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data shall comply with the relevant laws, regulations and standards of the relevant countries and regions.

[0202] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0203] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0204] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A wheel detection method characterized by, The method comprises: acquiring noise time domain data of the target wheel through a noise acquisition component corresponding to the target wheel according to a preset acquisition frequency; determining noise main frequency data of the target noise time domain data in a preset frequency band according to target noise time domain data in the noise time domain data, and determining a target wear order of the target wheel according to the noise main frequency data; determining a target sound pressure level density threshold corresponding to the target wear order according to the target wear order and a first corresponding relationship between a preset wear order and a sound pressure level density threshold; generating detection information indicating wheel abnormality in a case where a main frequency sound pressure level density in the noise main frequency data is greater than or equal to the target sound pressure level density threshold; The method further comprises: determining a reference wear degree threshold corresponding to a historical wear order of a sample wheel according to the historical wear order of the sample wheel and a second corresponding relationship between a preset wear order and a wear degree threshold; in a case where a wear degree of the sample wheel is greater than or equal to the reference wear degree threshold, historical main frequency data of the sample wheel to which the wear degree belongs is taken as reference data; a third corresponding relationship between a sound pressure level density threshold and a wear degree threshold is determined according to a sound pressure level density in the reference data and a preset density threshold determination strategy; for each wear degree threshold, a wear order corresponding to the wear degree threshold is determined in the second corresponding relationship, a sound pressure level density threshold corresponding to the wear degree threshold is determined in the third corresponding relationship, and then a sound pressure level density threshold corresponding to the wear order is determined, so as to obtain the first corresponding relationship; The third corresponding relationship between the sound pressure level density threshold and the wear degree threshold is determined according to the sound pressure level density in the reference data and the preset density threshold determination strategy, and comprises: for reference data of sample wheels belonging to the same wear degree threshold, a sound pressure level density satisfying a preset selection condition is determined in the sound pressure level density contained in each reference data, so as to obtain a sound pressure level density corresponding to the wear degree threshold; the third corresponding relationship between the sound pressure level density threshold and the wear degree threshold is determined according to the sound pressure level density corresponding to each wear degree threshold.

2. The method of claim 1, wherein, The noise time domain data comprises each acquisition time and a sound pressure level corresponding to each acquisition time; after the noise time domain data of the target wheel is acquired according to the preset acquisition frequency, the method further comprises: screening the sound pressure level less than or equal to a preset sound pressure level threshold, so as to obtain a target sound pressure level; taking noise time domain data formed based on the target sound pressure level and a target acquisition time corresponding to the target sound pressure level as target noise time domain data.

3. The method according to any one of claims 1 to 2, characterized in that, The noise main frequency data of the target noise time domain data in the preset frequency band is determined in noise frequency domain data corresponding to the target noise time domain data, and the target wear order of the target wheel is determined according to the noise main frequency data. ​ In target noise frequency domain data containing a target noise frequency and a target sound pressure level density corresponding to the target noise frequency, a target sound pressure level density peak value and a target noise frequency corresponding to the target sound pressure level density peak value are determined to obtain noise main frequency data; A target wear order is determined according to a main frequency frequency of the noise main frequency data, a preset target wheel diameter, and a target vehicle speed.

4. The method of claim 1, wherein, The determination of the sound pressure level density satisfying the preset selection condition comprises: determining a sound pressure level density corresponding to a preset quantile; or determining a sound pressure level density belonging to a preset first sound pressure level density interval, and determining a sound pressure level density corresponding to a mode in the sound pressure level density belonging to the preset first sound pressure level density interval; or determining a sound pressure level density belonging to a preset second sound pressure level density interval, and determining a sound pressure level density corresponding to a mean in the sound pressure level density belonging to the preset second sound pressure level density interval.

5. The method of claim 1, wherein, Before the determination of the wear degree threshold value corresponding to the historical wear order according to the historical wear order of the sample wheel and a preset second correspondence relationship between wear orders and wear degree threshold values, the method further comprises: acquiring historical noise time domain data of the sample wheel by a noise acquisition component corresponding to the sample wheel according to the preset acquisition frequency; determining historical main frequency data of target historical time domain data in the preset frequency range according to the target historical time domain data in the historical noise time domain data, and determining a historical wear order of the sample wheel according to the historical main frequency data.

6. A wheel detection device, characterized by The device comprises: a first acquisition module configured to acquire noise time domain data of a target wheel by a noise acquisition component corresponding to the target wheel according to a preset acquisition frequency; a first determination module configured to determine noise main frequency data of target noise time domain data in a preset frequency range according to the target noise time domain data in the noise time domain data, and determine a target wear order of the target wheel according to the noise main frequency data; a second determination module configured to determine a target sound pressure level density threshold value corresponding to the target wear order according to the target wear order and a preset first correspondence relationship between wear orders and sound pressure level density threshold values; a third determination module configured to generate detection information indicating wheel abnormality in a case where a main frequency sound pressure level density in the noise main frequency data is greater than or equal to the target sound pressure level density threshold value; The device further comprises: a fourth determination module configured to determine a reference wear degree threshold value corresponding to a historical wear order of a sample wheel according to the historical wear order of the sample wheel and a preset second correspondence relationship between wear orders and wear degree threshold values; a fifth determination module configured to use historical main frequency data of a sample wheel to which a wear degree belongs as reference data in a case where the wear degree of the sample wheel is greater than or equal to the reference wear degree threshold value; a sixth determination module configured to determine a third correspondence relationship between a sound pressure level density threshold value and a wear degree threshold value according to a sound pressure level density in the reference data and a preset density threshold value determination strategy. The seventh determining module is configured to, for each of the wear degree thresholds, determine, in the second correspondence, a wear order corresponding to the wear degree threshold, determine, in the third correspondence, a sound pressure level density threshold corresponding to the wear degree threshold, and further determine a sound pressure level density threshold corresponding to the wear order, to obtain the first correspondence. The sixth determining module is specifically configured to: for the reference data of the sample wheel to which the same wear degree threshold belongs, determine, in the sound pressure level densities contained in each of the reference data, a sound pressure level density satisfying a preset selection condition, to obtain a sound pressure level density corresponding to the wear degree threshold; and determine, according to the sound pressure level densities corresponding to each of the wear degree thresholds, a third correspondence between the sound pressure level density threshold and the wear degree threshold.

7. The apparatus of claim 6, wherein, Further comprising: The first screening module is configured to screen the sound pressure levels less than or equal to a preset sound pressure level threshold, to obtain a target sound pressure level. The first constructing module is configured to construct, as target noise time domain data, noise time domain data based on the target sound pressure level and a target acquisition time corresponding to the target sound pressure level.

8. The apparatus of claim 6, wherein, The first determining module is specifically configured to: In noise frequency domain data corresponding to the target noise time domain data, determine target noise frequency domain data corresponding to a preset frequency band; in the target noise frequency domain data containing a target noise frequency and a target sound pressure level density corresponding to the target noise frequency, determine a target sound pressure level density peak value and a target noise frequency corresponding to the target sound pressure level density peak value, to obtain noise main frequency data; and determine a target wear order according to a main frequency frequency of the noise main frequency data, a preset target wheel diameter, and a target vehicle speed. 9.A computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the computer device is configured to perform the method according to any one of claims 1-8 when the computer program is executed by the processor. The processor executes the computer program to implement the steps of the method in any one of claims 1 to 5.

10. A computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to implement the steps of the method in any one of claims 1 to 5.

Images