Axle box fault detection method and device, electronic equipment and storage medium

Abstract

The invention relates to the field of industrial production, and particularly discloses an axle box fault detection method and device, electronic equipment and a computer readable storage medium. The axle box fault detection method comprises the following steps: acquiring vibration data and sound data of a to-be-detected axle box; obtaining a vibration amplitude set corresponding to the vibration data; comparing the amplitude of each sound time-domain signal in the sound data with an amplitude threshold value, and determining a ratio of normal sound time-domain signals; wherein the amplitude threshold value is obtained according to sample sound data generated by the sample axle box in a non-fault state; and determining whether the axle box to be detected is in a fault state or not according to the normal sound time domain signal proportion and the vibration amplitude set. Compared with the prior art, the axle box fault detection method and device, the electronic equipment and the computer readable storage medium provided by the embodiment of the invention have the advantage that the accuracy of detecting the fault condition of the axle box can be improved.

Description

Technical Field

[0001] The present application relates to the field of industrial production, and more specifically, to an axle box fault detection method, device, electronic device and computer-readable storage medium. Background Art

[0002] In the field of multi-wire cutting, the cutting wires are often arranged spirally on multiple main rollers at a certain distance to form a cutting wire net, and the multi-wire cutting work is achieved through the grinding between the wire net and the workpiece. In current industrial applications, the two ends of each main roller are usually connected to the front and rear bearings, and the bearings at both ends of the main roller are usually set in two pairs of front and rear bearing boxes.

[0003] In the process of the main roller being driven to rotate by the motor, the bearing in the axle box may fail due to reasons such as over-temperature or excessive load. The existing technology usually makes judgments based on the operator's work experience. For example, when an abnormal sound or excessive temperature occurs in the axle box, it is considered that the bearing in the axle box has failed, and the axle box is repaired or replaced, resulting in the problem of low accuracy in judging the degree of axle box failure. Summary of the invention

[0004] The purpose of the present application is to provide an axle box fault detection method, device, electronic device and computer-readable storage medium, which can improve the accuracy of detecting axle box fault conditions.

[0005] In the first aspect, the present application provides an axle box fault detection method, comprising: obtaining vibration data and sound data of an axle box to be tested, wherein the axle box to be tested is a main roller axle box in a multi-wire cutting machine, and the vibration data includes multiple vibration time domain signals, and the sound data includes multiple sound time domain signals; performing noise reduction processing on each vibration time domain signal in the vibration data to obtain noise-reduced vibration data, and obtaining the amplitudes of all noise-reduced vibration time domain signals in the noise-reduced vibration data as a vibration amplitude set; comparing the amplitudes of each sound time domain signal in the sound data with an amplitude threshold value to determine the proportion of normal sound time domain signals; wherein the amplitude threshold value is obtained based on sample sound data generated by a sample axle box in a non-fault state; determining whether the axle box to be tested is in a fault state based on the proportion of normal sound time domain signals and the vibration amplitude set.

[0006] Compared with the prior art, in the axle box fault detection method provided in the embodiment of the present application, vibration data and sound data of the axle box to be tested are obtained, multiple vibration time domain signals in the vibration data are processed to obtain the vibration amplitude of the axle box to be tested, and multiple sound time domain signals in the sound data are processed to obtain the proportion of normal sound time domain signals in the sound data. According to the proportion of normal sound time domain signals and the vibration amplitude set, it is determined whether the axle box to be tested is in a faulty state, and the vibration data and sound data generated during the operation of the axle box to be tested are comprehensively considered, so as to improve the accuracy of detecting the fault condition of the axle box.

[0007] In an optional embodiment, the step of obtaining the amplitude threshold value includes: collecting multiple groups of sample sound data when the sample axle box is in a non-fault state; calculating the average of the amplitudes of the sound time domain signals in the multiple groups of sample sound data as an amplitude reference value; and determining the amplitude threshold value of the axle box to be tested based on the amplitude reference value.

[0008] In an optional embodiment, comparing the amplitude of each sound time domain signal in the sound data with the amplitude threshold value to determine the proportion of normal sound time domain signals includes: comparing the amplitude of each sound time domain signal in the sound data with the amplitude threshold value to obtain the number of normal sound time domain signals in the sound data; wherein, if the amplitude of any sound time domain signal is less than the amplitude threshold value, the sound time domain signal is determined to be a normal sound time domain signal; and determining the proportion of normal sound time domain signals based on the number of normal sound time domain signals and the total amount of the sound time domain signals.

[0009] In an optional embodiment, comparing the amplitude of each sound time domain signal in the sound data with an amplitude threshold value to determine the proportion of normal sound time domain signals includes: comparing the amplitude of each sound time domain signal in the sound data with an amplitude threshold value to obtain the number of abnormal sound time domain signals in the sound data; wherein, if the amplitude of any sound time domain signal is compared to be not less than the amplitude threshold value, the sound time domain signal is determined to be an abnormal sound time domain signal; and based on the number of abnormal sound time domain signals and the total amount of the sound time domain signals, the proportion of normal sound time domain signals is determined.

[0010] In an optional embodiment, determining whether the axle box to be tested is in a faulty state based on the proportion of the normal sound time-domain signal and the vibration amplitude set includes: judging whether the proportion of the normal sound time-domain signal is less than a set proportion, and obtaining a first judgment result, wherein the set proportion is determined based on the proportion of normal sample signals of the sample axle box in a faulty state; judging whether each vibration amplitude in the vibration amplitude set is not less than a set vibration amplitude, and obtaining a second judgment result, wherein the set vibration amplitude is obtained based on sample vibration data generated by the sample axle box in a non-faulty state; and determining whether the axle box to be tested is in a faulty state based on the first judgment result and the second judgment result.

[0011] In an optional embodiment, the determination of whether the axle box to be tested is in a faulty state is made based on the first judgment result and the second judgment result, including: if the first judgment result indicates that the proportion of the normal sound time domain signal is less than a set proportion, and the second judgment result indicates that there is at least one vibration amplitude not less than the set vibration amplitude, then it is determined that the axle box to be tested is in a faulty state.

[0012] In an optional embodiment, the determination of whether the axle box to be tested is in a faulty state is made based on the first judgment result and the second judgment result, including: if the first judgment result indicates that the proportion of the normal sound time domain signal is not less than a set proportion, and the second judgment result indicates that the vibration amplitude is not less than the set vibration amplitude and the duration exceeds a preset time length, then it is determined that the axle box to be tested is in a faulty state.

[0013] In an optional embodiment, the step of obtaining the set vibration amplitude is as follows: obtaining sample vibration data of the sample axle box in a non-fault state, the sample vibration data including a plurality of sample vibration time domain signals; normalizing each sample vibration time domain signal in the sample vibration data to obtain a sample normalized signal set, the sample normalized signal set including a plurality of sample normalized signals; and obtaining the set vibration amplitude according to the average amplitude of the sample normalized signal set.

[0014] In an optional embodiment, the step of obtaining the set ratio is as follows: obtaining N groups of sample fault sound data when the sample axle box is in a fault state, wherein N is an integer greater than 1; obtaining the proportion of N groups of normal sample signals among the N groups of sample fault sound data; and determining the set ratio based on the proportion of the N groups of normal sample signals.

[0015] In the second aspect, the present application provides an axle box fault detection device, comprising: a signal acquisition module, used to acquire vibration data and sound data of the axle box to be tested, wherein the axle box to be tested is the main roller axle box in a multi-wire cutting machine, and the vibration data includes multiple vibration time domain signals, and the sound data includes multiple sound time domain signals; a signal processing module, used to perform noise reduction processing on each vibration time domain signal in the vibration data to obtain noise-reduced vibration data, and obtain the amplitudes of all noise-reduced vibration time domain signals in the noise-reduced vibration data as a vibration amplitude set; and also used to compare the amplitudes of each sound time domain signal in the sound data with an amplitude threshold value to determine the proportion of normal sound time domain signals; wherein the amplitude threshold value is obtained based on sample sound data generated by the sound of the axle box to be tested in a non-fault state; a fault determination module, used to determine whether the axle box to be tested is in a fault state based on the proportion of normal sound time domain signals and the vibration amplitude set.

[0016] In a third aspect, the present application provides an electronic device comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the axle box fault detection method as described in any one of the aforementioned embodiments.

[0017] In a fourth aspect, the present application provides a computer-readable storage medium storing a computer program, wherein the computer program is executed by a processor to implement the axle box fault detection method described in any one of the aforementioned embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0019] Figure 1 A schematic flow chart of the axle box fault detection method provided in the first embodiment of the present application;

[0020] Figure 2 It is a schematic diagram of the vibration time domain signal actually collected without normalization processing;

[0021] Figure 3 It is a schematic diagram of the normalized vibration time domain signal actually collected;

[0022] Figure 4 This is a schematic diagram of the structure of the axle box fault detection device provided in Example 2 of the present application;

[0023] Figure 5 This is a schematic diagram of the structure of the electronic device provided in Example 3 of the present application. DETAILED DESCRIPTION

[0024] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. The components of the embodiments of the present application described and shown in the drawings here can be arranged and designed in various different configurations.

[0025] Therefore, the following detailed description of the embodiments of the present application provided in the accompanying drawings is not intended to limit the scope of the present application for which protection is sought, but merely represents selected embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present application.

[0026] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, further definition and explanation thereof is not required in subsequent drawings.

[0027] In the description of the present application, it should be noted that if the terms "upper", "lower", "inside", "outside", etc. appear to indicate an orientation or position relationship, they are based on the orientation or position relationship shown in the drawings, or are the orientation or position relationship in which the product of the application is usually placed when used. This is only for the convenience of describing the present application and simplifying the description, and does not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present application.

[0028] In addition, the terms “first”, “second”, etc., if used, are merely used to distinguish between the descriptions and should not be understood as indicating or implying relative importance.

[0029] It should be noted that, in the absence of conflict, the features in the embodiments of the present application may be combined with each other.

[0030] The first embodiment of the present application provides an axle box fault detection method, which is applied to an axle box fault detection device, such as Figure 1 As shown, the axle box fault detection method includes the following steps:

[0031] Step S101: Obtain vibration data and sound data of the axle box to be tested.

[0032] In this step, the axle box to be tested is the main roller axle box in the multi-wire cutting machine. When the multi-wire cutting machine is in operation, the axle box to be tested will generate vibrations during operation. The vibration signal of the axle box to be tested during operation is collected to obtain a vibration signal. Among them, the vibration signal may include a frequency domain signal and a time domain signal. The frequency domain signal is a relationship signal between the vibration amplitude and the vibration frequency, and the time domain signal is a relationship signal between the vibration amplitude and time. In the present application, the vibration time domain signal generated by the vibration during the operation of the axle box to be tested is obtained as vibration data.

[0033] Specifically, in some embodiments of the present application, the vibration signal and the sound signal of the axle box to be tested are continuously collected in a time period, so as to obtain N vibration time domain signals and M sound time domain signals in this time period, and the obtained N vibration time domain signals are used as vibration data, and the M sound time domain signals are used as sound data. Wherein, N and M are natural numbers greater than 1, and in different embodiments of the present application, the values ​​of N and M may be equal or unequal, and may be specifically set according to the sampling frequencies corresponding to the vibration time domain signals and the sound time domain signals.

[0034] When obtaining vibration data and sound data of the same time period, different values ​​can be set for the time period according to different actual situations. For example, the duration of the vibration time domain signal can be set according to the working accuracy of the axle box to be tested. For the axle box to be tested with higher working accuracy, it is more sensitive to axle box failures, and the time period can be set shorter, such as 3 seconds to 5 minutes, to obtain shorter vibration time domain signals and sound time domain signals as vibration data and sound data. For the axle box to be tested with lower working accuracy, the time period can be set longer, such as 4 minutes to 20 minutes, to obtain longer vibration time domain signals and sound time domain signals as vibration data and sound data. Specifically, the duration of the time period can be flexibly set according to actual situations.

[0035] In different embodiments of the present application, the method for obtaining the vibration time domain signal and the sound time domain signal may be to set a vibration detection device in the axle box fault detection device. For the acquisition process of the vibration time domain signal, the vibration detection device may be installed on the axle box to be tested, and the vibration detection device may be used to directly perform vibration detection on the axle box to be tested, thereby obtaining the vibration time domain signal generated by the vibration of the axle box to be tested. Among them, in some embodiments of the application, the vibration detection device may be, for example, a vibration acceleration sensor, a vibration infrared sensor and other equipment, which may be specifically set according to actual needs. For the acquisition process of the sound time domain signal, a sound detection device may be set in the axle box fault detection device, and the sound detection device may be installed on the axle box to be tested or near the axle box to be tested, and the sound detection device may be used to directly perform sound detection on the axle box to be tested, thereby obtaining the sound detection signal generated by the sound of the axle box to be tested. Among them, in some embodiments of the application, the sound detection device may be, for example, a sound sensor, a microphone and other equipment, which may be specifically set according to actual needs.

[0036] It can be understood that the aforementioned vibration detection equipment and sound detection equipment are arranged in the axle box fault detection device, and the vibration detection equipment and sound detection are used to perform vibration detection and sound detection on the axle box to be tested, so as to obtain the vibration time domain signal and sound time domain signal generated by the vibration of the axle box to be tested. These are only examples in some embodiments of the present application and do not constitute a limitation. In some other embodiments of the present application, other devices can also be used to detect the vibration and sound during the operation of the axle box to be tested, and upload the detected vibration time domain signal and sound time domain signal to the server, and a communication device is arranged in the axle box fault detection device, and the communication device can download the vibration time domain signal and sound time domain signal uploaded by other devices from the server.

[0037] Furthermore, in this step, when collecting the vibration time domain signal, the sampling frequency can be determined according to the vibration frequency of the axle box to be tested. Specifically, the vibration signal of the axle box to be tested can be initially sampled at an arbitrary sampling frequency to obtain the vibration frequency domain signal of the axle box to be tested, and the vibration frequency of the axle box to be tested is obtained according to the vibration frequency domain signal. The vibration frequency can be, for example, the maximum value, minimum value, mean value and other data of the frequency in the vibration frequency domain signal, and then the sampling frequency is determined according to the vibration frequency. Specifically, in some specific embodiments of the present application, the sampling frequency can be set to be greater than or equal to twice the vibration frequency. Similarly, in some embodiments of the present application, this sampling frequency can also be used to collect sound time domain signals to form sound data. Determining the sampling frequency according to the vibration frequency of the axle box to be tested can reduce the probability of high-frequency signals being sampled as low-frequency signals and increase the reliability of the collected vibration data and sound data.

[0038] Step S102: performing noise reduction processing on each vibration time domain signal in the vibration data to obtain noise-reduced vibration data, and obtaining the amplitudes of all noise-reduced vibration time domain signals in the noise-reduced vibration data as a vibration amplitude set.

[0039] In this step, for the vibration data, a preset noise reduction algorithm can be used to perform noise reduction processing on each vibration time domain signal in the vibration data to obtain a noise-reduced sound time domain signal corresponding to each vibration time domain signal, and each noise-reduced sound time domain signal constitutes the noise-reduced sound data.

[0040] Among them, in different embodiments of the present application, the preset noise reduction algorithm can be a singular value decomposition algorithm, a wavelet threshold noise reduction algorithm and other different noise reduction algorithms, which can be set according to actual needs.

[0041] In one embodiment of the present application, the amplitudes of all the noise reduction vibration time domain signals in the noise reduction vibration data can be directly obtained as a vibration amplitude set.

[0042] In addition, in some embodiments of the present application, each noise reduction vibration time domain signal in the noise reduction vibration data is normalized to obtain normalized vibration data, that is, each noise reduction vibration time domain signal in the noise reduction vibration data is centralized and normalized to obtain the corresponding normalized vibration time domain signal, and all the normalized vibration time domain signals obtained constitute the normalized vibration data, and then the amplitude of each normalized vibration time domain signal in the normalized vibration data is obtained, and the amplitude of all the normalized vibration time domain signals obtained is used as a vibration amplitude set. Normalizing the noise reduction vibration data can make the amplitudes of the obtained normalized vibration time domain signals be at the same order of magnitude, reduce the influence of a few special cases or sampling errors on the amplitude of the vibration time domain signal, and in addition, normalizing the noise reduction vibration data can also improve the contrast of the amplitudes between different vibration time domain signals.

[0043] In another embodiment of the present application, the amplitudes of all vibration time domain signals in the vibration data may be directly used as the vibration amplitude set, or the amplitudes of all normalized vibration time domain signals in the data may be used as the vibration amplitude set.

[0044] like Figure 2 The figure shows the actual collected vibration time domain signal without normalization. Figure 3 The figure shows the normalized vibration time domain signal obtained after normalization of the actual collected vibration time domain signal. Figure 2 and Figure 3 It can be clearly seen that Figure 2 The amplitude contrast in the unnormalized vibration time domain signal shown is low, while Figure 3 As shown, the amplitude contrast in the normalized vibration time domain signal obtained after normalization processing is high.

[0045] Step S103: comparing the amplitude of each sound time domain signal in the sound data with the amplitude threshold value to determine the proportion of normal sound time domain signals.

[0046] In some embodiments of the present application, each sound time domain signal in the sound data may be normalized to obtain multiple sound time domain normalized signals, and then the amplitude of each sound time domain normalized signal is obtained as the amplitude of the corresponding sound time domain signal. Normalizing the sound time domain signals can make the amplitudes of the obtained sound time domain normalized signals be at the same order of magnitude, reducing the impact of a few special cases or sampling errors on the set sound amplitude. In addition, normalizing the sound time domain signals can also improve the contrast of the amplitudes between different sound time domain signals.

[0047] In this step, the amplitude threshold value can be obtained based on the sample sound time domain signal set generated by the sample axle box in a non-fault state. Among them, the sample axle box can be an axle box of the same model as the axle box to be tested. In some embodiments of the present application, the sample axle box can also be the axle box to be tested itself, that is, the sample sound time domain signal is the sound signal generated when the axle box to be tested is in a non-fault state. Using the sound signal generated when the axle box to be tested itself is in a non-fault state as the sample sound time domain signal can make the correlation of the amplitude threshold value higher, and the accuracy of the final confirmation result of the fault degree of the axle box to be tested is also higher.

[0048] In different embodiments of the present application, the amplitude threshold value may be obtained in advance based on the sample sound time domain signal set, and in this step, the axle box fault monitoring device only needs to read the amplitude threshold value obtained in advance. In some other embodiments of the present application, in this step, the axle box fault monitoring device may directly read the sample sound time domain signal set, and then obtain the amplitude threshold value based on the sample sound time domain signal set.

[0049] In some embodiments of the present application, the number of sample axis boxes may be 1 or more, for example, 1, 3, 5, 10, etc., and this specification does not impose any specific limitation.

[0050] In some embodiments of the present application, the amplitude threshold value can be determined based on the amplitude mean of the sample sound time domain signal set when the sample axle box is in a non-fault state, and the sample sound time domain signal set includes the sample sound time domain signal when the sample axle box is in a non-fault state. Specifically, in some embodiments of the present application, multiple groups of sample sound data of the axle box to be tested in a non-fault state can be collected; the mean of the amplitude of the sound time domain signal in the multiple groups of sample sound data is calculated as the amplitude reference value; based on the amplitude reference value, the amplitude threshold value of the axle box to be tested is determined. Among them, in some embodiments of the present application, based on the amplitude reference value, the amplitude threshold value of the axle box to be tested is determined specifically by using the amplitude reference value as the amplitude threshold value. In some other embodiments of the present application, the product / quotient of the amplitude reference value and a preset weight value can also be used as the amplitude threshold value, and the sum / difference of the amplitude reference value and a preset setting value can also be used as the amplitude threshold value, which can be flexibly set according to actual needs. The preset weight value may be, for example, any value in the range of 0.9-1.2, and the preset setting value may be, for example, a preset constant value.

[0051] It can be understood that the aforementioned amplitude threshold value can be determined based on the amplitude mean of the sample sound time domain signal set, which is only an example in some embodiments of the present application. In some other embodiments of the present application, it can also be determined based on other data quantities such as the absolute average value of the amplitude of the sample sound time domain signal set, the amplitude waveform index, etc. as the amplitude threshold value, which can be flexibly set according to actual needs.

[0052] It can be understood that the aforementioned amplitude threshold value can be determined based on the amplitude mean of the sample sound time domain signal set, which is only an example in some embodiments of the present application. In some other embodiments of the present application, each sample sound time domain signal in the sample sound time domain signal set can also be normalized to obtain a sample sound time domain normalized signal set formed by multiple sample sound time domain normalized signals, and then the amplitude threshold value is obtained based on the average amplitude of the sample sound time domain normalized signal set. Normalizing the sample sound time domain signals can make the amplitudes of the obtained sample sound time domain normalized signals be at the same order of magnitude, reducing the impact of a few special cases or sampling errors on the amplitude threshold value. In addition, normalizing the sample sound time domain signals can also enhance the amplitude contrast between different sample sound time domain signals.

[0053] In some embodiments of the present application, obtaining an amplitude threshold value according to a sample sound time domain signal set may further include: determining whether the data fluctuation range of a plurality of sample sound time domain signals is within a preset fluctuation range, wherein the data fluctuation range may be characterized by data such as signal variance and standard deviation of the sample sound time domain signals, and the preset fluctuation range is a preset acceptable data fluctuation range. If the data fluctuation range of a plurality of sample sound time domain signals exceeds the preset fluctuation range, a first amplitude is obtained as the amplitude threshold value; if the data fluctuation range of a plurality of sample sound time domain signals is within the preset fluctuation range, a step is executed: normalizing each sample sound time domain signal in the sample sound time domain signal set. The first amplitude is a preset amplitude, which may be set in advance according to historical data, empirical data, and the like. If the data fluctuation range of the sample sound time domain signal set exceeds the preset fluctuation range, it indicates that the working state of the sample axle box is not stable, and at this time, the first amplitude is obtained as the amplitude threshold value, thereby reducing the influence of unstable data on the determination of the amplitude threshold value, thereby increasing the accuracy of the fault monitoring result of the axle box to be tested.

[0054] In this step, determining the proportion of normal sound time domain signals can be, for example, comparing the amplitude of each sound time domain signal in the sound data with the amplitude threshold value, and obtaining the number of normal sound time domain signals in the sound data; wherein, if the amplitude of any sound time domain signal is less than the amplitude threshold value, the sound time domain signal is determined to be a normal sound time domain signal; based on the number of normal sound time domain signals and the total amount of sound time domain signals, the proportion of normal sound time domain signals is determined. For example, the ratio of the number of normal sound time domain signals to the total amount of sound time domain signals can be calculated as the proportion of normal sound time domain signals.

[0055] It is understandable that the above is only an example of a method for determining the proportion of normal sound time domain signals in some embodiments of the present application, and does not constitute a limitation. In some other embodiments of the present application, for example, the amplitude of each sound time domain signal in the sound data can be compared with the amplitude threshold value to obtain the number of abnormal sound time domain signals in the sound data; wherein, if the amplitude of any sound time domain signal is not less than the amplitude threshold value, the sound time domain signal is determined to be an abnormal sound time domain signal; based on the number of abnormal sound time domain signals and the total amount of sound time domain signals, the proportion of normal sound time domain signals is determined. For example, the difference between the total amount of sound time domain signals and the number of abnormal sound time domain signals can be calculated, and then the ratio of the difference to the total amount of sound time domain signals is calculated as the proportion of normal sound time domain signals.

[0056] Step S104: Determine whether the axle box to be tested is in a fault state based on the normal sound time domain signal ratio and the vibration amplitude set.

[0057] In this step, it can be determined whether the proportion of normal sound time domain signals is less than the set proportion to obtain a first judgment result; and it can be determined whether each vibration amplitude in the vibration amplitude set is not less than the set vibration amplitude to obtain a second judgment result; and then based on the first judgment result and the second judgment result, it is determined whether the axle box to be tested is in a fault state.

[0058] The setting ratio may be determined according to the proportion of normal sample signals of the sample axle box in the fault state, and the step of obtaining the setting ratio may include, for example:

[0059] s1: Acquire N groups of sample fault sound data when the sample axle box is in a fault state, where N is an integer greater than 1. Specifically, each group of sample fault sound data may include, for example, a plurality of sample sound time domain signals.

[0060] s2: Obtain the proportion of N groups of normal sample signals of N groups of sample fault sound data. Each group of sample fault sound data includes multiple sample sound time domain signals, and the multiple sample sound time domain signals include some normal sound time domain signals and some abnormal sound time domain signals. The proportion of normal sample signals of each group of sample fault sound data can be determined by the ratio of the number of some normal sound time domain signals to the number of all sample sound time domain signals as in the method in the aforementioned step S103. For N groups of sample fault sound data, the proportion of N groups of normal sample signals can be obtained.

[0061] s3: Determine the set ratio according to the ratio of the N groups of normal sample signals. Specifically, the maximum value of the ratio of the N groups of normal sample signals can be used as the set ratio, or the average value of the ratio of the N groups of normal sample signals can be used as the set ratio, or the minimum value of the ratio of the N groups of normal sample signals can be used as the set ratio, or the set multiple of the maximum value, average value, minimum value, etc. of the ratio of the N groups of normal sample signals can be used as the set ratio. The specific setting can be made according to actual needs.

[0062] The set vibration amplitude may be obtained based on sample vibration data generated by a sample axle box in a non-fault state.

[0063] In some embodiments of the present application, the vibration amplitude can be set according to the amplitude mean of the sample vibration data when the sample axle box is in a non-fault state, and the sample vibration data includes a plurality of sample vibration time domain signals when the sample axle box is in a non-fault state. Specifically, in some embodiments of the present application, the average amplitude of each sample vibration time domain signal in the sample vibration data can be directly used as the vibration amplitude setting. It can be understood that the above is only an example of a specific calculation method for setting the vibration amplitude in some embodiments of the present application, and does not constitute a limitation. In some other embodiments of the present application, the product / quotient of the average amplitude of each sample vibration time domain signal in the sample vibration data and a preset weight value can also be used as the vibration amplitude setting, or the sum / difference of the average amplitude of each sample vibration time domain signal in the sample vibration data and a preset setting value can be used as the vibration amplitude setting, which can be flexibly set according to actual needs. Among them, the preset weight value can be, for example, any value in 0.9-1.2, and the preset setting value can be, for example, a preset constant value.

[0064] It can be understood that the aforementioned setting of the vibration amplitude can be determined based on the amplitude mean of the sample vibration data, which is only an example in some embodiments of the present application. In some other embodiments of the present application, the setting of the vibration amplitude can also be determined based on other data quantities such as the absolute average value of the amplitude of the sample vibration data, the amplitude waveform index, etc., and can be flexibly set according to actual needs.

[0065] It can be understood that the aforementioned set vibration amplitude can be determined based on the amplitude mean of the sample vibration data, which is only an example in some embodiments of the present application. In some other embodiments of the present application, each sample vibration time domain signal in the sample vibration data can also be normalized to obtain a sample vibration time domain normalized signal set formed by multiple sample vibration time domain normalized signals, and then the set vibration amplitude is obtained based on the average amplitude of the sample vibration time domain normalized signal set. Normalizing the sample vibration time domain signals can make the amplitudes of the obtained sample vibration time domain normalized signals be at the same order of magnitude, reducing the impact of a few special cases or sampling errors on the set vibration amplitude. In addition, normalizing the sample vibration time domain signals can also enhance the contrast of the amplitudes between different sample vibration time domain signals.

[0066] In some embodiments of the present application, obtaining a set vibration amplitude according to sample vibration data may also include: determining whether the data fluctuation range of multiple sample vibration time domain signals is within a preset fluctuation range, wherein the data fluctuation range can be characterized by data such as signal variance and standard deviation of the sample vibration time domain signals, and the preset fluctuation range is a preset acceptable data fluctuation range. If the data fluctuation range of multiple sample vibration time domain signals exceeds the preset fluctuation range, a second amplitude is obtained as the set vibration amplitude; if the data fluctuation range of multiple sample vibration time domain signals is within the preset fluctuation range, the step of normalizing each sample vibration time domain signal in the sample vibration data is executed. Among them, the second amplitude is a preset amplitude, which can be set in advance according to historical data, empirical data, etc. If the data fluctuation range of the sample vibration data exceeds the preset fluctuation range, it means that the working state of the sample axle box is not stable. At this time, the second amplitude is obtained as the set vibration amplitude, thereby reducing the influence of unstable data on the determination of the set vibration amplitude, thereby increasing the accuracy of the fault monitoring result of the axle box to be tested.

[0067] In some embodiments of the present application, determining whether the axle box to be tested is in a fault state according to the first judgment result and the second judgment result may include, for example:

[0068] If the first judgment result indicates that the proportion of normal sound time domain signals is less than the set proportion, and the second judgment result indicates that there is at least one vibration amplitude that is not less than the set vibration amplitude, it is determined that the axle box to be tested is in a fault state.

[0069] On the contrary, if the first judgment result indicates that the proportion of normal sound time domain signals is less than the set proportion, and the second judgment result indicates that each vibration amplitude is less than the set vibration amplitude, it is determined that the axle box to be tested is in a non-fault state.

[0070] If the first judgment result indicates that the proportion of normal sound time domain signals is not less than the set proportion, and the second judgment result indicates that the vibration amplitude is not less than the set vibration amplitude and the duration exceeds the preset time length, it is determined that the axle box to be tested is in a fault state.

[0071] On the contrary, if the first judgment result indicates that the proportion of normal sound time domain signals is not less than the set proportion, and the second judgment result indicates that the duration of the vibration amplitude being not less than the set vibration amplitude does not exceed the preset duration, it is determined that the axle box to be tested is in a non-fault state.

[0072] The preset duration is a threshold value of a preset duration, which can be set according to actual needs. In some embodiments of the present application, the value range of the preset duration can be, for example, 2-5 seconds. Further, the preset duration can be, for example, 3 seconds.

[0073] Compared with the prior art, in the axle box fault detection method provided in Example 1 of the present application, vibration data and sound data of the axle box to be tested are obtained, multiple vibration time domain signals in the vibration data are processed to obtain the vibration amplitude of the axle box to be tested, and multiple sound time domain signals in the sound data are processed to obtain the proportion of normal sound time domain signals in the sound data. According to the proportion of normal sound time domain signals and the vibration amplitude set, it is determined whether the axle box to be tested is in a faulty state, and the vibration data and sound data generated during the operation of the axle box to be tested are comprehensively considered, so as to improve the accuracy of detecting the fault condition of the axle box.

[0074] Embodiment 2 of the present application relates to an axle box fault detection device, such as Figure 4 As shown, including:

[0075] The signal acquisition module 201 is used to acquire vibration data and sound data of the axle box to be tested, wherein the axle box to be tested is a main roller axle box in a multi-wire cutting machine, the vibration data includes a plurality of vibration time domain signals, and the sound data includes a plurality of sound time domain signals;

[0076] The signal processing module 202 is used to perform noise reduction processing on each vibration time domain signal in the vibration data to obtain noise-reduced vibration data, and obtain the amplitudes of all noise-reduced vibration time domain signals in the noise-reduced vibration data as a vibration amplitude set; it is also used to compare the amplitudes of each sound time domain signal in the sound data with the amplitude threshold value to determine the proportion of normal sound time domain signals; wherein the amplitude threshold value is obtained based on the sample sound data generated by the sound of the axle box to be tested in a non-fault state;

[0077] The fault determination module 203 is used to determine whether the axle box to be tested is in a fault state according to the normal sound time domain signal ratio and the vibration amplitude set.

[0078] In an optional implementation, it also includes:

[0079] The amplitude threshold value acquisition module is used to collect multiple groups of sample sound data when the sample axle box is in a non-fault state; calculate the average of the amplitudes of the sound time domain signals in the multiple groups of sample sound data as the amplitude reference value; and determine the amplitude threshold value of the axle box to be tested based on the amplitude reference value.

[0080] In an optional embodiment, the signal processing module 202 is used to compare the amplitude of each sound time domain signal in the sound data with the amplitude threshold value to obtain the number of normal sound time domain signals in the sound data; wherein, if the amplitude of any of the sound time domain signals is compared to be smaller than the amplitude threshold value, the sound time domain signal is determined to be a normal sound time domain signal; based on the number of the normal sound time domain signals and the total amount of the sound time domain signals, the proportion of the normal sound time domain signals is determined.

[0081] In an optional embodiment, the signal processing module 202 is used to compare the amplitude of each sound time domain signal in the sound data with the amplitude threshold value to obtain the number of abnormal sound time domain signals in the sound data; wherein, if the amplitude of any of the sound time domain signals is not less than the amplitude threshold value, the sound time domain signal is determined to be an abnormal sound time domain signal; based on the number of the abnormal sound time domain signals and the total amount of the sound time domain signals, the proportion of the normal sound time domain signals is determined.

[0082] In an optional embodiment, the fault determination module 203 is used to determine whether the proportion of the normal sound time domain signal is less than a set proportion, and obtain a first judgment result, wherein the set proportion is determined based on the proportion of the normal sample signal of the sample axle box in a faulty state; determine whether each vibration amplitude in the vibration amplitude set is not less than a set vibration amplitude, and obtain a second judgment result, wherein the set vibration amplitude is obtained based on the sample vibration data generated by the sample axle box in a non-faulty state; and determine whether the axle box to be tested is in a faulty state based on the first judgment result and the second judgment result.

[0083] In an optional embodiment, the fault determination module 203 is used to determine that the axle box to be tested is in a fault state if the first judgment result indicates that the proportion of the normal sound time domain signal is less than a set proportion, and the second judgment result indicates that there is at least one vibration amplitude not less than the set vibration amplitude.

[0084] In an optional embodiment, the fault determination module 203 is used to determine that the axle box to be tested is in a fault state if the first judgment result indicates that the proportion of the normal sound time domain signal is not less than a set proportion, and the second judgment result indicates that the vibration amplitude is not less than the set vibration amplitude and the duration exceeds a preset time length.

[0085] In an optional implementation, it also includes:

[0086] A vibration amplitude acquisition module is set to obtain sample vibration data when the sample axle box is in a non-fault state, the sample vibration data including multiple sample vibration time domain signals; each sample vibration time domain signal in the sample vibration data is normalized to obtain a sample normalized signal set, the sample normalized signal set including multiple sample normalized signals; the set vibration amplitude is obtained according to the average amplitude of the sample normalized signal set.

[0087] In an optional implementation, it also includes:

[0088] A set ratio acquisition module is used to obtain N groups of sample fault sound data when the sample axle box is in a fault state, wherein N is an integer greater than 1; obtain the proportion of N groups of normal sample signals of the N groups of sample fault sound data; and determine the set ratio according to the proportion of the N groups of normal sample signals.

[0089] Compared with the prior art, in the axle box fault detection device provided in Example 2 of the present application, the vibration data and sound data of the axle box to be tested are acquired through the signal acquisition module 201, and the signal processing module 202 is used to process multiple vibration time domain signals in the vibration data to obtain the vibration amplitude of the axle box to be tested, and the signal processing module 202 is used to process multiple sound time domain signals in the sound data to obtain the proportion of normal sound time domain signals in the sound data, and finally the fault determination module 203 determines whether the axle box to be tested is in a faulty state according to the proportion of normal sound time domain signals and the vibration amplitude set. The fault determination module 203 comprehensively considers the vibration data and sound data generated during the operation of the axle box to be tested, so as to improve the accuracy of detecting the fault condition of the axle box.

[0090] In addition, in some other embodiments of the present application, the signal acquisition module 201 is also used to collect multiple groups of sample sound data when the sample axle box is in a non-fault state; the signal processing module 202 is also used to calculate the average of the amplitudes of the sound time domain signals in the multiple groups of sample sound data as the amplitude reference value; based on the amplitude reference value, determine the amplitude threshold value of the axle box to be tested.

[0091] The signal processing module 202 is also used to compare the amplitude of each sound time domain signal in the sound data with the amplitude threshold value to obtain the number of normal sound time domain signals in the sound data; wherein, if the amplitude of any sound time domain signal is compared to be less than the amplitude threshold value, the sound time domain signal is determined to be a normal sound time domain signal; based on the number of normal sound time domain signals and the total amount of sound time domain signals, the proportion of normal sound time domain signals is determined.

[0092] The signal processing module 202 is also used to compare the amplitude of each sound time domain signal in the sound data with the amplitude threshold value to obtain the number of abnormal sound time domain signals in the sound data; wherein, if the amplitude of any sound time domain signal is compared and is not less than the amplitude threshold value, the sound time domain signal is determined to be an abnormal sound time domain signal; based on the number of abnormal sound time domain signals and the total amount of sound time domain signals, the proportion of normal sound time domain signals is determined.

[0093] The fault determination module 203 is also used to determine whether the proportion of normal sound time domain signals is less than a set proportion, and obtain a first judgment result, wherein the set proportion is determined based on the proportion of normal sample signals of the sample axle box in a faulty state; determine whether each vibration amplitude in the vibration amplitude set is not less than a set vibration amplitude, and obtain a second judgment result, wherein the set vibration amplitude is obtained based on sample vibration data generated by the sample axle box in a non-faulty state; and determine whether the axle box to be tested is in a faulty state based on the first judgment result and the second judgment result. If the first judgment result indicates that the proportion of normal sound time domain signals is less than a set proportion, and the second judgment result indicates that each vibration amplitude is not less than the set vibration amplitude, then it is determined that the axle box to be tested is in a faulty state. If the first judgment result indicates that the proportion of normal sound time domain signals is not less than a set proportion, and the second judgment result indicates that the duration of the vibration amplitude not less than the set vibration amplitude exceeds a preset time length, then it is determined that the axle box to be tested is in a faulty state.

[0094] The signal acquisition module 201 is also used to acquire sample vibration data when the sample axle box is in a non-fault state, and the sample vibration data includes multiple sample vibration time domain signals. The signal processing module 202 is also used to normalize each sample vibration time domain signal in the sample vibration data to obtain a sample normalized signal set, and the sample normalized signal set includes multiple sample normalized signals; according to the average amplitude of the sample normalized signal set, the set vibration amplitude is acquired.

[0095] The signal acquisition module 201 is also used to obtain N groups of sample fault sound data when the sample axle box is in a fault state, where N is an integer greater than 1. The signal processing module 202 is also used to obtain the proportion of N groups of normal sample signals of the N groups of sample fault sound data; and determine the set ratio according to the proportion of the N groups of normal sample signals.

[0096] Embodiment 3 of the present application relates to an electronic device, such as Figure 5 As shown, it includes: at least one processor 301; and a memory 302 that is communicatively connected to the at least one processor 301; wherein the memory 302 stores instructions that can be executed by the at least one processor 301, and the instructions are executed by the at least one processor 301 so that the at least one processor 301 can execute the axle box fault detection method in the above-mentioned embodiments.

[0097] Among them, the memory and the processor are connected in a bus manner, and the bus may include any number of interconnected buses and bridges, and the bus connects various circuits of one or more processors and memories together. The bus can also connect various other circuits such as peripherals, voltage regulators, and power management circuits, which are well known in the art and are therefore not further described herein. The bus interface provides an interface between the bus and the transceiver. The transceiver can be one element or multiple elements, such as multiple receivers and transmitters, providing a unit for communicating with various other devices on a transmission medium. The data processed by the processor is transmitted on a wireless medium via an antenna, and further, the antenna also receives data and transmits the data to the processor.

[0098] The processor is responsible for managing the bus and general processing, and can also provide various functions, including timing, peripheral interfaces, voltage regulation, power management, and other control functions. Memory can be used to store data used by the processor when performing operations.

[0099] Embodiment 4 of the present application relates to a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, the above method embodiment is implemented.

[0100] That is, those skilled in the art can understand that all or part of the steps in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a program, and the program is stored in a storage medium, including several instructions to enable a device (which can be a single-chip microcomputer, chip, etc.) or a processor to execute all or part of the steps of each embodiment method of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0101] The above are only specific implementations of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed in the present application should be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.

Claims

1. A method for detecting axle box fault, characterized in that: include: Acquire vibration data and sound data of the axle box to be tested in the same time period, wherein the axle box to be tested is a main roller axle box in a multi-wire cutting machine, the vibration data includes multiple vibration time domain signals, and the sound data includes multiple sound time domain signals; Performing noise reduction processing on each vibration time domain signal in the vibration data to obtain noise-reduced vibration data, and acquiring amplitudes of all noise-reduced vibration time domain signals in the noise-reduced vibration data as a vibration amplitude set; Comparing the amplitude of each sound time domain signal in the sound data with the amplitude threshold value to determine the proportion of normal sound time domain signals; wherein the amplitude threshold value is obtained based on the sample sound data generated by the sample axle box in a non-fault state; Whether the axle box to be tested is in a fault state is determined based on the normal sound time domain signal ratio and the vibration amplitude set.

2. The axle box fault detection method according to claim 1, characterized in that: The step of obtaining the amplitude threshold value comprises: Collecting multiple groups of sample sound data of the sample axle box in a non-fault state; Calculating the average of the amplitudes of the sound time domain signals in the plurality of groups of sample sound data as an amplitude reference value; Based on the amplitude reference value, an amplitude threshold value of the axle box to be tested is determined.

3. The axle box fault detection method according to claim 1, characterized in that: The comparing the amplitude of each sound time domain signal in the sound data with the amplitude threshold value to determine the proportion of normal sound time domain signals includes: Comparing the amplitude of each sound time domain signal in the sound data with the amplitude threshold value to obtain the number of normal sound time domain signals in the sound data; wherein, if the amplitude of any of the sound time domain signals is less than the amplitude threshold value, the sound time domain signal is determined to be a normal sound time domain signal; Based on the number of the normal sound time domain signals and the total amount of the sound time domain signals, the proportion of the normal sound time domain signals is determined.

4. The axle box fault detection method according to claim 1, characterized in that: The comparing the amplitude of each sound time domain signal in the sound data with the amplitude threshold value to determine the proportion of normal sound time domain signals includes: Comparing the amplitude of each sound time domain signal in the sound data with the amplitude threshold value, and obtaining the number of abnormal sound time domain signals in the sound data; wherein, if the amplitude of any of the sound time domain signals is not less than the amplitude threshold value, the sound time domain signal is determined to be an abnormal sound time domain signal; Based on the number of the abnormal sound time-domain signals and the total amount of the sound time-domain signals, the proportion of the normal sound time-domain signals is determined.

5. The axle box fault detection method according to claim 1, characterized in that: The determining whether the axle box to be tested is in a fault state according to the normal sound time domain signal proportion and the vibration amplitude set includes: Determine whether the normal sound time domain signal ratio is less than a set ratio, and obtain a first determination result, wherein the set ratio is determined according to the normal sample signal ratio of the sample axle box in the fault state; Determine whether each vibration amplitude in the vibration amplitude set is not less than a set vibration amplitude to obtain a second determination result, wherein the set vibration amplitude is obtained based on sample vibration data generated by a sample axle box in a non-fault state; According to the first judgment result and the second judgment result, it is determined whether the axle box to be tested is in a fault state.

6. The axle box fault detection method according to claim 5, characterized in that: The step of determining whether the axle box to be tested is in a fault state according to the first judgment result and the second judgment result includes: If the first judgment result indicates that the proportion of the normal sound time domain signal is less than the set proportion, and the second judgment result indicates that there is at least one vibration amplitude not less than the set vibration amplitude, it is determined that the axle box to be tested is in a fault state.

7. The axle box fault detection method according to claim 5, characterized in that: The step of determining whether the axle box to be tested is in a fault state according to the first judgment result and the second judgment result includes: If the first judgment result indicates that the proportion of the normal sound time domain signal is not less than the set proportion, and the second judgment result indicates that the vibration amplitude is not less than the set vibration amplitude and the duration exceeds the preset time length, it is determined that the axle box to be tested is in a fault state.

8. The axle box fault detection method according to any one of claims 5 to 7, characterized in that: The steps for obtaining the set vibration amplitude are as follows: Acquire sample vibration data of the sample axle box in a non-fault state, wherein the sample vibration data includes a plurality of sample vibration time domain signals; Normalizing each sample vibration time domain signal in the sample vibration data to obtain a sample normalized signal set, wherein the sample normalized signal set includes a plurality of sample normalized signals; The set vibration amplitude is obtained according to the average amplitude of the sample normalized signal set.

9. The axle box fault detection method according to any one of claims 5 to 7, characterized in that: Steps for obtaining the set ratio: Acquire N groups of sample fault sound data when the sample axle box is in a fault state, wherein N is an integer greater than 1; Obtaining the proportion of N groups of normal sample signals of the N groups of sample fault sound data; The set ratio is determined according to the proportion of the N groups of normal sample signals.

10. An axle box fault detection device, characterized in that: include: A signal acquisition module, used to acquire vibration data and sound data of the axle box to be tested, wherein the axle box to be tested is a main roller axle box in a multi-wire cutting machine, the vibration data includes a plurality of vibration time domain signals, and the sound data includes a plurality of sound time domain signals; The signal processing module is used to perform noise reduction processing on each vibration time domain signal in the vibration data to obtain noise-reduced vibration data, and obtain the amplitudes of all noise-reduced vibration time domain signals in the noise-reduced vibration data as a vibration amplitude set; it is also used to compare the amplitudes of each sound time domain signal in the sound data with the amplitude threshold value to determine the proportion of normal sound time domain signals; wherein the amplitude threshold value is obtained based on sample sound data generated by the sound of the axle box to be tested in a non-fault state; A fault determination module is used to determine whether the axle box to be tested is in a fault state according to the normal sound time domain signal ratio and the vibration amplitude set.

11. An electronic device, characterized in that: include: at least one processor; and, a memory communicatively coupled to the at least one processor; The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the axle box fault detection method as described in any one of claims 1 to 9.

12. A computer-readable storage medium storing a computer program, characterized in that: The computer program is executed by a processor to implement the axle box fault detection method according to any one of claims 1 to 9.

Images