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

Abstract

The invention provides a sound-based axle box fault detection method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining a sound time domain signal set of a to-be-detected axle box in the cutting process of a current knife; each sound time domain signal in the sound time domain signal set is compared with a sound reference value, the normal sound ratio of the current cutter is determined, and the sound reference value is obtained according to sound time domain signals generated by a sample axle box in a non-fault state; the normal sound proportion is compared with a standard proportion, if the normal sound proportion does not reach the standard proportion, it is determined that the axle box to be detected is in a fault state, and the standard proportion is determined according to the normal sound proportion of a sample axle box in the fault state. According to the scheme, automatic fault detection is performed on the to-be-detected axle box according to the sound time domain signal generated by operation of the to-be-detected 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 sound-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 to be tested. Adjusting the spacing between the two main rollers is to adjust the spacing between the two pairs of front and rear axle boxes to be tested. In the process of driving the main roller to rotate by clicking, the axle box to be tested may fail due to factors such as excessive temperature or excessive load.

[0003] In the related art, the operator judges the fault of the axle box to be tested 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 sound-based axle box fault detection method and device, electronic device, and computer-readable storage medium, which are used to perform automated fault detection on the axle box to be tested based on the sound time domain signal generated by the operation of the axle box to be tested, thereby improving the accuracy and timeliness of fault detection.

[0005] In a first aspect, the present application provides a method for detecting axle box faults based on sound, comprising:

[0006] During the cutting process of the current knife, a sound time domain signal set of the axle box to be tested is obtained, wherein the sound time domain signal set includes multiple sound time domain signals, and the axle box to be tested is a main roller axle box in a multi-wire cutting machine;

[0007] Compare each sound time domain signal in the sound time domain signal set with a sound reference value to determine the normal sound ratio of the current knife, wherein the sound reference value is obtained based on the sound time domain signal generated by the sample axle box in a non-fault state;

[0008] The normal sound ratio is compared with the standard ratio. If the normal sound ratio does not reach the standard ratio, it is determined that the axle box to be tested is in a fault state, wherein the standard ratio is determined based on the normal sound ratio of the sample axle box in the fault state.

[0009] In one embodiment, the step of obtaining the sound reference value includes:

[0010] Acquire a multi-tool target sound time domain signal set when the sample axle box is in a non-fault state;

[0011] The sound reference value is obtained according to the amplitude mean of the multi-tool target sound time domain signal set.

[0012] In one embodiment, obtaining the sound reference value according to the amplitude mean of the multi-tool target sound time domain signal set includes:

[0013] The sound reference value is determined according to the amplitude mean and a preset coefficient, wherein the preset coefficient ranges from 1.2 to 1.5.

[0014] In one embodiment, the step of obtaining the standard ratio includes:

[0015] Collect a multi-tool fault sound time domain signal set when the sample axle box is in a fault state;

[0016] Determine the normal sound ratio of each knife according to the multi-knife fault sound time domain signal set;

[0017] According to the normal sound proportion of each knife, the average value of the normal sound proportion corresponding to the multi-knife fault sound time domain signal set is obtained;

[0018] The standard ratio is determined according to the average value of the normal sound ratio.

[0019] In one embodiment, comparing each sound time domain signal in the sound time domain signal set with the sound reference value to determine the normal sound proportion of the current knife includes:

[0020] Comparing each sound time domain signal in the sound time domain signal set with the sound reference value to obtain the number of normal sound time domain signals, wherein if the amplitude of any sound time domain signal compared is smaller than the sound reference value, the sound time domain signal is determined to be a normal sound time domain signal;

[0021] The normal sound ratio of the current knife is determined according to the number of normal sound time-domain signals and the total signal quantity included in the sound time-domain signal set.

[0022] In one embodiment, comparing each sound time domain signal in the sound time domain signal set with the sound reference value to determine the normal sound proportion of the current knife includes:

[0023] Comparing each sound time domain signal in the sound time domain signal set with the sound reference value to obtain the number of abnormal sound time domain signals, wherein if the amplitude of any sound time domain signal is not less than the sound reference value, the sound time domain signal is determined to be an abnormal sound time domain signal;

[0024] The normal sound ratio of the current knife is determined according to the number of abnormal sound time-domain signals and the total signal quantity included in the sound time-domain signal set.

[0025] In one embodiment, during the current cutting process of the knife, obtaining the sound time domain signal set of the axle box to be tested includes:

[0026] During the current cutting process of the knife, actual sound data of the axle box to be tested is obtained;

[0027] The actual sound data is subjected to denoising processing by using a preset denoising method to obtain the sound time domain signal set, wherein the preset denoising method includes a singular value decomposition method and a wavelet threshold denoising method.

[0028] In one embodiment, obtaining actual sound data of the axle box to be tested during the current cutting process of the knife includes:

[0029] During the cutting process of the current knife, all the sound time domain signals generated by the axle box to be tested when the current knife is completed are obtained to constitute the actual sound data.

[0030] In a second aspect, the present application also provides a sound-based axle box fault detection device, comprising:

[0031] An acquisition module, used for acquiring a sound time domain signal set of the axle box to be tested during the cutting process of the current knife, wherein the sound time domain signal set includes a plurality of sound time domain signals, and the axle box to be tested is a main roller axle box in a multi-wire cutting machine;

[0032] A comparison module, used to compare each sound time domain signal in the sound time domain signal set with a sound reference value to determine the normal sound ratio of the current knife; wherein the sound reference value is obtained based on the sound time domain signal generated by the sample axle box in a non-fault state;

[0033] A comparison module is used to compare the normal sound ratio with a standard ratio. If the normal sound ratio does not reach the standard ratio, it is determined that the axle box to be tested is in a fault state, wherein the standard ratio is determined based on the normal sound ratio of the sample axle box in the fault state.

[0034] In a third aspect, the present application further 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 sound-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 sound-based axle box fault detection method.

[0039] The present application scheme can construct a sound time domain signal based on the sound time domain signal generated during the operation of the axle box to be tested. By comparing the amplitude of each sound time domain signal in the sound time domain signal and the sound reference value, the number of normal sound time domain signals can be obtained, and then based on the number and the total amount of sound time domain signals in the sound time domain signal, the normal sound ratio can be determined. The normal sound ratio can characterize the time ratio of normal operation during the operation of the axle box to be tested; therefore, the larger the normal sound ratio, the greater the possibility that the axle box to be tested is in a non-fault state. By comparing the normal sound ratio with the standard ratio, when the normal sound ratio does not reach the standard ratio, it can be determined that the proportion of abnormal conditions during the operation of the axle box to be tested is high, indicating that the axle box to be tested is in a faulty state. This process can effectively avoid the problem of low accuracy of manual detection due to over-reliance on experience, and because the automated detection response time is shorter, the faulty axle box to be tested can be detected in time. 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 fault based on sound provided in an embodiment of the present application;

[0042] Figure 2 A schematic diagram of a sound time domain signal provided by an embodiment of the present application;

[0043] Figure 3 A schematic flow chart of a method for determining a standard ratio provided in an embodiment of the present application;

[0044] Figure 4 A block diagram of a sound-based axle box fault detection device provided in one embodiment of the present application;

[0045] Figure 5 A schematic diagram of an application scenario of a method for detecting axle box fault based on sound provided in an embodiment of the present application;

[0046] Figure 6 A schematic diagram of the structure of an electronic device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0047] 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.

[0048] 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.

[0049] See also Figure 1 , is a flow chart of a method for detecting axle box fault based on sound provided in an embodiment of the present application, such as Figure 1 As shown, the method may include the following steps 110 to 140.

[0050] Step 110: During the cutting process of the current knife, a sound time domain signal set of the axle box to be tested is obtained, wherein the sound time domain signal set includes multiple sound time domain signals, and the axle box to be tested is a main roller axle box in a multi-wire cutting machine.

[0051] The present application scheme can detect faults of each main roller axle box on the multi-wire cutting machine. Each axle box to be tested on the multi-wire cutting machine can be pre-set with a corresponding noise sensor to collect the sound time domain signal of each axle box to be tested.

[0052] The process of cutting a silicon rod into silicon wafers by a multi-wire saw is called one cut.

[0053] During the current cutting process of the knife, a noise sensor can be used to collect multiple sound time domain signals according to a preset sampling frequency, thereby obtaining actual sound data composed of the multiple sound time domain signals, and determining the sound time domain signal set with the actual sound data.

[0054] In actual application, the duration of a knife is usually 90 minutes to 120 minutes. The sound time domain signal collected in one cycle within a knife can be used as a sound time domain signal set. For details about the sound time domain signal set, see Figure 2 , and the amplitude of the sound time domain signal includes positive and negative directions, wherein the period can be set according to actual conditions, and the period can be, for example, 50 milliseconds, 100 milliseconds, and 200 milliseconds.

[0055] When the cutting time of the current knife reaches the preset time threshold, the actual sound data collected during this period can be used for fault detection of the axle box to be tested. Here, the time threshold can be configured as needed, and for example, the time threshold can be 5 minutes, 10 minutes, 20 minutes, etc.

[0056] In one embodiment, during the cutting process of the current knife, all the sound time domain signals generated by the axle box to be tested when the current knife is completed can be obtained to constitute actual sound data. In this case, since the sound time domain signal set determined by the actual sound data includes all the sound time domain signals generated by cutting a silicon rod, the sound time domain signal set can fully characterize the overall operation of the axle box to be tested during the process of cutting a silicon rod. Therefore, compared with the sound time domain signal set determined by the actual sound data composed of the sound time domain signals collected for a period of time within one knife, the sound time domain signal set generated by cutting a silicon rod can most accurately determine whether the axle box to be tested has a fault.

[0057] In one embodiment, actual sound data composed of a plurality of sound time-domain signals may be directly used as a sound time-domain signal set.

[0058] In another embodiment, since the multi-wire cutting machine equipped with the axle box to be tested has a complex composition and complex operating conditions, it is affected by factors such as load changes and mutual influence of components, which will cause a large amount of noise data to exist in the actual sound data. When the noise data is not considered and the actual sound data is directly used for fault detection, the problem of low detection accuracy may result. To solve this problem, after obtaining the actual sound data, a preset noise reduction method can be used to perform noise reduction processing on the actual sound data to obtain a sound time domain signal set, wherein the preset noise reduction method includes singular value decomposition (SVD) and wavelet threshold noise reduction method. By reducing the noise data in the actual sound data and optimizing the signal-to-noise ratio, the accuracy of subsequent fault detection with the help of the sound time domain signal set can be effectively improved.

[0059] Step 120: Compare each sound time domain signal in the sound time domain signal set with the sound reference value to determine the normal sound ratio of the current knife, wherein the sound reference value is obtained based on the sound time domain signal generated by the sample axle box in a non-fault state.

[0060] The sound reference value is used to filter the normal sound time domain signals in the sound time domain signal set. For any axle box to be tested, a corresponding sound reference value can be set for it. In one embodiment, the sound reference value can be obtained based on the sound time domain signal generated by the sample axle box in a non-fault state. Here, the sample axle box can be an axle box of the same batch or type as the axle box to be tested, so that the obtained sound reference value has a higher matching degree with the axle box to be tested.

[0061] In one embodiment, the sound time domain signal set can be compared with the sound reference value to determine the number of normal sound time domain signals of the current knife. For each sound time domain signal in the sound time domain signal set, the amplitude of each sound time domain signal can be compared with the sound reference value to check whether the amplitude is less than the sound reference value. On the one hand, if the amplitude of any sound time domain signal is not less than the sound reference value, it can be determined that the sound time domain signal is an abnormal sound time domain signal. On the other hand, if the amplitude of any sound time domain signal is less than the sound reference value, it can be determined that the sound time domain signal is a normal sound time domain signal. After comparing all the sound time domain signals in the sound time domain signal set, the number of normal sound time domain signals can be obtained.

[0062] After determining the number of normal sound time domain signals of the current knife, the normal sound ratio of the current knife can be determined based on the normal sound time domain signal data and the total signal amount included in the sound time domain signal set. Exemplarily, the normal sound ratio can be expressed by the following formula (1):

[0063] H=T / S (1)

[0064] Among them, H is the proportion of normal sound; T is the number of normal sound time domain signals; S is the total signal quantity contained in the sound time domain signal set.

[0065] In one embodiment, the sound time domain signal set can be compared with the sound reference value to determine the number of abnormal sound time domain signals of the current knife. For each sound time domain signal in the sound time domain signal set, the amplitude of each sound time domain signal can be compared with the sound reference value to check whether the amplitude is less than the sound reference value. On the one hand, if the amplitude of any sound time domain signal is not less than the sound reference value, it can be determined that the sound time domain signal is an abnormal sound time domain signal. On the other hand, if the amplitude of any sound time domain signal is less than the sound reference value, it can be determined that the sound time domain signal is a normal sound time domain signal. After comparing all the sound time domain signals in the sound time domain signal set, the number of abnormal sound time domain signals can be obtained.

[0066] After determining the number of abnormal sound time domain signals of the current knife, the normal sound ratio of the current knife can be determined based on the abnormal sound time domain signal data and the total signal amount included in the sound time domain signal set. Exemplarily, the normal sound ratio can be expressed by the following formula (2):

[0067] H=(SK) / S (2)

[0068] Among them, H is the proportion of normal sound; K is the number of abnormal sound time domain signals; S is the total signal quantity contained in the sound time domain signal set.

[0069] Step 130: Compare the normal sound ratio with the standard ratio. If the normal sound ratio does not reach the standard ratio, determine that the axle box to be tested is in a fault state, wherein the standard ratio is determined based on the normal sound ratio of the sample axle box in the fault state.

[0070] For each axle box to be tested, a corresponding standard ratio can be configured for it. The standard ratio is used to screen the axle boxes to be tested that have faults. In one embodiment, the standard ratio can be determined based on the normal sound ratio of the sample axle box in the fault state, as described below.

[0071] After obtaining the normal sound ratio corresponding to the axle box to be tested, it can be determined whether the normal sound ratio reaches the standard ratio corresponding to the axle box to be tested. In one case, if the normal sound ratio does not reach the standard ratio, it can be determined that the axle box to be tested has a fault and is in a faulty state. In another case, if the normal sound ratio reaches the standard ratio, it can be determined that the axle box to be tested has no fault and is in a non-faulty state.

[0072] When it is determined that any axle box to be tested is in a fault state, a prompt message may be output, which may indicate that the axle box to be tested is faulty, thereby promptly reminding the staff to repair the axle box to be tested.

[0073] Through the above measures, based on the sound time domain signals generated during the operation of the axle box to be tested, a sound time domain signal set can be constructed. By comparing the amplitude and sound reference value of each sound time domain signal in the sound time domain signal set, the number of normal sound time domain signals can be obtained, and then based on the number and the total amount of sound time domain signals in the sound time domain signal set, the normal sound ratio can be determined. The normal sound ratio can characterize the normal operation time ratio during the operation of the axle box to be tested; therefore, the larger the normal sound ratio, the greater the possibility that the axle box to be tested is in a non-fault state. By comparing the normal sound ratio with the standard ratio, when the normal sound ratio does not reach the standard ratio, it can be determined that the abnormal situation during the operation of the axle box to be tested accounts for a high proportion, indicating that the axle box to be tested is in a faulty state. This process can effectively avoid the problem of low accuracy of manual detection due to over-reliance on experience, and because the automated detection response time is shorter, the axle box to be tested with faults can be detected in time.

[0074] In one embodiment, before executing step 120, the sound reference value corresponding to the axle box to be tested can be obtained. When the sample axle box is in a non-fault state, the sound time domain signal can be collected by the noise sensor when the multi-wire cutting machine is running. After each cut of the multi-wire cutting machine is completed, all the sound time domain signals generated by the sample axle box in this cut can be obtained to form a target sound time domain signal set. After the multi-knife cutting is completed, the multi-knife target sound time domain signal set of the sample axle box in a non-fault state can be obtained.

[0075] After obtaining the multi-tool target sound time domain signal set of the sample axle box, the amplitude mean of multiple sound time domain signals in the multi-tool target sound time domain signal set can be calculated, and the sound reference value can be obtained based on the amplitude mean. Exemplarily, the amplitude mean can be added to a preset constant to obtain the sound reference value. Here, the preset constant can be configured based on experience, representing the offset between the maximum amplitude of the sound time domain signal allowed by the axle box to be tested in a non-fault state and the amplitude mean.

[0076] In one embodiment, after calculating the amplitude mean of multiple sound time domain signals in the multi-blade target sound time domain signal set, it can be adjusted according to the preset coefficient on the basis of the amplitude mean to obtain the sound reference value. Here, the preset coefficient can be configured as needed. Exemplarily, the preset coefficient can be a value between 1.2 and 1.5, for example, it can be 1.2, 1.3, 1.4 and 1.5. In one embodiment, the amplitude mean can be multiplied by the preset coefficient to obtain the sound reference value. Alternatively, the amplitude mean can be used as the base and the preset coefficient can be used as the exponent to calculate the sound reference value. Preferably, the product of the amplitude mean and the preset coefficient is used as the sound reference value.

[0077] In addition, for some axle boxes to be tested with large fluctuations in sound time domain signals, sound reference values ​​can be configured for them based on experience.

[0078] Through this measure, the amplitude mean is amplified by a preset coefficient to obtain a sound reference value, which may include the amplitude mean and the offset between the maximum amplitude allowed by the axle box to be tested in a non-fault state and the amplitude mean. Compared with amplifying the amplitude mean by a preset constant to obtain the sound reference value, the sound reference value amplified by the preset coefficient can characterize the allowed offset in terms of proportion, which is more helpful for subsequent screening of normal sound time domain signals.

[0079] In one embodiment, before executing step 130, a standard ratio corresponding to the axle box to be tested may be obtained. Figure 3 , is a flow chart of a method for determining a standard ratio provided in an embodiment of the present application, such as Figure 3 As shown, the method may include the following steps 310 to 330.

[0080] Step 310: Collect a multi-tool fault sound time domain signal set when the sample shaft box is in a fault state.

[0081] When the sample axle box is in a faulty state, the sound time domain signal can be collected by the noise sensor while the multi-wire cutting machine is running, and a fault sound time domain signal set can be constructed based on the collected sound time domain signal. After each cut of the multi-wire cutting machine is completed, a single-cut fault sound time domain signal set of the sample axle box can be obtained. After the multi-cut cutting is completed, a multi-cut fault sound time domain signal set of the sample axle box in a faulty state can be obtained.

[0082] Step 320: Determine the normal sound ratio of each switch according to the multi-switch fault sound time domain signal set.

[0083] After obtaining a multi-tool fault sound time domain signal set when the sample axle box is in a faulty state, for each tool fault sound time domain signal set, the amplitude and sound reference value of each sound time domain signal in the fault sound time domain signal set can be compared to determine the number of normal sound time domain signals. Furthermore, based on the number of normal sound time domain signals and the total signal amount corresponding to each tool fault sound time domain signal set, the normal sound proportion of each tool can be calculated.

[0084] Step 330: Calculate the average value of the normal sound ratio corresponding to the multi-switch fault sound time domain signal set according to the normal sound ratio of each switch.

[0085] Step 340: Determine a standard ratio based on the average of the normal sound ratio.

[0086] After obtaining multiple normal sound proportions, the average of the multiple sound time domain signal proportions can be calculated to obtain the average of the normal sound proportions corresponding to the multi-tool fault sound time domain signal set.

[0087] Further, the average value of the normal sound proportion can be used as the standard proportion, the product of the average value of the normal sound proportion and the preset coefficient can be used as the standard proportion, and the sum of the average value of the normal sound proportion and the preset value can also be used as the standard proportion, which is not specifically limited in this specification. Here, the standard proportion can generally be between 18% and 32%, and for example, the standard proportion can be 25%.

[0088] Through the above measures, since the multiple groups of fault sound time domain signal sets reflected by the sample axle box in the fault state can characterize the noise emitted by the axle box to be tested in the fault state, after obtaining the multiple groups of fault sound time domain signal sets in the fault state, by converting the normal sound proportion corresponding to each group of fault sound time domain signal sets, the proportion of normal sound time domain signals in the fault state can be determined; further, using the average value of the normal sound proportions corresponding to the multiple groups of fault sound time domain signal sets as the standard ratio can reduce errors and make the accuracy of obtaining the standard ratio higher.

[0089] Figure 4is a block diagram of a device for detecting axle box fault based on sound according to an embodiment of the present invention, such as Figure 4 As shown, the device may include:

[0090] The acquisition module 410 is used to acquire the sound time domain signal set of the axle box to be tested during the cutting process of the current knife, wherein the sound time domain signal set includes multiple sound time domain signals, and the axle box to be tested is a main roller axle box in the multi-wire cutting machine;

[0091] A comparison module 420 is used to compare each sound time domain signal in the sound time domain signal set with a sound reference value to determine the normal sound ratio of the current knife; wherein the sound reference value is obtained based on the sound time domain signal generated by the sample axle box in a non-fault state;

[0092] The comparison module 430 is used to compare the normal sound ratio with the standard ratio. If the normal sound ratio does not reach the standard ratio, it is determined that the axle box to be tested is in a fault state, wherein the standard ratio is determined based on the normal sound ratio of the sample axle box in the fault state.

[0093] In one embodiment, the device further comprises:

[0094] The generating module 440 is used to obtain a multi-tool target sound time domain signal set when the sample axle box is in a non-fault state; and obtain the sound reference value according to the amplitude mean of the multi-tool target sound time domain signal set.

[0095] In one embodiment, the generating module 440 is further configured to:

[0096] The sound reference value is determined according to the amplitude mean and a preset coefficient, wherein the preset coefficient ranges from 1.2 to 1.5.

[0097] In one embodiment, the generating module 440 is further configured to:

[0098] Collect a multi-tool fault sound time domain signal set when the sample axle box is in a fault state;

[0099] Determine the normal sound ratio of each knife according to the multi-knife fault sound time domain signal set;

[0100] According to the normal sound proportion of each knife, the average value of the normal sound proportion corresponding to the multi-knife fault sound time domain signal set is obtained;

[0101] The standard ratio is determined according to the average value of the normal sound ratio.

[0102] In one embodiment, the comparison module 420 is further configured to:

[0103] Comparing each sound time domain signal in the sound time domain signal set with the sound reference value to obtain the number of normal sound time domain signals, wherein if the amplitude of any sound time domain signal compared is smaller than the sound reference value, the sound time domain signal is determined to be a normal sound time domain signal;

[0104] The normal sound ratio of the current knife is determined according to the number of normal sound time-domain signals and the total signal quantity included in the sound time-domain signal set.

[0105] In one embodiment, the comparison module 420 is further configured to:

[0106] Comparing each sound time domain signal in the sound time domain signal set with the sound reference value to obtain the number of abnormal sound time domain signals, wherein if the amplitude of any sound time domain signal is not less than the sound reference value, the sound time domain signal is determined to be an abnormal sound time domain signal;

[0107] The normal sound ratio of the current knife is determined according to the number of abnormal sound time-domain signals and the total signal quantity included in the sound time-domain signal set.

[0108] In one embodiment, the acquisition module 410 is further configured to:

[0109] During the current cutting process of the knife, actual sound data of the axle box to be tested is obtained;

[0110] The actual sound data is subjected to denoising processing by using a preset denoising method to obtain the sound time domain signal set, wherein the preset denoising method includes a singular value decomposition method and a wavelet threshold denoising method.

[0111] In one embodiment, the acquisition module 410 is further configured to:

[0112] During the cutting process of the current knife, all the sound time domain signals generated by the axle box to be tested when the current knife is completed are obtained to constitute the actual sound data.

[0113] 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 sound-based axle box fault detection method, which will not be repeated here.

[0114] Figure 5 Schematic diagram of the application scenario of the sound-based axle box fault detection method provided in the embodiment of the present application. Figure 5As shown, the application scenario includes a client 20 and a server 30; the client 20 can be a noise sensor, used to collect sound time domain signals for the axle box to be tested, and hand over the sound time domain signals composed of multiple sound time domain signals to the server 30 for processing; the server 30 can be a host, a server, a server cluster or a cloud computing center, which can obtain the sound time domain signal and detect whether there is a fault in the axle box to be tested based on the sound time domain signal.

[0115] like Figure 6 As shown, this embodiment provides an electronic device 1, including: at least one processor 11 and a memory 12, Figure 6 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 30, which is used to execute the sound-based axle box fault detection method.

[0116] 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.

[0117] 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 sound-based axle box fault detection method provided by the present application.

[0118] 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.

[0119] 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.

[0120] 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 detecting axle box faults based on sound, characterized in that: include: During the cutting process of the current knife, a sound time domain signal set of the axle box to be tested is obtained, wherein the sound time domain signal set includes multiple sound time domain signals, and the axle box to be tested is a main roller axle box in a multi-wire cutting machine; Compare each sound time domain signal in the sound time domain signal set with a sound reference value to determine the normal sound ratio of the current knife, wherein the sound reference value is obtained based on the sound time domain signal generated by the sample axle box in a non-fault state; The normal sound ratio is compared with the standard ratio. If the normal sound ratio does not reach the standard ratio, it is determined that the axle box to be tested is in a fault state, wherein the standard ratio is determined based on the normal sound 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 sound reference value comprises: Acquire a multi-tool target sound time domain signal set when the sample axle box is in a non-fault state; The sound reference value is obtained according to the amplitude mean of the multi-tool target sound time domain signal set.

3. The method according to claim 2, characterized in that The step of obtaining the sound reference value according to the amplitude mean of the multi-blade target sound time domain signal set comprises: The sound reference value is determined according to the amplitude mean and a preset coefficient, wherein the preset coefficient ranges from 1.2 to 1.

5.

4. The method according to claim 2, characterized in that: The step of obtaining the standard ratio includes: Collect a multi-tool fault sound time domain signal set when the sample axle box is in a fault state; Determine the normal sound ratio of each knife according to the multi-knife fault sound time domain signal set; According to the normal sound proportion of each knife, the average value of the normal sound proportion corresponding to the multi-knife fault sound time domain signal set is obtained; The standard ratio is determined according to the average value of the normal sound proportion.

5. The method according to claim 1, characterized in that The step of comparing each sound time domain signal in the sound time domain signal set with the sound reference value to determine the normal sound proportion of the current knife includes: Comparing each sound time domain signal in the sound time domain signal set with the sound reference value to obtain the number of normal sound time domain signals, wherein if the amplitude of any sound time domain signal compared is smaller than the sound reference value, the sound time domain signal is determined to be a normal sound time domain signal; The normal sound ratio of the current knife is determined according to the number of normal sound time-domain signals and the total signal quantity included in the sound time-domain signal set.

6. The method according to claim 1, characterized in that The step of comparing each sound time domain signal in the sound time domain signal set with the sound reference value to determine the normal sound proportion of the current knife includes: Comparing each sound time domain signal in the sound time domain signal set with the sound reference value to obtain the number of abnormal sound time domain signals, wherein if the amplitude of any sound time domain signal is not less than the sound reference value, the sound time domain signal is determined to be an abnormal sound time domain signal; The normal sound ratio of the current knife is determined according to the number of abnormal sound time-domain signals and the total signal quantity included in the sound time-domain signal set.

7. The method according to claim 1, characterized in that The step of obtaining a sound time domain signal set of the axle box to be tested during the current cutting process of the knife comprises: During the current cutting process of the knife, actual sound data of the axle box to be tested is obtained; The actual sound data is subjected to denoising processing by using a preset denoising method to obtain the sound time domain signal set, wherein the preset denoising method includes a singular value decomposition method and a wavelet threshold denoising method.

8. The method according to claim 7, characterized in that The actual sound data of the axle box to be tested is obtained during the current cutting process of the knife, including: During the cutting process of the current knife, all the sound time domain signals generated by the axle box to be tested when the current knife is completed are obtained to constitute the actual sound data.

9. A sound-based axle box fault detection device, characterized in that: include: An acquisition module, used for acquiring a sound time domain signal set of the axle box to be tested during the cutting process of the current knife, wherein the sound time domain signal set includes a plurality of sound time domain signals, and the axle box to be tested is a main roller axle box in a multi-wire cutting machine; A comparison module, used to compare each sound time domain signal in the sound time domain signal set with a sound reference value to determine the normal sound ratio of the current knife; wherein the sound reference value is obtained based on the sound time domain signal generated by the sample axle box in a non-fault state; A comparison module is used to compare the normal sound ratio with a standard ratio. If the normal sound ratio does not reach the standard ratio, it is determined that the axle box to be tested is in a fault state, wherein the standard ratio is determined based on the normal sound 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 sound-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 sound-based axle box fault detection method described in any one of claims 1-8.

Images