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

Abstract

The invention provides an axle box fault identification method, electronic equipment and a computer readable storage medium. The axle box fault identification method comprises the steps of obtaining vibration data and sound data generated by a to-be-identified axle box; wherein the axle box to be identified is a main roll shaft box in the multi-wire cutting machine; determining a normal vibration time domain signal proportion according to the amplitude of each vibration time domain signal in the vibration data and a first amplitude threshold; determining a normal sound time domain signal proportion according to the amplitude of each sound time domain signal in the sound data and a second amplitude threshold; and determining whether the axle box to be identified is in a fault state or not according to the normal vibration time domain signal proportion and the normal sound time domain signal proportion. According to the scheme, automatic fault recognition can be achieved according to the vibration data and the sound data generated in the operation process of the axle box, and therefore the accuracy and timeliness of fault detection are improved.

Description

Technical Field

[0001] The present application relates to the technical field of equipment fault detection, and in particular to an axle box fault identification method and device, an electronic device, and a 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 pitch, and the multi-wire interval work is realized through the grinding between the wire net and the workpiece. In current industrial applications, the two ends of the main roller are usually connected to the front and rear axle boxes. Adjusting the spacing between the two main rollers is to adjust the spacing between the two pairs of front and rear axle boxes. In the process of driving the main roller to rotate by clicking, the axle box may fail due to factors such as excessive temperature or excessive load.

[0003] In the related art, the operator judges the axle box fault based on his / her own work experience. However, the accuracy of manual fault detection is low, and there is a problem that the fault cannot be detected in time. Summary of the invention

[0004] The purpose of the embodiments of the present application is to provide an axle box fault identification method and electronic device, and a computer-readable storage medium, which are used to realize automatic fault identification based on the vibration data and sound data generated during the operation of the axle box, thereby improving the accuracy and timeliness of fault detection.

[0005] On the one hand, the present application provides an axle box fault identification method, comprising:

[0006] Acquire vibration data and sound data generated by the axle box to be identified; wherein the axle box to be identified is a main roller axle box in a multi-wire cutting machine;

[0007] Determine the proportion of normal vibration time-domain signals according to the amplitude of each vibration time-domain signal in the vibration data and a first amplitude threshold; wherein the first amplitude threshold is obtained according to the vibration time-domain signal generated by the sample axle box in a non-fault state;

[0008] Determine the proportion of normal sound time domain signals according to the amplitude of each sound time domain signal in the sound data and a second amplitude threshold; wherein the second amplitude threshold is obtained according to the sound time domain signal generated by the sample axle box in a non-fault state;

[0009] Whether the axle box to be identified is in a fault state is determined according to the proportion of the normal vibration time domain signal and the proportion of the normal sound time domain signal.

[0010] In one embodiment, determining whether the axle box to be identified is in a fault state according to the proportion of the normal vibration time domain signal and the proportion of the normal sound time domain signal includes:

[0011] Compare the normal vibration time domain signal ratio with the normal vibration ratio threshold to obtain a first comparison result; wherein the normal vibration ratio threshold is obtained based on the vibration time domain signal generated by the sample axle box under a fault state;

[0012] Compare the normal sound time domain signal ratio with the normal sound ratio threshold to obtain a second comparison result; wherein the normal sound ratio threshold is obtained based on the sound time domain signal generated by the sample axle box under the fault state;

[0013] According to the first comparison result and the second comparison result, it is determined whether the axle box to be identified is in a fault state.

[0014] In one embodiment, determining whether the axle box to be identified is in a fault state according to the first comparison result and the second comparison result includes:

[0015] If the proportion of the normal vibration time domain signal of the axle box to be identified is not greater than the normal vibration proportion threshold, and the proportion of the normal sound time domain signal of the axle box to be identified is not greater than the normal sound proportion threshold, it is determined that the axle box to be identified is in a fault state.

[0016] In one embodiment, determining whether the axle box to be identified is in a fault state according to the proportion of the normal vibration time domain signal and the proportion of the normal sound time domain signal includes:

[0017] If the normal vibration time domain signal ratio is not greater than the normal vibration ratio threshold, and the normal sound time domain signal ratio is greater than the normal sound ratio threshold, determining whether the duration during which the normal vibration time domain signal ratio is not greater than the normal vibration ratio threshold exceeds a first preset duration;

[0018] If exceeded, it is determined that the axle box to be identified is in a fault state.

[0019] In one embodiment, determining whether the axle box to be identified is in a fault state according to the proportion of the normal vibration time domain signal and the proportion of the normal sound time domain signal includes:

[0020] If the normal vibration time domain signal ratio is greater than the normal vibration ratio threshold, and the normal sound time domain signal ratio is not greater than the normal sound ratio threshold, determining whether the duration of the normal sound time domain signal ratio being not greater than the normal sound ratio threshold exceeds a second preset duration;

[0021] If exceeded, it is determined that the axle box to be identified is in a fault state.

[0022] In one embodiment, the step of obtaining the first amplitude threshold comprises:

[0023] 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;

[0024] Calculating the mean value of the amplitude of the sample vibration time domain signal in the sample vibration data as the vibration reference value;

[0025] Based on the vibration reference value, the first amplitude threshold is determined.

[0026] In one embodiment, the step of obtaining the second amplitude threshold comprises:

[0027] Acquiring sample sound data when the sample axle box is in a non-fault state, wherein the sample sound data includes a plurality of sample sound time domain signals;

[0028] Calculating the mean of the amplitudes of the sample sound time domain signals in the sample sound data as the sound reference value;

[0029] Based on the sound reference value, the second amplitude threshold is determined.

[0030] In one embodiment, the step of obtaining the normal vibration ratio threshold comprises:

[0031] Acquire N groups of fault vibration data when the sample axle box is in a fault state; wherein N is an integer greater than 1;

[0032] Obtaining the proportion of N normal vibration time domain signals of the N groups of fault vibration data;

[0033] The normal vibration ratio threshold is determined according to the ratios of the N normal vibration time domain signals.

[0034] In one embodiment, the step of obtaining the normal sound proportion threshold comprises:

[0035] Acquire M groups of fault sound data when the sample axle box is in a fault state; wherein M is an integer greater than 1;

[0036] Obtaining the proportion of M normal sound time domain signals of the M groups of fault sound data;

[0037] The normal sound proportion threshold is determined according to the proportions of the M normal sound time-domain signals.

[0038] On the other hand, the present application provides an axle box fault identification device, comprising:

[0039] A collection module, used to obtain vibration data and sound data generated by the axle box to be identified; wherein the axle box to be identified is a main roller axle box in a multi-wire cutting machine;

[0040] A first determination module, used to determine the proportion of normal vibration time-domain signals according to the amplitude of each vibration time-domain signal in the vibration data and a first amplitude threshold; wherein the first amplitude threshold is obtained according to the vibration time-domain signal generated by the sample axle box in a non-fault state;

[0041] A second determination module is used to determine the proportion of normal sound time domain signals according to the amplitude of each sound time domain signal in the sound data and a second amplitude threshold; wherein the second amplitude threshold is obtained according to the sound time domain signal generated by the sample axle box in a non-fault state;

[0042] The identification module is used to determine whether the axle box to be identified is in a fault state according to the proportion of the normal vibration time domain signal and the proportion of the normal sound time domain signal.

[0043] Furthermore, the present application provides an electronic device, the electronic device comprising:

[0044] processor;

[0045] a memory for storing processor-executable instructions;

[0046] Wherein, the processor is configured to execute the above-mentioned axle box fault identification method.

[0047] In addition, the present application provides a computer-readable storage medium, which stores a computer program. The computer program can be executed by a processor to complete the above-mentioned axle box fault identification method.

[0048] According to the present application, during the operation of the axle box to be identified, the proportion of normal vibration time-domain signals and the proportion of normal sound time-domain signals can be converted based on the collected vibration data and sound data. Since the proportion of normal vibration time-domain signals can characterize the overall normal situation of the vibration dimension during the operation of the axle box, and the proportion of normal sound time-domain signals can characterize the overall normal situation of the sound dimension during the operation of the axle box, with the help of the proportion of normal vibration time-domain signals and the proportion of normal sound time-domain signals, the parameters of both the vibration dimension and the sound dimension can be combined to perform automatic fault identification on the axle box to be identified, thereby solving the problem of insufficient accuracy and timeliness that may exist due to manual fault identification. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the technical solution of the embodiments of the present application, the drawings required for use in the embodiments of the present application are briefly introduced below.

[0050] Figure 1 A schematic flow chart of an axle box fault identification method provided in one embodiment of the present application;

[0051] Figure 2 A schematic diagram of vibration data provided by an embodiment of the present application;

[0052] Figure 3 A schematic diagram of vibration data provided by another embodiment of the present application;

[0053] Figure 4 A schematic diagram of sound data provided by an embodiment of the present application;

[0054] Figure 5 A schematic diagram of a specific process of a fault identification method provided in an embodiment of the present application;

[0055] Figure 6 A schematic flow chart of a method for determining a first amplitude threshold value provided in an embodiment of the present application;

[0056] Figure 7 A schematic flow chart of a method for determining a second amplitude threshold value provided in an embodiment of the present application;

[0057] Figure 8 A schematic flow chart of a method for determining a normal vibration ratio threshold value provided in an embodiment of the present application;

[0058] Fig. 9 A flowchart of a method for determining a normal sound ratio threshold provided in an embodiment of the present application;

[0059] Fig.10 A block diagram of an axle box fault identification device provided in one embodiment of the present application;

[0060] Fig.11 A schematic diagram of an application scenario of the axle box fault identification method provided in one embodiment of the present application;

[0061] Fig.12 A schematic diagram of the structure of an electronic device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0062] The technical solutions in the embodiments of the present application will be described below in conjunction with the drawings in the embodiments of the present application.

[0063] Similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings. At the same time, in the description of this application, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.

[0064] See also Figure 1 , is a flow chart of an axle box fault identification method provided in an embodiment of the present application, such as Figure 1 As shown, the method may include the following steps 110 to 140.

[0065] Step 110: Acquire vibration data and sound data generated by the axle box to be identified in the same time period; wherein the axle box to be identified is a main roller axle box in a multi-wire cutting machine.

[0066] In a specific implementation process, the vibration data includes a plurality of vibration time-domain signals, and similarly, the sound data includes a plurality of sound time-domain signals.

[0067] This solution is used to identify the fault of the axle box on the multi-wire cutting machine. For each axle box to be identified on the multi-wire cutting machine, corresponding vibration collection equipment and sound collection equipment can be installed respectively. The vibration collection equipment is used to collect vibration data, and the sound collection equipment is used to collect sound data. Exemplarily, the vibration collection equipment can be a vibration acceleration sensor, an eddy current sensor, etc.; the sound collection equipment can be a sound sensor.

[0068] The vibration frequency of the axle box is about below 1000 Hz. When sampling, the sampling frequency must follow Shannon's sampling theorem. The sampling theorem is: the sampling frequency fs is at least twice the highest frequency of the signal of interest. Half of the sampling frequency is called the Nyquist frequency, also known as the analysis bandwidth, or simply bandwidth. When the sampling frequency setting does not meet the sampling theorem, that is, the sampling frequency is less than 2 times the signal frequency, the original high-frequency signal will be sampled as a low-frequency signal, resulting in a lower accuracy of the sampled data. When a frequency higher than 2 times the signal frequency is used, the accuracy of the collected data is higher because the matching degree between the collected data and the frequency is higher.

[0069] See also Figure 2 , which is a schematic diagram of vibration data provided by an embodiment of the present application. When the sampling frequency is set to 5000 Hz, the vibration data composed of multiple vibration time domain signals collected is as follows: Figure 2 As shown, the amplitude of the vibration time domain signal includes positive and negative directions.

[0070] See also Figure 3 , which is a schematic diagram of vibration data provided by another embodiment of the present application. When the sampling frequency is set to 12000 Hz, the vibration data composed of multiple vibration time domain signals collected is as follows: Figure 3 shown.

[0071] During the current cutting process of the multi-wire saw, the vibration time domain signal can be continuously collected through the vibration collection equipment corresponding to the axle box to be identified. When the multi-wire saw is just started, the amplitude of the vibration time domain signal fluctuates greatly. When the cutting time reaches the preset time threshold, the vibration time domain signal collected during this period can be used to form vibration data, and the sound time domain signal collected during this period can be used to form sound data. Here, one cut refers to the cutting process of the multi-wire saw cutting a silicon rod into silicon wafers. The time threshold can be configured based on experience. For example, the time threshold can be between 1 and 5 minutes, such as 3 minutes, 4 minutes or 5 minutes.

[0072] See also Figure 4 , is a schematic diagram of sound data provided by an embodiment of the present application, such as Figure 4 As shown, multiple sound time domain signals collected in the same time period constitute sound data, and the amplitude of the sound time domain signal includes a positive direction and a negative direction.

[0073] In some embodiments of the present application, 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 conditions. For example, the duration of the vibration time domain signal can be set according to the working accuracy of the axle box to be identified. For the axle box to be identified with higher working accuracy, it is more sensitive to axle box failure, and the time period can be set shorter, such as 3 seconds to 5 minutes, to obtain the vibration time domain signal and sound time domain signal of shorter duration as vibration data and sound data. For the axle box to be identified with lower working accuracy, the time period can be set longer, such as 4 minutes to 20 minutes, to obtain the vibration time domain signal and sound time domain signal of longer duration as vibration data and sound data. Specifically, the duration of the time period can be flexibly set according to the actual conditions.

[0074] During the current cutting process, the multi-wire cutting machine can continuously collect sound time domain signals through the sound collection equipment corresponding to the axle box to be identified. When the multi-wire cutting machine is just started, the amplitude of the sound time domain signal fluctuates greatly. When the cutting time reaches the preset time threshold, the sound time domain signal collected during this period can be used as sound data for the first fault identification. Here, the time threshold is the same as the aforementioned time threshold.

[0075] In one embodiment, due to the complex composition of the multi-wire cutting machine, it is affected by factors such as load changes and component interactions during operation, resulting in the collected original vibration data and original sound data containing a large amount of noise data. If the collected original vibration data and original sound data are directly used for fault identification, it may lead to low recognition accuracy. To solve this problem, the vibration data and sound data can be denoised separately by a denoising algorithm, so that the denoised vibration data and sound data can be used for subsequent fault identification, effectively improving the recognition accuracy. Here, the denoising algorithm may include but is not limited to singular value decomposition (SVD) and wavelet threshold denoising method.

[0076] Step 120: Determine the proportion of normal vibration time domain signals based on the amplitude of each vibration time domain signal in the vibration data and a first amplitude threshold; wherein the first amplitude threshold is obtained based on the vibration time domain signal generated by the sample axle box in a non-fault state.

[0077] In step 120, the absolute amplitude of each vibration time domain signal in the vibration data can be compared with the first amplitude threshold to determine the proportion of normal vibration time domain signals; or each vibration time domain signal in the vibration data can be normalized, and the amplitude of each normalized vibration time domain signal can be compared with the first amplitude threshold to determine the proportion of normal vibration time domain signals.

[0078] The first amplitude threshold is used to filter the normal vibration time domain signal. For each axle box to be identified, a corresponding first amplitude threshold can be preconfigured for it. In one embodiment, the first amplitude threshold can be obtained based on the vibration time domain signal generated by the sample axle box in a non-fault state, as described below.

[0079] In one embodiment, the amplitude of each vibration time domain signal is compared with the first amplitude threshold value one by one, and the amplitude signal with an amplitude less than the first amplitude threshold value is determined as a normal vibration time domain signal. After all normal vibration time domain signals in the vibration data are determined, the number of all normal vibration time domain signals can be counted, and then the proportion of normal vibration time domain signals can be determined based on the number and the total number of signals in the vibration data.

[0080] Exemplarily, the normal vibration time domain signal ratio can be expressed by the following formula (1):

[0081] L=T1 / S (1)

[0082] Among them, L is the proportion of normal vibration time domain signals; T1 is the number of normal vibration time domain signals; S is the total amount of vibration time domain signals in the vibration data.

[0083] In one embodiment, the amplitude of each vibration time domain signal is compared with the first amplitude threshold value one by one, and the amplitude signal with an amplitude not less than the first amplitude threshold value is determined as an abnormal vibration time domain signal. After determining all abnormal vibration time domain signals in the vibration data, the number of all abnormal vibration time domain signals can be counted, and then the proportion of normal vibration time domain signals can be determined based on the number and the total number of signals in the vibration data.

[0084] Exemplarily, the normal vibration time domain signal ratio can be expressed by the following formula (2):

[0085] L=(S-T2) / S (2)

[0086] Among them, L is the proportion of normal vibration time domain signals; T2 is the number of abnormal vibration time domain signals; S is the total amount of vibration time domain signals in the vibration data.

[0087] Step 130: Determine the proportion of normal sound time domain signals based on the amplitude of each sound time domain signal in the sound data and the second amplitude threshold; wherein the second amplitude threshold is obtained based on the sound time domain signal generated by the axle box to be identified in a non-fault state.

[0088] In step 130, the absolute amplitude of each sound time domain signal in the sound data can be compared with the second amplitude threshold to determine the proportion of normal sound time domain signals; or each sound time domain signal in the sound data can be normalized, and the amplitude of each normalized sound time domain signal can be compared with the second amplitude threshold to determine the proportion of normal sound time domain signals.

[0089] The second amplitude threshold is used to filter the normal sound time domain signal. For each axle box to be identified, a corresponding second amplitude threshold can be preconfigured for it. In one embodiment, the second amplitude threshold can be obtained based on the sound time domain signal generated by the sample axle box in a non-fault state, as described below.

[0090] In one embodiment, the amplitude of each sound time domain signal is compared with the second amplitude threshold value one by one, and the sound time domain signal with an amplitude less than the second amplitude threshold value is determined as a normal sound time domain signal. After all normal sound time domain signals in the sound data are determined, the number of all normal sound time domain signals can be counted, and then the proportion of normal sound time domain signals can be determined based on the number and the total amount of signals in the sound data.

[0091] Exemplarily, the normal sound time domain signal ratio can be expressed by the following formula (3):

[0092] H=F1 / W (2)

[0093] Among them, H is the proportion of normal sound time domain signals; F1 is the number of normal sound time domain signals; W is the total amount of sound time domain signals in the sound data.

[0094] In one embodiment, the amplitude of each sound time domain signal is compared with the second amplitude threshold value one by one, and the sound time domain signal whose amplitude is not less than the second amplitude threshold value is determined as an abnormal sound time domain signal. After all abnormal sound time domain signals in the sound data are determined, the number of all abnormal sound time domain signals can be counted, and then the proportion of normal sound time domain signals can be determined based on the number and the total number of signals in the sound data.

[0095] Exemplarily, the normal sound time domain signal ratio can be expressed by the following formula (4):

[0096] H=(W-F2) / W (4)

[0097] Among them, H is the proportion of normal sound time domain signals; F2 is the number of abnormal sound time domain signals; W is the total amount of sound time domain signals in the sound data.

[0098] Step 140: Determine whether the axle box to be identified is in a fault state according to the proportion of normal vibration time domain signals and the proportion of normal sound time domain signals.

[0099] After obtaining the normal vibration time domain signal ratio and the normal sound time domain signal ratio, the operating status of the axle box to be identified can be identified based on the normal vibration time domain signal ratio and the normal sound time domain signal ratio to determine whether there is a fault.

[0100] Through the above measures, during the operation of the axle box to be identified, based on the collected vibration data and sound data, the proportion of normal vibration time domain signals and the proportion of normal sound time domain signals can be converted. Since the proportion of normal vibration time domain signals can characterize the overall normal situation of the vibration dimension during the operation of the axle box, and the proportion of normal sound time domain signals can characterize the overall normal situation of the sound dimension during the operation of the axle box, with the help of the normal vibration time domain signal proportion and the normal sound time domain signal proportion, the two aspects of vibration dimension and sound dimension parameters can be combined to perform automatic fault identification on the axle box to be identified, which solves the problems of insufficient accuracy and timeliness that may exist in manual fault identification.

[0101] In one embodiment, see Figure 5 , is a schematic diagram of a specific flow chart of a fault identification method provided in an embodiment of the present application, such as Figure 5 As shown, the method may include the following steps 510 to 530.

[0102] Step 510: Compare the normal vibration time domain signal ratio with the normal vibration ratio threshold to obtain a first comparison result; wherein the normal vibration ratio threshold is obtained based on the vibration time domain signal generated by the sample axle box under a fault state.

[0103] The normal vibration percentage threshold value can be configured as needed. Exemplarily, the normal vibration percentage threshold value can be between 20% and 30%. For example, the normal vibration percentage threshold value can be 28%. In one embodiment, the normal vibration percentage threshold value can be obtained based on the vibration time domain signal generated by the sample axle box under the fault state, as described below.

[0104] After obtaining the normal vibration time domain signal ratio, the normal vibration time domain signal ratio is compared with the normal vibration ratio threshold to obtain a first comparison result. The first comparison result is that the normal vibration time domain signal ratio is greater than the normal vibration ratio threshold, or the first comparison result is that the normal vibration time domain signal ratio is not greater than the normal vibration ratio threshold.

[0105] Step 520: Compare the normal sound time domain signal ratio with the normal sound ratio threshold to obtain a second comparison result; wherein the normal sound ratio threshold is obtained based on the sound time domain signal generated by the sample axle box under a fault state.

[0106] The normal sound ratio threshold value can be configured as needed. Exemplarily, the normal sound ratio threshold value can be between 18% and 32%. For example, the normal sound ratio threshold value can be 25%. In one embodiment, the normal sound ratio threshold value can be obtained based on the sound time domain signal generated by the sample axle box under the fault state, as described below for details.

[0107] After obtaining the normal sound time domain signal ratio, the normal sound time domain signal ratio is compared with the normal sound ratio threshold to obtain a second comparison result. The second comparison result is that the normal sound time domain signal ratio is greater than the normal sound ratio threshold, or the second comparison result is that the normal sound time domain signal ratio is not greater than the normal sound ratio threshold.

[0108] Step 530: Determine whether the axle box to be identified is in a fault state according to the first comparison result and the second comparison result.

[0109] After obtaining the first comparison result and the second comparison result, it can be determined whether the axle box to be identified has a fault.

[0110] Through the above measures, the normal vibration proportion threshold is compared with the normal vibration time domain signal proportion, and the normal sound proportion threshold is compared with the normal sound time domain signal proportion, so as to obtain a first comparison result representing whether the vibration condition is qualified and a second comparison result representing whether the sound condition is qualified, so that the operating status of the axle box to be identified can be determined based on the first comparison result and the second comparison result.

[0111] In one embodiment, if the proportion of the normal vibration time domain signal of the axle box to be identified is not greater than the normal vibration proportion threshold, and the proportion of the normal sound time domain signal of the axle box to be identified is not greater than the normal sound proportion threshold, it means that the axle box to be identified is abnormal in terms of both the vibration dimension and the sound dimension, and it can be determined that the axle box to be identified is in a fault state. At this time, a prompt message for the axle box can be output, and the prompt message is used to indicate the axle box fault and prompt the staff to perform maintenance.

[0112] If the normal vibration time domain signal ratio of the axle box to be identified is greater than the normal vibration ratio threshold, and the normal sound time domain signal ratio of the axle box to be identified is greater than the normal sound ratio threshold, it means that there is no abnormality in the axle box to be identified from both the vibration dimension and the sound dimension, and it can be determined that the axle box to be identified is in a non-fault state. At this time, the operating status of the axle box to be identified can continue to be monitored.

[0113] Through the above measures, when the proportion of normal vibration time domain signals and the proportion of normal sound time domain signals are both greater than the threshold, or are not greater than the threshold, it is possible to accurately determine whether the axle box to be identified is in a non-fault state or a fault state based on the conditions in two dimensions.

[0114] In one embodiment, if the proportion of normal vibration time domain signals of the axle box to be identified is not greater than the normal vibration proportion threshold, and the proportion of normal sound time domain signals of the axle box to be identified is greater than the normal sound proportion threshold, it means that from the vibration dimension, the axle box to be identified may have an abnormality, while from the sound dimension, the axle box to be identified does not have an abnormality. In other words, the axle box to be identified may have a fault, but its operating status cannot be directly determined based on the first comparison result and the second comparison result currently obtained.

[0115] In another embodiment, the operating status of the axle box to be identified can continue to be monitored, and all first comparison results and all second comparison results within a cutting cycle (one cut) can be obtained. Of course, real-time monitoring can also be performed. After the first comparison result and the second comparison result are obtained for the first time, the normal vibration time domain signal ratio can be compared with the normal vibration ratio threshold value at every set acquisition cycle, and the normal sound time domain signal ratio is not greater than the normal sound ratio threshold value. In this way, multiple first comparison results and multiple second comparison results can be obtained, and this specification does not make specific restrictions. The following specifically takes all the first comparison results and all the second comparison results within one cut as an example.

[0116] Based on all the first comparison results obtained within one cut, it can be determined whether the duration of the normal vibration time domain signal ratio being no greater than the normal vibration ratio threshold exceeds the first preset duration. Here, the first preset duration can be configured as required. Exemplarily, the first preset duration can be 5 seconds.

[0117] On the one hand, if it exceeds, it means that from the vibration dimension, there is an abnormality in the axle box to be identified, and it can be determined that the axle box to be identified is faulty and in a faulty state. At this time, a prompt message for the axle box can be output. On the other hand, if it does not exceed, it means that it is impossible to accurately determine that there is an abnormality in the axle box to be identified from the vibration dimension, and it can be determined that there is no fault in the axle box to be identified and it is in a non-faulty state. At this time, the operating status of the axle box to be identified can continue to be monitored.

[0118] Through the above measures, when it is determined that the axle box to be identified may be abnormal in a single vibration dimension, the operating status of the axle box to be identified can continue to be monitored in the vibration dimension, so that when the duration of the normal vibration time domain signal ratio not exceeding the normal vibration ratio threshold exceeds the first preset duration, it can be determined that the identified axle box has a fault from the vibration dimension. In one embodiment, if the normal vibration time domain signal ratio of the axle box to be identified is greater than the normal vibration ratio threshold, and the normal sound time domain signal ratio of the axle box to be identified is not greater than the normal sound ratio threshold, it means that from the sound dimension, the axle box to be identified may be abnormal, but from the vibration dimension, the axle box to be identified does not have an abnormality. In other words, the axle box to be identified may be faulty, but its operating status cannot be directly determined based on the first comparison result and the second comparison result currently obtained.

[0119] In another embodiment, the operating status of the axle box to be identified can continue to be monitored, and all first comparison results and all second comparison results within a cutting cycle (one cut) can be obtained. Of course, real-time monitoring can also be performed. After the first comparison result and the second comparison result are obtained for the first time, the normal vibration time domain signal ratio can be compared with the normal vibration ratio threshold value at every set acquisition cycle, and the normal sound time domain signal ratio is not greater than the normal sound ratio threshold value. In this way, multiple first comparison results and multiple second comparison results can be obtained, and this specification does not make specific restrictions. The following specifically takes all the first comparison results and all the second comparison results within one cut as an example.

[0120] Based on all the second comparison results obtained within one cut, it can be determined whether the duration of the normal sound time domain signal ratio being no greater than the normal sound ratio threshold exceeds the second preset duration. Here, the second preset duration can be configured as required. Exemplarily, the second preset duration can be 10 seconds.

[0121] On the one hand, if it exceeds, it means that from the sound dimension, there is an abnormality in the axle box to be identified, and it can be determined that the axle box to be identified is faulty and in a faulty state. At this time, a prompt message for the axle box can be output. On the other hand, if it does not exceed, it means that it is impossible to accurately determine that there is an abnormality in the axle box to be identified from the sound dimension, and it can be determined that there is no fault in the axle box to be identified and it is in a non-faulty state. At this time, the operating status of the axle box to be identified can continue to be monitored.

[0122] Through the above measures, when it is determined that the axle box to be identified may have an abnormality in a single sound dimension, the operating status of the axle box to be identified can continue to be monitored in the sound dimension. Therefore, when the duration during which the proportion of the normal sound time domain signal is not greater than the normal sound proportion threshold exceeds the second preset duration, it can be determined that there is a fault in the identified axle box from the sound dimension.

[0123] In one embodiment, before executing step 120 , a corresponding first amplitude threshold may be determined for each axle box to be identified. Figure 6 A flowchart of a method for determining a first amplitude threshold value provided in an embodiment of the present application is shown in FIG. Figure 6 As shown, the method may include the following steps 610 to 630.

[0124] Step 610: Collect sample vibration data of a sample axle box in a non-fault state, wherein the sample vibration data includes a plurality of vibration time domain signals.

[0125] When the sample shaft box is in a non-faulty state, during multiple operations of the multi-wire cutting machine, multiple vibration time domain signals of the sample shaft box can be collected by the vibration collection equipment to form sample vibration data. Here, the sample vibration data can include vibration time domain signals in one or more knives.

[0126] Step 620: Calculate the mean value of the amplitude of the sample vibration time domain signal in the sample vibration data as the vibration reference value.

[0127] Step 630: Determine a first amplitude threshold of the axle box to be identified based on the vibration reference value.

[0128] After obtaining multiple sets of sample vibration data, the mean of the amplitudes of multiple sample vibration time domain signals in the multiple sets of sample vibration data can be calculated and used as the vibration reference value. After obtaining the vibration reference value, the first amplitude threshold can be converted according to the vibration reference value. Exemplarily, the vibration reference value can be added to the first set constant to obtain the first amplitude threshold. Here, the first set constant can be configured based on experience to characterize the maximum amplitude of the vibration time domain signal allowed by the axle box in a non-fault state and the offset of the amplitude mean.

[0129] In one embodiment, the vibration reference value can be multiplied by the first adjustment coefficient to obtain the first amplitude threshold. Here, the first adjustment coefficient can be configured as needed. Exemplarily, the first adjustment coefficient is a value between 1.2 and 1.5, such as: 1.2, 1.3, 1.4 or 1.5.

[0130] In one embodiment, the first amplitude threshold may be calculated with the vibration reference value as the base and the first adjustment coefficient as the exponent. Of course, preferably, the product of the vibration reference value and the first adjustment coefficient is used as the first amplitude threshold.

[0131] Through the above measures, after calculating the mean of the amplitudes of the sample vibration time domain signals of the sample axle box in the non-fault state, the mean can be amplified to obtain a first amplitude threshold, which includes a vibration reference value and an offset between the maximum amplitude allowed by the axle box in the non-fault state and the vibration reference value, so that the normal vibration time domain signals can be screened subsequently with the help of the first amplitude threshold.

[0132] In one embodiment, if the vibration time domain signal of any axle box to be identified has a large fluctuation, a corresponding first amplitude threshold value may be configured for the axle box to be identified based on experience.

[0133] In one embodiment, before executing step 130, a corresponding second amplitude threshold may be determined for each axle box to be identified. Figure 7 , is a flow chart of a method for determining a second amplitude threshold value provided in an embodiment of the present application, such as Figure 7As shown, the method may include the following steps 710 to 730.

[0134] Step 710: Collect sample sound data of a sample axle box in a non-fault state, wherein the sample sound data includes a plurality of sound time domain signals.

[0135] When the sample spool box is in a non-fault state, during the multiple operations of the multi-wire cutting machine, the sound time domain signal of the sample spool box can be collected by the sound collection equipment to form sample sound data. Here, the sample sound data can include the sound time domain signal of one or more knives.

[0136] Step 720: Calculate the average of the amplitudes of the sample sound time domain signals in the sample sound data as the sound reference value.

[0137] Step 730: Determine a second amplitude threshold of the axle box to be identified based on the sound reference value.

[0138] After obtaining multiple groups of sample sound data, the mean of the amplitudes of multiple sample sound time domain signals in the multiple groups of sample sound data can be calculated and used as the sound reference value. After obtaining the sound reference value, the second amplitude threshold can be converted according to the sound reference value. Exemplarily, the second amplitude threshold can be obtained by adding the second set constant to the sound reference value. Here, the second set constant can be configured based on experience, representing the maximum amplitude of the sound time domain signal allowed by the axle box in a non-fault state and the offset of the amplitude mean.

[0139] In one embodiment, the sound reference value may be multiplied by the second adjustment coefficient to obtain the second amplitude threshold. Here, the second adjustment coefficient may be configured as needed. Exemplarily, the second adjustment coefficient is a value between 1.2 and 1.5, such as 1.2, 1.3, 1.4 or 1.5.

[0140] In one embodiment, the sound reference value can be used as the base and the second adjustment coefficient can be used as the exponent to calculate the second amplitude threshold. Of course, preferably, the product of the sound reference value and the second adjustment coefficient is used as the second amplitude threshold.

[0141] Through the above measures, after calculating the mean of the amplitudes of the sample sound time domain signals of the sample axle box in the non-fault state, the mean can be amplified to obtain a second amplitude threshold, which includes the sound reference value and the offset between the maximum amplitude allowed by the axle box in the non-fault state and the sound reference value, so that the normal sound time domain signals can be screened subsequently with the help of the second amplitude threshold.

[0142] In one embodiment, if the sound time domain signal of any axle box to be identified has large fluctuations, a corresponding second amplitude threshold may be configured for the axle box to be identified based on experience.

[0143] In one embodiment, before executing step 510, a normal vibration ratio threshold may be generated. Figure 8 , is a flow chart of a method for determining a normal vibration ratio threshold value provided in an embodiment of the present application, such as Figure 8 As shown, the method may include the following steps 810 to 830.

[0144] Step 810: When the sample axle box is in a fault state, collect N groups of fault vibration data; wherein N is an integer greater than 1.

[0145] When the sample shaft box is in a faulty state, during the N-times operation of the multi-wire cutting machine, the vibration time domain signal of the sample shaft box can be collected by the vibration collection equipment to form fault vibration data, thereby obtaining N groups of fault vibration data. Here, each time the multi-wire cutting machine performs a cut, a group of fault vibration data can be collected.

[0146] Step 820: Obtain the proportions of N normal vibration time domain signals in N groups of fault vibration data.

[0147] Step 830: Determine a normal vibration ratio threshold according to the ratios of N normal vibration time domain signals.

[0148] For each set of fault vibration data, the amplitude of each vibration time domain signal in the fault vibration data can be compared with the first amplitude threshold, so as to screen out the normal vibration time domain signal. The proportion of normal vibration time domain signals can be obtained by dividing the number of normal vibration time domain signals by the total number of vibration time domain signals in the set of fault vibration data.

[0149] By calculation, the proportions of N normal vibration time domain signals corresponding to N groups of fault vibration data can be obtained. After obtaining the proportions of N normal vibration time domain signals, the average of the proportions of N normal vibration time domain signals can be further calculated and used as the normal vibration proportion threshold of the axle box to be identified.

[0150] Through the above measures, since the N groups of fault vibration data generated by the sample axle box under the fault state can characterize the vibration conditions under the fault state, after obtaining the N groups of fault vibration data, the proportion of normal vibration time domain signals corresponding to each group of fault vibration data can be calculated to determine the proportion of normal vibration time domain signals under the fault state; using the average of the proportions of N normal vibration time domain signals as the normal vibration proportion threshold, the error can be reduced and a more reliable normal vibration proportion threshold can be selected.

[0151] In one embodiment, before executing step 520, a normal sound ratio threshold may be generated. Fig. 9 , is a flow chart of a method for determining a normal sound ratio threshold value provided in an embodiment of the present application, such as Fig. 9 As shown, the method may include the following steps 910 to 930.

[0152] Step 910: When the sample axle box is in a fault state, collect M groups of fault sound data; wherein M is an integer greater than 1.

[0153] When the sample axle box is in a faulty state, during the N-times operation of the multi-wire cutting machine, the sound time domain signal of the sample axle box can be collected by the sound collection equipment to form fault sound data, thereby obtaining M groups of fault sound data. Here, each time the multi-wire cutting machine performs a cut, a group of fault sound data can be collected.

[0154] Step 920: Obtain the proportions of M normal sound time-domain signals of M groups of fault sound data.

[0155] Step 930: Determine a normal sound ratio threshold according to the ratios of the M normal sound time-domain signals.

[0156] For each set of fault sound data, the amplitude of each sound time domain signal in the fault sound data can be compared with the second amplitude threshold, so as to screen out normal sound time domain signals. The number of normal sound time domain signals is divided by the total number of sound time domain signals in the set of fault sound data to obtain the proportion of normal sound time domain signals.

[0157] By calculation, the proportions of M normal sound time domain signals corresponding to the M groups of fault sound data can be obtained. After obtaining the proportions of M normal sound time domain signals, the average of the proportions of M normal sound time domain signals can be further calculated and used as the normal sound proportion threshold of the axle box to be identified.

[0158] Through the above measures, since the M groups of fault sound data generated by the sample axle box under the fault state can characterize the sound conditions under the fault state, after obtaining the M groups of fault sound data, the proportion of normal sound time domain signals corresponding to each group of fault sound data can be calculated to determine the proportion of normal sound time domain signals under the fault state; using the average of the proportions of M normal sound time domain signals as the normal sound proportion threshold, the error can be reduced and a more reliable normal sound proportion threshold can be selected.

[0159] Fig.10 is a block diagram of an axle box fault identification device according to an embodiment of the present invention. Fig.10 As shown, the device may include:

[0160] The acquisition module 1010 is used to acquire vibration data and sound data generated by the axle box to be identified; wherein the axle box to be identified is the main roller axle box in the multi-wire cutting machine;

[0161] A first determination module 1020 is used to determine the proportion of normal vibration time domain signals according to the amplitude of each vibration time domain signal in the vibration data and a first amplitude threshold; wherein the first amplitude threshold is obtained according to the vibration time domain signal generated by the sample axle box in a non-fault state;

[0162] A second determination module 1030 is used to determine the proportion of normal sound time domain signals according to the amplitude of each sound time domain signal in the sound data and a second amplitude threshold; wherein the second amplitude threshold is obtained according to the sound time domain signal generated by the sample axle box in a non-fault state;

[0163] The identification module 1040 is used to determine whether the axle box to be identified is in a fault state according to the proportion of the normal vibration time domain signal and the proportion of the normal sound time domain signal.

[0164] In one embodiment, the identification module 1040 is further configured to:

[0165] Compare the normal vibration time domain signal ratio with the normal vibration ratio threshold to obtain a first comparison result; wherein the normal vibration ratio threshold is obtained based on the vibration time domain signal generated by the sample axle box under a fault state;

[0166] Compare the normal sound time domain signal ratio with the normal sound ratio threshold to obtain a second comparison result; wherein the normal sound ratio threshold is obtained based on the sound time domain signal generated by the sample axle box under the fault state;

[0167] According to the first comparison result and the second comparison result, it is determined whether the axle box to be identified is in a fault state.

[0168] In one embodiment, the identification module 1040 is further configured to:

[0169] If the proportion of the normal vibration time domain signal of the axle box to be identified is not greater than the normal vibration proportion threshold, and the proportion of the normal sound time domain signal of the axle box to be identified is not greater than the normal sound proportion threshold, it is determined that the axle box to be identified is in a fault state.

[0170] In one embodiment, the identification module 1040 is further configured to:

[0171] If the normal vibration time domain signal ratio is not greater than the normal vibration ratio threshold, and the normal sound time domain signal ratio is greater than the normal sound ratio threshold, determining whether the duration during which the normal vibration time domain signal ratio is not greater than the normal vibration ratio threshold exceeds a first preset duration;

[0172] If exceeded, it is determined that the axle box to be identified is in a fault state.

[0173] In one embodiment, the identification module 1040 is further configured to:

[0174] If the normal vibration time domain signal ratio is greater than the normal vibration ratio threshold, and the normal sound time domain signal ratio is not greater than the normal sound ratio threshold, determining whether the duration of the normal sound time domain signal ratio being not greater than the normal sound ratio threshold exceeds a second preset duration;

[0175] If exceeded, it is determined that the axle box to be identified is in a fault state.

[0176] In one embodiment, the device further comprises:

[0177] A threshold acquisition module is used to obtain sample vibration data when the sample axle box is in a non-fault state, wherein the sample vibration data includes multiple sample vibration time domain signals; calculate the average of the amplitudes of the sample vibration time domain signals in the sample vibration data as a vibration reference value; and determine the first amplitude threshold based on the vibration reference value.

[0178] In one embodiment, the threshold acquisition module is used to obtain sample sound data when the sample axle box is in a non-fault state, wherein the sample sound data includes multiple sample sound time domain signals; calculate the average of the amplitudes of the sample sound time domain signals in the sample sound data as the sound reference value; and determine the second amplitude threshold based on the sound reference value.

[0179] In one embodiment, the threshold acquisition module is used to obtain N groups of fault vibration data when the sample axle box is in a fault state; wherein N is an integer greater than 1; obtain the proportion of N normal vibration time domain signals of the N groups of fault vibration data; and determine the normal vibration proportion threshold value based on the proportion of the N normal vibration time domain signals.

[0180] In one embodiment, the threshold acquisition module is used to obtain M groups of fault sound data when the sample axle box is in a fault state; wherein M is an integer greater than 1; obtain the proportions of M normal sound time domain signals of the M groups of fault sound data; and determine the normal sound proportion threshold value based on the proportions of the M normal sound time domain signals.

[0181] The implementation process of the functions and effects of each module in the above-mentioned device is specifically described in the implementation process of the corresponding steps in the above-mentioned axle box fault identification method, and will not be repeated here.

[0182] Fig.11 Schematic diagram of the application scenario of the axle box fault identification method provided in the embodiment of the present application. Fig.11As shown, the application scenario includes a client 20, a client 30 and a server 40; the client 20 may be a vibration collection device installed on the axle box to be identified, for collecting vibration data of the axle box; the client 30 may be a sound collection device installed on the axle box to be identified, for collecting sound data of the axle box; the server 40 may be a host, a server, a server cluster or a cloud computing center, which may obtain the vibration data collected by the client 20, obtain the sound data collected by the client 30, and identify whether the axle box is faulty based on the vibration data and the sound data.

[0183] like Fig.12 As shown, this embodiment provides an electronic device 1, including: at least one processor 11 and a memory 12, Fig.12 A processor 11 is taken as an example. The processor 11 and the memory 12 are connected via a bus 10. The memory 12 stores instructions that can be executed by the processor 11. The instructions are executed by the processor 11 so that the electronic device 1 can execute all or part of the process of the method in the following embodiment. In one embodiment, the electronic device 1 can be the above-mentioned server 40, which is used to execute the axle box fault identification method.

[0184] The memory 12 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable red-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, disk or optical disk.

[0185] The present application also provides a computer-readable storage medium, which stores a computer program. The computer program can be executed by the processor 11 to complete the axle box fault identification method provided in the present application.

[0186] In several embodiments provided in the present application, the disclosed devices and methods may also be implemented in other ways. The device embodiments described above are merely schematic, for example, the flowcharts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the devices, methods and computer program products according to the multiple embodiments of the present application. In this regard, each box in the flowchart or block diagram may represent a module, a program segment or a part of a code, and a module, a program segment or a part of a code contains one or more executable instructions for implementing a specified logical function. In some alternative implementations, the functions marked in the box may also occur in an order different from that marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they may sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or the flowchart, and the combination of boxes in the block diagram and / or the flowchart, can be implemented with a dedicated hardware-based system that performs a specified function or action, or can be implemented with a combination of dedicated hardware and computer instructions.

[0187] In addition, the functional modules in the various embodiments of the present application may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.

[0188] If the function is implemented in the form of a software function module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the various embodiments 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.

Claims

1. A method for identifying axle box fault, characterized in that: include: Acquire vibration data and sound data generated by the axle box to be identified in the same time period; wherein the axle box to be identified is a main roller axle box in a multi-wire cutting machine; Determine the proportion of normal vibration time-domain signals according to the amplitude of each vibration time-domain signal in the vibration data and a first amplitude threshold; wherein the first amplitude threshold is obtained according to the vibration time-domain signal generated by the sample axle box in a non-fault state; Determine the proportion of normal sound time domain signals according to the amplitude of each sound time domain signal in the sound data and a second amplitude threshold; wherein the second amplitude threshold is obtained according to the sound time domain signal generated by the sample axle box in a non-fault state; Whether the axle box to be identified is in a fault state is determined according to the proportion of the normal vibration time domain signal and the proportion of the normal sound time domain signal.

2. The method according to claim 1, characterized in that The determining whether the axle box to be identified is in a fault state according to the proportion of the normal vibration time domain signal and the proportion of the normal sound time domain signal comprises: Compare the normal vibration time domain signal ratio with the normal vibration ratio threshold to obtain a first comparison result; wherein the normal vibration ratio threshold is obtained based on the vibration time domain signal generated by the sample axle box under the fault state; Compare the normal sound time domain signal ratio with the normal sound ratio threshold to obtain a second comparison result; wherein the normal sound ratio threshold is obtained based on the sound time domain signal generated by the sample axle box under the fault state; According to the first comparison result and the second comparison result, it is determined whether the axle box to be identified is in a fault state.

3. The method according to claim 2, characterized in that The step of determining whether the axle box to be identified is in a fault state according to the first comparison result and the second comparison result includes: If the proportion of the normal vibration time domain signal of the axle box to be identified is not greater than the normal vibration proportion threshold, and the proportion of the normal sound time domain signal of the axle box to be identified is not greater than the normal sound proportion threshold, it is determined that the axle box to be identified is in a fault state.

4. The method according to claim 2, characterized in that: The determining whether the axle box to be identified is in a fault state according to the proportion of the normal vibration time domain signal and the proportion of the normal sound time domain signal comprises: If the normal vibration time domain signal ratio is not greater than the normal vibration ratio threshold, and the normal sound time domain signal ratio is greater than the normal sound ratio threshold, determining whether the duration during which the normal vibration time domain signal ratio is not greater than the normal vibration ratio threshold exceeds a first preset duration; If exceeded, it is determined that the axle box to be identified is in a fault state.

5. The method according to claim 2, characterized in that: The determining whether the axle box to be identified is in a fault state according to the proportion of the normal vibration time domain signal and the proportion of the normal sound time domain signal comprises: If the normal vibration time domain signal ratio is greater than the normal vibration ratio threshold, and the normal sound time domain signal ratio is not greater than the normal sound ratio threshold, determining whether the duration of the normal sound time domain signal ratio being not greater than the normal sound ratio threshold exceeds a second preset duration; If exceeded, it is determined that the axle box to be identified is in a fault state.

6. The method according to any one of claims 1 to 5, characterized in that: The step of obtaining the first amplitude threshold comprises: 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; Calculating the mean value of the amplitude of the sample vibration time domain signal in the sample vibration data as the vibration reference value; Based on the vibration reference value, the first amplitude threshold is determined.

7. The method according to any one of claims 1 to 5, characterized in that: The step of obtaining the second amplitude threshold comprises: Acquiring sample sound data when the sample axle box is in a non-fault state, wherein the sample sound data includes a plurality of sample sound time domain signals; Calculating the mean of the amplitudes of the sample sound time domain signals in the sample sound data as the sound reference value; Based on the sound reference value, the second amplitude threshold is determined.

8. The method according to any one of claims 2 to 5, characterized in that: The step of obtaining the normal vibration ratio threshold comprises: Acquire N groups of fault vibration data when the sample axle box is in a fault state; wherein N is an integer greater than 1; Obtaining the proportion of N normal vibration time domain signals of the N groups of fault vibration data; The normal vibration ratio threshold is determined according to the ratios of the N normal vibration time domain signals.

9. The method according to any one of claims 2 to 5, characterized in that: The step of obtaining the normal sound proportion threshold comprises: Acquire M groups of fault sound data when the sample axle box is in a fault state; wherein M is an integer greater than 1; Obtaining the proportion of M normal sound time domain signals of the M groups of fault sound data; The normal sound proportion threshold is determined according to the proportions of the M normal sound time-domain signals.

10. An axle box fault identification device, characterized in that: include: A collection module, used to obtain vibration data and sound data generated by the axle box to be identified; wherein the axle box to be identified is a main roller axle box in a multi-wire cutting machine; A first determination module, used to determine the proportion of normal vibration time-domain signals according to the amplitude of each vibration time-domain signal in the vibration data and a first amplitude threshold; wherein the first amplitude threshold is obtained according to the vibration time-domain signal generated by the sample axle box in a non-fault state; A second determination module is used to determine the proportion of normal sound time domain signals according to the amplitude of each sound time domain signal in the sound data and a second amplitude threshold; wherein the second amplitude threshold is obtained according to the sound time domain signal generated by the sample axle box in a non-fault state; The identification module is used to determine whether the axle box to be identified is in a fault state according to the proportion of the normal vibration time domain signal and the proportion of the normal sound time domain signal.

11. An electronic device, characterized in that: The electronic device comprises: processor; a memory for storing processor-executable instructions; Wherein, the processor is configured to execute the axle box fault identification method described in any one of claims 1-9.

12. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, and the computer program can be executed by a processor to complete the axle box fault identification method described in any one of claims 1-9.

Images