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

Abstract

The invention provides a vibration-based axle box fault detection method and device, electronic equipment and a storage medium, and the method comprises the steps that target vibration data of a to-be-detected axle box is obtained, the target vibration data comprises a plurality of vibration time domain signals, and the to-be-detected axle box is a main roller shaft box in a multi-wire cutting machine; the amplitude of each vibration time domain signal in the target vibration data is compared with an amplitude threshold value, a normal signal proportion is determined, and the amplitude threshold value is obtained according to a vibration time domain signal generated by vibration of a sample axle box in a non-fault state; whether the normal signal proportion reaches a set proportion or not is judged, if not, it is determined that the axle box to be detected is in a fault state, and the set proportion is determined according to the normal sample signal proportion of the sample axle box in the fault state. According to the scheme, fault detection is automatically realized based on the vibration condition of the axle box, so that 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 a vibration-based axle box fault detection method and device, electronic equipment, and computer-readable storage medium. Background Art

[0002] In the field of multi-wire cutting, the cutting wires are often arranged spirally on multiple main rollers at a certain 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 a vibration-based axle box fault detection method and device, electronic equipment, and computer-readable storage medium, which are used to automatically realize fault detection based on the vibration conditions of the axle box, thereby improving the accuracy and timeliness of fault detection.

[0005] On the one hand, the present application provides a method for detecting axle box faults based on vibration, comprising:

[0006] Acquire target vibration data of an axle box to be detected, wherein the target vibration data includes a plurality of vibration time domain signals, and the axle box to be detected is a main roller axle box in a multi-wire cutting machine;

[0007] Comparing the amplitude of each vibration time domain signal in the target vibration data with the amplitude threshold value to determine the normal signal ratio, wherein the amplitude threshold value is obtained based on the vibration time domain signal generated by the sample axle box vibration in a non-fault state;

[0008] Determine whether the normal signal ratio reaches a set ratio. If not, determine that the axle box to be detected is in a fault state, wherein the set ratio is determined based on the normal sample signal ratio of the sample axle box in the fault state.

[0009] In one embodiment, the step of obtaining the amplitude threshold value includes:

[0010] Acquire multiple groups of sample target vibration data when the sample axle box is in a non-fault state;

[0011] Calculating the mean of the amplitudes of the vibration time domain signals in the plurality of groups of sample target vibration data as an amplitude reference value;

[0012] The amplitude threshold value is determined according to the amplitude reference value.

[0013] In one embodiment, the step of obtaining the set ratio includes:

[0014] Acquire N groups of sample fault vibration data when the sample axle box is in a fault state, wherein N is an integer greater than 1;

[0015] Obtaining the proportion of N normal sample signals of the N groups of sample fault vibration data;

[0016] The set ratio is determined according to the proportion of the N normal sample signals.

[0017] In one embodiment, determining the amplitude threshold value according to the amplitude reference value includes:

[0018] The amplitude threshold value is determined according to the amplitude reference value and a preset adjustment coefficient, wherein the preset adjustment coefficient has a value range of 1.2 to 1.8.

[0019] In one embodiment, comparing the amplitude of each vibration time domain signal in the target vibration data with the amplitude threshold value to determine the normal signal ratio includes:

[0020] Comparing the amplitude of each vibration time domain signal in the target vibration data with the amplitude threshold value, obtaining the number of normal vibration time domain signals in the target vibration data, wherein if the amplitude of any vibration time domain signal is less than the amplitude threshold value, the vibration time domain signal is determined to be a normal vibration time domain signal;

[0021] The normal signal ratio is determined based on the number of normal vibration time-domain signals in the target vibration data and the total amount of vibration time-domain signals in the target vibration data.

[0022] In one embodiment, comparing the amplitude of each vibration time domain signal in the target vibration data with the amplitude threshold value to determine the normal signal ratio includes:

[0023] Comparing the amplitude of each vibration time domain signal in the target vibration data with the amplitude threshold value, obtaining the number of abnormal vibration time domain signals in the target vibration data, wherein if the amplitude of any vibration time domain signal is not less than the amplitude threshold value, the vibration time domain signal is determined to be an abnormal vibration time domain signal;

[0024] The normal signal ratio is determined based on the number of abnormal vibration time-domain signals in the target vibration data and the total amount of vibration time-domain signals in the target vibration data.

[0025] In one embodiment, obtaining target vibration data of the axle box to be tested includes:

[0026] Collecting actual vibration data of the axle box to be tested;

[0027] Based on a preset noise reduction algorithm, the actual vibration data is subjected to noise reduction processing to obtain the target vibration data; wherein the noise reduction algorithm is a singular value decomposition or a wavelet threshold noise reduction method.

[0028] In one embodiment, the collecting of actual vibration data of the axle box to be tested includes:

[0029] All vibration time domain signals generated by the axle box to be tested for cutting a silicon rod are collected to form the actual vibration data.

[0030] In addition, the present application provides a vibration-based axle box fault detection device, comprising:

[0031] An acquisition module, used for acquiring target vibration data of an axle box to be detected, wherein the target vibration data includes a plurality of vibration time domain signals, and the axle box to be detected is a main roller axle box in a multi-wire cutting machine;

[0032] A determination module, used to compare the amplitude of each vibration time domain signal in the target vibration data with the amplitude threshold value to determine the normal signal ratio, wherein the amplitude threshold value is obtained based on the vibration time domain signal generated by the sample axle box vibration in a non-fault state;

[0033] The judgment module is used to judge whether the normal signal ratio reaches a set ratio. If not, it is determined that the axle box to be detected is in a fault state, wherein the set ratio is determined based on the normal sample signal ratio of the sample axle box in the fault state.

[0034] Furthermore, the present application provides an electronic device, the electronic device comprising:

[0035] processor;

[0036] a memory for storing processor-executable instructions;

[0037] Wherein, the processor is configured to execute the above-mentioned vibration-based axle box fault detection method.

[0038] 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 vibration-based axle box fault detection method.

[0039] The present application scheme can use the vibration time domain signals collected during the operation of the axle box. By comparing the amplitudes and amplitude threshold values ​​of each vibration time domain signal, the number of normal vibration time domain signals can be obtained, and then based on the number and the total amount of vibration time domain signals, the proportion of normal signals can be determined, and the proportion of normal signals can be compared with the set proportion. When the proportion of normal signals does not reach the set proportion, it can be determined that abnormalities exist in most cases during the operation of the axle box, indicating that the axle box is in a faulty state. Therefore, by performing automated fault detection on the axle box, the problem of low accuracy in manual detection due to excessive reliance on experience is avoided, and faulty axle boxes can be detected in a timely manner. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] 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.

[0041] Figure 1 A schematic flow chart of a method for detecting axle box faults based on vibration provided in one embodiment of the present application;

[0042] Figure 2 A schematic diagram of vibration data provided by an embodiment of the present application;

[0043] Figure 3 A schematic diagram of vibration data provided by another embodiment of the present application;

[0044] Figure 4 A schematic diagram of a flow chart of a method for obtaining an amplitude threshold value provided in an embodiment of the present application;

[0045] Figure 5 A schematic diagram of a flow chart of a method for obtaining a set ratio provided in an embodiment of the present application;

[0046] Figure 6 A block diagram of an axle box fault detection device based on vibration provided in one embodiment of the present application;

[0047] Figure 7 A schematic diagram of an application scenario of a vibration-based axle box fault detection method provided in an embodiment of the present application;

[0048] Figure 8 A schematic diagram of the structure of an electronic device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0049] 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.

[0050] 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.

[0051] See also Figure 1 , is a flow chart of a vibration-based axle box fault detection method provided in an embodiment of the present application, such as Figure 1 As shown, the method may include the following steps 110 to 130.

[0052] Step 110: Acquire target vibration data of the axle box to be detected, wherein the target vibration data includes a plurality of vibration time domain signals, and the axle box to be detected is a main roller axle box in a multi-wire cutting machine.

[0053] The present application scheme can detect faults of the axle boxes on the multi-wire cutting machine. For each axle box on the multi-wire cutting machine that needs to be detected for faults, corresponding vibration time domain signal acquisition equipment can be installed respectively. For example, the vibration time domain signal acquisition equipment can be a vibration acceleration sensor and an eddy current sensor.

[0054] The vibration frequency of the axle box is about 1000 Hz. When sampling, the sampling frequency must follow Shannon's sampling theorem. The sampling theorem is: the sampling frequency f s 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 satisfy 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 lower accuracy of the sampled data. When the frequency is higher than 2 times the signal frequency, the accuracy of the collected data is higher due to the higher matching degree between the collected data and the frequency.

[0055] 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 4 shown.

[0056] 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 5 shown.

[0057] During the operation of the multi-wire cutting machine equipped with the axle box to be tested, the vibration time domain signal acquisition equipment corresponding to the axle box to be tested can be used to continuously collect vibration time domain signals, and actual vibration data can be constructed based on the collected multiple vibration time domain signals, and the target vibration data can be determined using the actual vibration data.

[0058] In one embodiment, when the operation time of the multi-wire cutting machine reaches a preset time threshold, the actual vibration data consisting of multiple vibration time domain signals collected during this period can be used for fault detection. Here, the preset time threshold can be configured as needed. For example, the preset time threshold can be 20 minutes, 30 minutes, 1 hour, etc.

[0059] In one embodiment, after the multi-wire saw completes one cut, all vibration time domain signals generated by the axle box to be detected for cutting one silicon rod can be collected to form actual vibration data for fault detection. Here, one cut refers to the cutting process of the multi-wire saw cutting one silicon rod into silicon wafers.

[0060] In this case, since the actual vibration data includes all the vibration time domain signals generated by cutting a silicon rod, the actual vibration data can fully characterize the overall operation of the axle box to be tested during the process of cutting a silicon rod. Therefore, compared with collecting vibration time domain signals for a period of time to form actual vibration data, the actual vibration data generated by cutting a silicon rod can most accurately determine whether the axle box to be tested has a fault.

[0061] In one embodiment, the collected actual vibration data may be directly used as the target vibration data.

[0062] In one embodiment, the collected multiple vibration time domain signals can be used to form actual vibration data, and the actual vibration data can be subjected to noise reduction processing based on a preset noise reduction algorithm to obtain target vibration data. The noise reduction algorithm can be a singular value decomposition (SVD) or a wavelet threshold noise reduction method.

[0063] The equipment equipped with axle boxes has complex components and operating conditions. Factors such as load changes and the mutual influence of components will cause a lot of noise data in the actual vibration data collected. If the noise data is not considered and fault detection is performed directly based on the actual vibration data, the subsequent detection accuracy will be seriously affected. By performing noise reduction processing on the actual vibration data and optimizing the signal-to-noise ratio, the accuracy of fault detection can be effectively improved.

[0064] Step 120: Compare the amplitude of each vibration time domain signal in the target vibration data with the amplitude threshold value to determine the normal signal ratio, wherein the amplitude threshold value is obtained based on the vibration time domain signal generated by the sample axle box vibration in a non-fault state.

[0065] The amplitude threshold value is used to screen the normal vibration time domain signal. For any axle box to be detected, a corresponding amplitude threshold value can be set for it. In one embodiment, the amplitude threshold value can be obtained based on the vibration time domain signal generated by the vibration of the sample axle box in a non-fault state. Here, the sample axle box can be the axle box to be detected in a non-fault state for collecting the vibration time domain signal to generate the amplitude threshold value.

[0066] In one embodiment, the amplitude of each vibration time domain signal in the target vibration data is compared with the amplitude threshold value. If the amplitude of any vibration time domain signal is less than the amplitude threshold value, it can be determined that the vibration time domain signal is a normal vibration time domain signal. After comparing the amplitudes of all vibration time domain signals in the target vibration data with the amplitude threshold value one by one, the number of all normal vibration time domain signals can be counted. After obtaining the number of normal vibration time domain signals, the proportion of normal signals can be determined based on the number of normal vibration time domain signals in the target vibration data and the total amount of vibration time domain signals in the target vibration data.

[0067] Exemplarily, the normal signal ratio can be expressed by the following formula (1):

[0068] L=T1 / S (1)

[0069] Among them, L is the proportion of normal signals; T1 is the number of normal vibration time domain signals; S is the total amount of vibration time domain signals in the target vibration data.

[0070] In one embodiment, the amplitude of each vibration time domain signal in the target vibration data is compared with the amplitude threshold value. If the amplitude of any vibration time domain signal is not less than the amplitude threshold value, the vibration time domain signal can be determined to be an abnormal vibration time domain signal. After comparing the amplitudes of all vibration time domain signals in the target vibration data with the amplitude threshold value one by one, the number of all abnormal vibration time domain signals can be counted. After obtaining the number of abnormal vibration time domain signals, the proportion of normal signals can be determined based on the number of abnormal vibration time domain signals in the target vibration data and the total amount of vibration time domain signals in the target vibration data.

[0071] Exemplarily, the normal signal ratio can be expressed by the following formula (2):

[0072] L=(S-T2) / S(2)

[0073] Among them, L is the proportion of normal signals; T2 is the number of abnormal vibration time domain signals; S is the total amount of vibration time domain signals in the target vibration data.

[0074] Step 130: Determine whether the normal signal ratio reaches a set ratio. If not, determine that the axle box to be detected is in a fault state, wherein the set ratio is determined based on the normal sample signal ratio of the sample axle box in the fault state.

[0075] After obtaining the normal signal ratio, it can be determined whether the normal signal ratio reaches the set ratio. Here, the set ratio is used to distinguish whether the axle box is faulty. In one case, the normal signal ratio corresponding to the axle box to be detected reaches the set ratio, which means that from the vibration time domain signal, the axle box to be detected has no abnormalities in most cases during operation. At this time, it can be determined that the axle box to be detected is in a non-fault state. In another case, the normal signal ratio corresponding to the axle box to be detected does not reach the set ratio, which means that from the vibration time domain signal, the axle box to be detected has no abnormalities in most cases during operation. It can be determined that the axle box to be detected has a fault and is in a faulty state. If the axle box to be detected has a fault, an alarm message can be output so that the staff can repair the axle box in the faulty state in time.

[0076] Through the above measures, with the help of the vibration time domain signals collected during the operation of the axle box, by comparing the amplitudes and amplitude threshold values ​​of each vibration time domain signal, the number of normal vibration time domain signals can be obtained, and then based on the number and the total amount of vibration time domain signals, the proportion of normal signals can be determined, and the proportion of normal signals can be compared with the set proportion. When the proportion of normal signals does not reach the set proportion, it can be determined that abnormalities exist in most cases during the operation of the axle box, indicating that the axle box is in a faulty state; therefore, by performing automated fault detection on the axle box, the problem of low accuracy in manual detection due to excessive reliance on experience is avoided, and faulty axle boxes can be detected in a timely manner.

[0077] In one embodiment, before executing the above step 120, an amplitude threshold value may be determined for the axle box to be detected. Figure 4 , is a flow chart of a method for obtaining an amplitude threshold value provided in an embodiment of the present application, such as Figure 4 As shown, the method may include the following steps 410 to 430.

[0078] Step 410: Acquire multiple groups of sample target vibration data when the sample axle box is in a non-fault state.

[0079] When the multi-wire cutting machine is running and the sample axle box is in a non-fault state, the vibration time domain signal of the sample axle box can be collected through the vibration time domain signal collection equipment. All vibration time domain signals collected by the multi-wire cutting machine for each completed cut constitute a set of sample actual vibration data, and then the sample target vibration data is determined based on the set of sample actual vibration data. As shown above, a set of sample actual vibration data can be directly determined as sample target vibration data, or a set of sample actual vibration data can be subjected to noise reduction processing to obtain a set of sample target vibration data. After the multi-wire cutting machine completes multiple cuts, multiple sets of sample target vibration data can be obtained.

[0080] Step 420: Calculate the average of the amplitudes of the vibration time domain signals in the multiple groups of sample target vibration data as the amplitude reference value.

[0081] After obtaining multiple groups of sample target vibration data, the mean of the amplitudes may be calculated for multiple vibration time domain signals in the multiple groups of sample target vibration data, and the calculated mean may be used as the amplitude reference value.

[0082] Step 430: Determine the amplitude threshold value according to the amplitude reference value.

[0083] After obtaining the amplitude reference value, the amplitude reference value can be added to the set constant to obtain the amplitude threshold value. Here, the set constant can be configured based on experience, representing the offset between the maximum amplitude allowed by the axle box in a non-fault state and the amplitude mean.

[0084] Through the above measures, for each axle box that needs to be tested on the multi-wire cutting machine, the corresponding amplitude threshold value can be generated for the axle box by collecting its sample target vibration data in a non-fault state.

[0085] In one embodiment, after obtaining the amplitude reference value, the amplitude threshold value can be determined according to the amplitude reference value and the preset adjustment coefficient. The preset adjustment coefficient can be configured as needed. Exemplarily, the preset adjustment coefficient can be a value between 1.2 and 1.8, for example, 1.2, 1.5, 1.6 and 1.8.

[0086] In one embodiment, the amplitude reference value may be multiplied by a preset adjustment coefficient to obtain an amplitude threshold value. Alternatively, the amplitude reference value may be used as a base and the preset adjustment coefficient may be used as an exponent to calculate the amplitude threshold value. Preferably, the product of the amplitude reference value and the preset adjustment coefficient is used as the amplitude threshold value.

[0087] Through this measure, the amplitude reference value is amplified by a preset adjustment coefficient to obtain an amplitude threshold value, which includes the amplitude reference value and the offset between the maximum amplitude allowed by the axle box in a non-fault state and the amplitude reference value. Compared with amplifying the amplitude reference value by setting a constant to obtain the amplitude threshold value, the amplitude threshold value amplified by the preset adjustment coefficient can characterize the allowed offset in terms of proportion, which is more helpful for subsequent screening of normal vibration time domain signals.

[0088] In one embodiment, before executing the above step 130, a set ratio may be determined for the axle box to be tested. Figure 5 , is a flow chart of a method for obtaining a set ratio provided in an embodiment of the present application, such as Figure 5 As shown, the method may include the following steps 510 to 530.

[0089] Step 510: Acquire N groups of sample fault vibration data when the sample axle box is in a fault state, where N is an integer greater than 1.

[0090] When the multi-wire cutting machine is running and the sample shaft box is in a faulty state, the vibration time domain signal can be collected for the sample shaft box through the vibration time domain signal collection equipment. All vibration time domain signals collected by the multi-wire cutting machine after completing one operation constitute a set of sample actual vibration data, and then the sample fault vibration data is determined based on the set of sample actual vibration data. After the multi-wire cutting machine runs N times, N sets of sample fault vibration data can be obtained. Here, the multi-wire cutting machine completing one operation can be the completion of one cut, or it can be the process from the beginning to the shutdown due to shaft box failure in the process of cutting a silicon rod.

[0091] Step 520: Obtain the proportion of N normal sample signals in N groups of sample fault vibration data.

[0092] For each set of sample fault vibration data, the amplitude of the vibration time domain signal in the set of sample fault vibration data is compared with the amplitude threshold value to determine the normal vibration time domain signal. The number of normal vibration time domain signals is divided by the total amount of vibration time domain signals in the sample fault vibration data to obtain the proportion of normal signals corresponding to the sample fault vibration data. With N sets of sample fault vibration data, the proportion of N normal signals can be calculated.

[0093] Step 530: Determine a set ratio according to the proportion of N normal sample signals.

[0094] In one embodiment, after obtaining the proportions of N normal signals, the average of the proportions of N normal signals may be calculated as the set proportion. Here, the calculated set proportion is usually between 20% and 30%, and preferably, the set proportion may be 28%.

[0095] In one embodiment, after obtaining N groups of normal signal proportions, a maximum value may be selected from the N normal signal proportions, and the maximum value is used as the set proportion.

[0096] Through the above measures, since the multiple groups of sample fault vibration data reflected by the sample axle box under the fault state can characterize the vibration situation under the fault state, after obtaining the multiple groups of sample fault vibration data under the fault state, by converting the normal signal proportion corresponding to each group of sample fault vibration data, the proportion of normal vibration time domain signals under the fault state can be determined; further, using the average of the normal signal proportions corresponding to the multiple groups of sample fault vibration data as the set ratio can reduce errors and select a more reliable set ratio; and using the maximum value of the normal signal proportions corresponding to the multiple groups of sample fault vibration data as the set ratio can increase the inspection threshold of the non-fault state, ensuring that the smallest fault can also be screened out later.

[0097] Figure 6 is a block diagram of a vibration-based axle box fault detection device according to an embodiment of the present invention, such as Figure 6 As shown, the device may include:

[0098] An acquisition module 610 is used to acquire target vibration data of an axle box to be detected, wherein the target vibration data includes a plurality of vibration time domain signals, and the axle box to be detected is a main roller axle box in a multi-wire cutting machine;

[0099] A determination module 620 is used to compare the amplitude of each vibration time domain signal in the target vibration data with the amplitude threshold value to determine the normal signal ratio, wherein the amplitude threshold value is obtained based on the vibration time domain signal generated by the sample axle box vibration in a non-fault state;

[0100] The judgment module 630 is used to judge whether the normal signal ratio reaches the set ratio. If not, it is determined that the axle box to be detected is in a fault state, wherein the set ratio is determined based on the normal sample signal ratio of the sample axle box in the fault state.

[0101] In one embodiment, the device further comprises:

[0102] The acquisition module 610 is further used to acquire multiple groups of sample target vibration data when the sample axle box is in a non-fault state;

[0103] A calculation module 640 is used to calculate the average of the amplitudes of the vibration time domain signals in the plurality of groups of sample target vibration data as an amplitude reference value;

[0104] The determination module 620 is further configured to determine the amplitude threshold value according to the amplitude reference value.

[0105] In one embodiment, the device further comprises:

[0106] The acquisition module 610 is further used to acquire N groups of sample fault vibration data when the sample axle box is in a fault state, wherein N is an integer greater than 1;

[0107] The determination module 620 is further used to obtain the proportion of N normal sample signals in the N groups of sample fault vibration data; and determine the set ratio according to the proportion of the N normal sample signals.

[0108] In one embodiment, the determination module 620 is further configured to determine the amplitude threshold value according to the amplitude reference value and a preset adjustment coefficient, wherein the preset adjustment coefficient has a value range of 1.2 to 1.8.

[0109] In one embodiment, the determination module 620 is further configured to:

[0110] Comparing the amplitude of each vibration time domain signal in the target vibration data with the amplitude threshold value, obtaining the number of normal vibration time domain signals in the target vibration data, wherein if the amplitude of any vibration time domain signal is less than the amplitude threshold value, the vibration time domain signal is determined to be a normal vibration time domain signal;

[0111] The normal signal ratio is determined based on the number of normal vibration time-domain signals in the target vibration data and the total amount of vibration time-domain signals in the target vibration data.

[0112] In one embodiment, the determination module 620 is further configured to:

[0113] Comparing the amplitude of each vibration time domain signal in the target vibration data with the amplitude threshold value, obtaining the number of abnormal vibration time domain signals in the target vibration data, wherein if the amplitude of any vibration time domain signal is not less than the amplitude threshold value, the vibration time domain signal is determined to be an abnormal vibration time domain signal;

[0114] The normal signal ratio is determined based on the number of abnormal vibration time-domain signals in the target vibration data and the total amount of vibration time-domain signals in the target vibration data.

[0115] In one embodiment, the acquisition module 610 is further configured to:

[0116] Collecting actual vibration data of the axle box to be tested;

[0117] Based on a preset noise reduction algorithm, the actual vibration data is subjected to noise reduction processing to obtain the target vibration data; wherein the noise reduction algorithm is a singular value decomposition or a wavelet threshold noise reduction method.

[0118] In one embodiment, the acquisition module 610 is further configured to:

[0119] All vibration time domain signals generated by the axle box to be tested for cutting a silicon rod are collected to form the actual vibration data.

[0120] 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 vibration-based axle box fault detection method, which will not be repeated here.

[0121] Figure 7 Schematic diagram of an application scenario of the vibration-based axle box fault detection method provided in an embodiment of the present application. Figure 7 As shown, the application scenario includes a client 20 and a server 30; the client 20 can be a vibration time domain signal acquisition equipment installed on the axle box, used to collect target vibration data of the axle box; the server 30 can be a host, a server, a server cluster or a cloud computing center, which can obtain the target vibration data collected by the client 20 and detect whether there is a fault in the axle box based on the target vibration data.

[0122] like Figure 8 As shown, this embodiment provides an electronic device 1, including: at least one processor 11 and a memory 12, Figure 8 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 above embodiment. In one embodiment, the electronic device 1 can be the above-mentioned server 30, which is used to execute the vibration-based axle box fault detection method.

[0123] 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.

[0124] 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 vibration-based axle box fault detection method provided by the present application.

[0125] 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.

[0126] 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.

[0127] 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 vibration-based axle box fault detection method, characterized in that: include: Acquire target vibration data of an axle box to be detected, wherein the target vibration data includes a plurality of vibration time domain signals, and the axle box to be detected is a main roller axle box in a multi-wire cutting machine; Comparing the amplitude of each vibration time domain signal in the target vibration data with the amplitude threshold value to determine the normal signal ratio, wherein the amplitude threshold value is obtained based on the vibration time domain signal generated by the sample axle box vibration in a non-fault state; Determine whether the normal signal ratio reaches a set ratio. If not, determine that the axle box to be detected is in a fault state, wherein the set ratio is determined based on the normal sample signal ratio of the sample axle box in the fault state.

2. The method according to claim 1, characterized in that: The step of obtaining the amplitude threshold value comprises: Acquire multiple groups of sample target vibration data when the sample axle box is in a non-fault state; Calculating the mean of the amplitudes of the vibration time domain signals in the plurality of groups of sample target vibration data as an amplitude reference value; The amplitude threshold value is determined according to the amplitude reference value.

3. The method according to claim 2, characterized in that The step of obtaining the set ratio includes: Acquire N groups of sample 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 sample signals of the N groups of sample fault vibration data; The set ratio is determined according to the proportion of the N normal sample signals.

4. The method according to claim 2, characterized in that: The step of determining the amplitude threshold value according to the amplitude reference value comprises: The amplitude threshold value is determined according to the amplitude reference value and a preset adjustment coefficient, wherein the preset adjustment coefficient has a value range of 1.2 to 1.

8.

5. The method according to claim 2 or 3, characterized in that: The comparing the amplitude of each vibration time domain signal in the target vibration data with the amplitude threshold value to determine the proportion of normal signals includes: Comparing the amplitude of each vibration time domain signal in the target vibration data with the amplitude threshold value, obtaining the number of normal vibration time domain signals in the target vibration data, wherein if the amplitude of any vibration time domain signal is less than the amplitude threshold value, the vibration time domain signal is determined to be a normal vibration time domain signal; The normal signal ratio is determined based on the number of normal vibration time-domain signals in the target vibration data and the total amount of vibration time-domain signals in the target vibration data.

6. The method according to claim 2 or 3, characterized in that: The comparing the amplitude of each vibration time domain signal in the target vibration data with the amplitude threshold value to determine the proportion of normal signals includes: Comparing the amplitude of each vibration time domain signal in the target vibration data with the amplitude threshold value, obtaining the number of abnormal vibration time domain signals in the target vibration data, wherein if the amplitude of any vibration time domain signal is not less than the amplitude threshold value, the vibration time domain signal is determined to be an abnormal vibration time domain signal; The normal signal ratio is determined based on the number of abnormal vibration time-domain signals in the target vibration data and the total amount of vibration time-domain signals in the target vibration data.

7. The method according to claim 1, characterized in that The step of obtaining target vibration data of the axle box to be tested includes: Collecting actual vibration data of the axle box to be tested; Based on a preset noise reduction algorithm, the actual vibration data is subjected to noise reduction processing to obtain the target vibration data; wherein the noise reduction algorithm is a singular value decomposition or a wavelet threshold noise reduction method.

8. The method according to claim 7, characterized in that The collecting of actual vibration data of the axle box to be tested comprises: All vibration time domain signals generated by the axle box to be tested for cutting a silicon rod are collected to form the actual vibration data.

9. A vibration-based axle box fault detection device, characterized in that: include: An acquisition module, used for acquiring target vibration data of an axle box to be detected, wherein the target vibration data includes a plurality of vibration time domain signals, and the axle box to be detected is a main roller axle box in a multi-wire cutting machine; A determination module, used to compare the amplitude of each vibration time domain signal in the target vibration data with the amplitude threshold value to determine the normal signal ratio, wherein the amplitude threshold value is obtained based on the vibration time domain signal generated by the sample axle box vibration in a non-fault state; The judgment module is used to judge whether the normal signal ratio reaches a set ratio. If not, it is determined that the axle box to be detected is in a fault state, wherein the set ratio is determined based on the normal sample signal ratio of the sample axle box in the fault state.

10. 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 vibration-based axle box fault detection method according to any one of claims 1-8.

11. 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 vibration-based axle box fault detection method according to any one of claims 1-8.

Images