A transformer abnormal state diagnosis and early warning method based on voiceprint features

Abstract

The present invention discloses a method for diagnosing and warning abnormal conditions of transformers based on voiceprint features. The method comprises obtaining a network topology diagram and voiceprint information of transformer network nodes; utilizing a support vector machine algorithm to classify voiceprint information data and generate a class voiceprint dataset, establishing an optimization model for transformer abnormal voiceprint data, updating and outputting the voiceprint features of the transformer abnormal state based on the transformer abnormal voiceprint data optimization model, and then generating and outputting transformer abnormal state analysis results through similarity analysis based on a database of abnormal voiceprint graph features. By optimizing and smoothing the voiceprint features, the present invention can realize transformer voiceprint information identification and updating in complex sound field environments, thereby improving the accuracy and robustness of the subsequent fusion diagnosis model and further enhancing the effectiveness of transformer abnormal state diagnosis and warning.

Description

Technical Field

[0001] The present invention relates to the technical field of transformer data processing, and in particular to a transformer abnormal state diagnosis and early warning method based on voiceprint features. Background Art

[0002] During operation, power transformers emit continuous vibration signals, which contain numerous pulses and fluctuations caused by mechanical faults. These signals are the primary data source for evaluating the transformer's operating condition. Transformer anomalies can manifest as abnormalities in data from multiple monitoring / detection methods, while others manifest as abnormalities in data from a single or limited number of monitoring / detection methods. Ultrasonic and conventional pulse current methods are considered effective methods for detecting insulation faults in electrical equipment. However, if discharge faults can also be identified based on oil chromatography data, the diagnosis of insulation faults becomes even more certain. Vibration analysis is even more effective for monitoring the condition of transformer windings and cores.

[0003] However, the existing ultrasonic, conventional pulse current and vibration analysis methods are limited in their processing of the voiceprint features of transformer winding and core abnormality diagnosis, making it difficult to integrate the subsequent ultrasonic, vibration and partial discharge instrument feature information for diagnosis. To this end, we propose a transformer abnormality diagnosis and early warning method based on voiceprint features. Summary of the Invention

[0004] In view of the above problems existing in the existing transformer data processing, the present invention is proposed.

[0005] Therefore, one of the objects of the present invention is to provide a method for diagnosing and warning of abnormal conditions of transformers based on voiceprint features. By optimizing and smoothing the voiceprint features of the ultrasonic and vibration voiceprint signals of the transformer in the topological structure, it is possible to realize the recognition and update of transformer voiceprint information in a complex sound field environment, so as to improve the accuracy and robustness of the subsequent fusion diagnosis model, and improve the fusion diagnosis processing and analysis method, thereby further improving the effect of diagnosis and warning of abnormal conditions of transformers.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] In one aspect, the present invention provides a method for diagnosing and warning abnormal conditions of transformers based on voiceprint features, comprising the following steps:

[0008] Step 1: Obtain the network topology and voiceprint information of the transformer network nodes;

[0009] Step 2: Using a support vector machine algorithm, the network topology diagram of the transformer network nodes and the classified sample data of the voiceprint information are projected into a high-dimensional space to divide the data into category voiceprint information data and generate a category voiceprint data set;

[0010] Step 3: Establishing a transformer abnormal voiceprint data optimization model, wherein the transformer abnormal voiceprint data optimization model and objective function are determined with the maximum processing output of the transformer abnormal voiceprint in the transformer network node network topology diagram as the goal;

[0011] Step 4: Optimize the model and objective function according to the abnormal voiceprint data of the transformer, and use feature smoothing processing to complete the update and output of the voiceprint features of the abnormal state of the transformer to form the voiceprint spectrum feature data of the abnormal state of the transformer;

[0012] Step five: Based on the voiceprint feature data of the transformer abnormal state, an abnormal voiceprint feature database of the transformer abnormal state is formed; and then, based on the abnormal voiceprint feature database, a similarity analysis is performed to generate an analysis result of the transformer abnormal state; and after matching the analysis result of the transformer abnormal state, a detection result of the transformer abnormal state fault type is obtained and output.

[0013] As a preferred solution of the present invention, in step 2, the network topology diagram of the transformer network nodes and the classification sample data of the voiceprint information are classified into linear data in a high-dimensional space using a support vector machine algorithm, and the input network topology diagram of the transformer network nodes and the voiceprint information samples are divided by finding the optimal classification hyperplane;

[0014] Project the divided sample data back to the source space to achieve the division of nonlinear samples, and according to the Mercer theorem of the kernel function, use the kernel function that meets the preset conditions as the inner product of the high-dimensional space to replace the inner product of the source space;

[0015] The nonlinear transformation of SVM is converted into the objective function of quadratic programming to obtain the voiceprint information classification function, and a category voiceprint dataset is generated according to the voiceprint information classification function.

[0016] As a preferred solution of the present invention, the maximum processing output of the abnormal voiceprint of the transformer in the transformer network node network topology diagram is taken as the goal, and the optimization model and objective function of the abnormal voiceprint data of the transformer are determined as follows:

[0017]

[0018] Where, max f(bit) is the maximum amount of processed output data of transformer abnormal voiceprint in the network topology diagram within the preset time, B jis the rated processing capacity data of transformer j, m is the total number of transformer groups in the network topology diagram, T is the preset time data, t j represents the processing time of transformer j, is the increased processing capacity data of transformer j.

[0019] As a preferred solution of the present invention, wherein: the abnormal state fault types of the transformer include transformer winding fault, transformer core fault, transformer internal discharge fault and transformer tap changer fault;

[0020] The transformer winding faults include inter-turn short circuit faults, inter-phase short circuit faults, inter-strand short circuit faults and winding deformation faults;

[0021] The transformer core fault includes a multi-point grounding fault and a core overheating fault;

[0022] The transformer internal discharge fault includes partial discharge fault, spark discharge fault and arc discharge fault.

[0023] As a preferred solution of the present invention, an abnormal voiceprint spectrum feature database of the transformer abnormal state is formed based on the voiceprint spectrum feature data of the transformer abnormal state. Specifically, according to the voiceprint spectrum feature data of several transformer abnormal states, combined with a preset voiceprint vibration sensor signal weighting matrix, a weighted MUSIC algorithm is used to calculate the spatial spectrograms of the voiceprint spectrum feature data of several transformer abnormal states, and the spatial spectrograms are converted into a plane image, and then the fault type of the transformer abnormal state is selected and determined.

[0024] As a preferred solution of the present invention, in step 4, the feature smoothing process is as follows:

[0025]

[0026] Among them, p i Expressed as the predicted value of the i-th category, λ i represents the weight value of the i-th category, n is the total number of items in the i-th category, r i Represents the characteristic parameter value of the i-th category, r n Expressed as the characteristic parameter value of the total category, p n It is expressed as the predicted value of the total category, and cos(·) represents the cosine function.

[0027] As a preferred solution of the present invention, wherein: according to the abnormal voiceprint spectrum feature database, similarity is calculated between the voiceprint spectrum feature data to be identified and each abnormal voiceprint spectrum feature sample in the abnormal voiceprint spectrum feature database through similarity analysis, and the maximum similarity calculation result of the similarity calculation of the voiceprint spectrum feature data to be identified is compared with the preset threshold of each corresponding abnormal voiceprint spectrum feature sample, and the corresponding abnormal voiceprint spectrum feature and the abnormal state of the transformer are matched and output after comparative analysis.

[0028] As a preferred solution of the present invention, step 1, when obtaining the network topology diagram and voiceprint information of the transformer network nodes, also includes denoising the obtained transformer voiceprint information.

[0029] As a preferred solution of the present invention, after matching the transformer abnormal state analysis results in step 5 to obtain the transformer abnormal state fault type detection result and outputting it, it also includes a fusion pulse current method detection method to fuse the transformer abnormal state fault type detection result. The fusion model is as follows:

[0030]

[0031] Among them, G(U,E) represents the fusion data of the transformer abnormal state fault type detection results, U represents the set of unified data of the current transformer abnormal voiceprint fusion processing; E represents the current transformer abnormal voiceprint fusion processing event; U j The unified data representing the current transformer abnormal state fault type, U a Indicates the unified data of the abnormal transformer soundprint detected by the pulse current method; w(U j ,E) represents the support degree of the unified data of the current transformer abnormal state fault type to the current transformer abnormal voiceprint fusion processing event; corr(U j ,U a ) represents the unified data U of the current transformer abnormal state fault type j Unified data U of the transformer abnormal soundprint detected by the current transformer abnormal soundprint pulse current method a correlation.

[0032] Compared with the existing technology, the beneficial effects of the present invention are as follows: the present invention optimizes and smoothes the voiceprint features of the ultrasonic and vibration voiceprint signals of the transformer in the topological structure, thereby realizing the recognition and update of transformer voiceprint information in a complex sound field environment, thereby improving the accuracy and robustness of the subsequent fusion diagnosis model, and improving the fusion diagnosis processing and analysis method, further improving the effect of transformer abnormal state diagnosis and early warning. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. Those skilled in the art can also derive other drawings based on these drawings without inventive effort. Among them:

[0034] Figure 1 This is a flow chart of the transformer abnormal state diagnosis and early warning method based on voiceprint features of the present invention;

[0035] Figure 2 Schematic diagram of the influence of 100Hz, 200Hz and 300Hz no-load voltage on the vibration characteristics of the iron core of the present invention. DETAILED DESCRIPTION

[0036] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions of the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the described embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field are within the scope of protection of the present invention.

[0037] First, this embodiment proposes a transformer abnormal state diagnosis and early warning method based on voiceprint features. By optimizing and smoothing the ultrasonic and vibration voiceprint signals of the transformer in the topological structure, it can realize the recognition and update of transformer voiceprint information in a complex sound field environment, so as to improve the accuracy and robustness of the subsequent fusion diagnosis model. Secondly, it improves the fusion diagnosis processing and analysis method, further improving the effect of transformer abnormal state diagnosis and early warning.

[0038] This embodiment presents a multi-dimensional performance optimization approach to addressing issues caused by environmental noise, mixed faults, and unknown faults. Experimental results demonstrate that the proposed condition monitoring and fault diagnosis system can quickly distinguish faulty operating conditions in diverse noise environments and provide diagnostics and early warnings for transformer abnormalities.

[0039] specifically refer to Figure 1 and Figure 2 , is an embodiment of the present invention, which provides a transformer abnormal state diagnosis and early warning method based on voiceprint features, comprising the following steps:

[0040] Step 1: Obtain the network topology and voiceprint information of the transformer network nodes;

[0041] Step 2: Use the support vector machine algorithm to project the network topology of the transformer network nodes and the classified sample data of the voiceprint information into a high-dimensional space, divide them into category voiceprint information data, and generate a category voiceprint data set;

[0042] Step 3: Establishing a transformer abnormal voiceprint data optimization model, wherein the transformer abnormal voiceprint data optimization model and objective function are determined with the maximum processing output of the transformer abnormal voiceprint in the transformer network node network topology diagram as the goal;

[0043] Step 4: Optimize the model and objective function based on the abnormal voiceprint data of the transformer, and use feature smoothing processing to update and output the voiceprint features of the abnormal state of the transformer to form the voiceprint spectrum feature data of the abnormal state of the transformer;

[0044] Step 5: Based on the voiceprint feature data of the transformer abnormal state, an abnormal voiceprint feature database of the transformer abnormal state is formed. Then, according to the abnormal voiceprint feature database, similarity analysis is performed to generate the transformer abnormal state analysis result. After matching the transformer abnormal state analysis result, the transformer abnormal state fault type detection result is obtained and output.

[0045] Step 6: Fusion pulse current detection method is used to fuse the transformer abnormal state fault type detection results. After matching the transformer abnormal state analysis results, the transformer abnormal state fault type detection results are obtained and output, and then the transformer abnormal state fault type detection results are fused. The fusion model is as follows:

[0046]

[0047] Among them, G(U,E) represents the fusion data of the transformer abnormal state fault type detection results, U represents the set of unified data of the current transformer abnormal voiceprint fusion processing; E represents the current transformer abnormal voiceprint fusion processing event; U j The unified data representing the current transformer abnormal state fault type, U a Indicates the unified data of the abnormal transformer soundprint detected by the pulse current method; w(U j ,E) represents the support degree of the unified data of the current transformer abnormal state fault type to the current transformer abnormal voiceprint fusion processing event; corr(U j ,U a ) represents the unified data U of the current transformer abnormal state fault type j Unified data U of the transformer abnormal soundprint detected by the current transformer abnormal soundprint pulse current method a correlation.

[0048] Based on the above, the optimized voiceprint information is fused with data from other pulse current methods to construct a highly accurate and robust diagnostic model. This model can comprehensively analyze various data to provide a more comprehensive transformer condition assessment. Furthermore, the optimized voiceprint features and fused diagnostic model of this embodiment significantly improve the accuracy and robustness of transformer abnormal condition diagnosis, reducing the likelihood of false positives and missed negatives. Furthermore, by improving data processing and analysis methods, the diagnostic process is more efficient and can quickly respond to abnormal transformer conditions.

[0049] Specifically, in step 1, while obtaining the network topology and voiceprint information of the transformer network nodes, this embodiment also includes denoising the obtained transformer voiceprint information. The voiceprint information includes the transformer's ultrasonic and vibration voiceprint signals. The basic principle of ultrasonic detection of transformer winding deformation is as follows: an ultrasonic probe is attached to a certain location on the transformer's outer casing wall, ensuring that the center of the ultrasonic probe is aligned with the winding under test and that the probe is in close contact with the transformer body. The ultrasonic transmitting circuit synchronously emits a signal, causing the ultrasonic probe to simultaneously transmit ultrasonic waves. Ultrasonic waves propagate within the transformer as longitudinal waves, passing through the steel wall and transformer oil before reaching the transformer winding. They are then reflected at the interface between the transformer winding's insulation and the copper surface. Similarly, the reflected echo passes through the transformer oil and the outer casing, traveling a predetermined path to the ultrasonic receiving probe, generating a received electrical pulse signal. The vibration analysis method, however, considers the transformer winding's mechanical structure as a mechanical structure composed of mass, stiffness, and damping. Therefore, any changes in the winding's structure or stresses are reflected in its mechanical dynamics, or vibration characteristics.

[0050] Also refer to Figure 2 As shown, where U is the load voltage, U N is the rated voltage, (U / U N ) 2 The fundamental frequency amplitude is represented by a piezoelectric accelerometer measuring the vibration on the housing surface under no-load conditions. The figure shows that as the no-load voltage increases, the vibration signal's frequency components increase. When the no-load voltage is less than half the rated voltage, the fundamental frequency component of the vibration signal, 100 Hz, has a nearly linear relationship with the square of the voltage. When the no-load voltage exceeds half the rated voltage, a nonlinear trend gradually emerges. The explanation is as follows: the nonlinearity of the core's magnetostrictive effect means that when the excitation flux increases, the vibration does not increase linearly with the square of the flux. Slightly higher-frequency harmonics likely originate from vibrations generated by electromagnetic attraction between the silicon steel sheets.

[0051] In addition, in step 2 of this embodiment, the support vector machine algorithm is used to classify the network topology diagram of the transformer network nodes and the classification sample data of the voiceprint information, specifically the classification sample data into linear in the high-dimensional space, by finding the optimal classification hyperplane and dividing the input network topology diagram of the transformer network nodes and the voiceprint information samples;

[0052] Project the divided sample data back to the source space to achieve the division of nonlinear samples. According to the Mercer theorem of kernel function, which is an important concept in machine learning and kernel methods, it provides a necessary and sufficient condition for a function to be used as a kernel function. The kernel function that meets the preset conditions is used as the inner product in the high-dimensional space to replace the inner product in the source space.

[0053] The nonlinear transformation of SVM is converted into the objective function of quadratic programming to obtain the voiceprint information classification function, and a category voiceprint dataset is generated according to the voiceprint information classification function.

[0054] In step 3 of this embodiment, preferably, the maximum processing output of the abnormal voiceprint of the transformer in the transformer network node network topology diagram is taken as the goal, and the transformer abnormal voiceprint data optimization model and objective function are determined as follows:

[0055]

[0056] Where maxf(bit) is the maximum amount of processed output data of transformer abnormal voiceprint in the network topology diagram within the preset time, B j is the rated processing capacity data of transformer j, m is the total number of transformer groups in the network topology diagram, T is the preset time data, t j represents the processing time of transformer j, is the increased processing capacity data of transformer j.

[0057] This embodiment is particularly optimized for the recognition of incremental transformer voiceprint information in the topology of network nodes in complex sound field environments, so that it can accurately and efficiently recognize the transformer voiceprint information in incremental situations under various environmental conditions.

[0058] Specifically, in this embodiment, the transformer abnormal state fault types include transformer winding fault, transformer core fault, transformer internal discharge fault and transformer tap changer fault;

[0059] Transformer winding faults include turn-to-turn short circuit faults, phase-to-phase short circuit faults, winding strand short circuit faults, and winding deformation faults;

[0060] Transformer core faults include multi-point grounding faults and core overheating faults;

[0061] Transformer internal discharge faults include partial discharge faults, spark discharge faults, and arc discharge faults.

[0062] This embodiment further forms an abnormal voiceprint spectrum feature database of the transformer abnormal state based on the voiceprint spectrum feature data of the transformer abnormal state. Specifically, according to the voiceprint spectrum feature data of several transformer abnormal states, combined with a preset voiceprint vibration sensor signal weighting matrix, a weighted MUSIC algorithm is used to calculate the spatial spectrograms of the voiceprint spectrum feature data of several transformer abnormal states, and the spatial spectrograms are converted into a plane image, and then the fault type of the transformer abnormal state is selected and determined.

[0063] In order to further reduce the impact of noise, this embodiment uses a specific algorithm to smooth the voiceprint signal to ensure the stability and reliability of the signal. Specifically, in step 4, the feature smoothing process is shown in the following formula:

[0064]

[0065] Among them, p i Expressed as the predicted value of the i-th category, λ i represents the weight value of the i-th category, n is the total number of items in the i-th category, r i Represents the characteristic parameter value of the i-th category, r n Expressed as the characteristic parameter value of the total category, p n It is expressed as the predicted value of the total category, and cos(·) represents the cosine function.

[0066] Specifically, this embodiment performs similarity analysis based on the abnormal voiceprint feature database. The similarity calculation is performed between the voiceprint feature data to be identified and each abnormal voiceprint feature sample in the abnormal voiceprint feature database. The maximum similarity calculated for the similarity of the voiceprint feature data to be identified is compared with a preset threshold for each corresponding abnormal voiceprint feature sample. After comparative analysis, the corresponding abnormal voiceprint feature and the abnormal status of the transformer are matched and output. Through the above processing, the present invention can achieve real-time identification and updating of transformer voiceprint information, which is crucial for monitoring the operating status of the transformer and predicting potential faults.

[0067] This embodiment optimizes and smoothes the ultrasonic and vibration soundprint signals of the transformer in the topological structure, thereby realizing the recognition and update of transformer soundprint information in a complex sound field environment, thereby improving the accuracy and robustness of the subsequent fusion diagnosis model, and improving the fusion diagnosis processing and analysis method, further improving the effect of transformer abnormal state diagnosis and early warning.

[0068] In the above embodiments, all or part of the embodiments may be implemented using software, hardware, firmware, or any combination thereof. When implemented using software, all or part of the embodiments may be implemented in the form of a computer program product. A computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the processes or functions according to the present application are generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transferred from one computer-readable storage medium to another.

[0069] It should be understood that various parts of the present application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. All or part of the steps of the above embodiment method can be completed by instructing the relevant hardware through a program, which can be stored in a computer-readable storage medium. When the program is executed, it includes one or a combination of the steps of the method embodiment.

[0070] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing module, or each unit may exist physically separately, or two or more units may be integrated into a single module. The aforementioned integrated modules may be implemented in the form of hardware or in the form of software functional modules. If the aforementioned integrated modules are implemented in the form of software functional modules and sold or used as independent products, they may also be stored in a computer-readable storage medium. The storage medium may be a read-only memory, a magnetic disk, or an optical disk, etc.

[0071] The above are only specific embodiments of the present application, but the scope of protection of the present application is not limited thereto. Any person skilled in the art can easily conceive of various modifications or substitutions within the technical scope disclosed in this application, and such modifications or substitutions should be included in the scope of protection of the present application. Therefore, the scope of protection of the present application should be based on the scope of protection of the claims.

Claims

1. A transformer abnormal state diagnosis and early warning method based on voiceprint features, characterized by: The following steps are involved: Step 1: Obtain the network topology and voiceprint information of the transformer network nodes; Step 2: Using a support vector machine algorithm, the network topology diagram of the transformer network nodes and the classified sample data of the voiceprint information are projected into a high-dimensional space to divide the data into category voiceprint information data and generate a category voiceprint data set; Step 3: Establish an optimization model for transformer abnormal voiceprint data. The optimization model and objective function of the transformer abnormal voiceprint data are determined with the maximum processing output of the transformer abnormal voiceprint in the transformer network node network topology diagram as the goal. Specifically, the model and objective function are as follows: Where, max f(bit) is the maximum amount of processed output data of transformer abnormal voiceprint in the network topology diagram within the preset time, B j is the rated processing capacity data of transformer j, m is the total number of transformer groups in the network topology diagram, T is the preset time data, t j represents the processing time of transformer j, is the increased processing capacity data of transformer j; Step 4: Optimize the model and objective function according to the abnormal voiceprint data of the transformer, and use feature smoothing processing to complete the update and output of the voiceprint features of the abnormal state of the transformer to form the voiceprint spectrum feature data of the abnormal state of the transformer; Step five: Based on the voiceprint feature data of the transformer abnormal state, an abnormal voiceprint feature database of the transformer abnormal state is formed; and then, based on the abnormal voiceprint feature database, a similarity analysis is performed to generate an analysis result of the transformer abnormal state; and after matching the analysis result of the transformer abnormal state, a detection result of the transformer abnormal state fault type is obtained and output.

2. The transformer abnormal state diagnosis and early warning method based on voiceprint features according to claim 1 is characterized in that: In step 2, the network topology diagram of the transformer network nodes and the classification sample data of the voiceprint information are classified into linear data in a high-dimensional space by using a support vector machine algorithm, and the optimal classification hyperplane is found and the input network topology diagram of the transformer network nodes and the voiceprint information samples are divided; Project the divided sample data back to the source space to achieve the division of nonlinear samples, and according to the Mercer theorem of the kernel function, use the kernel function that meets the preset conditions as the inner product of the high-dimensional space to replace the inner product of the source space; The nonlinear transformation of SVM is converted into the objective function of quadratic programming to obtain the voiceprint information classification function, and a category voiceprint dataset is generated according to the voiceprint information classification function.

3. The transformer abnormal state diagnosis and early warning method based on voiceprint features according to claim 1 is characterized in that: The transformer abnormal state fault types include transformer winding fault, transformer core fault, transformer internal discharge fault and transformer tap changer fault; The transformer winding faults include inter-turn short circuit faults, inter-phase short circuit faults, inter-strand short circuit faults and winding deformation faults; The transformer core fault includes a multi-point grounding fault and a core overheating fault; The transformer internal discharge fault includes partial discharge fault, spark discharge fault and arc discharge fault.

4. The transformer abnormal state diagnosis and early warning method based on voiceprint features according to claim 3 is characterized in that: Based on the voiceprint spectrum feature data of the abnormal state of the transformer, an abnormal voiceprint spectrum feature database of the abnormal state of the transformer is formed. Specifically, according to the voiceprint spectrum feature data of several abnormal states of the transformer, combined with a preset voiceprint vibration sensor signal weighting matrix, a weighted MUSIC algorithm is used to calculate the spatial spectrograms of the voiceprint spectrum feature data of several abnormal states of the transformer, and the spatial spectrograms are converted into a plane image, and then the fault type of the abnormal state of the transformer is selected and determined.

5. The transformer abnormal state diagnosis and early warning method based on voiceprint features according to claim 1 is characterized in that: In step 4, the feature smoothing process is as follows: Among them, p i Expressed as the predicted value of the i-th category, λ i represents the weight value of the i-th category, n is the total number of items in the i-th category, r i Represents the characteristic parameter value of the i-th category, r n Expressed as the characteristic parameter value of the total category, p n It is expressed as the predicted value of the total category, and cos(·) represents the cosine function.

6. The transformer abnormal state diagnosis and early warning method based on voiceprint features according to claim 1 is characterized in that: According to the abnormal voiceprint spectrum feature database, similarity is calculated between the voiceprint spectrum feature data to be identified and each abnormal voiceprint spectrum feature sample in the abnormal voiceprint spectrum feature database through similarity analysis. The maximum similarity calculation result of the similarity calculation of the voiceprint spectrum feature data to be identified is compared with the preset threshold of each corresponding abnormal voiceprint spectrum feature sample. After the comparative analysis, the corresponding abnormal voiceprint spectrum feature and the abnormal state of the transformer are matched and output.

7. The transformer abnormal state diagnosis and early warning method based on voiceprint features according to claim 1 is characterized in that: Step 1, when obtaining the network topology diagram and voiceprint information of the transformer network nodes, also includes denoising the obtained transformer voiceprint information.

8. The transformer abnormal state diagnosis and early warning method based on voiceprint features according to claim 1 is characterized in that: After matching the transformer abnormal state analysis results in step 5 to obtain the transformer abnormal state fault type detection results and output them, the method further includes a fusion pulse current method detection method to fuse the transformer abnormal state fault type detection results. The fusion model is as follows: Among them, G(U,E) represents the fusion data of the transformer abnormal state fault type detection results, U represents the set of unified data of the current transformer abnormal voiceprint fusion processing; E represents the current transformer abnormal voiceprint fusion processing event; U j The unified data representing the current transformer abnormal state fault type, U a Indicates the unified data of the abnormal transformer soundprint detected by the pulse current method; w(U j ,E) represents the support degree of the unified data of the current transformer abnormal state fault type to the current transformer abnormal voiceprint fusion processing event; corr(U j ,U a ) represents the unified data U of the current transformer abnormal state fault type j Unified data U of the transformer abnormal soundprint detected by the current transformer abnormal soundprint pulse current method a correlation.

Images