Sound curve-based electrical equipment detection method, device, equipment and storage medium

Abstract

The application discloses an electrical equipment detection method and device based on a sound curve, an electrical equipment, and a storage medium. The method comprises the following steps: collecting a real-time sound curve of a target electrical equipment during operation, performing segmentation processing on the real-time sound curve to obtain a continuous sound curve to be matched; converting the sound curve to be matched into a target class rotation vector circle in a pre-constructed coordinate system based on a rotation vector method, determining a plurality of target pole point arrays corresponding to the target class rotation vector circle, and respectively calculating target point average speeds and target point average accelerations of the plurality of target pole point arrays; and determining a detection result corresponding to the target electrical equipment based on the target point average speeds, the target point average accelerations, standard point average speeds and standard point average accelerations corresponding to standard sound curves of the electrical equipment under a plurality of operating states. The recognition efficiency of the sound curve is improved, and the electrical equipment detection efficiency is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of device detection, and in particular to an electrical device detection method and device based on sound curves, an electrical device detection apparatus, and a storage medium. BACKGROUND

[0002] During the operation of an electrical device, there are various operating states, such as operation, shutdown, standby, and fault, and the sound emitted by the electrical device will vary due to the working state of the internal electrical and mechanical components in different operating states.

[0003] The prior art usually analyzes and decomposes the acquired sound characteristic curve in the frequency domain, converts the sound signal from the time domain to the frequency domain, and then identifies and learns through an artificial intelligence algorithm to extract the feature quantity of different sound patterns, thereby achieving real-time identification of the device state and improving the efficiency of electrical device detection. SUMMARY

[0004] The present application provides an electrical device detection method and device based on sound curves, and a storage medium, to solve the problem of low efficiency of electrical device detection.

[0005] According to an aspect of the present application, an electrical device detection method based on sound curves is provided, which comprises:

[0006] acquiring a real-time sound curve of a target electrical device in operation, and performing segmentation processing on the real-time sound curve to obtain a continuous sound curve to be matched;

[0007] converting the sound curve to be matched into a target class of rotational vector circles in a pre-constructed coordinate system based on a rotational vector method, determining a plurality of target pole point arrays corresponding to the target class of rotational vector circles, and respectively calculating the target point average speed and the target point average acceleration of the plurality of target pole point arrays;

[0008] determining a detection result corresponding to the target electrical device based on the target point average speed, the target point average acceleration, the standard point average speed and the standard point average acceleration corresponding to the standard sound curve of the electrical device in a plurality of operating states.

[0009] According to another aspect of the present application, an electrical device detection apparatus based on sound curves is provided, which comprises:

[0010] a sound curve acquisition module configured to acquire a real-time sound curve of a target electrical device in operation, and perform segmentation processing on the real-time sound curve to obtain a continuous sound curve to be matched;

[0011] a curve conversion module, configured to convert the to-be-matched sound curve into a target class rotation vector circle in a pre-constructed coordinate system based on a rotation vector method, determine a plurality of target polar point arrays corresponding to the target class rotation vector circle, and respectively calculate target point average speeds and target point average accelerations of the plurality of target polar point arrays;

[0012] a device detection module, configured to determine a detection result corresponding to the target electrical device based on the target point average speeds, the target point average accelerations, standard point average speeds and standard point average accelerations corresponding to standard sound curves of electrical devices in a plurality of operating states.

[0013] According to another aspect of the present application, an electronic device is provided, which comprises:

[0014] at least one processor; and

[0015] a memory connected to the at least one processor in communication; wherein,

[0016] the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to perform the electrical device detection method based on sound curves according to any one of the embodiments of the present application.

[0017] According to another aspect of the present application, a computer readable storage medium is provided, which stores computer instructions for enabling a processor to perform the electrical device detection method based on sound curves according to any one of the embodiments of the present application when executed.

[0018] The technical solution of the embodiments of the present application effectively extracts the continuous to-be-matched sound curve from the real-time sound curve of the target electrical device, converts the to-be-matched sound curve into a target class rotation vector circle in a pre-constructed coordinate system, determines a plurality of target polar point arrays corresponding to the target class rotation vector circle, respectively calculates target point average speeds and target point average accelerations of the plurality of target polar point arrays, and helps to improve the accuracy of sound matching and identification. The detection result corresponding to the target electrical device is determined based on the target point average speeds, the target point average accelerations, standard point average speeds and standard point average accelerations corresponding to standard sound curves of electrical devices in a plurality of operating states, which solves the problem of low efficiency of electrical device detection, improves the identification efficiency of sound curves, and improves the efficiency of electrical device detection.

[0019] It is to be understood that the details set forth herein do not limit the scope of the embodiments of the application to the specific embodiments described. The foregoing detailed description has set forth various embodiments of the devices and / or processes via the use of specific terminology. However, embodiments of the application should not be construed as limited to the foregoing aspects, and the terminology used herein should not be read to limit the claims by implication to specific embodiments. BRIEF DESCRIPTION OF DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiments description. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without any creative effort on the basis of these drawings.

[0021] Figure 1 is a flow chart of an electrical equipment detection method based on sound curve according to the first embodiment of the present application;

[0022] Figure 2a is a flow chart of an electrical equipment detection method based on sound curve according to the second embodiment of the present application;

[0023] Figure 2b is a sound curve conversion schematic diagram of an optional example of an electrical equipment detection method based on sound curve according to the second embodiment of the present application;

[0024] Figure 3 is a structural schematic diagram of an electrical equipment detection device based on sound curve according to the third embodiment of the present application;

[0025] Figure 4 is a structural schematic diagram of an electronic device for implementing an electrical equipment detection method based on sound curve according to the present application. DETAILED DESCRIPTION

[0026] In order to make the technical personnel in the art better understand the present application scheme, the following will combine the drawings in the embodiments of the present application, and the technical solutions in the embodiments of the present application will be described clearly and completely. Obviously, the described embodiments are only some embodiments of the present application, not all. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without any creative effort should belong to the scope of protection of the present application.

[0027] It is to be understood that the terminology "includes", "comprises", "comprising", "has", "having", "contains" and / or "containing", or variants thereof, as used herein is meant to be open-ended, and includes the stated features, integers, steps and / or elements but not excluding others. Thus, use of such terminology is meant to convey that the feature, integer, step and / or element so stated is an optional element and that the application may, at any given time, include one or more such features, integers, steps and / or elements, whether recited or not.

[0028] Embodiment one

[0029] Figure 1 A flowchart of an electrical equipment detection method based on sound curve is provided for the first embodiment of the application. The embodiment can be applied to electrical equipment detection. The method can be performed by an electrical equipment detection device based on sound curve. The device can be realized in the form of hardware and / or software. The device can be configured in an electronic device. As shown in the figure, the method comprises the following steps. Figure 1

[0030] S110, collecting a real-time sound curve of a target electrical equipment in operation, and performing segmentation processing on the real-time sound curve to obtain a continuous sound curve to be matched.

[0031] The real-time sound curve can be understood as a curve obtained by processing and analyzing the sound signal generated by the electrical equipment.

[0032] Specifically, the sound of the electrical equipment can be collected on site by a robot, and the sound can be converted into a sound curve, which is then transmitted to a computer for storage to obtain a real-time electrical equipment sound curve.

[0033] S120, converting the sound curve to be matched into a target class rotational vector circle in a pre-constructed coordinate system based on the rotational vector method, determining a plurality of target polar point arrays corresponding to the target class rotational vector circle, and calculating the target point average speed and target point average acceleration of the plurality of target polar point arrays, respectively.

[0034] The target class rotational vector circle can be understood as a reference circle. The target polar point array can include a highest point array, a lowest point array, a leftmost point array, and a rightmost point array.

[0035] ​Optionally, the converting the to-be-matched sound curve into a target quasi-rotation vector circle in a pre-constructed coordinate system based on the rotation vector method comprises: determining a maximum amplitude of the to-be-matched sound curve, constructing an initial quasi-rotation vector circle with the maximum amplitude as the radius and the origin of the coordinate system as the center, and projecting a point on the to-be-matched sound curve onto the transverse axis of the initial quasi-rotation vector circle; calculating a first derivative of the to-be-matched sound curve, determining a rotation direction of the point on the real-time sound curve based on the first derivative; taking the leftmost point of the initial quasi-rotation vector circle as a rotation starting point, and anchoring the point on the to-be-matched sound curve on the initial quasi-rotation vector circle based on the rotation direction to obtain a target quasi-rotation vector circle.

[0036] Specifically, the maximum amplitude of the to-be-matched sound curve is taken as the radius of the quasi-rotation vector circle, the movement of the sound curve to the positive direction of the x-axis (i.e., the first derivative of the point is positive) is defined as the clockwise rotation direction of the quasi-rotation vector circle, and the movement of the sound curve to the negative direction of the x-axis (i.e., the first derivative of the point is negative) is defined as the counterclockwise rotation direction. For the selection of the rotation starting point, considering the movement direction of the starting point of the sound curve, the leftmost point of the vector circle is selected as the rotation starting point. Then, the value of the x-axis corresponding to each point on the sound curve is projected onto the x-axis of the rotation vector circle, and the sound curve point is anchored on the initial quasi-rotation vector circle by judging the rotation direction to obtain a target quasi-rotation vector circle.

[0037] In the embodiment of the present application, by converting the sound curve into a quasi-rotation vector circle, the sound characteristics are mapped to a circular structure, which can make the sound characteristics more intuitive in vision. The feature information of multiple dimensions included in the sound signal can be presented in a more compact and integrated manner, facilitating subsequent comprehensive analysis of the sound signal based on the quasi-rotation vector circle.

[0038] Optionally, the determining a plurality of target polar point arrays corresponding to the target quasi-rotation vector circle comprises: extracting a target polar point on the target quasi-rotation vector circle, wherein the target polar point comprises a highest point, a lowest point, a leftmost point and a rightmost point; for each target polar point, extracting a plurality of interval points based on a preset interval on both sides of the target polar point, determining a polar point array corresponding to the target polar point based on the target polar point and the plurality of interval points; and determining a plurality of target polar point arrays corresponding to the target quasi-rotation vector circle based on the polar point arrays corresponding to the plurality of target polar points.

[0039] Specifically, after the point of the sound curve is anchored on the circle, the four target polar points of the circle, i.e., the highest point, the lowest point, the leftmost point and the rightmost point, are taken, and a plurality of interval points are extracted based on a preset interval. The preset interval can be pre-set according to experience, which is not limited in the embodiment.

[0040] Exemplarily, taking four target poles Ahigh, Alow, Aleft and Aright as examples, for each target pole, 10 points with an interval of are taken on both sides of the target pole to form four target pole arrays respectively:

[0041] S1 = [Ah1...Ah10, Ahigh, Ah11...Ah20]

[0042] S2 = [Aw1...Aw10, Alow, Aw11...Aw20]

[0043] S3 = [At1...At10, Aleft, At11...At20]

[0044] S4 = [Ar1...Ar10, Aright, Ar11...Ar20]

[0045] Each target pole array includes the target pole and 20 points on both sides of the target pole with an interval of .

[0046] Optionally, in the case where one point on the target class rotation vector circle corresponds to multiple points on the sound curve to be matched, the point average speed of the target pole array is calculated by the following formula:

[0047]

[0048] wherein v represents the point speed, Δt represents the interval, represents the arc length of the point of the target pole array on the target class rotation vector circle within the interval of Δt;

[0049]

[0050] wherein represents the point average speed of the target pole array, N represents the total number of points in the target pole array, i represents the ith point in the target pole array, and v i represents the point speed of the ith point in the target pole array.

[0051] Specifically, since the point frequency of the point on the vector circle, one point on the vector circle corresponds to multiple point speeds. In order to match subsequently, the speed should be unified. After calculating the speed corresponding to each point in the target pole array, the average acceleration of the vector circle point needs to be calculated. The point average speed of each point in the target pole array is calculated to obtain a point average speed array corresponding to the target pole array. The arrangement order of the points in the point average speed array is consistent with the arrangement order of the target pole array.

[0052] Optionally, after the point average speed of each point of the vector circle is determined, the point average speed array of the above array can be obtained. For example, the point average speed arrays corresponding to the target pole points S1, S2, S3 and S4 are G1, G2, G3 and G4. Each point average speed of the point average speed arrays of the vector circles of multiple continuous sound curves is compared one by one, and the difference is defined as the similarity, which is expressed by the formula as follows:

[0053]

[0054] wherein η is the similarity, m and n respectively correspond to the point average speed arrays corresponding to the same pole points of each sound curve, and i is the i th point in the array.

[0055] If the similarity η satisfies the normal distribution, i.e. η ~ N(0, 0.1), it indicates that the multiple sound curves satisfying the speed trend are consistent, and can be unified as the same sound curve of the running state.

[0056] Optionally, in the case that one point on the target class rotation vector circle corresponds to multiple points on the sound curve to be matched, the point average acceleration of the target pole point array is calculated, including: differentiating the target pole point array to obtain multiple point accelerations corresponding to the target pole point array; determining the point average acceleration corresponding to the target pole point array based on the multiple point accelerations.

[0057] Specifically, the point acceleration is obtained by differentiating the point speed, which is expressed by the formula as follows:

[0058]

[0059] wherein a is the point acceleration, v is the point speed, and Δt is the time interval.

[0060] By calculating the point acceleration of the target pole point array, the point average acceleration of the target pole point array is further calculated to obtain the point average acceleration array corresponding to the target pole point array, such as P1, P2, P3 and P4.

[0061] S130, based on the target point average speed, the target point average acceleration, the standard point average speed and the standard point average acceleration corresponding to the standard sound curve of the electrical equipment in multiple running states, a detection result corresponding to the target electrical equipment is determined.

[0062] Specifically, a sound database can be constructed in advance, and the sound database stores standard sound curves of the electrical equipment in various operating states, standard point average speeds corresponding to the standard sound curves of the electrical equipment in various operating states, and standard point average accelerations corresponding to the standard sound curves of the electrical equipment in various operating states. The detection result corresponding to the target electrical equipment is determined by the target point average speed, the target point average acceleration, and the sound database.

[0063] The technical scheme of the embodiment of the present application effectively extracts the continuous to-be-matched sound curve from the real-time sound curve of the target electrical equipment, converts the to-be-matched sound curve into a target class rotation vector circle in a pre-constructed coordinate system, determines a plurality of target pole point arrays corresponding to the target class rotation vector circle, and respectively calculates the target point average speed and the target point average acceleration of the plurality of target pole point arrays, which helps to improve the accuracy of sound matching and identification. The detection result corresponding to the target electrical equipment is determined based on the target point average speed, the target point average acceleration, the standard point average speed corresponding to the standard sound curve of the electrical equipment in various operating states, and the standard point average acceleration, which solves the problem of low efficiency of electrical equipment detection, improves the identification efficiency of the sound curve, and improves the efficiency of electrical equipment detection.

[0064] Embodiment Two

[0065] Figure 2a A flowchart of an electrical equipment detection method based on a sound curve is provided for the second embodiment of the present application. This embodiment is a further refinement of how to determine the detection result corresponding to the target electrical equipment based on the target point average speed, the target point average acceleration, the standard point average speed corresponding to the standard sound curve of the electrical equipment in various operating states, and the standard point average acceleration in the above-mentioned embodiments. As shown in Figure 2a The method comprises the following steps:

[0066] S210, collecting a real-time sound curve of a target electrical equipment in operation, and performing segmentation processing on the real-time sound curve to obtain a continuous to-be-matched sound curve.

[0067] S220, converting the to-be-matched sound curve into a target class rotation vector circle in a pre-constructed coordinate system based on the rotation vector method, determining a plurality of target pole point arrays corresponding to the target class rotation vector circle, and respectively calculating the target point average speed and the target point average acceleration of the plurality of target pole point arrays.

[0068] S230, respectively determine a standard pole array corresponding to a standard sound curve in each operating state, and determine a standard point average speed and a standard point average acceleration corresponding to the standard pole array.

[0069] S240, match a point average speed of each target pole array with a standard point average speed of the standard pole array corresponding thereto to obtain a first matching degree.

[0070] Optionally, the first matching degree is determined by the following formula:

[0071]

[0072] wherein, α ki is a matching degree of the point average speed with the standard point average speed, represents a point average speed of an i-th point corresponding to a k-th target pole array, represents a point average speed of an i-th point corresponding to a k-th standard pole array;

[0073]

[0074] wherein, τ1 is the first matching degree, K represents a total number of the target pole arrays, and I represents a total number of points in all the target pole arrays.

[0075] S250, match a point average acceleration of each target pole array with a standard point average acceleration of the standard pole array corresponding thereto to obtain a second matching degree.

[0076] Specifically, the second matching degree is determined by the following formula:

[0077]

[0078] wherein, β ki is a matching degree of the point average acceleration with the standard point average acceleration, represents a point average acceleration of an i-th point corresponding to a k-th target pole array, represents a point average acceleration of an i-th point corresponding to a k-th standard pole array;

[0079]

[0080] wherein, τ2 is the second matching degree, K represents a total number of the target pole arrays, and I represents a total number of points in all the target pole arrays.

[0081] S260, determine a target standard sound curve matched with the sound curve to be matched based on the first matching degree and the second matching degree, and determine a detection result corresponding to the target electrical device based on an operating state corresponding to the target standard sound curve.

[0082] Specifically, if the first matching degree and the second matching degree of the sound curve to be matched are both higher than a preset matching degree threshold, the standard sound curve is determined as the target standard sound curve matched with the sound curve to be matched, and an operating state corresponding to the target standard sound curve is determined as an operating state corresponding to the target electrical device. If the first matching degree and the second matching degree are both lower than the preset matching degree threshold, the standard sound curve with the highest first matching degree and second matching degree is determined as the target standard sound curve matched with the sound curve to be matched, the target class rotation vector circle of the sound curve to be matched and the class rotation vector circle of the standard sound curve are unified in radius, and steps S220-S260 are repeated. If the sound curve to be matched still cannot be matched, it indicates that the electrical device is operating abnormally, a detection result of the abnormal operation is returned, and the sound curve to be matched is stored in the sound database. The preset matching degree threshold can be set according to experience, which is not limited in the embodiment.

[0083] Optionally, in the case that one point on the target class rotation vector circle corresponds to a plurality of points on the sound curve to be matched, a point frequency corresponding to each point in the target pole point array is determined, and a third matching degree is obtained by matching the point frequency of each target pole point array with a standard point frequency of the standard pole point array corresponding thereto. In the case that the first matching degree, the second matching degree and the third matching degree are all higher than the preset matching degree threshold, the standard sound curve satisfying the preset matching degree threshold is determined as the target standard sound curve matched with the sound curve to be matched.

[0084] The technical scheme of the embodiment of the application comprehensively considers a plurality of characteristics of the sound curve, and improves the accuracy and reliability of determining the state of the electrical device based on the sound curve.

[0085] As an optional example of the first embodiment of the present application, the sound curve-based electrical equipment detection method of the present embodiment specifically comprises the following steps:

[0086] Step 1: Construct a sound database, collect the sound curve of the electrical equipment on site

[0087] Extract the sound curve of the electrical equipment in various operating states, divide and input into the sound database according to different states such as normal operation and fault, so as to perform the subsequent matching step. Collect the sound curve on site by the robot, and then transmit it to the computer end to save the real-time electrical equipment sound curve.

[0088] Step 2: Divide the continuous sound curve collected on site according to its repeated appearance frequency to form a typical curve

[0089] Process the collected sound curve, divide the image with no fluctuation for a long time in the middle to form each continuous sound curve to be matched. Then, Figure 2b An optional example of sound curve conversion schematic diagram of the sound curve-based electrical equipment detection method is provided. As shown in Figure 2b , the sound curve to be matched is converted into a target class rotation vector circle in a pre-constructed coordinate system based on the rotation vector method, and the irregular continuous sound curve is converted into a class rotation vector.

[0090] The specific steps are as follows:

[0091] Take the maximum amplitude of the sound curve to be matched as the radius of the class rotation vector circle, and define the movement of the sound curve to the positive direction of the x-axis (i.e., the first derivative of the point is positive) as the clockwise rotation direction of the class rotation vector circle, and the movement to the negative direction of the x-axis as the counterclockwise direction. For the selection of the rotation starting point, considering the movement direction of the starting point of the sound curve, the leftmost point of the vector circle should be selected as the rotation starting point. Then, project the value of each point on the sound curve to be matched on the x-axis to the x-axis of the target class rotation vector circle, and then determine the point of the sound curve to be anchored on the circle by judging the rotation direction.

[0092] After anchoring the points of the sound curve to be matched on the circle, take the four extreme points of the circle, i.e., the highest point, the lowest point, the leftmost point, and the rightmost point, and take 10 points on each side of the extreme points with an interval of to form four arrays respectively:

[0093] S1=[Ah1...Ah10,Ahigh,Ah11...Ah20]

[0094] S2=[Aw1...Aw10,Alow,Aw11...Aw20]

[0095] S3=[At1...At10,Aleft,At11...At20]

[0096] S4 = [Ar1...Ar10, Aright, Ar11...Ar20]

[0097] First, the point acceleration, due to the irregularity of the sound curve, the point running speed can not be obtained by the slope. Take the same interval Δt, take a point of the sound curve, and let the point on the vector circle corresponding to the point pass through the arc length in the interval Then the point speed of the point is

[0098]

[0099] Where v represents the point speed, Δt represents the interval, The arc length of the point of the target pole array on the target class rotation vector circle in the interval Δt is represented.

[0100]

[0101] Where, The average speed of the point of the target pole array is represented, N represents the total number of points in the target pole array, i represents the i-th point in the target pole array, and v i The point speed of the i-th point in the target pole array is represented.

[0102] By the above method, the point average speed of each point of the vector circle is obtained, and the point average speed array of the above array is obtained, which is G1, G2, G3, G4. Each element of the point average speed array of the vector circle of multiple continuous sound curves is compared one by one, and the difference is defined as the similarity, that is, η

[0103]

[0104] Where η is the similarity, m and n respectively correspond to the point average speed array corresponding to the same pole of each sound curve, and i is the i-th point in the array.

[0105] If the similarity η satisfies the normal distribution, that is, η ~ N(0, 0.1), it indicates that the multiple sound curves with the same speed meet the consistent trend, and can be unified as the same running state sound curve.

[0106] Step 3 similarity matching

[0107] For the sound curves of various running states extracted from the sound database, the sound curves are converted into class rotation vectors by the same method, and the pole array is obtained.

[0108] Then take the real-time collected curve to be matched and the standard sound curve in the database for matching:

[0109] For the sound curve to be matched and the standard sound curve in the database, the point average speed array of each is obtained, and the point average speed array of the sound curve to be matched is compared with the point average speed array of the standard sound curve in the database one by one to obtain a ratio defined as a matching degree, and the ratio of the point average speed is a first matching degree, i.e.

[0110]

[0111] wherein, α ki is the matching degree of the point average speed and the standard point average speed, represents the point average speed of the i-th point corresponding to the k-th target pole array, represents the point average speed of the i-th point corresponding to the k-th standard pole array.

[0112]

[0113] wherein, τ1 is the first matching degree, K represents the total number of target pole arrays, and I represents the total number of points in all target pole arrays.

[0114] Then, the point acceleration array is defined, and a second matching degree is obtained through comparison:

[0115] The point acceleration is obtained by differentiating the point speed, and is expressed by the following formula:

[0116]

[0117] wherein, a is the point acceleration, v is the point speed, and Δt is the time interval.

[0118] The point average acceleration of the target pole array is calculated by calculating the point acceleration of the target pole array, and the point average acceleration array corresponding to the target pole array, such as P1, P2, P3, and P4, is obtained.

[0119] The second matching degree is determined by the following formula:

[0120]

[0121] wherein, β ki represents the matching degree of the point average acceleration and the standard point average acceleration, represents the point average acceleration of the i-th point corresponding to the k-th target pole array, represents the point average acceleration of the i-th point corresponding to the k-th standard pole array.

[0122]

[0123] Wherein, τ2 is the second matching degree, K represents the total number of target pole array, and I represents the total number of points in all target pole arrays.

[0124] Optionally, because of the irregularity of the sound curve, one point on the vector circle may correspond to multiple points on the sound curve in the anchoring process, which may cause differences in characteristics (such as point speed, point acceleration, etc.) of one point on the vector circle in traversal, and thus a point frequency is proposed, that is, the number of points on the sound curve corresponding to one point on the vector circle, and each point on the vector circle in the S1, s2, S3, S4 array is one-to-one corresponding to obtain the point frequency N of each point to form the point frequency array M1, M2, M3, M4.

[0125] Specifically, in the case where one point on the target class rotation vector circle corresponds to multiple points on the sound curve to be matched, the point frequency corresponding to each point in the target pole array is determined, and each point frequency of the target pole array is matched with the standard point frequency of the standard pole array corresponding thereto to obtain a third matching degree.

[0126] Step 4: Determine the curve with the highest matching degree to confirm the running state of the device

[0127] For the sound curve to be matched, the standard sound curve stored in the sound database and the standard pole array corresponding to the standard sound curve under each running state are traversed, and the standard point average speed and the standard point average acceleration corresponding to the standard pole array are determined.

[0128] Exemplarily, the obtained first matching degree and second matching degree are compared, the standard sound curve with the highest matching degree and both the first matching degree and the second matching degree higher than 0.9 is taken as the target standard sound curve, that is, the target standard sound curve matched with the sound curve to be matched. If there are multiple standard sound curves with the first matching degree and the second matching degree higher than 0.9, the standard sound curve with the highest matching degree can be determined by assigning weights to the first matching degree and the second matching degree and by weighted summation; or the standard sound curve with the highest third matching degree can be selected by calculating the point frequency matching degree of the multiple standard sound curves with the first matching degree and the second matching degree higher than 0.9, that is, the third matching degree.

[0129] If the first matching degree and the second matching degree are both lower than the preset matching degree threshold, the standard sound curve with the highest first matching degree and the second matching degree of the sound curve to be matched is determined, the target class rotation vector circle of the sound curve to be matched and the class rotation vector circle of the standard sound curve are unified in radius, and the first matching degree and the second matching degree are repeatedly calculated. If the matching still cannot be achieved, it indicates that the electrical equipment is running abnormally, the detection result of the abnormal running is returned, and the abnormal sound curve to be matched is stored in the sound database.

[0130] The technical scheme of the embodiment of the present application is that, by dividing the continuous sound curve, the conversion method of the quasi-rotation vector is obtained by imitating the conversion of the rotation vector, and on this basis, the characteristic quantity of each pole of the quasi-rotation vector circle is researched to form the typical curve collected in real time, so that the subsequent matching is more efficient. In the matching process, the array comparison of the point speed and the point acceleration is introduced, so that the matching process is more representative and accurate. Compared with the complex spectrum analysis and artificial intelligence algorithm, the embodiment adopts a more convenient image conversion analysis method, simplifies the identification process, reduces the technical threshold, and improves the matching efficiency. The conversion method of the quasi-rotation vector and the array characteristic quantity analysis method are adopted, the continuous sound curve is divided to form the typical curve, then the typical curve is matched with the extracted curve in the database to obtain the most suitable curve, and the running state corresponding to the typical curve is determined. This can avoid the matching errors caused by the problems such as high requirement for computing resources and serious dependence on sample data in the identification process of the algorithm. The application scene of the present application requires low, is suitable for various electrical equipment production scenes, and has universal applicability.

[0131] Embodiment three

[0132] Figure 3 A structure schematic diagram of an electrical equipment detection device based on a sound curve provided by the third embodiment of the present application is shown in the figure. Figure 3 As shown in the figure, the device comprises a sound curve collection module 310, a curve conversion module 320, and an equipment detection module 330.

[0133] The sound curve collection module 310 is used to collect the real-time sound curve of the target electrical equipment in operation, and divide the real-time sound curve to obtain a continuous sound curve to be matched. The curve conversion module 320 is used to convert the sound curve to be matched into a target quasi-rotation vector circle in a pre-constructed coordinate system based on the rotation vector method, determine a plurality of target pole arrays corresponding to the target quasi-rotation vector circle, and calculate the target point average speed and the target point average acceleration of the plurality of target pole arrays. The equipment detection module 330 is used to determine the detection result corresponding to the target electrical equipment based on the target point average speed, the target point average acceleration, the standard point average speed and the standard point average acceleration corresponding to the standard sound curve of the electrical equipment in a plurality of running states.

[0134] The technical scheme of the embodiment of the application acquires a real-time sound curve of a target electrical equipment in operation through a sound curve acquisition module, performs segmentation processing on the real-time sound curve to obtain a continuous sound curve to be matched, effectively extracts the continuous sound curve to be matched from the real-time sound curve of the target electrical equipment, converts the sound curve to be matched into a target quasi-rotational vector circle under a pre-constructed coordinate system through a curve conversion module, determines a plurality of target pole point arrays corresponding to the target quasi-rotational vector circle, and respectively calculates target point average speeds and target point average accelerations of the plurality of target pole point arrays, which helps to improve the accuracy of sound matching and identification, determines a detection result corresponding to the target electrical equipment based on the target point average speeds, the target point average accelerations, standard point average speeds and standard point average accelerations corresponding to standard sound curves of the electrical equipment under a plurality of operating states through a device detection module, solves the problem of low efficiency of electrical equipment detection, and improves the identification efficiency of the sound curve and the efficiency of electrical equipment detection.

[0135] Optionally, the curve conversion module comprises:

[0136] An initial quasi-rotational vector circle construction unit is configured to determine a maximum amplitude of the sound curve to be matched, construct an initial quasi-rotational vector circle with the maximum amplitude as a radius and a coordinate system origin as a center, and project points on the sound curve to be matched onto a transverse axis of the initial quasi-rotational vector circle.

[0137] A rotation direction determination unit is configured to calculate a first derivative of the sound curve to be matched, and determine a rotation direction of points on the real-time sound curve based on the first derivative.

[0138] A target quasi-rotational vector circle determination unit is configured to take a leftmost point of the initial quasi-rotational vector circle as a rotation starting point, anchor points on the sound curve to be matched on the initial quasi-rotational vector circle based on the rotation direction, and obtain a target quasi-rotational vector circle.

[0139] Optionally, the curve conversion module comprises:

[0140] A target pole point extraction unit is configured to extract target pole points on the target quasi-rotational vector circle, wherein the target pole points include a highest point, a lowest point, a leftmost point and a rightmost point.

[0141] A pole point array determination unit is configured to, for each target pole point, extract a plurality of interval points based on a preset interval on both sides of the target pole point, and determine a pole point array corresponding to the target pole point based on the target pole point and the plurality of interval points.

[0142] The target pole array determination unit is configured to determine a plurality of target pole arrays corresponding to the target class rotation vector circle based on a plurality of target poles corresponding to pole arrays.

[0143] Optionally, the curve conversion module is specifically configured to calculate the point average speed of the target pole array by the following formula in a case where one point on the target class rotation vector circle corresponds to a plurality of points on the sound curve to be matched:

[0144]

[0145] wherein v represents the point speed, Δt represents the interval, represents the arc length of the point of the target pole array on the target class rotation vector circle within the interval of Δt;

[0146]

[0147] wherein, represents the point average speed of the target pole array, N represents the total number of points in the target pole array, i represents the i-th point in the target pole array, and v i represents the point speed of the i-th point in the target pole array.

[0148] Optionally, the curve conversion module comprises:

[0149] The differential processing unit is configured to perform differential processing on the target pole array to obtain a plurality of point accelerations corresponding to the target pole array in a case where one point on the target class rotation vector circle corresponds to a plurality of points on the sound curve to be matched.

[0150] The point average acceleration determination unit is configured to determine a point average acceleration corresponding to the target pole array based on a plurality of point accelerations.

[0151] Optionally, the device detection module comprises:

[0152] The standard pole array determination unit is configured to determine a standard pole array corresponding to a standard sound curve in each operating state, and determine a standard point average speed and a standard point average acceleration corresponding to the standard pole array.

[0153] The first matching degree acquisition unit is configured to match the point average speed of each target pole array with the standard point average speed of the standard pole array corresponding thereto to obtain a first matching degree.

[0154] The second matching degree acquisition unit is configured to match the point average acceleration of each target pole array with the standard point average acceleration of the standard pole array corresponding thereto to obtain a second matching degree.

[0155] The detection result determination unit is configured to determine a target standard sound curve matched with the sound curve to be matched based on the first matching degree and the second matching degree, and determine a detection result corresponding to the target electrical device based on an operating state corresponding to the target standard sound curve.

[0156] Optionally, the first matching degree acquisition unit is specifically configured to determine the first matching degree by the following formula:

[0157]

[0158] Wherein, α ki is a matching degree of the point average speed and the standard point average speed, represents a point average speed of the i-th point corresponding to the k-th target pole array, represents a point average speed of the i-th point corresponding to the k-th standard pole array.

[0159]

[0160] Wherein, τ1 is the first matching degree, K represents the total number of target pole arrays, and I represents the total number of points in all target pole arrays.

[0161] The electrical device detection device based on the sound curve provided by the embodiment of the application can execute the electrical device detection method based on the sound curve provided by any embodiment of the application, and has the corresponding function modules and beneficial effects of the execution method.

[0162] Embodiment four

[0163] Figure 4 A structural schematic diagram of an electronic device 10 that can be used to implement embodiments of the present application is shown. The electronic device is intended to represent various forms of digital computers, such as laptops, desktops, tablets, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular telephones, smart phones, wearable devices (e.g., headsets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be examples only, and are not intended to limit the implementations of the present application described and / or claimed in this document.

[0164] As Figure 4As shown, the electronic device 10 includes at least one processor 11, and a memory, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., communicatively connected to the at least one processor 11, where the memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes according to the computer programs stored in the read-only memory (ROM) 12 or loaded into the random access memory (RAM) 13 from the storage unit 18. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0165] Various components in the electronic device 10 are connected to the I / O interface 15, including an input unit 16, such as a keyboard, a mouse, etc., an output unit 17, such as various types of displays, a speaker, etc., a storage unit 18, such as a magnetic disk, an optical disk, etc., and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network, such as the Internet, and / or various telecommunication networks.

[0166] The processor 11 can be various general and / or special-purpose processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 performs various methods and processes described above, such as the method for electrical device detection based on sound profile.

[0167] In some embodiments, the method for electrical device detection based on sound profile can be implemented as a computer program tangibly embodied in a computer readable storage medium, such as the storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed onto the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the method for electrical device detection based on sound profile described above can be performed. Alternatively, in other embodiments, the processor 11 can be configured to perform the method for electrical device detection based on sound profile by any other appropriate means, such as by means of firmware.

[0168] The various embodiments of the systems and techniques described above can be implemented in digital electronic circuitry, integrated circuitry, a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), a system on a chip (SOC), a load programmable logic device (CPLD), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include implementation in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be special or general purpose, coupled to receive data and instructions from, and to transmit data and instructions to, a storage system, at least one input device, and at least one output device.

[0169] Computer programs used to implement the processes of the application can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the computer program, when executed, can cause instructions defined in the flow charts and / or block diagrams to be implemented on the computer or other programmable apparatus. The computer programs can be executed entirely on a machine, partially on a machine, partially on a machine as a stand-alone software package, partially on a machine and partially on a remote machine or entirely on a remote machine or server.

[0170] In the context of the present application, a computer-readable storage medium can be a tangible medium that can contain or store computer programs for use by or in connection with an instruction execution system, apparatus, or device. Computer-readable storage media can include, but are not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium can be a machine-readable signal medium. More specific examples of the machine-readable storage medium will include one or more lines of electrical connections, portable computer disks, hard disk drives, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or Flash memory), optical fibers, portable compact disc read-only memories (CD-ROMs), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0171] To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic device having a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the electronic device. Other kinds of devices can be used to provide for interaction with a user as well; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form, including acoustic, speech, or tactile input.

[0172] The systems and techniques described here can be implemented in a computing system that includes a back end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front end component (e.g., a user computer having a graphical user interface or a Web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back end, middleware, or front end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0173] The computing system can include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. A server can be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system, to solve the defects of large management difficulty and weak business scalability in traditional physical host and VPS service.

[0174] It should be understood that the various forms of flow shown above can be re-ordered, added to, or deleted from without departing from the scope of the present disclosure. For example, the steps recited in the present disclosure can be executed in parallel, executed in sequence, or executed in a different order, as long as the desired results of the present disclosure are achieved, and the present disclosure is not limited herein.

[0175] The specific embodiments described above are not intended to be limiting, and persons skilled in the art will appreciate that various modifications, combinations, sub-combinations and alternatives can be made to the specific embodiments without departing from the spirit and principles of the disclosure. Accordingly, the disclosure is not limited to the specific embodiments described above, but only by the scope of the appended claims.

Claims

1. A method for testing electrical equipment based on sound curves, characterized in that, include: The real-time sound curve of the target electrical equipment during operation is collected, and the real-time sound curve is segmented to obtain a continuous sound curve to be matched. Based on the rotation vector method, the sound curve to be matched is converted into a target class rotation vector circle in a pre-constructed coordinate system. Multiple target pole arrays corresponding to the target class rotation vector circle are determined, and the average velocity and average acceleration of the target points of the multiple target pole arrays are calculated respectively. The detection result corresponding to the target electrical equipment is determined based on the target point average velocity, the target point average acceleration, and the standard point average velocity and standard point average acceleration corresponding to the standard sound curves of the electrical equipment under various operating conditions.

2. The method according to claim 1, characterized in that, The step of converting the sound curve to be matched into a target-class rotating vector circle in a pre-constructed coordinate system based on the rotating vector method includes: Determine the maximum amplitude of the sound curve to be matched, construct an initial class of rotating vector circles with the origin of the coordinate system as the center and the maximum amplitude as the radius, and project the points on the sound curve to be matched onto the horizontal axis of the initial class of rotating vector circles; Calculate the first derivative of the sound curve to be matched, and determine the rotation direction of the points on the real-time sound curve based on the first derivative; Using the leftmost endpoint of the initial class rotation vector circle as the rotation starting point, the points on the sound curve to be matched are anchored on the initial class rotation vector circle based on the rotation direction to obtain the target class rotation vector circle.

3. The method according to claim 1, characterized in that, The determination of the array of multiple target poles corresponding to the target class rotation vector circle includes: Extract the target poles on the target class rotation vector circle, wherein the target poles include the highest point, the lowest point, the leftmost endpoint, and the rightmost endpoint; For each target pole, multiple interval points are extracted on both sides of the target pole based on a preset interval, and a pole array corresponding to the target pole is determined based on the target pole and the multiple interval points; Based on the pole arrays corresponding to the multiple target poles, determine the multiple target pole arrays corresponding to the target class rotation vector circle.

4. The method according to claim 1, characterized in that, When a point on the target class rotation vector circle corresponds to multiple points on the sound curve to be matched, the average velocity of the target pole array is calculated using the following formula: Where v represents the point velocity, and Δt represents the interval. This represents the arc length traversed by the points in the target pole array on the target class rotation vector circle within an interval of Δt; in, Let v represent the average velocity of the target pole array, N represent the total number of points in the target pole array, and i represent the i-th point in the target pole array. i This represents the point velocity of the i-th point in the target pole array.

5. The method according to claim 1, characterized in that, When a point on the target class rotation vector circle corresponds to multiple points on the sound curve to be matched, the point-average acceleration of the target pole array is calculated, including: The target pole array is differentiated to obtain the accelerations of multiple points corresponding to the target pole array; The average acceleration of the points corresponding to the target pole array is determined based on the acceleration of the points.

6. The method according to claim 1, characterized in that, The determination of the detection result corresponding to the target electrical equipment based on the target point average velocity, the target point average acceleration, and the standard point average velocity and standard point average acceleration corresponding to the standard sound curves of the electrical equipment under various operating states includes: Determine the standard pole array corresponding to the standard sound curve for each operating state, and determine the standard point average velocity and standard point average acceleration corresponding to the standard pole array; The point average velocity of each target pole array is matched with the standard point average velocity of its corresponding standard pole array to obtain a first matching degree. The point-average acceleration of each target pole array is matched with the standard point-average acceleration of its corresponding standard pole array to obtain a second matching degree; Based on the first matching degree and the second matching degree, a target standard sound curve that matches the sound curve to be matched is determined, and based on the operating state corresponding to the target standard sound curve, a detection result corresponding to the target electrical equipment is determined.

7. The method according to claim 6, characterized in that, The first degree of matching is determined using the following formula: Where, α ki The degree of matching between the point average velocity and the standard point average velocity. This represents the average point velocity of the i-th point corresponding to the k-th target pole array. This represents the point average velocity of the i-th point corresponding to the k-th standard pole array; Where τ1 is the first matching degree, K represents the total number of target pole arrays, and I represents the total number of points in all target pole arrays.

8. An electrical equipment testing device based on sound curves, characterized in that, include: The sound curve acquisition module is used to acquire the real-time sound curve of the target electrical equipment during operation, and to segment the real-time sound curve to obtain a continuous sound curve to be matched. The curve conversion module is used to convert the sound curve to be matched into a target-type rotating vector circle in a pre-constructed coordinate system based on the rotating vector method, determine multiple target pole arrays corresponding to the target-type rotating vector circle, and calculate the average velocity and average acceleration of the target points of the multiple target pole arrays respectively. The equipment detection module is used to determine the detection result corresponding to the target electrical equipment based on the target point average velocity, the target point average acceleration, and the standard point average velocity and standard point average acceleration corresponding to the standard sound curves of the electrical equipment under various operating states.

9. An electronic device, characterized in that, At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the electrical equipment detection method based on sound curves as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that, when executed by a processor, implement the electrical equipment detection method based on sound curves as described in any one of claims 1-7.

Images