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

Abstract

The application relates to 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: obtaining vibration data and sound data generated by vibration of an axle box to be detected in a same time period; performing noise reduction processing on the vibration data and the sound data respectively to obtain noise-reduced vibration data and noise-reduced sound data; obtaining an amplitude of each noise-reduced vibration time domain signal and a vibration amplitude ratio of a set vibration amplitude to obtain a vibration ratio set; obtaining an amplitude of each noise-reduced sound time domain signal and a sound ratio of a set sound amplitude to obtain a sound ratio set; and determining whether the axle box to be detected is in a fault state according to the vibration ratio set and the sound ratio set. Compared with the prior art, the axle box fault detection method, device, electronic equipment and computer readable storage medium provided by the application have the advantage of improving the accuracy of fault detection of the axle box.

Description

Technical Field

[0001] This application relates to the field of industrial production, and more specifically, to a method, apparatus, electronic device, and computer-readable storage medium for detecting axle box faults. Background Technology

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

[0003] During the rotation of the main roller driven by the motor, the bearings in the axle box may fail due to reasons such as excessive temperature or excessive load. The existing technology usually relies on the operator's work experience to make a judgment. For example, if there is abnormal noise or excessive temperature in the axle box, it will be assumed that the bearings in the axle box have failed, and the axle box will be repaired or replaced. This results in a problem of low accuracy in judging whether the axle box has failed. Summary of the Invention

[0004] The purpose of this application is to provide a method, apparatus, electronic device and computer-readable storage medium for axle box fault detection, which can improve the accuracy of axle box fault detection.

[0005] In a first aspect, this application provides a method for detecting axle box faults, comprising: acquiring vibration data and sound data generated by the vibration of a test axle box within the same time period, wherein the test axle box 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 the vibration data and the sound data respectively to obtain noise-reduced vibration data and noise-reduced sound data; acquiring the amplitude of each noise-reduced vibration time-domain signal in the noise-reduced vibration data and the vibration ratio of a set vibration amplitude to obtain a vibration ratio set, wherein the set vibration amplitude is obtained based on the vibration time-domain signal generated by the vibration of a sample axle box in a non-fault state; acquiring the amplitude of each noise-reduced sound time-domain signal in the noise-reduced sound data and the sound ratio of a set sound amplitude to obtain a sound ratio set, wherein the set sound amplitude is obtained based on the sound time-domain signal generated by the sound of a sample axle box in a non-fault state; and determining whether the test axle box is in a fault state based on the vibration ratio set and the sound ratio set.

[0006] Compared with existing technologies, the axle box fault detection method provided in this application acquires and analyzes vibration and sound data generated by the axle box under test during operation. It obtains the amplitude of each noise-reduced vibration time-domain signal in the noise-reduced vibration data and the vibration ratio of a set vibration amplitude, thus obtaining a vibration ratio set. Similarly, it obtains the amplitude of each noise-reduced sound time-domain signal in the noise-reduced sound data and the sound ratio of a set sound amplitude, thus obtaining a sound ratio set. Finally, based on the vibration ratio set and the sound ratio set, it determines whether the axle box under test is in a fault state. By comprehensively considering both the vibration and sound data generated by the axle box under test during operation to determine whether it is in a fault state, the accuracy of fault detection results can be effectively improved. Furthermore, noise reduction processing is applied to the vibration data and the sound data separately, which reduces the impact of noise data on the detection results, further improving the accuracy of fault detection results.

[0007] In an optional implementation, determining whether the axle box under test is in a fault state based on the vibration ratio set and the sound ratio set includes: if at least one vibration ratio in the vibration ratio set has an amplitude greater than the set vibration amplitude, and at least one sound ratio in the sound ratio set has an amplitude greater than the set sound amplitude, then the axle box under test is determined to be in the fault state.

[0008] In an optional implementation, determining whether the axle box under test is in a fault state based on the vibration ratio set and the sound ratio set includes: if no vibration ratio in the vibration ratio set represents an amplitude greater than a set vibration amplitude, then obtaining the percentage of sound ratios in the sound ratio set whose amplitudes are greater than the set sound amplitude; if the percentage of sound ratios is greater than a preset first threshold, then determining that the axle box under test is in the fault state. If no vibration ratio in the vibration ratio set represents an amplitude greater than the set vibration amplitude, it indicates that the vibration characteristics of the axle box under test are not abnormal. In this case, a secondary analysis is performed based on the percentage of sound ratios in the sound ratio set whose amplitudes are greater than the set sound amplitude, thereby better detecting the fault condition of the axle box under test.

[0009] In an optional implementation, determining whether the axle box under test is in a fault state based on the vibration ratio set and the sound ratio set includes: if no sound ratio in the sound ratio set represents an amplitude greater than a set sound amplitude, then obtaining the percentage of vibration ratios in the vibration ratio set whose amplitudes are greater than the set vibration amplitude; if the percentage of vibration ratios is greater than a preset second threshold, then determining that the axle box under test is in the fault state. If no sound ratio in the sound ratio set represents an amplitude greater than the set sound amplitude, it indicates that the sound characteristics of the axle box under test are not abnormal. In this case, a secondary analysis is performed based on the percentage of vibration ratios in the vibration ratio set whose amplitudes are greater than the set vibration amplitude, thereby better detecting the fault condition of the axle box under test.

[0010] In an optional implementation, the values ​​of the first set threshold and the second set threshold range from 50% to 60%.

[0011] In an optional implementation, the step of obtaining the set vibration amplitude includes: obtaining a set of vibration time-domain signals of the sample axle box in a non-faulty state; normalizing the set of vibration time-domain signals of the sample axle box to obtain a normalized vibration time-domain signal set of the sample axle box; and obtaining the set vibration amplitude based on the average amplitude of the normalized vibration time-domain signal set of the sample axle box.

[0012] In an optional implementation, the step of obtaining the set sound amplitude includes: obtaining a set of sound time-domain signals of the sample axle box in a non-faulty state; normalizing the set of sound time-domain signals of the sample axle box to obtain a normalized sound time-domain signal set of the sample axle box; and obtaining the set sound amplitude based on the average amplitude of the normalized sound time-domain signal set of the sample axle box.

[0013] In an optional implementation, acquiring vibration data and sound data generated by the vibration of the axle box under test within the same time period includes: determining a sampling frequency based on the acquired vibration frequency of the axle box under test, wherein the sampling frequency is not less than twice the vibration frequency; and acquiring the vibration data and sound data within the same time period based on the sampling frequency. Determining the sampling frequency based on the vibration frequency of the axle box under test can reduce the probability of high-frequency signals being sampled as low-frequency signals, thereby increasing the reliability of the acquired vibration data and sound data.

[0014] Secondly, this application provides a shaft box fault detection device, comprising: a signal acquisition module, used to acquire vibration data and sound data generated by the vibration of a shaft box under test within the same time period, wherein the shaft box to be identified is the main roller shaft box of a multi-wire cutting machine, the vibration data includes multiple vibration time-domain signals, and the sound data includes multiple sound time-domain signals; a noise reduction module, used to perform noise reduction processing on the vibration data and the sound data respectively to obtain noise-reduced vibration data and noise-reduced sound data; and a signal processing module, used to acquire each of the noise-reduced vibration time-domain signals in the noise-reduced vibration data. The system includes a set of vibration ratios between the amplitude of a signal and a set of vibration amplitudes, wherein the set vibration amplitude is obtained based on the vibration time-domain signal generated by the vibration of a sample axle box in a non-fault state; it is also used to acquire a set of sound ratios between the amplitude of each noise reduction sound time-domain signal and a set of sound amplitudes in the noise reduction sound data, wherein the set sound amplitude is obtained based on the sound time-domain signal generated by the sound of a sample axle box in a non-fault state; and a fault determination module, which is used to determine whether the axle box under test is in a fault state based on the vibration ratio set and the sound ratio set.

[0015] Thirdly, this application provides an electronic device, including: 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, the instructions being executed by the at least one processor to enable the at least one processor to perform the axle box fault detection method as described in any of the foregoing embodiments.

[0016] Fourthly, this application provides a computer-readable storage medium storing a computer program, which is executed by a processor to implement the axle box fault detection method described in any of the foregoing embodiments. Attached Figure Description

[0017] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 This is a schematic flowchart of the axle box fault monitoring method provided in Embodiment 1 of this application;

[0019] Figure 2 This is a schematic diagram of the axle box fault monitoring device provided in Embodiment 2 of this application;

[0020] Figure 3This is a schematic diagram of the structure of the electronic device provided in Embodiment 3 of this application. Detailed Implementation

[0021] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. The components of the embodiments of this application described and shown in the accompanying drawings can generally be arranged and designed in various different configurations.

[0022] Therefore, the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely to illustrate selected embodiments of the application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0023] It should be noted that similar labels and letters in the following figures indicate similar items. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures.

[0024] In the description of this application, it should be noted that if the terms "upper", "lower", "inner", "outer", etc. appear to indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings, or the orientation or positional relationship that the product of this application is usually placed in, it is only for the convenience of describing this application and simplifying the description, and does not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of this application.

[0025] Furthermore, the terms "first" and "second" are used only to distinguish descriptions and should not be interpreted as indicating or implying relative importance.

[0026] It should be noted that, where there is no conflict, the features in the embodiments of this application can be combined with each other.

[0027] Embodiment 1 of this application provides a method for detecting axle box faults, 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:

[0028] Step S101: Obtain vibration data and sound data generated by the vibration of the shaft box under test within the same time period.

[0029] In this step, the shaft box to be tested is the main roller shaft box of a multi-wire cutting machine. During the operation of the multi-wire cutting machine, the shaft box to be tested will vibrate. By acquiring the vibration signal of the shaft box during its operation, the vibration signal can be obtained. The vibration signal can include frequency domain signals and time domain signals. The frequency domain signal is the relationship between vibration amplitude and vibration frequency, and the time domain signal is the relationship between vibration amplitude and time. In this application, the vibration time domain signal generated by the shaft box during its operation is obtained as the vibration data.

[0030] In addition, the vibration generated by the axle box under test during operation will produce sound. In this application, the sound time domain signal of the sound emitted by the axle box under test during operation is also obtained as sound data.

[0031] Specifically, in some embodiments of this application, vibration signals and sound signals of the shaft box to be tested are continuously collected within a time period, thereby obtaining N vibration time-domain signals and M sound time-domain signals within this time period. The acquired N vibration time-domain signals are used as vibration data, and the M sound time-domain signals are used as sound data. Here, N and M are natural numbers greater than 1, and in different embodiments of this application, the values ​​of N and M can be equal or unequal, specifically set according to the sampling frequencies corresponding to the vibration time-domain signals and sound time-domain signals.

[0032] When acquiring vibration and sound data within the same time period, different time periods can be set according to different actual conditions. For example, the duration of the vibration time-domain signal can be set according to the working accuracy of the axle box under test. For axle boxes with high working accuracy, which are more sensitive to axle box failures, a shorter time period can be set, such as 3 seconds to 5 minutes, to acquire shorter vibration and sound time-domain signals as vibration and sound data. Conversely, for axle boxes with lower working accuracy, a longer time period can be set, such as 4 minutes to 20 minutes, to acquire longer vibration and sound time-domain signals as vibration and sound data. In short, the duration of the time period can be flexibly set according to the actual situation.

[0033] In different embodiments of this application, the method for acquiring vibration time-domain signals and sound time-domain signals can be to install a vibration detection device in the axle box fault detection device. For the acquisition of vibration time-domain signals, the vibration detection device can be installed on the axle box to be tested, and vibration detection can be performed directly on the axle box to obtain the vibration time-domain signal generated by the vibration of the axle box. In some embodiments of the application, the vibration detection device can be, for example, a vibration acceleration sensor, a vibration infrared sensor, etc., and can be specifically configured according to actual needs. For the acquisition of sound time-domain signals, a sound detection device can be installed in the axle box fault detection device, either on or inside the axle box to be tested, and sound detection can be performed directly on the axle box to obtain the sound detection signal generated by the sound of the axle box. In some embodiments of the application, the sound detection device can be, for example, a sound sensor, a microphone, etc., and can be specifically configured according to actual needs.

[0034] It is understood that the aforementioned installation of vibration detection equipment and sound detection equipment in the axle box fault detection device, through which the vibration and sound detection equipment of the axle box under test are used to detect vibration and sound, thereby obtaining the vibration time-domain signal and sound time-domain signal generated by the vibration of the axle box under test, is only an example in some embodiments of this application and does not constitute a limitation. In some other embodiments of this application, other devices may be used to detect the vibration and sound of the axle box under test during operation and upload the detected vibration time-domain signal and sound time-domain signal to the server. A communication device is installed in the axle box fault detection device, which can download the vibration time-domain signal and sound time-domain signal uploaded by other devices from the server.

[0035] Furthermore, in this step, when acquiring the vibration time-domain signal, the sampling frequency can be determined based on the vibration frequency of the shaft box under test. Specifically, firstly, the vibration signal of the shaft box under test can be initially sampled at any sampling frequency to obtain the vibration frequency-domain signal of the shaft box under test. The vibration frequency of the shaft box under test is then obtained based on the vibration frequency-domain signal. The vibration frequency can be, for example, the maximum, minimum, or average value of the frequency in the vibration frequency-domain signal. Then, the sampling frequency is determined based on the vibration frequency. Specifically, in some specific embodiments of this application, the sampling frequency can be set to be greater than or equal to twice the vibration frequency. Similarly, in some embodiments of this application, this sampling frequency can also be used to acquire sound time-domain signals to form sound data. Determining the sampling frequency based on the vibration frequency of the shaft box under test can reduce the probability of high-frequency signals being sampled as low-frequency signals, increasing the reliability of the acquired vibration and sound data.

[0036] Step S102: Perform noise reduction processing on the vibration data and sound data respectively to obtain noise-reduced vibration data and noise-reduced sound data.

[0037] In this step, for vibration data, a preset denoising algorithm can be used to denoise each vibration time-domain signal in the vibration data to obtain the denoised sound time-domain signal corresponding to each vibration time-domain signal. Each denoised sound time-domain signal constitutes the denoised sound data.

[0038] For audio data, a preset noise reduction algorithm can be used to perform noise reduction processing on each audio time-domain signal in the audio data to obtain the noise-reduced audio time-domain signal corresponding to each audio time-domain signal. Each noise-reduced audio time-domain signal constitutes noise-reduced audio data.

[0039] In different embodiments of this application, the preset denoising algorithm can be a singular value decomposition algorithm, a wavelet threshold denoising algorithm, or other different denoising algorithms, which can be set according to actual needs.

[0040] In the embodiments of this application, the noise reduction algorithm used to reduce sound data and the noise reduction algorithm used to reduce vibration data can be the same or different, and can be selected according to actual needs.

[0041] Step S103: Obtain the amplitude of each noise-reduced vibration time-domain signal in the noise-reduced vibration data and the vibration ratio of the set vibration amplitude to obtain a vibration ratio set.

[0042] In some embodiments of this application, the various denoised vibration time-domain signals in the denoised vibration data can be normalized to obtain multiple normalized vibration time-domain signals. Then, the amplitude of each normalized vibration time-domain signal is obtained as the amplitude of its corresponding denoised vibration time-domain signal. Normalizing the denoised vibration time-domain signals ensures that the amplitudes of the obtained normalized vibration time-domain signals are on the same order of magnitude, reducing the impact of a few special cases or sampling errors on the set vibration amplitude. Furthermore, normalizing the denoised vibration time-domain signals can improve the contrast between the amplitudes of different denoised vibration time-domain signals.

[0043] In this step, the vibration amplitude can be set based on the sample vibration time-domain signal set generated by the sample axle box in a non-faulty state. The sample axle box can be the same model as the axle box under test. In some embodiments of the present invention, the sample axle box can also be the axle box under test itself; that is, the sample vibration time-domain signal is the vibration signal generated by the axle box under test when it is in a non-faulty state. Using the vibration signal generated by the axle box under test itself when it is in a non-faulty state as the sample vibration time-domain signal can make the set vibration amplitude more relevant, and the accuracy of the final confirmation result of the fault degree of the axle box under test is also higher.

[0044] In different embodiments of the present invention, the set vibration amplitude can be obtained in advance based on the sample vibration time-domain signal set. In this step, the axle box fault monitoring device only needs to read the pre-obtained set vibration amplitude. In some other embodiments of the present invention, in this step, the axle box fault monitoring device can also directly read the sample vibration time-domain signal set and then obtain the set vibration amplitude based on the sample vibration time-domain signal set.

[0045] In some embodiments of the present invention, the vibration amplitude can be determined based on the average amplitude of the sample vibration time-domain signal set of the sample shaft box in a non-faulty state. The sample vibration time-domain signal set includes the sample vibration time-domain signals of the sample shaft box in a non-faulty state. Specifically, in some embodiments of the present invention, the average amplitude of each sample vibration time-domain signal in the sample vibration time-domain signal set can be directly used as the set vibration amplitude. It is understood that the foregoing is only an example of the specific calculation method for setting the vibration amplitude in some embodiments of the present invention and does not constitute a limitation. In some other embodiments of the present invention, the product / quotient of the average amplitude of each sample vibration time-domain signal in the sample vibration time-domain signal set and a preset weight value can also be used as the set vibration amplitude. Alternatively, the sum / difference of the average amplitude of each sample vibration time-domain signal in the sample vibration time-domain signal set and a preset setting value can be used as the set vibration amplitude. The specific settings can be flexibly configured according to actual needs. The preset weight value can be any value between 0.9 and 1.2, and the preset setting value can be a preset constant value.

[0046] In the embodiments described in this specification, there may be one or more sample shaft boxes, such as 1, 2, 5, and 10, etc. This specification does not impose any specific limitations.

[0047] It is understood that the aforementioned setting of vibration amplitude based on the average amplitude of the sample vibration time-domain signal set is only an example in some embodiments of the present invention. In some other embodiments of the present invention, the setting vibration amplitude may also be determined based on other data such as the absolute average amplitude of the sample vibration time-domain signal set and amplitude waveform indicators. The specific setting can be flexibly made according to actual needs.

[0048] It is understood that the aforementioned setting of the vibration amplitude based on the average amplitude of the sample vibration time-domain signal set is merely an illustrative example in some embodiments of the present invention. In other embodiments of the present invention, the vibration time-domain signals of each sample vibration in the sample vibration time-domain signal set may be normalized to obtain a sample vibration time-domain normalized signal set composed of multiple sample vibration time-domain normalized signals. Then, the set vibration amplitude may be obtained based on the average amplitude of the sample vibration time-domain normalized signal set. Normalizing the sample vibration time-domain signals can ensure that the amplitudes of the obtained sample vibration time-domain normalized signals are on the same order of magnitude, reducing the impact of a few special cases or sampling errors on the set vibration amplitude. Furthermore, normalizing the sample vibration time-domain signals can also improve the contrast of amplitudes between different sample vibration time-domain signals.

[0049] In some embodiments of the present invention, obtaining the set vibration amplitude based on the sample vibration time-domain signal set may further 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 the signal variance and standard deviation of the sample vibration time-domain signals, and the preset fluctuation range is a pre-set acceptable data fluctuation range. If the data fluctuation range of multiple sample vibration time-domain signals exceeds the preset fluctuation range, a first 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 time-domain signal set is executed. The first amplitude is a pre-set amplitude, which can be pre-set based on historical data, empirical data, etc. If the data fluctuation range of the sample vibration time-domain signal set exceeds the preset fluctuation range, it indicates that the working state of the sample axle box is unstable. Obtaining the first amplitude as the set vibration amplitude reduces the impact of unstable data on the determination of the set vibration amplitude, thereby increasing the accuracy of the fault monitoring results of the axle box under test.

[0050] Step S104: Obtain the amplitude of each noise reduction time-domain signal in the noise reduction sound data and the sound ratio of the set sound amplitude to obtain the sound ratio set.

[0051] In some embodiments of this application, the time-domain signals of each noise-reduced audio signal in the noise-reduced audio data can be normalized to obtain multiple normalized time-domain signals. Then, the amplitude of each normalized time-domain signal is obtained as the amplitude of its corresponding noise-reduced audio time-domain signal. Normalizing the noise-reduced audio time-domain signals ensures that the amplitudes of the obtained normalized time-domain signals are on the same order of magnitude, reducing the impact of a few special cases or sampling errors on the set audio amplitude. Furthermore, normalizing the noise-reduced audio time-domain signals can improve the contrast between the amplitudes of different noise-reduced audio time-domain signals.

[0052] In this step, the set sound amplitude can be obtained from the set of sample sound time-domain signals generated by a sample axle box in a non-faulty state. The sample axle box can be the same model as the axle box under test. In some embodiments of the present invention, the sample axle box can also be the axle box under test itself; that is, the sample sound time-domain signal is the sound signal generated by the axle box under test when it is in a non-faulty state. Using the sound signal generated by the axle box under test itself when it is in a non-faulty state as the sample sound time-domain signal can make the set sound amplitude more correlated, and the accuracy of the final confirmation result of the fault degree of the axle box under test is also higher.

[0053] In different embodiments of the present invention, the set sound amplitude can be obtained in advance based on a sample sound time-domain signal set. In this step, the axle box fault monitoring device only needs to read the pre-obtained set sound amplitude. In some other embodiments of the present invention, in this step, the axle box fault monitoring device can also directly read the sample sound time-domain signal set and then obtain the set sound amplitude based on the sample sound time-domain signal set.

[0054] In some embodiments of the present invention, the set sound amplitude can be determined based on the average amplitude of the sample sound time-domain signal set of the sample shaft box in a non-faulty state. The sample sound time-domain signal set includes multiple sample sound time-domain signals of the sample shaft box in a non-faulty state. Specifically, in some embodiments of the present invention, the average amplitude of each sample sound time-domain signal in the sample sound time-domain signal set can be directly used as the set sound amplitude. It is understood that the foregoing is only an example of the specific calculation method for setting the sound amplitude in some embodiments of the present invention and does not constitute a limitation. In some other embodiments of the present invention, the product / quotient of the average amplitude of each sample sound time-domain signal in the sample sound time-domain signal set and a preset weight value can also be used as the set sound amplitude. Alternatively, the sum / difference of the average amplitude of each sample sound time-domain signal in the sample sound time-domain signal set and a preset setting value can be used as the set sound amplitude. The specific settings can be flexibly configured according to actual needs. The preset weight value can be any value between 0.9 and 1.2, and the preset setting value can be a preset constant value.

[0055] It is understood that the aforementioned setting of the sound amplitude based on the average amplitude of the sample sound time-domain signal set is only an example in some embodiments of the present invention. In some other embodiments of the present invention, the setting of the sound amplitude may also be determined based on other data such as the absolute average amplitude and amplitude waveform index of the sample sound time-domain signal set. The specific setting can be flexibly made according to actual needs.

[0056] It is understood that the aforementioned setting of the sound amplitude based on the average amplitude of the sample sound time-domain signal set is merely an illustrative example in some embodiments of the present invention. In other embodiments of the present invention, the sample sound time-domain signals in the sample sound time-domain signal set may be normalized to obtain a sample sound time-domain normalized signal set, and then the set sound amplitude may be obtained based on the average amplitude of the sample sound time-domain normalized signal set. Normalizing the sample sound time-domain signals can ensure that the amplitudes of the obtained sample sound time-domain normalized signals are on 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 sample sound time-domain signals can also improve the contrast of amplitudes between different sample sound time-domain signals.

[0057] In some embodiments of the present invention, obtaining the set sound amplitude based on the sample sound time-domain signal set may further include: determining whether the data fluctuation range of multiple sample sound time-domain signals is within a preset fluctuation range, wherein the data fluctuation range can be characterized by data such as the signal variance and standard deviation of the sample sound time-domain signals, and the preset fluctuation range is a pre-set acceptable data fluctuation range. If the data fluctuation range of multiple sample sound time-domain signals exceeds the preset fluctuation range, a second amplitude is obtained as the set sound amplitude; if the data fluctuation range of multiple sample sound time-domain signals is within the preset fluctuation range, the step of normalizing each sample sound time-domain signal in the sample sound time-domain signal set is performed. The second amplitude is a pre-set amplitude, which can be pre-set based on historical data, empirical data, etc. 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 unstable. Obtaining the second amplitude as the set sound amplitude reduces the impact of unstable data on the determination of the set sound amplitude, thereby increasing the accuracy of the fault monitoring results of the axle box under test.

[0058] Step S105: Determine whether the shaft box under test is in a fault state based on the vibration ratio set and the sound ratio set.

[0059] In this step, the vibration ratio set can be detected to determine whether there is at least one vibration ratio whose amplitude is greater than a set vibration amplitude, and whether there is no vibration ratio whose amplitude is greater than a set vibration amplitude. Similarly, the sound ratio set can be detected to determine whether there is at least one sound ratio whose amplitude is greater than a set sound amplitude, and whether there is no sound ratio whose amplitude is greater than a set sound amplitude.

[0060] If at least one vibration ratio amplitude is found to be greater than the set vibration amplitude in the vibration ratio set, and at least one sound ratio amplitude is found to be greater than the set sound amplitude in the sound ratio set, then the test axle box can be determined to be in a faulty state.

[0061] If it is found that there is no vibration ratio in the set of vibration ratios with an amplitude greater than the set vibration amplitude, and there is no sound ratio in the set of sound ratios with an amplitude greater than the set sound amplitude, then it can be determined that the axle box under test is in a non-faulty state, that is, the fuel tank under test is in a normal working state.

[0062] If no vibration ratio in the vibration ratio set is found to have an amplitude greater than the set vibration amplitude, but at least one sound ratio in the sound ratio set has an amplitude greater than the set sound amplitude, then the percentage of sound ratios in the sound ratio set with amplitudes greater than the set sound amplitude is obtained. If this percentage is greater than a preset first threshold, then the axle box under test is determined to be in a faulty state.

[0063] If at least one vibration ratio in the vibration ratio set is found to have an amplitude greater than a set vibration amplitude, while no sound ratio in the sound ratio set has an amplitude greater than a set sound amplitude, then the percentage of vibration ratios in the vibration ratio set with amplitudes greater than the set vibration amplitude is obtained. If this percentage is greater than a preset second threshold, then the axle box under test is determined to be in a faulty state.

[0064] In some embodiments of this application, the amplitude of the noise-reduced vibration time-domain signal corresponding to each vibration ratio can be determined based on the relationship between each vibration ratio in the vibration ratio set and a set constant value (e.g., a constant 1). When the vibration ratio is greater than the set constant value, it indicates that the amplitude of the noise-reduced vibration time-domain signal corresponding to the vibration ratio is greater than the set vibration amplitude. When the vibration ratio is less than the set constant value, it indicates that the amplitude of the noise-reduced vibration time-domain signal corresponding to the vibration ratio is less than the set vibration amplitude. When the vibration ratio is equal to the set constant value, it indicates that the amplitude of the noise-reduced vibration time-domain signal corresponding to the vibration ratio is equal to the set vibration amplitude.

[0065] In some embodiments of this application, the amplitude of the noise-reduced audio time-domain signal corresponding to each sound ratio can be determined based on the relationship between each sound ratio in the sound ratio set and a set constant value (e.g., a constant 1). When the sound ratio is greater than the set constant value, it indicates that the amplitude of the noise-reduced audio time-domain signal corresponding to the sound ratio is greater than the set sound amplitude. When the sound ratio is less than the set constant value, it indicates that the amplitude of the noise-reduced audio time-domain signal corresponding to the sound ratio is less than the set sound amplitude. When the sound ratio is equal to the set constant value, it indicates that the amplitude of the noise-reduced audio time-domain signal corresponding to the sound ratio is equal to the set sound amplitude.

[0066] Specifically, the percentage of sound ratios in the sound ratio set whose amplitude is greater than a set sound amplitude can be: the ratio of the number of sound ratios in the sound ratio set that are greater than a set constant value to the total number of sound ratios.

[0067] Specifically, the percentage of vibration ratios in the vibration ratio set whose amplitude is greater than the set vibration amplitude can be: the ratio of the number of vibration ratios in the vibration ratio set that are greater than the set constant value to the total number of vibration ratios.

[0068] The first and second set thresholds range from 50% to 60%. In different embodiments of this application, the first and second set thresholds may be equal or unequal. When the first and second set thresholds are equal, there is only one set threshold.

[0069] Compared with the prior art, the axle box fault detection method provided in Embodiment 1 of this application acquires and analyzes the vibration data and sound data generated by the vibration of the axle box under test during operation. It obtains the amplitude of each denoised vibration time-domain signal in the denoised vibration data and the vibration ratio of a set vibration amplitude to obtain a vibration ratio set. Similarly, it obtains the amplitude of each denoised sound time-domain signal in the denoised sound data and the sound ratio of a set sound amplitude to obtain a sound ratio set. Finally, based on the vibration ratio set and the sound ratio set, it determines whether the axle box under test is in a fault state. By comprehensively considering the vibration data and sound data generated by the axle box under test during operation to determine whether it is in a fault state, the accuracy of the fault detection results can be effectively improved. Furthermore, denoising the vibration data and sound data separately can reduce the impact of noise data on the detection results, further improving the accuracy of the fault detection results.

[0070] Embodiment 2 of the present invention relates to a bearing box fault detection device, such as... Figure 2 As shown, it includes:

[0071] The signal acquisition module 201 is used to acquire vibration data and sound data generated by the vibration of the shaft box to be tested within the same time period. The shaft box to be identified is the main roller shaft box in the multi-wire cutting machine. The vibration data includes multiple vibration time-domain signals, and the sound data includes multiple sound time-domain signals.

[0072] The noise reduction module 202 is used to perform noise reduction processing on vibration data and sound data respectively to obtain noise-reduced vibration data and noise-reduced sound data;

[0073] The signal processing module 203 is used to acquire the amplitude of each noise-reduced vibration time-domain signal in the noise-reduced vibration data and a set of vibration ratios for a set vibration amplitude, wherein the set vibration amplitude is obtained based on the vibration time-domain signal generated by the vibration of the sample axle box under non-fault conditions; it is also used to acquire the amplitude of each noise-reduced sound time-domain signal in the noise-reduced sound data and a set of sound ratios for a set sound amplitude, wherein the set sound amplitude is obtained based on the sound time-domain signal generated by the sound of the sample axle box under non-fault conditions;

[0074] The fault determination module 204 is used to determine whether the shaft box under test is in a fault state based on the vibration ratio set and the sound ratio set.

[0075] In one optional implementation, the fault determination module 204 is used to determine that the shaft box under test is in the fault state if there is at least one vibration ratio characterization amplitude greater than the set vibration amplitude in the vibration ratio set and at least one sound ratio characterization amplitude greater than the set sound amplitude in the sound ratio set.

[0076] In one optional implementation, the fault determination module 204 is used to obtain the percentage of sound ratios in the sound ratio set whose amplitude is greater than the set vibration amplitude if there is no vibration ratio in the vibration ratio set whose amplitude is greater than the set vibration amplitude; and if the percentage of sound ratios is greater than a preset first set threshold, then determine that the shaft box under test is in the fault state.

[0077] In one optional implementation, the fault determination module 204 is used to obtain the percentage of vibration ratios in the vibration ratio set whose amplitude is greater than the set vibration amplitude if there is no sound ratio in the sound ratio set whose amplitude is greater than the set vibration amplitude. If the percentage of vibration ratios is greater than a preset second set threshold, the module determines that the shaft box under test is in the fault state.

[0078] In one optional implementation, the values ​​of the first set threshold and the second set threshold range from 50% to 60%.

[0079] In one alternative implementation, it further includes:

[0080] A vibration amplitude acquisition module is set to acquire the vibration time-domain signal set of the sample axle box in a non-fault state; the vibration time-domain signal set of the sample axle box is normalized to obtain the vibration time-domain normalized signal set of the sample axle box; and the set vibration amplitude is acquired based on the average amplitude of the vibration time-domain normalized signal set of the sample axle box.

[0081] In one alternative implementation, it further includes:

[0082] A sound amplitude acquisition module is set up to acquire the sound time-domain signal set of the sample axle box in a non-fault state; the sound time-domain signal set of the sample axle box is normalized to obtain the sound time-domain normalized signal set of the sample axle box; and the set sound amplitude is acquired based on the average amplitude of the sound time-domain normalized signal set of the sample axle box.

[0083] In one optional implementation, the signal acquisition module 201 is used to determine a sampling frequency based on the acquired vibration frequency of the shaft box to be tested, wherein the sampling frequency is not less than twice the vibration frequency; and to collect the vibration data and the sound data within the same time period based on the sampling frequency.

[0084] Compared with the prior art, in the axle box fault detection device provided in Embodiment 2 of the present invention, the signal acquisition module 201 acquires the vibration data and sound data generated by the vibration of the axle box under test during operation. The signal processing module 203 acquires the amplitude of each noise-reduced vibration time-domain signal in the noise-reduced vibration data and the vibration ratio of the set vibration amplitude to obtain a vibration ratio set. The signal processing module 203 also acquires the amplitude of each noise-reduced sound time-domain signal in the noise-reduced sound data and the sound ratio of the set sound amplitude to obtain a sound ratio set. Finally, the fault determination module 204 determines whether the axle box under test is in a fault state based on the vibration ratio set and the sound ratio set. By comprehensively considering the vibration data and sound data generated by the vibration of the axle box under test during operation to determine whether it is in a fault state, the accuracy of the fault detection results can be effectively improved. In addition, the noise reduction module 202 performs noise reduction processing on the vibration data and sound data respectively, which can reduce the impact of noise data on the detection results and further improve the accuracy of the fault detection results.

[0085] In some embodiments of this application, the fault determination module 204 is specifically used to determine that the axle box under test is in a fault state when at least one vibration ratio amplitude in the vibration ratio set is greater than a set vibration amplitude and at least one sound ratio amplitude in the sound ratio set is greater than a set sound amplitude; and when no vibration ratio amplitude in the vibration ratio set is greater than the set vibration amplitude, to obtain the percentage of sound ratios in the sound ratio set whose amplitude is greater than the set sound amplitude, and to determine that the axle box under test is in a fault state when the percentage of sound ratios is greater than a preset first threshold; and when no sound ratio amplitude in the sound ratio set is greater than the set sound amplitude, to obtain the percentage of vibration ratios in the vibration ratio set whose amplitude is greater than the set vibration amplitude, and to determine that the axle box under test is in a fault state when the percentage of vibration ratios is greater than a preset second threshold.

[0086] The signal processing module 203 is specifically used to acquire the vibration time-domain signal set of the sample shaft box in a non-fault state; normalize the vibration time-domain signal set of the sample shaft box to obtain a normalized vibration time-domain signal set of the sample shaft box; obtain a set vibration amplitude based on the average amplitude of the normalized vibration time-domain signal set of the sample shaft box; and acquire the sound time-domain signal set of the sample shaft box in a non-fault state; normalize the sound time-domain signal set of the sample shaft box to obtain a normalized sound time-domain signal set of the sample shaft box; obtain a set sound amplitude based on the average amplitude of the normalized sound time-domain signal set of the sample shaft box.

[0087] The signal acquisition module 201 is specifically used to determine the sampling frequency based on the acquired vibration frequency of the shaft box to be tested, wherein the sampling frequency is not less than twice the vibration frequency; and to collect vibration data and sound data within the same time period based on the sampling frequency.

[0088] Embodiment 3 of this application relates to an electronic device, such as... Figure 3 As shown, it includes: at least one processor 301; and a memory 302 communicatively connected to at least one processor 301; wherein the memory 302 stores instructions executable by at least one processor 301, the instructions being executed by at least one processor 301 to enable at least one processor 301 to execute the axle box fault detection method in the above embodiments.

[0089] The memory and processor are connected via a bus, which can include any number of interconnecting buses and bridges, connecting various circuits of one or more processors and memories. The bus can also connect various other circuits, such as peripheral devices, voltage regulators, and power management circuits, which are well known in the art and will not be described further herein. The bus interface provides an interface between the bus and the transceiver. The transceiver can be a single element or multiple elements, such as multiple receivers and transmitters, providing a unit for communicating with various other devices over a transmission medium. Data processed by the processor is transmitted over the wireless medium via an antenna, which further receives data and transmits it to the processor.

[0090] The processor manages the bus and general processing, and also provides various functions, including timing, peripheral interfaces, voltage regulation, power management, and other control functions. Memory is used to store data used by the processor during operation.

[0091] Embodiment 4 of this application relates to a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, it implements the method embodiments described above.

[0092] That is, those skilled in the art will understand that all or part of the steps in the methods of the above embodiments can be implemented by a program instructing related hardware. This program is stored in a storage medium and includes several instructions to cause a device (which may be a microcontroller, chip, etc.) or processor to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, a portable hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0093] The above are merely specific embodiments of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method for detecting axle box faults, characterized in that, include: The vibration data and sound data generated by the vibration of the shaft box under test within the same time period are acquired. The shaft box under test is the main roller shaft 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. The vibration data and the sound data are respectively subjected to noise reduction processing to obtain noise-reduced vibration data and noise-reduced sound data; The amplitude of each noise-reduced vibration time-domain signal in the noise-reduced vibration data and the vibration ratio of a set vibration amplitude are obtained to obtain a vibration ratio set, wherein the set vibration amplitude is obtained based on the vibration time-domain signal generated by the vibration of the sample shaft box under non-fault conditions; The amplitude of each noise reduction time-domain signal in the noise reduction sound data is obtained and the sound ratio of a set sound amplitude is obtained to obtain a sound ratio set, wherein the set sound amplitude is obtained based on the sound time-domain signal generated by the sample shaft box sound in a non-fault state; Based on the vibration ratio set and the sound ratio set, determine whether the shaft box under test is in a fault state; Determining whether the axle box under test is in a fault state based on the vibration ratio set and the sound ratio set includes: if at least one vibration ratio in the vibration ratio set has an amplitude greater than a set vibration amplitude, and at least one sound ratio in the sound ratio set has an amplitude greater than a set sound amplitude, then the axle box under test is determined to be in the fault state; or, If no vibration ratio in the vibration ratio set represents an amplitude greater than the set vibration amplitude, then the percentage of sound ratios in the sound ratio set representing amplitudes greater than the set sound amplitude is obtained. If the percentage of sound ratios is greater than a preset first threshold, then the test axle box is determined to be in the fault state; or... If there is no sound ratio in the sound ratio set whose amplitude is greater than the set sound amplitude, then the percentage of vibration ratios in the vibration ratio set whose amplitude is greater than the set vibration amplitude is obtained. If the percentage of vibration ratios is greater than a preset second threshold, then the shaft box under test is determined to be in the fault state. The values ​​of the first set threshold and the second set threshold range from 50% to 60%.

2. The axle box fault detection method according to claim 1, characterized in that, The step of obtaining the set vibration amplitude includes: Obtain the vibration time-domain signal set of the sample shaft box in a non-faulty state; The vibration time-domain signal set of the sample axle box is normalized to obtain the vibration time-domain normalized signal set of the sample axle box. The set vibration amplitude is obtained based on the average amplitude of the normalized time-domain signal set of the sample shaft box.

3. The axle box fault detection method according to claim 1, characterized in that, The step of obtaining the set sound amplitude includes: Obtain the set of acoustic time-domain signals of the sample shaft box in a non-faulty state; The sound time-domain signal set of the sample shaft box is normalized to obtain the sound time-domain normalized signal set of the sample shaft box; The set sound amplitude is obtained based on the average amplitude of the time-domain normalized signal set of the sample shaft box.

4. The axle box fault detection method according to claim 1, characterized in that, The acquisition of vibration and sound data generated by the vibration of the axle box under test within the same time period includes: Based on the obtained vibration frequency of the shaft box to be tested, a sampling frequency is determined, wherein the sampling frequency is not less than twice the vibration frequency; The vibration data and sound data are collected within the same time period according to the sampling frequency.

5. A fault detection device for axle boxes, characterized in that, include: The signal acquisition module is used to acquire vibration data and sound data generated by the vibration of the shaft box under test within the same time period. The shaft box under test is the main roller shaft 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. A noise reduction module is used to perform noise reduction processing on the vibration data and the sound data respectively to obtain noise-reduced vibration data and noise-reduced sound data; The signal processing module is configured to acquire the amplitude of each noise-reduced vibration time-domain signal in the noise-reduced vibration data and a vibration ratio set of a set vibration amplitude, wherein the set vibration amplitude is obtained based on the vibration time-domain signal generated by the vibration of the sample axle box under a non-fault state; and is further configured to acquire the amplitude of each noise-reduced sound time-domain signal in the noise-reduced sound data and a sound ratio set of a set sound amplitude, wherein the set sound amplitude is obtained based on the sound time-domain signal generated by the sound of the sample axle box under a non-fault state; The fault determination module is used to determine whether the shaft box under test is in a fault state based on the vibration ratio set and the sound ratio set. The fault determination module is specifically used to determine that the shaft box under test is in the fault state if at least one vibration ratio in the vibration ratio set has an amplitude greater than the set vibration amplitude, and at least one sound ratio in the sound ratio set has an amplitude greater than the set sound amplitude; or, If no vibration ratio in the vibration ratio set represents an amplitude greater than the set vibration amplitude, then the percentage of sound ratios in the sound ratio set representing amplitudes greater than the set sound amplitude is obtained. If the percentage of sound ratios is greater than a preset first threshold, then the test axle box is determined to be in the fault state; or... If there is no sound ratio in the sound ratio set whose amplitude is greater than the set sound amplitude, then the percentage of vibration ratios in the vibration ratio set whose amplitude is greater than the set vibration amplitude is obtained. If the percentage of vibration ratios is greater than a preset second threshold, then the shaft box under test is determined to be in the fault state. The values ​​of the first set threshold and the second set threshold range from 50% to 60%.

6. An electronic device, characterized in that, include: At least one processor; And, a memory communicatively connected to the at least one processor; The memory stores instructions that can be executed by the at least one processor, which, when executed by the at least one processor, enables the at least one processor to perform the axle box fault detection method as described in any one of claims 1 to 4.

7. 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 4.

Images