Abnormal sound signal detection method, device, equipment and readable storage medium

Abstract

The present invention discloses an abnormal sound signal detection method, device, system and computer-readable storage medium, which are applied to the technical field of electronic equipment. In order to solve the technical problems of high cost and low efficiency of existing abnormal sound detection, the present invention proposes to pick up the sound signal of the product to be tested during the preset operation process; analyze the sound signal to determine the number of cycles of the periodic abnormal sound signal; and determine whether the product to be tested has abnormal operation based on the number of cycles. When detecting periodic abnormal sounds in a production test environment, the sound signal of the product to be tested during the preset operation process is picked up, and the sound signal is analyzed to determine the number of cycles of the periodic abnormal sound signal during the preset operation process, and then further determine whether the product to be tested has abnormal operation based on the number of cycles, which saves human resources and costs and improves test efficiency and accuracy.

Description

Technical Field

[0001] The present invention relates to the technical field of electronic equipment, and in particular to a method, device, equipment and computer-readable storage medium for detecting an abnormal sound signal. Background Art

[0002] For the optical drive module of the game console, in order to verify whether its disc ejection performance is abnormal, its performance needs to be tested on the production line. At present, the test method commonly used in the production line is to detect abnormal sounds by manual listening, but this method not only consumes a lot of human resources and labor costs, but also easily causes auditory fatigue and leads to misjudgment.

[0003] In view of this, how to provide an abnormal sound signal detection method, device, equipment and computer-readable storage medium that solve the above-mentioned technical problems has become a problem that needs to be solved by those skilled in the art. Summary of the invention

[0004] The purpose of the embodiments of the present invention is to provide a method, device, equipment and computer-readable storage medium for detecting an abnormal sound signal, which saves human resources and costs and improves test efficiency and accuracy.

[0005] In order to solve the above technical problems, an embodiment of the present invention provides a method for detecting an abnormal sound signal, comprising:

[0006] Pick up the sound signal of the product under test during the preset operation process;

[0007] Analyze the sound signal to determine the number of cycles of the periodic abnormal sound signal;

[0008] Based on the number of cycles, it is determined whether the product under test operates abnormally.

[0009] Optionally, analyzing the sound signal to determine the number of cycles of occurrence of the periodic abnormal sound signal includes:

[0010] Performing denoising on the sound signal to obtain a denoised sound signal;

[0011] Performing frame processing on the de-noised sound signal, and calculating the power value corresponding to each frame signal;

[0012] Obtaining a power curve according to each of the power values;

[0013] The power curve is analyzed based on a preset abnormal sound distribution to determine the number of cycles of occurrence of the periodic abnormal sound signal.

[0014] Optionally, calculating the power value corresponding to each frame signal includes:

[0015] Performing a Fast Fourier Transform (FFT) analysis on each frame of signal to obtain an FFT curve corresponding to each frame of the signal;

[0016] According to each of the FFT curves, a power value corresponding to each frame of the signal is calculated.

[0017] Optionally, analyzing the power curve based on a preset abnormal sound distribution to determine the number of cycles of occurrence of the periodic abnormal sound signal includes:

[0018] Obtaining a characteristic value threshold in advance based on a preset noise distribution;

[0019] Extracting each characteristic value of the power curve;

[0020] Each of the characteristic values ​​is analyzed based on the characteristic value threshold to determine the number of periods in which the periodic abnormal sound signal occurs.

[0021] Optionally, before extracting the characteristic value of the power curve, the method further includes:

[0022] Smoothing the power curve;

[0023] The extracting the characteristic value of the power curve comprises:

[0024] Extract the eigenvalues ​​of the smoothed power curve.

[0025] Optionally, extracting the characteristic value of the smoothed power curve includes:

[0026] Extracting the extreme values ​​of the smoothed power curve;

[0027] Determine a characteristic value group for each signal period according to each of the extreme values;

[0028] Then, each of the characteristic values ​​is analyzed based on the characteristic value threshold to determine the number of cycles of the periodic abnormal sound signal, including:

[0029] For each signal period, determine whether each characteristic value in the characteristic value group meets the characteristic value threshold requirement. If so, the signal period is the period of the periodic abnormal sound signal.

[0030] Calculate the number of times the disc ejection noise signal appears in each signal cycle.

[0031] Optionally, the characteristic value group includes: a maximum value, a left minimum value, a right minimum value, a rising part width, a rising part height, a falling part width and a falling part height.

[0032] Optionally, determining whether the test object operates abnormally based on the number of cycles includes:

[0033] It is determined whether the number of cycles exceeds a preset number threshold. If so, the operation of the product under test is abnormal; otherwise, the operation of the product under test is normal.

[0034] Optionally, the picking up of a sound signal of the product to be tested during a preset operation process includes:

[0035] Pick up the sound signal of the product under test during the disc ejection process;

[0036] Then, the periodic abnormal sound signal includes a periodic disc ejection abnormal sound signal.

[0037] The embodiment of the present invention further provides an abnormal sound signal detection device, comprising:

[0038] A pickup module is used to pick up the sound signal of the product under test during the preset operation process;

[0039] An analysis module, used to analyze the sound signal and determine the number of cycles of the periodic abnormal sound signal;

[0040] A determination module is used to determine whether the product to be tested operates abnormally based on the number of cycles.

[0041] The embodiment of the present invention further provides an abnormal sound signal detection system, including:

[0042] Memory for storing computer programs;

[0043] A processor is used to implement the steps of the abnormal sound signal detection method as described above when executing the computer program.

[0044] An embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the abnormal sound signal detection method described above are implemented.

[0045] The embodiments of the present invention provide an abnormal sound signal detection method, device, system and computer-readable storage medium. The method includes: picking up the sound signal of a product under test during a preset operation process; analyzing the sound signal to determine the number of cycles of the periodic abnormal sound signal; and determining whether the product under test operates abnormally based on the number of cycles.

[0046] It can be seen that when the present invention detects periodic abnormal sounds in a production test environment, the sound signal of the product to be tested during a preset operation is picked up and the sound signal is analyzed to determine the number of cycles of the periodic abnormal sound signal during the preset operation. Then, based on the number of cycles, it is further determined whether the product to be tested has an operational abnormality, thereby saving human resources and costs and improving test efficiency and accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the prior art and the drawings required for use in the embodiments are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0048] Figure 1 A schematic diagram of a flow chart of a method for detecting an abnormal sound signal provided by an embodiment of the present invention;

[0049] Figure 2 A power value curve of a product with abnormal disc rejection provided by an embodiment of the present invention;

[0050] Figure 3 A schematic diagram of the magnitude of the extreme values ​​in the characteristic values ​​of a disc ejection abnormal sound signal of one cycle provided by an embodiment of the present invention;

[0051] Figure 4 For Figure 3 Schematic diagram of characteristic values ​​corresponding to the disc ejection noise signal;

[0052] Figure 5 A schematic diagram of a power curve in the presence of large signal environmental noise provided by an embodiment of the present invention;

[0053] Figure 6 A schematic diagram of the structure of an abnormal sound signal detection device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0054] The embodiments of the present invention provide a method, device, equipment and computer-readable storage medium for detecting an abnormal sound signal, which saves human resources and costs and improves test efficiency and accuracy.

[0055] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0056] Please refer to Figure 1 , Figure 1 A flowchart of a method for detecting an abnormal sound signal provided by an embodiment of the present invention. The method comprises:

[0057] S110: Picking up the sound signal of the product under test during the preset operation process;

[0058] Specifically, in a production test environment, the product under test can be placed on a test fixture, and the upper computer can be used to control the product under test to perform a preset operation. The specific operation type of the preset operation can be determined according to the specific product type of the product under test. For example, for the optical drive module, the preset operation can be a disc ejection operation. When the product under test is controlled to perform the preset operation, the sound signal of the product under test during the preset operation is picked up by the microphone. In actual applications, before controlling the product under test to perform the preset operation, the microphone can be turned on first, and then the product under test can be controlled to perform the preset operation, and the microphone can be turned off after the operation of the product under test is completed, thereby ensuring that the sound signal during the entire operation process can be picked up.

[0059] S120: Analyze the sound signal to determine the number of cycles of the periodic abnormal sound signal;

[0060] It should be noted that when analyzing the sound signal, the sound signal corresponding to the entire operation process can be first intercepted from the entire sound signal picked up, and then the sound signal of this part can be analyzed. For products that produce periodic abnormal sounds when the operation is abnormal, when analyzing the sound signal of the corresponding product to be tested, if the product to be tested has abnormal operation, there will be periodic abnormal sound signals (that is, multiple identical sounds that appear at a certain frequency) in the sound signal. By analyzing the sound signal, the number of cycles of the periodic abnormal sound signal can be determined. For example, for the optical drive module type of product to be tested, when an abnormality occurs during disc ejection (such as jamming), the product will produce obvious periodic abnormal sounds of "click, click, click...", where one "click" is one cycle. If the disc is not ejected successfully, that is, when the disc is stuck, the "click", "click", "click"... sounds will continue to appear until the preset disc ejection time is exceeded, and the disc ejection action is stopped, and the corresponding "click", "click", "click"... will stop. In the embodiment of the present invention, the sound signal of the disc ejection process can be analyzed to further determine the number of cycles of the "click", "click", "click"... "disc ejection abnormal sound signals in the sound signal.

[0061] S130: Determine whether the product under test operates abnormally based on the number of cycles.

[0062] Specifically, after determining the number of cycles in which the periodic abnormal sound signal appears during the preset operation of the product to be tested, it is possible to determine whether the product to be tested has an operation abnormality based on the number of cycles. Specifically, it can be determined whether the number of cycles exceeds a preset number threshold. If it exceeds the preset number threshold, it is determined that the product to be tested has an operation abnormality; if it does not exceed the preset number threshold, it is determined that the product to be tested is operating normally.

[0063] For example, for a product to be tested such as an optical drive module, the preset number threshold may be, for example, 10 times. Of course, its actual value may be obtained in advance by analyzing the number of occurrences of abnormal disc ejection sound signals of samples with abnormal disc ejection. Its specific value may be determined based on actual conditions, and the embodiments of the present invention do not make any special limitations thereto.

[0064] Furthermore, the process of analyzing the sound signal in the above S120 to determine the number of cycles of the periodic abnormal sound signal may specifically include:

[0065] Performing denoising on the sound signal to obtain a denoised sound signal;

[0066] The denoised sound signal is divided into frames and the power value corresponding to each frame signal is calculated;

[0067] A power curve is obtained according to each power value;

[0068] The power curve is analyzed based on the preset abnormal sound distribution to determine the number of cycles of the periodic abnormal sound signal.

[0069] It should be noted that, since there will be environmental noise when testing the product under test in the production test environment, the environmental noise includes small signal noise (the sound of the staff talking in a low voice, etc.) and large signal noise (such as the humming sound emitted by the production equipment in the environment or the louder sound emitted by other objects, etc.), therefore, the present invention can first perform denoising on the sound signal, specifically, first perform wavelet denoising on the sound signal to be analyzed to remove the sound signal with a smaller amplitude in the sound signal to obtain the denoised sound signal. The denoised sound signal is framed, specifically, it can be framed in a manner of 256 samples per frame and 85% overlap between two adjacent frames to obtain a multi-frame signal. Of course, in actual applications, the specific values ​​of the number of samples and the overlap rate can be determined according to actual needs, and the present invention does not make any special restrictions on this. For each frame signal, the corresponding power value is calculated, and then the power curve corresponding to the sound signal is obtained according to each power value, and the power curve is analyzed according to the preset abnormal sound distribution (for example, the signal distribution of "da", "da", "da"...), and each periodic abnormal sound signal in the sound signal is further determined, and the number of cycles of the periodic abnormal sound signal is determined. Among them, the preset abnormal sound distribution can be obtained in advance by analyzing the power curve of the sound signal of the abnormal operation sample (NG product) during the operation process and the power curve of the sound signal of the normal operation sample during the operation process.

[0070] Specifically, in the embodiment of the present invention, when calculating the power of each frame signal, FFT (Fast Fourier Transformation) analysis can be performed on each frame signal to obtain an FFT curve corresponding to each frame signal; based on each FFT curve, the power value corresponding to each frame signal is calculated.

[0071] It should also be noted that, in practical applications, before the above-mentioned denoising process is performed on the sound signal to obtain the denoised sound signal, the method may further include:

[0072] The total power value of the sound signal is calculated, and when the total power value is within a preset range, a step of performing denoising on the sound signal to obtain a denoised sound signal is performed.

[0073] Specifically, in order to further improve the detection efficiency in the embodiment of the present invention, after determining the sound signal corresponding to the preset operation process, the total power value of the sound signal can be calculated, and it can be further determined whether the total power value is within the preset range. When the total power value is too small (less than the minimum value of the preset range) or too large (greater than the maximum value of the preset range), it means that a recording anomaly occurred when recording the sound signal, and it is necessary to adjust the microphone and other recording equipment, and then return to re-execute the step of picking up the sound signal of the product to be tested during the preset operation process. If the total power value is within the preset range, it means that there is no recording anomaly when recording the sound signal, and then the subsequent step of denoising the sound signal can be entered to obtain the denoised sound signal.

[0074] Furthermore, the above-mentioned analysis of the power curve based on the preset abnormal sound distribution to determine the number of cycles of the periodic abnormal sound signal includes:

[0075] Obtaining a characteristic value threshold in advance based on a preset noise distribution;

[0076] Extract each characteristic value of the power curve;

[0077] Each eigenvalue is analyzed based on the eigenvalue threshold to determine the number of cycles of the periodic abnormal sound signal.

[0078] Specifically, a preset abnormal sound distribution can be obtained by first analyzing the power curve of the sound signal of the abnormal operation sample during the operation process and the power curve of the sound signal of the normal operation sample during the operation process. For example, for the optical drive module, the sound signal of the optical drive module sample with abnormal disc ejection during the disc ejection process can be first analyzed to obtain a power curve, and the abnormal sound distribution of the disc ejection abnormal sound signal can be obtained based on the power curve, and the characteristic value threshold can be obtained based on the abnormal sound distribution, wherein, when there are multiple characteristic values, a corresponding characteristic value threshold (specifically a threshold range) can be obtained for each characteristic value, and then when testing the product to be tested, the obtained power curve is subjected to characteristic value extraction to obtain each characteristic value, and then each characteristic value is analyzed based on the corresponding characteristic value threshold, so as to determine the periodic abnormal sound signal in the sound signal and calculate the number of cycles of the periodic abnormal sound signal.

[0079] Of course, in practical applications, in addition to determining the periodic abnormal sound signal by extracting and analyzing the characteristic values, other methods can be used to analyze the power curve to further determine each periodic abnormal sound signal and its cycle number. For example, the periodic abnormal sound signal of the power curve of the NG product can be fitted with a function to obtain a continuous function and the corresponding function characteristic value, and then the power curve of the product to be tested is analyzed based on the function characteristic value to determine the periodic abnormal sound signal and its cycle number.

[0080] Furthermore, before extracting the characteristic value of the power curve, the following steps may be specifically included:

[0081] Smoothing the power curve;

[0082] Then, the corresponding process of extracting the characteristic value of the power curve may include:

[0083] Extract the eigenvalues ​​of the smoothed power curve.

[0084] It should be noted that, in order to further reduce misjudgment and improve detection accuracy, in the embodiment of the present invention, the power curve may be smoothed first to remove small jitters, and then feature value extraction may be performed on the smoothed power curve to obtain various feature values.

[0085] Furthermore, the process of extracting the characteristic value of the smoothed power curve may specifically include:

[0086] Extracting the extreme values ​​of the smoothed power curve;

[0087] According to each extreme value, the characteristic value group of each signal period is determined;

[0088] Specifically, after obtaining each extreme value, each maximum value can be determined first, and then for each maximum value, two minimum values ​​adjacent to the maximum value can be determined from each extreme value, thereby determining each group of maximum values, left minimum values ​​and right minimum values. The signals between each group of left minimum values, maximum values ​​and right minimum values ​​constitute a signal cycle, thereby obtaining multiple signal cycles, and for the left minimum value, maximum value and right minimum value of each signal cycle, the width of the rising part, the height of the rising part, the width of the falling part and the height of the falling part in the signal cycle are further obtained to obtain the characteristic value group of each signal cycle. The characteristic value group of each signal cycle can specifically include characteristic values ​​such as maximum value, left minimum value, right minimum value, width of the rising part, height of the rising part, width of the falling part and height of the falling part.

[0089] Take the disc eject operation as an example. Figure 2 The power value curve of the product with abnormal disc ejection is shown in the dashed box A, which is a cycle of the abnormal disc ejection sound signal. Figure 3 is the magnitude of the extreme value of the characteristic value of the disc ejection noise signal for one cycle, including the maximum value Y max , left minimum value Y min_L and the right minimum Y min_R , Figure 4 For Figure 3 The rising part width X1, the rising part height Y1, the falling part width X2 and the falling part height Y2 in the characteristic values ​​corresponding to the disc ejection abnormal sound signal.

[0090] Then, each eigenvalue is analyzed based on the eigenvalue threshold to determine the number of cycles of the periodic abnormal sound signal, including:

[0091] For each signal period eigenvalue group, determine whether each eigenvalue in the eigenvalue group meets the eigenvalue threshold requirement. If so, the signal period is the period of the periodic abnormal sound signal.

[0092] Calculate the number of times the disc ejection noise signal appears in each signal cycle.

[0093] It should be noted that the threshold of each type of characteristic value can be determined in advance according to the characteristic values ​​of a certain number of samples with abnormal operating performance and the characteristic values ​​of samples with normal operating performance, so as to obtain the preset characteristic value threshold for each type of characteristic value. For example, when the characteristic value group includes: maximum value, left minimum value, right minimum value, rising part width, rising part height, falling part width and falling part height, the preset characteristic threshold also correspondingly includes the maximum value threshold range, the left minimum value threshold range, the right minimum value threshold range, the rising part width threshold range, the rising part height threshold range, the falling part width threshold range, the falling part height threshold range, the falling part height threshold range, the falling part height threshold range, the falling part height threshold range, the falling part height threshold range, the falling part height threshold range, the falling part height threshold range, the falling part height threshold range, the falling part height threshold range, the falling part height threshold range, the falling part height threshold range, the falling part height threshold range, the falling part height threshold range, the falling part height threshold range, the falling part height threshold range, the falling part height threshold range, the falling part width ... width threshold range, the falling part height threshold range, the falling part height threshold range, the falling part height threshold range, the falling part height threshold range, the falling part width threshold range, the falling part height threshold range, the falling part height threshold range, the falling part height It is divided into a width threshold range and a descending part height threshold range. For each signal period's feature value group, when each feature value in the feature value group is within the corresponding threshold range, it indicates that the corresponding signal period is the period of the disc ejection abnormal sound signal, and cumulative counting is performed to obtain the number of periods when the periodic abnormal sound signal appears in each signal period. For example, for the disc ejection operation, the number of periods when the disc ejection abnormal sound signal appears in the signal period (that is, the number of times the "click" signal appears) is determined, and when the number of periods exceeds the preset number threshold, it is determined that the product under test has an abnormal disc ejection abnormal sound.

[0094] In addition, if Figure 5 As shown, since the characteristic values ​​of the large signal environmental noise (such as the signal at the dotted box B) and the disc ejection abnormal sound signal are quite different, in the embodiment of the present invention, each characteristic value in each signal cycle is analyzed based on the preset characteristic value threshold to count the number of cycles in which the disc ejection abnormal sound signal appears, which can filter out the interference of large signal noise in the environment, thereby improving the test accuracy.

[0095] It can be seen that when the present invention detects the abnormal sound of disc ejection in a production test environment, the sound signal of the product to be tested during the disc ejection process is picked up and the sound signal is analyzed to determine the number of cycles of the abnormal sound signal of the disc ejection process, and then based on the number of cycles, it is further determined whether the product to be tested has abnormal disc ejection, which saves human resources and costs and improves test efficiency and accuracy.

[0096] Based on the above embodiments, the present invention also provides a device for detecting abnormal sound signals. Figure 6 , the device comprises:

[0097] The pickup module 21 is used to pick up the sound signal of the product under test during the preset operation process;

[0098] An analysis module 22 is used to analyze the sound signal and determine the number of cycles of the periodic abnormal sound signal;

[0099] The determination module 23 is used to determine whether the product to be tested operates abnormally based on the number of cycles.

[0100] It should be noted that the abnormal sound signal detection device provided in the embodiment of the present invention has the same beneficial effects as the abnormal sound signal detection method provided in the above embodiment, and for the specific introduction of the abnormal sound signal detection method involved in the embodiment of the present invention, please refer to the above embodiment, and the present invention will not be repeated here.

[0101] Based on the above embodiment, an embodiment of the present invention further provides an abnormal sound signal detection system, which includes:

[0102] Memory for storing computer programs;

[0103] The processor is used to implement the steps of the abnormal sound signal detection method as described above when executing the computer program.

[0104] For example, the processor in the embodiment of the present invention can be specifically used to pick up the sound signal of the product under test during a preset operation process; analyze the sound signal to determine the number of cycles of the periodic abnormal sound signal; and determine whether the product under test operates abnormally based on the number of cycles.

[0105] Based on the above embodiments, an embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the above abnormal sound signal detection method are implemented.

[0106] The computer-readable storage medium may include: a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and other media that can store program codes.

[0107] In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part.

[0108] It should also be noted that, in this specification, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "comprise", "include" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the statement "comprises a ..." does not exclude the presence of other identical elements in the process, method, article or device including the element.

[0109] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0110] The steps of the method or algorithm described in conjunction with the embodiments disclosed herein may be implemented directly using hardware, a software module executed by a processor, or a combination of the two. The software module may be placed in a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

[0111] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for detecting an abnormal sound signal, characterized in that: include: Pick up the sound signal of the product under test during the disc ejection process; Calculating the total power value of the sound signal, and executing the next step when the total power value is within a preset range; and returning to the step of picking up the sound signal of the product to be tested during the disc ejection process after adjusting the recording device when the total power value is outside the preset range; Analyze the sound signal to determine the number of cycles of the periodic abnormal sound signal; The periodic abnormal sound signal is a plurality of identical sounds that appear at a certain frequency, including a periodic disc ejection abnormal sound signal; Determine whether the product to be tested operates abnormally based on the number of cycles; wherein: The analyzing the sound signal to determine the number of cycles of the periodic abnormal sound signal includes: Performing denoising on the sound signal to obtain a denoised sound signal; Performing frame processing on the de-noised sound signal, and calculating the power value corresponding to each frame signal; Obtaining a power curve according to each of the power values; The power curve is analyzed based on a preset abnormal sound distribution to determine the number of cycles of occurrence of the periodic abnormal sound signal; wherein the preset abnormal sound distribution is obtained in advance by analyzing the power curve of the sound signal of the abnormal operation sample during the operation process and the power curve of the sound signal of the normal operation sample during the operation process.

2. The abnormal sound signal detection method according to claim 1, characterized in that: The calculating of the power value corresponding to each frame signal includes: Performing a Fast Fourier Transform (FFT) analysis on each frame of signal to obtain an FFT curve corresponding to each frame of the signal; According to each of the FFT curves, a power value corresponding to each frame of the signal is calculated.

3. The abnormal sound signal detection method according to claim 1, characterized in that: The analyzing the power curve based on the preset abnormal sound distribution to determine the number of cycles of the periodic abnormal sound signal, includes: Obtaining a characteristic value threshold in advance based on a preset noise distribution; Extracting each characteristic value of the power curve; Each of the characteristic values ​​is analyzed based on the characteristic value threshold to determine the number of periods in which the periodic abnormal sound signal occurs.

4. The abnormal sound signal detection method according to claim 3, characterized in that: Before extracting the characteristic value of the power curve, the method further includes: Smoothing the power curve; The extracting the characteristic value of the power curve comprises: Extract the eigenvalues ​​of the smoothed power curve.

5. The abnormal sound signal detection method according to claim 4, characterized in that: The step of extracting the characteristic value of the smoothed power curve includes: Extracting the extreme values ​​of the smoothed power curve; Determine a characteristic value group for each signal period according to each of the extreme values; Then, each of the characteristic values ​​is analyzed based on the characteristic value threshold to determine the number of cycles of the periodic abnormal sound signal, including: For each signal period, determine whether each characteristic value in the characteristic value group meets the characteristic value threshold requirement. If so, the signal period is the period of the periodic abnormal sound signal. Calculate the number of times the disc ejection noise signal appears in each signal cycle.

6. The abnormal sound signal detection method according to claim 5, characterized in that: The characteristic value group includes: a maximum value, a left minimum value, a right minimum value, a rising portion width, a rising portion height, a falling portion width and a falling portion height.

7. The abnormal sound signal detection method according to claim 1, characterized in that: The determining whether the test product operates abnormally based on the number of cycles includes: It is determined whether the number of cycles exceeds a preset number threshold. If so, the operation of the product under test is abnormal; otherwise, the operation of the product under test is normal.

8. A device for detecting abnormal sound signals, characterized in that: include: A pickup module is used to pick up the sound signal of the product to be tested during the process of ejecting the disc, calculate the total power value of the sound signal, and trigger the analysis module when the total power value is within a preset range; when the total power value is outside the preset range, adjust the recording device and return to the step of picking up the sound signal of the product to be tested during the process of ejecting the disc; An analysis module, used to analyze the sound signal and determine the number of cycles of the periodic abnormal sound signal; The periodic abnormal sound signal is a plurality of identical sounds that appear at a certain frequency, including a periodic disc ejection abnormal sound signal; A determination module is used to determine whether the test product operates abnormally based on the number of cycles; wherein: The analysis module comprises: Performing denoising on the sound signal to obtain a denoised sound signal; Performing frame processing on the de-noised sound signal, and calculating the power value corresponding to each frame signal; Obtaining a power curve according to each of the power values; The power curve is analyzed based on a preset abnormal sound distribution to determine the number of cycles of occurrence of the periodic abnormal sound signal; wherein the preset abnormal sound distribution is obtained in advance by analyzing the power curve of the sound signal of the abnormal operation sample during the operation process and the power curve of the sound signal of the normal operation sample during the operation process.

9. A system for detecting abnormal sound signals, characterized in that: include: Memory for storing computer programs; A processor, configured to implement the steps of the abnormal sound signal detection method according to any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the abnormal sound signal detection method according to any one of claims 1 to 7 are implemented.

Images