GIS partial discharge mode identification method and system based on chaos theory

Abstract

The invention discloses a GIS partial discharge mode recognition method and system based on the chaos theory, and relates to the technical field of GIS partial discharge mode recognition, and the method comprises the steps: collecting a partial discharge signal caused by a typical insulation defect, and forming a PRPD pattern sample; each PRPD pattern sample is preprocessed, and the signal amplitude is normalized; and obtaining chaotic characteristics according to a chaos theory, carrying out classification and identification by using a support vector machine, recording a mode to which partial discharge belongs, and completing identification. According to the method, the recognition accuracy of the insulation defect is remarkably improved, and the robustness and practicability of the system are enhanced.

Description

Technical Field

[0001] The invention relates to the technical field of GIS local discharge pattern recognition, in particular to a GIS local discharge pattern recognition method and system based on chaos theory. Background Art

[0002] Partial discharge is a key parameter to describe the insulation condition of gas insulated switchgear (GIS). Its existence and development will lead to equipment insulation aging, which may eventually cause power failures. At present, traditional methods based on statistical features mainly rely on partial discharge pattern image feature analysis, resulting in a low recognition rate for certain types of partial discharge. In addition, these methods fail to fully utilize the relevant information and interactions between different partial discharge pulses.

[0003] Chaos science is an emerging discipline that studies complex systems, especially nonlinear systems, which are highly sensitive. Chaotic phenomena are common in partial discharge processes, especially in partial discharge pulse sequences under the same voltage phase. This study extracts chaotic features of partial discharge characteristics generated by four typical insulation defects (such as metal protrusions, free-moving particles, fixed metal particles, and air gaps) and completes partial discharge pattern recognition. Summary of the invention

[0004] The purpose of this section is to summarize some aspects of embodiments of the present invention and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section and the specification abstract and the invention title of this application to avoid blurring the purpose of this section, the specification abstract and the invention title, and such simplifications or omissions cannot be used to limit the scope of the present invention.

[0005] The present invention starts from the chaotic characteristics of PD signals, combines complementary chaotic characteristics and statistical characteristics at the decision-making level using an information fusion algorithm, solves the problem of GIS partial discharge pattern recognition, and proposes the present invention.

[0006] Therefore, the present invention provides a GIS partial discharge pattern recognition method and system based on chaos theory, which can solve the above-mentioned problems.

[0007] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0008] In a first aspect, the present invention provides a GIS partial discharge pattern recognition method based on chaos theory, which includes collecting partial discharge signals caused by typical insulation defects and forming PRPD pattern samples;

[0009] Each PRPD pattern sample was preprocessed and the signal amplitude was normalized;

[0010] The chaotic characteristics are obtained according to the chaos theory, and the support vector machine is used for classification and identification, and the mode of partial discharge is recorded to complete the identification.

[0011] As a preferred solution of the GIS partial discharge pattern recognition method based on chaos theory described in the present invention, the typical insulation defects include needle-shaped defects, particle-shaped defects, metal-shaped defects and gap-shaped defects;

[0012] The acquisition method is to collect signals from metal protrusions, free-moving particles, metal particles fixed on the surface of insulators, and air gaps, and generate PRPD pattern samples.

[0013] As a preferred solution of the GIS partial discharge pattern recognition method based on chaos theory described in the present invention, the preprocessing includes:

[0014] Each PRPD pattern sample is preprocessed and then the signal amplitude is normalized to [0,1], and the calculation formula is as follows:

[0015]

[0016] Among them, v max and v min Refers to the maximum and minimum values ​​of all signal pulse amplitudes in a sample; V * i V i The normalized pulse signal.

[0017] As a preferred solution of the GIS partial discharge pattern recognition method based on chaos theory described in the present invention, wherein: the chaotic characteristics obtained according to chaos theory include:

[0018] Reconstruct the phase space, that is, use the time series of a certain system component to reconstruct an m-dimensional phase space and obtain a group space vector. The calculation formula is as follows:

[0019]

[0020] Where τ is the time delay, m is the embedding dimension, and m≥2d+1, d is the number of independent variables in the system, and X i is the phase point of the reconstructed phase space.

[0021] As a preferred solution of the GIS partial discharge pattern recognition method based on chaos theory described in the present invention, wherein: the chaotic characteristics obtained according to chaos theory also include:

[0022] Calculate the maximum Lyapunov exponent, that is, assume that the first i point X in the reconstructed phase space i The nearest neighbor is X ip , and the following conditions are met, the calculation formula is as follows:

[0023] ||X ip -X i ||=min j ||X j -X i ||

[0024] Among them, ║·║ is the Euclidean distance.

[0025] As a preferred solution of the GIS partial discharge pattern recognition method based on chaos theory described in the present invention, wherein: the chaotic characteristics are obtained according to the chaos theory, and further comprising:

[0026] Specify the time interval between two points and make the following assumptions:

[0027] τ w / Δt<|ji|<Bτ w / Δt 1<B<10

[0028] Among them, τ w is the time window width, τ w / Δt<|ji| ensures X i and X ip are not on the same track, |ji| is the index difference between two points in the time series, |ji| <Bτ w / Δt ensures one-time calculation of λ i The number of points required is very small, and B is a constant;

[0029] The partial maximum Lyapunov exponent in the direction of maximum diffusion is calculated as follows:

[0030]

[0031] Among them, h is the step size, j is the number of iterations, max h To find the h value that maximizes the separation ratio, that is, to find the optimal time step to maximize the separation speed;

[0032] When the time interval is less than τ w When , the two points are considered to be on the same track. The following formula is used to verify that the two points are still on each track after the nearest neighbor evolution. The formula is as follows:

[0033] 1<h<aτ w / τ(0<a<1)

[0034]

[0035] Where a is a scaling factor less than 1, which is used to adjust the upper limit of the time step h, b·(80°) is the angle threshold, which is used to determine whether two points are still on the same track, and M is the total number of points in the data set;

[0036] The obtained λ1(i) is the partial maximum Lyapunov index of the system, and the maximum Lyapunov index obtained is:

[0037]

[0038] Where λ1 is the average maximum Lyapunov exponent.

[0039] As a preferred solution of the GIS local discharge pattern recognition method based on chaos theory described in the present invention, wherein:

[0040] In a second aspect, the present invention provides a GIS partial discharge pattern recognition system based on chaos theory, which includes: a data acquisition module, a preprocessing module and a discharge analysis module;

[0041] The data acquisition module is used to collect partial discharge signals caused by typical insulation defects and form PRPD pattern samples;

[0042] The preprocessing module is used to preprocess each PRPD pattern sample and normalize the signal amplitude;

[0043] The discharge analysis module is used to obtain chaotic characteristics according to chaos theory, and use a support vector machine to perform classification and identification, record the mode to which the partial discharge belongs, and complete the identification.

[0044] In a third aspect, the present invention provides a computer device, including a memory and a processor, wherein the memory stores a computer program, wherein: when the processor executes the computer program, the steps of a GIS local discharge pattern recognition method based on chaos theory are implemented.

[0045] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, the steps of a GIS local discharge pattern recognition method based on chaos theory are implemented.

[0046] Compared with the prior art, the beneficial effects of the present invention are that the chaotic characteristics of the PD signal pattern diagram under different voltage phases are analyzed for the first time, the chaotic characteristics are extracted, and then applied to pattern recognition, achieving better recognition effect; compared with the traditional pattern recognition method, the recognition method based on chaotic characteristics has strong complementarity; the recognition accuracy of insulation defects is significantly improved, enhancing the robustness and practicality of the system. BRIEF DESCRIPTION OF THE DRAWINGS

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

[0048] Figure 1 A method flow chart of a GIS partial discharge pattern recognition method and system based on chaos theory provided by one embodiment of the present invention;

[0049] Figure 2 An internal structure diagram of a computer device of a GIS partial discharge pattern recognition method and system based on chaos theory provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0050] In order to make the above-mentioned purposes, features and advantages of the present invention more understandable, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0051] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0052] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0053] Example 1

[0054] Reference Figure 1-Figure 2 , which is the first embodiment of the present invention, provides a GIS partial discharge pattern recognition method based on chaos theory, including:

[0055] This application provides an effective solution to the above-mentioned problems. Next, multiple embodiments will be combined to explain in detail how to implement the GIS partial discharge pattern recognition method based on chaos theory;

[0056] Figure 1A method flow chart of a GIS partial discharge pattern recognition method and system based on chaos theory is shown, including:

[0057] S1: Collect partial discharge signals caused by typical insulation defects and form PRPD pattern samples;

[0058] Furthermore, typical insulation defects include needle-like defects, particle-like defects, metal-like defects, and gap-like defects;

[0059] The acquisition method is to collect signals from metal protrusions, free-moving particles, metal particles fixed on the surface of insulators, and air gaps, and generate PRPD pattern samples.

[0060] S2: preprocess each PRPD pattern sample and normalize the signal amplitude;

[0061] Furthermore, the pretreatment includes:

[0062] Each PRPD pattern sample is preprocessed and then the signal amplitude is normalized to [0,1], and the calculation formula is as follows:

[0063]

[0064] Among them, v max and v min Refers to the maximum and minimum values ​​of all signal pulse amplitudes in a sample; V * i V i The normalized pulse signal.

[0065] S3: Obtain the chaotic characteristics according to chaos theory, and use support vector machine for classification and identification, record the mode to which the partial discharge belongs, and complete the identification.

[0066] Furthermore, the chaotic characteristics are obtained according to the chaos theory, including:

[0067] Reconstruct the phase space, that is, use the time series of a certain system component to reconstruct an m-dimensional phase space and obtain a group space vector. The calculation formula is as follows:

[0068]

[0069] Where τ is the time delay, m is the embedding dimension, and m≥2d+1, d is the number of independent variables in the system, and X i is the phase point of the reconstructed phase space.

[0070] Further, calculate the maximum Lyapunov exponent, that is, assume that the first i point X in the reconstructed phase space i The nearest neighbor is X ip, and the following conditions are met, the calculation formula is as follows:

[0071] ||X ip -X i ||=min j ||X j -X i ||

[0072] Among them, ║·║ is the Euclidean distance.

[0073] Furthermore, the time interval between two points is specified, and the following assumptions are given:

[0074] τ w / Δt<|ji|<Bτ w / Δt 1<B<10

[0075] Among them, τ w is the time window width, τ w / Δt<|ji| ensures X i and X ip are not on the same track, |ji| is the index difference between two points in the time series, |ji| <Bτ w / Δt ensures one-time calculation of λ i The number of points required is very small, and B is a constant;

[0076] The partial maximum Lyapunov exponent in the direction of maximum diffusion is calculated as follows:

[0077]

[0078] Among them, h is the step size, j is the number of iterations, max h To find the h value that maximizes the separation ratio, that is, to find the optimal time step to maximize the separation speed;

[0079] When the time interval is less than τ w When , the two points are considered to be on the same track. The following formula is used to verify that the two points are still on each track after the nearest neighbor evolution. The formula is as follows:

[0080] 1<h<aτ w / τ(0<a<1)

[0081]

[0082] Where a is a scaling factor less than 1, which is used to adjust the upper limit of the time step h, b·(80°) is the angle threshold, which is used to determine whether two points are still on the same track, and M is the total number of points in the data set;

[0083] The obtained λ1(i) is the partial maximum Lyapunov index of the system, and the maximum Lyapunov index obtained is:

[0084]

[0085] Where λ1 is the average maximum Lyapunov exponent.

[0086] Furthermore, the classification and recognition using support vector machines includes:

[0087] Design the first SVM classifier to identify G defects and the other three defects (M, P, N), mark all sample data corresponding to G defects as positive, and mark the other three defects as negative;

[0088] For the remaining three defects, a second SVM classifier is designed to identify N-type defects and two other insulation defects;

[0089] The sample data corresponding to the N types of defects are marked as positive, and the other two types of defects are marked as negative. At the same time, the third SVM classifier is designed to identify the remaining two types of defects.

[0090] Furthermore, this embodiment also provides a GIS partial discharge pattern recognition system based on chaos theory, including: a data acquisition module, a preprocessing module and a discharge analysis module;

[0091] The data acquisition module is used to collect partial discharge signals caused by typical insulation defects and form PRPD pattern samples;

[0092] The preprocessing module is used to preprocess each PRPD pattern sample and normalize the signal amplitude;

[0093] The discharge analysis module is used to obtain chaotic characteristics based on chaos theory, and use support vector machines for classification and identification, record the mode to which the partial discharge belongs, and complete the identification.

[0094] This embodiment also provides a computer device, which may be a terminal, and its internal structure diagram may be as shown in FIG. Figure 2As shown. The computer device includes a processor, a memory, a communication interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a comprehensive evaluation method suitable for orderly access of large-scale distributed power sources is implemented. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covered on the display screen, or a key, trackball or touchpad set on the computer device housing, or an external keyboard, touchpad or mouse.

[0095] This embodiment further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented:

[0096] Collect partial discharge signals caused by typical insulation defects and form PRPD pattern samples;

[0097] Each PRPD pattern sample was preprocessed and the signal amplitude was normalized;

[0098] The chaotic characteristics are obtained according to the chaos theory, and the support vector machine is used for classification and identification, and the mode of partial discharge is recorded to complete the identification.

[0099] Example 2

[0100] Reference Figure 1 - Figure 2 , which is the second embodiment of the present invention, and this embodiment provides a GIS partial discharge pattern recognition method based on chaos theory. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through economic benefit calculation and simulation experiments.

[0101] Example

[0102] Section 1: Detailed process of test preparation and implementation

[0103] In this embodiment, the GIS partial discharge pattern recognition method based on chaos theory collects typical insulation defect signals and generates PRPD pattern samples, based on which different types of partial discharge patterns are classified and identified. The experimental objects are different types of insulation defect signals, including needle-like defects, particle defects, metal defects, and gap defects. High-frequency sampling instruments are used in the signal acquisition process, and the signals come from metal protrusions, freely moving particles, metal particles fixed on the surface of the insulator, and signal sources in the air gap. The discharge signals of each defect type are collected multiple times to ensure the representativeness and accuracy of the data.

[0104] The collected signal data is first normalized through the preprocessing module, and the amplitude range is normalized to [0,1]. The purpose of this process is to eliminate the amplitude difference of the original signal and ensure the comparability and stability of the signal.

[0105] Next, the processed signal is analyzed according to chaos theory, the phase space is reconstructed and its maximum Lyapunov exponent is calculated. The phase space reconstruction uses the time series of the signal, and the selection of time delay and embedding dimension is based on empirical formulas. By calculating the maximum Lyapunov exponent, we can quantify the chaotic characteristics of the signal and effectively distinguish different types of partial discharge signals.

[0106] After the chaotic characteristics analysis, support vector machines (SVM) are used to classify the various discharge modes. Specifically, three SVM classifiers are used for step-by-step classification: the first SVM classifier distinguishes G-type defects from other types of defects; the second classifier further distinguishes N-type defects from M and P-type defects; finally, the third SVM classifier distinguishes the remaining M-type defects from P-type defects. The training of each classifier depends on the chaotic characteristics and normalized signal features.

[0107] Finally, combining the above steps, the experiment successfully identified different types of partial discharge defects by recording the recognition results of each partial discharge mode. The experimental data will be used to further analyze and verify the advantages of this method over the existing technology in recognition accuracy and classification efficiency, as shown in Table 1.

[0108] Table 1 Experimental data table

[0109]

[0110] From the above experimental data, it can be seen that the GIS partial discharge pattern recognition method based on chaos theory has a high recognition accuracy rate for different types of partial discharge defects. First, the calculation results of the maximum Lyapunov exponent show that the signals of all defects show obvious chaotic characteristics, which enables the analysis method based on chaos theory to effectively distinguish different types of partial discharge patterns.

[0111] Through the application of the support vector machine (SVM) classifier, the experimental data further showed that the classification accuracy of this method is high. For example, the recognition rate of G-type defects is generally high, up to 98%. Other types of defects also showed high recognition rates, among which the accuracy of particle defects reached 96%, while the recognition accuracy of metal and gap defects was 95% and 92%. These data fully demonstrate the advantages of this method in classification, especially in the step-by-step classification of multiple classifiers, SVM can accurately distinguish different types of partial discharge defects in most cases.

[0112] Compared with the existing technology, the traditional partial discharge pattern recognition method mostly relies on manually set thresholds or simple statistical features, which often leads to classification errors when dealing with complex defect patterns. By introducing the method of combining chaos theory with SVM, the nonlinear characteristics of the signal can be fully utilized to significantly improve the accuracy and stability of recognition. In addition, the normalization processing and chaos characteristic analysis used in the experiment further optimized the signal processing process and avoided the influence of the original signal amplitude difference.

[0113] In general, the present invention successfully realizes efficient and accurate identification of different types of partial discharge patterns by combining chaos theory and SVM classification technology. Compared with the existing technology, it has significant innovation and advantages, especially in dealing with complex partial discharge patterns, showing higher robustness and recognition rate. These experimental results provide strong theoretical support for the practical application of this method, and it can be applied to real-time monitoring and fault diagnosis of GIS equipment, with broad application prospects.

[0114] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

[0115] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can adopt the form of complete hardware embodiments, complete software embodiments, or embodiments in combination with software and hardware. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code. The scheme in the embodiments of the present application can be implemented in various computer languages, for example, object-oriented programming language Java and literal scripting language JavaScript, etc.

[0116] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0117] These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0118] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0119] Although the preferred embodiments of the present application have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the present application.

[0120] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A GIS partial discharge pattern recognition method based on chaos theory, characterized by: Including, collecting partial discharge signals caused by typical insulation defects and forming PRPD pattern samples; Each PRPD pattern sample was preprocessed and the signal amplitude was normalized; The chaotic characteristics are obtained according to the chaos theory, and the support vector machine is used for classification and identification, and the mode of partial discharge is recorded to complete the identification.

2. The GIS partial discharge pattern recognition method based on chaos theory as claimed in claim 1, characterized in that: The typical insulation defects include needle-shaped defects, particle-shaped defects, metal-shaped defects and gap-shaped defects; The acquisition method is to collect signals from metal protrusions, free-moving particles, metal particles fixed on the surface of insulators, and air gaps, and generate PRPD pattern samples.

3. The GIS partial discharge pattern recognition method based on chaos theory as claimed in claim 2, characterized in that: The pretreatment includes: Each PRPD pattern sample is preprocessed and then the signal amplitude is normalized to [0,1], and the calculation formula is as follows: Among them, v max and v min Refers to the maximum and minimum values ​​of all signal pulse amplitudes in a sample; V * i V i The normalized pulse signal.

4. The GIS partial discharge pattern recognition method based on chaos theory as claimed in claim 3 is characterized by: The chaotic characteristics obtained according to the chaos theory include: Reconstruct the phase space, that is, use the time series of a certain system component to reconstruct an m-dimensional phase space and obtain a group space vector. The calculation formula is as follows: Where τ is the time delay, m is the embedding dimension, and m≥2d+1, d is the number of independent variables in the system, and X i is the phase point of the reconstructed phase space.

5. The GIS partial discharge pattern recognition method based on chaos theory as claimed in claim 4, characterized in that: The chaotic characteristics obtained according to chaos theory also include: Calculate the maximum Lyapunov exponent, that is, assume that the first i point X in the reconstructed phase space i The nearest neighbor is X ip , and the following conditions are met, the calculation formula is as follows: ||X ip -X i ||=min j ||X j -X i || Here, ||·|| is the Euclidean distance.

6. The GIS partial discharge pattern recognition method based on chaos theory as claimed in claim 5, characterized in that: The chaotic characteristics obtained according to chaos theory also include: Specify the time interval between two points and make the following assumptions: t w / Δt<|ji|<Bτ w / Δt 1<B<10 Among them, τ w is the time window width, τ w / Δt<|ji| ensures X i and X ip are not on the same track, |ji| is the index difference between two points in the time series, |ji| <Bτ w / Δt ensures one-time calculation of λ i The number of points required is very small, and B is a constant; The partial maximum Lyapunov exponent in the direction of maximum diffusion is calculated as follows: Among them, h is the step size, j is the number of iterations, max h To find the h value that maximizes the separation ratio, that is, to find the optimal time step to maximize the separation speed; When the time interval is less than τ w When , the two points are considered to be on the same track. The following formula is used to verify that the two points are still on each track after the nearest neighbor evolution. The formula is as follows: 1<h<at w / τ(0<a<1) Where a is a scaling factor less than 1, which is used to adjust the upper limit of the time step h, b·(80°) is the angle threshold, which is used to determine whether two points are still on the same track, and M is the total number of points in the data set; The obtained λ1(i) is the partial maximum Lyapunov index of the system, and the maximum Lyapunov index obtained is: Where λ1 is the average maximum Lyapunov exponent.

7. The GIS partial discharge pattern recognition method based on chaos theory as claimed in claim 6, characterized in that: The use of support vector machines for classification and recognition includes: Design the first SVM classifier to identify G defects and the other three defects (M, P, N), mark all sample data corresponding to G defects as positive, and mark the other three defects as negative; For the remaining three defects, a second SVM classifier is designed to identify N-type defects and two other insulation defects; The sample data corresponding to the N types of defects are marked as positive, and the other two types of defects are marked as negative. At the same time, the third SVM classifier is designed to identify the remaining two types of defects.

8. A GIS partial discharge pattern recognition system based on chaos theory, based on the GIS partial discharge pattern recognition method based on chaos theory according to any one of claims 1 to 7, characterized in that: Including data acquisition module, preprocessing module and discharge analysis module; The data acquisition module is used to collect partial discharge signals caused by typical insulation defects and form PRPD pattern samples; The preprocessing module is used to preprocess each PRPD pattern sample and normalize the signal amplitude; The discharge analysis module is used to obtain chaotic characteristics according to chaos theory, and use a support vector machine to perform classification and identification, record the mode to which the partial discharge belongs, and complete the identification.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the GIS partial discharge pattern recognition method based on chaos theory according to any one of claims 1 to 7 are 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 steps of the GIS partial discharge pattern recognition method based on chaos theory according to any one of claims 1 to 7 are implemented.

Images