Converter valve discharge voiceprint monitoring method and system, electronic equipment and medium

Abstract

The invention relates to a converter valve discharge voiceprint monitoring method and system, electronic equipment and a medium. The method comprises the following steps: dividing voiceprint signals according to operating voltage and operating current and working conditions; performing point symmetry transformation operation and rectangular coordinate transformation on the normal state voiceprint signal to obtain a normal state rectangular coordinate; performing point symmetry transformation operation and rectangular coordinate transformation on the fault state voiceprint signal to obtain a fault state rectangular coordinate; training samples are made according to the normal state rectangular coordinates and the fault state rectangular coordinates under the same working condition, and the graph convolutional neural network is trained through the training samples; and obtaining a voiceprint signal of the converter valve to be monitored, performing preprocessing, and performing detection through the trained graph convolutional neural network to obtain a converter valve fault diagnosis result.

Description

Technical Field

[0001] The present disclosure relates to a method, system, electronic equipment and medium for monitoring converter valve discharge soundprints, and belongs to the technical field of power transmission and transformation operation and maintenance. Background Art

[0002] Converter valves are core components of direct current (DC) transmission systems. Accurate monitoring of their operating status is crucial for ensuring operational reliability, availability, and efficient maintenance. During actual operation, converter valves are subject to abnormal operating conditions such as load and overvoltage, as well as harsh electromagnetic environments. These abnormal operating conditions, along with the natural aging of components, can easily lead to abnormal discharges in converter valve components. Defects in converter transformers can develop during operation due to factors such as manufacturing processes, external damage, and excessive voltage / current, triggering partial discharges. These defects can further develop, ultimately leading to breakdown of the converter transformer's insulation components and potentially causing fires, explosions, and other serious accidents. Current monitoring methods for converter valve discharges include ultraviolet (UV) signal monitoring, ultra-high frequency (UHF) monitoring, and soundprint monitoring. Soundprint monitoring is widely recognized for its non-contact and easily accessible nature. However, current research suffers from diagnostic inaccuracies, particularly the difficulty in diagnosing weak discharge soundprints in the presence of strong background noise. Summary of the Invention

[0003] In order to overcome the above problems, the present disclosure provides a method, system, electronic device and medium for monitoring converter valve discharge soundprint.

[0004] The technical solutions disclosed in this disclosure are as follows:

[0005] In a first aspect, the present disclosure provides a method for monitoring converter valve discharge soundprints, comprising:

[0006] Collecting normal-state voiceprint signals under different working conditions, performing a point-symmetric transformation operation on the normal-state voiceprint signals to obtain polar coordinate system coordinates of the normal-state voiceprint signals, and performing a rectangular coordinate transformation on the polar coordinate system coordinates of the normal-state voiceprint signals to obtain normal-state rectangular coordinates;

[0007] Collecting fault state voiceprint signals under different working conditions, performing a point symmetric transformation operation on the fault state voiceprint signals to obtain polar coordinate system coordinates of the fault state voiceprint signals, and performing a rectangular coordinate transformation on the polar coordinate system coordinates of the fault state voiceprint signals to obtain rectangular coordinates of the fault state;

[0008] Creating training samples based on normal state rectangular coordinates and fault state rectangular coordinates under the same working conditions, and training the graph convolutional neural network using the training samples;

[0009] The voiceprint signal of the converter valve to be monitored is obtained, and after preprocessing, it is detected through the trained graph convolutional neural network to obtain the converter valve fault diagnosis result.

[0010] Furthermore, a point-symmetric transformation operation is performed on the normal state voiceprint signal, specifically:

[0011]

[0012] Among them, r base (i) is the polar coordinate radius of point i, i = 1, 2, 3, ..., T s , T s is the length of the normal voiceprint signal, x base_i is the normal state voiceprint signal, T s is the length of the normal voiceprint signal, x base_min and x base_max are the minimum and maximum values of the voiceprint signal in normal state, θ base (i) is the counterclockwise rotation angle of point i about the mirror symmetry plane, θ is the rotation angle of the mirror symmetry plane, l is the time interval, g is the angle magnification factor, and g<θ, is the angle of rotation of point i in the clockwise direction about the mirror symmetry plane.

[0013] Furthermore, the polar coordinate system of the normal voiceprint signal is transformed into rectangular coordinates, specifically:

[0014] x base_ θ _ i =r base (i)cos(θ base (i));

[0015] y base_θ_i =r base (i)sin(θ base (i));

[0016]

[0017] Among them, x base_θ_i is the horizontal coordinate of the rectangular coordinate system of the point under the counterclockwise rotation angle, y base_θ_i is the ordinate of the rectangular coordinate system of the point under the counterclockwise rotation angle, is the horizontal coordinate of the rectangular coordinate system of the point under the clockwise rotation angle, The ordinate of the rectangular coordinate system of the point under the clockwise rotation angle.

[0018] Furthermore, a point-symmetric transformation operation is performed on the fault state voiceprint signal, specifically:

[0019]

[0020] Among them, r test (i) is the normalized fault state voiceprint signal, x test_i is the fault state voiceprint signal, θ test (i) is the angle of rotation of point i in the counterclockwise direction about the mirror symmetry plane, is the angle of rotation of point i in the clockwise direction about the mirror symmetry plane.

[0021] Furthermore, the polar coordinate system coordinates of the fault state voiceprint signal are transformed into rectangular coordinates, specifically:

[0022] x test_ θ _i =r test (i)cos(θ test (i));

[0023] y test_θ_i =r test (i)sin(θ test (i));

[0024]

[0025] Among them, x test_θ_i is the horizontal coordinate of the rectangular coordinate system of point i under the counterclockwise rotation angle, y test_θ_i is the ordinate of the rectangular coordinate system of point i under the counterclockwise rotation angle, is the horizontal coordinate of the rectangular coordinate system of point i under the clockwise rotation angle, is the ordinate of the rectangular coordinate system of point i under the clockwise rotation angle.

[0026] Furthermore, training samples are prepared based on the normal state rectangular coordinates and the fault state rectangular coordinates under the same working conditions, specifically:

[0027] Obtain several normal state rectangular coordinates and fault state rectangular coordinates under the same working conditions and convert them into three-dimensional coordinates. The three-dimensional coordinates of the normal state rectangular coordinates are and The three-dimensional coordinates of the rectangular coordinates of the fault state are (x test_θ_i ,y test_θ_i ,z) and And z≠0;

[0028] Polar coordinates are obtained by randomly combining the normal state rectangular coordinates and the fault state rectangular coordinates in the following way:

[0029]

[0030] Among them, d θ (i) and is the polar coordinate radius of the fault sample from the normal sample in counterclockwise and clockwise angles, θ(i) and The rotation angles are counterclockwise and clockwise;

[0031] The polar coordinates are plotted in a polar coordinate system, and corresponding working conditions and fault types are marked to obtain training samples.

[0032] Furthermore, the preprocessing of the voiceprint signal of the converter valve to be monitored is specifically as follows:

[0033] Obtaining the operating voltage and operating current of the converter valve to be monitored, and determining the operating condition of the converter valve according to the operating voltage and operating current of the converter valve to be monitored;

[0034] Obtain a normal state voiceprint signal of the same working condition as the converter valve to be monitored, perform a point symmetric transformation operation on the normal state voiceprint signal to obtain a polar coordinate system coordinate of the normal state voiceprint signal of the same working condition, and perform a rectangular coordinate transformation on the polar coordinate system coordinate of the normal state voiceprint signal of the same working condition to obtain a rectangular coordinate system coordinate of the normal state voiceprint signal of the same working condition;

[0035] Performing a point-symmetric transformation operation on the converter valve soundprint signal to be monitored to obtain the polar coordinate system coordinates of the converter valve soundprint signal to be monitored, and performing a rectangular coordinate transformation on the polar coordinate system coordinates of the converter valve soundprint signal to be monitored to obtain the rectangular coordinates of the converter valve to be monitored;

[0036] A test sample is produced according to the rectangular coordinates of the normal state under the same working conditions and the rectangular coordinates of the converter valve to be monitored.

[0037] In a second aspect, the present disclosure provides a converter valve discharge soundprint monitoring system, comprising a data acquisition module, a data processing module, and a data output module;

[0038] The data acquisition module collects the operating voltage, operating current and soundprint signals of the converter valve under different working conditions;

[0039] The data processing module processes the data collected by the data acquisition module according to the converter valve discharge soundprint monitoring method described in the first aspect to obtain a converter valve fault diagnosis result;

[0040] The data output module outputs the converter valve fault diagnosis result.

[0041] In a third aspect, the present disclosure provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, wherein when the processor executes the computer program, the method for monitoring the discharge soundprint of a converter valve as described in the first aspect is implemented.

[0042] In a fourth aspect, the present disclosure provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the method for monitoring the discharge soundprint of a converter valve as described in the first aspect is implemented.

[0043] The present disclosure has the following beneficial effects:

[0044] The point symmetry method of the existing technology will mask some weak change features in the overall features, which is reflected in the polar coordinate image as the difference between the images before and after the fault is small.

[0045] The present disclosure incorporates the spatial distance difference between the fault signal and the normal signal in the same period to further amplify the feature difference, thereby improving the accuracy of fault diagnosis. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 This is a flow chart of a method according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0047] In order to make the purpose, technical solutions and advantages of the embodiments of the present disclosure more clear, the technical solutions of the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings of the embodiments of the present disclosure. Obviously, the described embodiments are part of the embodiments of the present disclosure, not all of the embodiments. Based on the described embodiments of the present disclosure, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present disclosure.

[0048] Unless otherwise defined, the technical or scientific terms used in this disclosure should have the usual meanings understood by people with ordinary skills in the field to which this disclosure belongs. The "first", "second" and similar words used in this disclosure do not indicate any order, quantity or importance, but are only used to distinguish different components. "Include" or "comprise" and similar words mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly. In order to keep the following description of the embodiments of the present disclosure clear and concise, the present disclosure omits detailed descriptions of some known functions and known components.

[0049] The present disclosure will be described in detail below with reference to the accompanying drawings and specific embodiments.

[0050] First, reference Figure 1The present disclosure provides a method for monitoring converter valve discharge soundprints, comprising:

[0051] Collecting normal-state voiceprint signals under different working conditions, performing a point-symmetric transformation operation on the normal-state voiceprint signals to obtain polar coordinate system coordinates of the normal-state voiceprint signals, and performing a rectangular coordinate transformation on the polar coordinate system coordinates of the normal-state voiceprint signals to obtain normal-state rectangular coordinates;

[0052] Collecting fault state voiceprint signals under different working conditions, performing a point symmetric transformation operation on the fault state voiceprint signals to obtain polar coordinate system coordinates of the fault state voiceprint signals, and performing a rectangular coordinate transformation on the polar coordinate system coordinates of the fault state voiceprint signals to obtain rectangular coordinates of the fault state;

[0053] Creating training samples based on normal state rectangular coordinates and fault state rectangular coordinates under the same working conditions, and training the graph convolutional neural network using the training samples;

[0054] The voiceprint signal of the converter valve to be monitored is obtained, and after preprocessing, it is detected through the trained graph convolutional neural network to obtain the converter valve fault diagnosis result.

[0055] Specifically, the converter valve operating conditions include rated operating conditions, undervoltage operating conditions, overvoltage operating conditions, etc.

[0056] In one embodiment of the present disclosure, a point-symmetric transformation operation is performed on the normal state voiceprint signal, specifically:

[0057]

[0058] Among them, r base (i) is the polar coordinate radius of point i, i = 1, 2, 3, ..., T s , T s is the length of the normal voiceprint signal, x base_i is the normal state voiceprint signal, x base_min and x nase_max are the minimum and maximum values of the voiceprint signal in normal state, θ base (i) is the counterclockwise rotation angle of point i about the mirror symmetry plane, θ is the rotation angle of the mirror symmetry plane, l is the time interval, g is the angle magnification factor, and g<θ, is the angle of rotation of point i in the clockwise direction about the mirror symmetry plane.

[0059] This embodiment converts a one-dimensional time series signal into a two-dimensional polar coordinate image signal, which is more intuitive and can observe the sample characteristics on the image.

[0060] In one embodiment of the present disclosure, the polar coordinate system of the normal voiceprint signal is transformed into rectangular coordinates, specifically:

[0061] x base_ θ _ i =r base (i)cos(θ base (i));

[0062] y base_θ_i =r base (i)sin(θ base (i));

[0063]

[0064] Among them, x base_θ_i is the horizontal coordinate of the rectangular coordinate system of the point under the counterclockwise rotation angle, y base_θ_i is the ordinate of the rectangular coordinate system of the point under the counterclockwise rotation angle, is the horizontal coordinate of the rectangular coordinate system of the point under the clockwise rotation angle, The ordinate of the rectangular coordinate system of the point under the clockwise rotation angle.

[0065] The two-dimensional polar coordinate image will mask some weak features. This embodiment converts the polar coordinates into rectangular coordinates, which can introduce the spatial distance variation characteristics between the fault state and the normal state.

[0066] In one embodiment of the present disclosure, a point-symmetric transformation operation is performed on the fault state voiceprint signal, specifically:

[0067]

[0068] Among them, r test (i) is the normalized fault state voiceprint signal, x test_i is the fault state voiceprint signal, θ test (i) is the angle of rotation of point i in the counterclockwise direction about the mirror symmetry plane, is the angle of rotation of point i in the clockwise direction about the mirror symmetry plane.

[0069] In one embodiment of the present disclosure, the polar coordinate system coordinates of the fault state voiceprint signal are transformed into rectangular coordinates, specifically:

[0070] x test_ θ _i =r test (i)cos(θ test (i));

[0071] y test_θ_i =r test (i)sin(θ test (i));

[0072]

[0073] Among them, x test_θ_i is the horizontal coordinate of the rectangular coordinate system of point i under the counterclockwise rotation angle, y test_θ_i is the ordinate of the rectangular coordinate system of point i under the counterclockwise rotation angle, is the horizontal coordinate of the rectangular coordinate system of point i under the clockwise rotation angle, is the ordinate of the rectangular coordinate system of point i under the clockwise rotation angle.

[0074] The fault state voiceprint signal is converted in the same way as the normal state voiceprint signal, which facilitates the subsequent fusion of the two to produce training samples.

[0075] In one embodiment of the present disclosure, training samples are prepared based on the normal state rectangular coordinates and the fault state rectangular coordinates under the same working conditions, specifically:

[0076] Obtain several normal state rectangular coordinates and fault state rectangular coordinates under the same working conditions and convert them into three-dimensional coordinates. The three-dimensional coordinates of the normal state rectangular coordinates are and The three-dimensional coordinates of the rectangular coordinates of the fault state are (x test_θ_i ,y test_θ_i ,z) and And z≠0;

[0077] Polar coordinates are obtained by randomly combining the normal state rectangular coordinates and the fault state rectangular coordinates in the following way:

[0078]

[0079] Among them, d θ (i) and is the polar coordinate radius of the fault sample from the normal sample in counterclockwise and clockwise angles, θ(i) and The rotation angles are counterclockwise and clockwise;

[0080] The polar coordinates are plotted in a polar coordinate system, and corresponding working conditions and fault types are marked to obtain training samples.

[0081] This embodiment converts the rectangular coordinates into polar coordinates after taking the spatial distance into consideration, draws a polar coordinate image, and displays the change features on the image.

[0082] z is a preset value. Under the same working condition, the z values of the rectangular coordinates of different fault states are the same.

[0083] The above method discloses the method for producing fault state training samples. The normal state training samples are produced in the following manner, specifically:

[0084] Polar coordinates are obtained by randomly combining different normal rectangular coordinates in the following way:

[0085]

[0086] Among them, d θ (i) and is the polar coordinate radius of normal sample 1 from normal sample 2 in counterclockwise and clockwise angles, θ(i) and The angle of rotation in counterclockwise and clockwise directions; x base_θ_i1 、x base_θ_i2 、y base_θ_i1 and y base_θ_i2 are the normal rectangular coordinates of normal sample 1 and normal sample 2, z0 is a preset value, and z0≠0, z0≠z.

[0087] The polar coordinates are plotted in a polar coordinate system, and corresponding working conditions and fault types are marked to obtain training samples, where the training sample set is a normal state training sample.

[0088] In one embodiment of the present disclosure, the preprocessing of the voiceprint signal of the converter valve to be monitored is specifically as follows:

[0089] Obtaining the operating voltage and operating current of the converter valve to be monitored, and determining the operating condition of the converter valve according to the operating voltage and operating current of the converter valve to be monitored;

[0090] Obtain a normal state voiceprint signal of the same working condition as the converter valve to be monitored, perform a point symmetric transformation operation on the normal state voiceprint signal to obtain a polar coordinate system coordinate of the normal state voiceprint signal of the same working condition, and perform a rectangular coordinate transformation on the polar coordinate system coordinate of the normal state voiceprint signal of the same working condition to obtain a rectangular coordinate system coordinate of the normal state voiceprint signal of the same working condition;

[0091] Performing a point-symmetric transformation operation on the converter valve soundprint signal to be monitored to obtain the polar coordinate system coordinates of the converter valve soundprint signal to be monitored, and performing a rectangular coordinate transformation on the polar coordinate system coordinates of the converter valve soundprint signal to be monitored to obtain the rectangular coordinates of the converter valve to be monitored;

[0092] A test sample is produced according to the rectangular coordinates of the normal state under the same working conditions and the rectangular coordinates of the converter valve to be monitored.

[0093] In a second aspect, the present disclosure provides a converter valve discharge soundprint monitoring system, comprising a data acquisition module, a data processing module, and a data output module;

[0094] The data acquisition module collects the operating voltage, operating current and soundprint signals of the converter valve under different working conditions;

[0095] The data processing module processes the data collected by the data acquisition module according to the converter valve discharge soundprint monitoring method described in the first aspect to obtain a converter valve fault diagnosis result;

[0096] The data output module outputs the converter valve fault diagnosis result.

[0097] In a third aspect, an electronic device includes a memory, a processor, and a computer program stored in the memory and running on the processor, wherein when the processor executes the computer program, the method for monitoring the discharge soundprint of the converter valve as described in the first aspect is implemented.

[0098] The fourth invention is a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the converter valve discharge soundprint monitoring method as described in the first aspect.

[0099] The flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, program segment, or a part of code, and the module, program segment, or a part of code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order than that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of the boxes in the block diagram and / or flowchart, can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0100] The units involved in the embodiments described in this disclosure may be implemented in software or hardware, wherein the name of a unit does not necessarily limit the unit itself.

[0101] The functions described above herein may be performed, at least in part, by one or more hardware logic components. For example, and without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chip (SOCs), complex programmable logic devices (CPLDs), and the like.

[0102] The above description is merely a preferred embodiment of the present disclosure and an illustration of the technical principles employed. Those skilled in the art should understand that the scope of disclosure involved in the present disclosure is not limited to the technical solutions formed by the specific combination of the above-mentioned technical features, but also includes other technical solutions formed by any combination of the above-mentioned technical features or their equivalents without departing from the above-mentioned disclosed concepts. For example, a technical solution formed by replacing the above-mentioned features with (but not limited to) technical features with similar functions disclosed in this disclosure.

[0103] In addition, although each operation is described in a specific order, this should not be understood as requiring these operations to be performed in the specific order shown or in a sequential order. Under certain circumstances, multitasking and parallel processing may be advantageous. Similarly, although some specific implementation details have been included in the above discussion, these should not be interpreted as limiting the scope of the present disclosure. Some features described in the context of a separate embodiment can also be implemented in a single embodiment in combination. On the contrary, the various features described in the context of a single embodiment can also be implemented in multiple embodiments individually or in any suitable sub-combination mode.

[0104] Although the subject matter has been described in language specific to structural features and / or methodological logical acts, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are merely example forms of implementing the claims.

[0105] Regarding this disclosure, the following points need to be explained:

[0106] (1) The drawings of the embodiments of the present disclosure only relate to the structures related to the embodiments of the present disclosure. Other structures may refer to conventional designs.

[0107] (2) In the absence of conflict, the embodiments of the present disclosure and the features therein may be combined with each other to form new embodiments.

[0108] The above descriptions are merely embodiments of the present disclosure and are not intended to limit the patent scope of the present disclosure. Any equivalent structures made using the contents of the present disclosure and the drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present disclosure.

Claims

1. A method for monitoring converter valve discharge soundprint, characterized in that: include: Collecting normal-state voiceprint signals under different working conditions, performing a point-symmetric transformation operation on the normal-state voiceprint signals to obtain polar coordinate system coordinates of the normal-state voiceprint signals, and performing a rectangular coordinate transformation on the polar coordinate system coordinates of the normal-state voiceprint signals to obtain normal-state rectangular coordinates; Collecting fault state voiceprint signals under different working conditions, performing a point symmetric transformation operation on the fault state voiceprint signals to obtain polar coordinate system coordinates of the fault state voiceprint signals, and performing a rectangular coordinate transformation on the polar coordinate system coordinates of the fault state voiceprint signals to obtain rectangular coordinates of the fault state; Creating training samples based on normal state rectangular coordinates and fault state rectangular coordinates under the same working conditions, and training the graph convolutional neural network using the training samples; The voiceprint signal of the converter valve to be monitored is obtained, and after preprocessing, it is detected through the trained graph convolutional neural network to obtain the converter valve fault diagnosis result.

2. The converter valve discharge soundprint monitoring method according to claim 1, characterized in that: Performing a point-symmetric transformation operation on the normal state voiceprint signal, specifically: Among them, r base (i) is the polar coordinate radius of point i, i = 1, 2, 3, ..., T s , T s is the length of the normal voiceprint signal, x base_i is the normal state voiceprint signal, x base_min and x base_max are the minimum and maximum values of the voiceprint signal in normal state, θ base (i) is the counterclockwise rotation angle of point i about the mirror symmetry plane, θ is the rotation angle of the mirror symmetry plane, l is the time interval, g is the angle magnification factor, and g<θ, is the angle of rotation of point i in the clockwise direction about the mirror symmetry plane.

3. The method for monitoring converter valve discharge soundprint according to claim 2, characterized in that: The polar coordinate system of the normal voiceprint signal is transformed into rectangular coordinates, specifically: x base_θ_i =r base (i)cos(θ base (i)); y base_θ_i =r base (i)sin(θ base (i)); Among them, x base_θ_i is the horizontal coordinate of the rectangular coordinate system of the point under the counterclockwise rotation angle, y base_θ_i is the ordinate of the rectangular coordinate system of the point under the counterclockwise rotation angle, is the horizontal coordinate of the rectangular coordinate system of the point under the clockwise rotation angle, The ordinate of the rectangular coordinate system of the point under the clockwise rotation angle.

4. The method for monitoring converter valve discharge soundprint according to claim 2, characterized in that: Performing a point-symmetric transformation operation on the fault state voiceprint signal, specifically: Among them, r tr t (i) is the normalized fault state voiceprint signal, x test_i is the fault state voiceprint signal, θ test (i) is the angle of rotation of point i in the counterclockwise direction about the mirror symmetry plane, is the angle of rotation of point i in the clockwise direction about the mirror symmetry plane.

5. The method for monitoring converter valve discharge soundprint according to claim 4, characterized in that: Perform rectangular coordinate transformation on the polar coordinate system of the fault state voiceprint signal, specifically: x test_ θ _ i=r test (i)cos(θ test (i)); y test_θ_i =r test (i)sin(θ test (i)); Among them, x test_θ_i is the horizontal coordinate of the rectangular coordinate system of point i under the counterclockwise rotation angle, y test_θ_i is the ordinate of the rectangular coordinate system of point i under the counterclockwise rotation angle, is the horizontal coordinate of the rectangular coordinate system of point i under the clockwise rotation angle, is the ordinate of the rectangular coordinate system of point i under the clockwise rotation angle.

6. The method for monitoring converter valve discharge soundprint according to claim 5, characterized in that: The training samples are made based on the normal state rectangular coordinates and fault state rectangular coordinates under the same working conditions, specifically: Obtain several normal state rectangular coordinates and fault state rectangular coordinates under the same working conditions and convert them into three-dimensional coordinates. The three-dimensional coordinates of the normal state rectangular coordinates are and The three-dimensional coordinates of the rectangular coordinates of the fault state are (x test_θ_i ,y test_θ_i ,z) and And z≠0; Polar coordinates are obtained by randomly combining the normal state rectangular coordinates and the fault state rectangular coordinates in the following way: Among them, d θ (i) and is the polar coordinate radius of the fault sample from the normal sample in counterclockwise and clockwise angles, θ(i) and The rotation angles are counterclockwise and clockwise; The polar coordinates are plotted in a polar coordinate system, and corresponding working conditions and fault types are marked to obtain training samples.

7. The method for monitoring converter valve discharge soundprint according to claim 6, characterized in that: The preprocessing of the voiceprint signal of the converter valve to be monitored is as follows: Obtaining the operating voltage and operating current of the converter valve to be monitored, and determining the operating condition of the converter valve according to the operating voltage and operating current of the converter valve to be monitored; Obtain a normal state voiceprint signal of the same working condition as the converter valve to be monitored, perform a point symmetric transformation operation on the normal state voiceprint signal to obtain a polar coordinate system coordinate of the normal state voiceprint signal of the same working condition, and perform a rectangular coordinate transformation on the polar coordinate system coordinate of the normal state voiceprint signal of the same working condition to obtain a rectangular coordinate system coordinate of the normal state voiceprint signal of the same working condition; Performing a point-symmetric transformation operation on the converter valve soundprint signal to be monitored to obtain the polar coordinate system coordinates of the converter valve soundprint signal to be monitored, and performing a rectangular coordinate transformation on the polar coordinate system coordinates of the converter valve soundprint signal to be monitored to obtain the rectangular coordinates of the converter valve to be monitored; A test sample is produced according to the rectangular coordinates of the normal state under the same working conditions and the rectangular coordinates of the converter valve to be monitored.

8. A converter valve discharge soundprint monitoring system, characterized in that: It includes data acquisition module, data processing module and data output module; The data acquisition module collects the operating voltage, operating current and soundprint signals of the converter valve under different working conditions; The data processing module processes the data collected by the data acquisition module according to the converter valve discharge soundprint monitoring method according to any one of claims 1 to 7 to obtain a converter valve fault diagnosis result; The data output module outputs the converter valve fault diagnosis result.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the method for monitoring the discharge soundprint of a converter valve according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for monitoring the discharge soundprint of a converter valve according to any one of claims 1 to 7 is implemented.

Images