Power grid real fault identification method and system based on multi-source information fusion

Abstract

The invention discloses a power grid real fault identification method and system based on multi-source information fusion, and the method comprises the steps: carrying out the modal decomposition of electrical quantity information, carrying out the analysis and processing of a fault current signal in a fault element set according to improved Hilbert transformation, and obtaining an electrical quantity fault degree corresponding to the electrical quantity information; switching value information is obtained, a hierarchical weighted fuzzy Petri network is adopted to process and analyze the switching value information, and an element fuzzy fault degree corresponding to the switching value information is obtained; performing multi-source information fusion on the electrical quantity fault degree and the component fuzzy fault degree according to an improved D-S evidence theory to obtain fusion data; and performing fault identification on the fused data according to a fault identification decision method containing a Gaussian mixture model to obtain a fault element. A fault diagnosis decision model based on a Gaussian mixture model is adopted to realize fusion of switching value information and electrical quantity signals, and identification of a power grid fault state is realized.

Description

Technical Field

[0001] The present invention belongs to the technical field of power grid fault identification, and in particular relates to a method and system for identifying real power grid faults based on multi-source information fusion. Background Art

[0002] As the power system becomes more and more complex, the value of the massive data generated in the complex power secondary circuit has become an important guarantee for driving the high reliability, safety and stability of the power system. Distinguishing and identifying the real fault state of the power grid and the abnormal state of the secondary circuit based on multiple information sources such as fault recording and protection information is an important way to improve the detection and early warning of hidden dangers in the power secondary circuit. At present, fault waveform data classification methods such as those based on typical abnormal characteristics have the limitation of extracting a single feature, as well as poor noise resistance and difficulty in adapting to complex and changeable dynamic electrical environments. The power secondary circuit has a long chain and involves many types of circuit equipment. Power engineers are basically unable to traverse all fault points in all intermediate links to build a signal classification and recognition method that adapts to all abnormal situations. In particular, some early and deep hidden dangers are often extremely unstable, and the abnormal form is constantly changing. There is basically no fixed reference formula to apply. Even with the update of the external environment or the change of the operating status, it presents a repeated evolution of "initial appearance-gradual appearance-obvious-gradual appearance-initial appearance". Accurate detection is very difficult, resulting in a serious lag in the exposure time of hidden dangers. In addition, the identification of unknown new abnormal waveforms has relied on long-term observation, collection, outbreak, summary and analysis by power grid operators to obtain experience and relevant parameters. This is completely uncontrollable and has a long optimization and refinement cycle. At the same time, the early warning and identification system faces the problem of continuous upgrading and maintenance in the later stages of construction. Summary of the invention

[0003] The present invention provides a method and system for identifying real faults in a power grid based on multi-source information fusion, which is used to solve the technical problem that when distinguishing between the real fault state of the power grid and the abnormal state of a secondary circuit, the extracted features are single, resulting in poor identification effect.

[0004] In a first aspect, the present invention provides a method for identifying real faults in a power grid based on multi-source information fusion, comprising:

[0005] Searching for fault areas in the power grid to form a set of fault components;

[0006] Acquiring electrical quantity information, performing modal decomposition on the electrical quantity information, and analyzing and processing the fault current signal in the fault component set according to an improved Hilbert transform to obtain an electrical quantity fault degree corresponding to the electrical quantity information;

[0007] Acquire switch quantity information, and use a hierarchical weighted fuzzy Petri net to process and analyze the switch quantity information to obtain a fuzzy fault degree of a component corresponding to the switch quantity information;

[0008] According to the improved DS evidence theory, multi-source information fusion is performed on the electrical quantity fault degree and the component fuzzy fault degree to obtain fused data;

[0009] Fault identification is performed on the fused data according to a fault identification decision method including a Gaussian mixture model to obtain a faulty component.

[0010] In a second aspect, the present invention provides a real fault identification system for a power grid based on multi-source information fusion, comprising:

[0011] A search module configured to search for a fault area of ​​the power grid to form a set of fault components;

[0012] A decomposition module is configured to obtain electrical quantity information, perform modal decomposition on the electrical quantity information, and analyze and process the fault current signal in the fault component set according to an improved Hilbert transform to obtain an electrical quantity fault degree corresponding to the electrical quantity information;

[0013] A processing module is configured to obtain switch quantity information, and process and analyze the switch quantity information using a hierarchical weighted fuzzy Petri net to obtain a component fuzzy fault degree corresponding to the switch quantity information;

[0014] A fusion module is configured to perform multi-source information fusion on the electrical quantity fault degree and the component fuzzy fault degree according to an improved DS evidence theory to obtain fused data;

[0015] The identification module is configured to perform fault identification on the fused data according to a fault identification decision method including a Gaussian mixture model to obtain a faulty component.

[0016] In a third aspect, an electronic device is provided, comprising: at least one processor, and a memory communicatively connected to the at least one processor, wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can perform the steps of the method for identifying real faults in a power grid based on multi-source information fusion according to any embodiment of the present invention.

[0017] In a fourth aspect, the present invention further provides a computer-readable storage medium having a computer program stored thereon, wherein when the program instructions are executed by a processor, the processor executes the steps of the method for identifying real faults in a power grid based on multi-source information fusion according to any embodiment of the present invention.

[0018] The present invention discloses a method and system for identifying real faults in power grids based on multi-source information fusion. The method and system extract the corresponding fault features through hierarchical weighted fuzzy Petri net and Hilbert transform to obtain the fault degree of electrical quantity (i.e., amplitude distortion degree, fault energy degree) and fuzzy fault degree. Then, a fault diagnosis decision model based on Gaussian mixture model is used to realize the fusion of switch quantity information and electrical quantity signal, so as to realize the identification of power grid fault status. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] 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 some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0020] Figure 1 A flowchart of a method for identifying real faults in a power grid based on multi-source information fusion provided by an embodiment of the present invention;

[0021] Figure 2 A structural block diagram of a power grid real fault identification system based on multi-source information fusion provided by an embodiment of the present invention;

[0022] Figure 3 It is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0023] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0024] See also Figure 1 , which shows a flow chart of a method for identifying real faults in a power grid based on multi-source information fusion of the present application.

[0025] like Figure 1 As shown, the real fault identification method of the power grid based on multi-source information fusion specifically includes the following steps:

[0026] Step S101, searching the fault area of ​​the power grid to form a fault component set;

[0027] Step S102, acquiring electrical quantity information, performing modal decomposition on the electrical quantity information, and analyzing and processing the fault current signal in the fault component set according to the improved Hilbert transform to obtain the electrical quantity fault degree corresponding to the electrical quantity information.

[0028] In this step, the input original signal is assumed to be f(t), and the extreme point R(t) of the original signal is calculated;

[0029] The linear transformation method is used to transform the extreme point R(t) and generate the corresponding residual r(t), which is expressed as:

[0030]

[0031] In the formula, R(t j ) is t j The extreme point of the original signal at time R(t j+1 ) is t j+1 The extreme value point of the original signal at time t is the sampling time, t j is the sampling time corresponding to the jth extreme point, t j+1 is the sampling time corresponding to the j+1th extreme point;

[0032] The residual r(t) is subtracted from the original signal to obtain an intrinsic mode function of the original signal, and the original signal is decomposed into a plurality of unique intrinsic mode components and a residual according to the intrinsic mode function.

[0033] It should be noted that the electrical quantity fault degree includes the amplitude distortion degree and the current fault energy degree. The fault current signal in the fault component set is analyzed and processed according to the improved Hilbert transform, and the electrical quantity fault degree corresponding to the electrical quantity information is obtained, including:

[0034] Perform Hilbert transform on the first five FIMD components of the fault line current. Assume that the instantaneous amplitude of the jth FIMD component of line i at time k is a according to the definition of instantaneous amplitude. ij (k), according to a ij (k) Calculate the effective value of the instantaneous current amplitude of the jth FIMD component of the i-th line before and after the fault occurs. The expression is:

[0035]

[0036] In the formula, A ij1 is the effective value of the instantaneous current amplitude of the jth FIMD component of the i-th line before the fault occurs, A ij2is the effective value of the instantaneous current amplitude of the jth FIMD component of the i-th line after the fault occurs, N is the number of sampling points corresponding to the end time of one cycle after the fault occurs, and l is the number of sampling points corresponding to the fault moment;

[0037] Calculate the distortion of the fault line current signal, the expression is:

[0038]

[0039] The distortion degree of the fault line current signal is normalized, and the expression is:

[0040]

[0041] In the formula, m i is the normalized distortion of the i-th fault line current signal, c j is the jth fault current signal distortion, c i is the distortion degree of the i-th fault current signal, L is the total number of lines;

[0042] Calculate the matrix of normalized amplitude distortion, the expression is:

[0043] M=[m1,m2,…,m L ],

[0044] Where M is the column phase quantity composed of the normalized distortion degree of the fault line current signal, m1 is the normalized distortion degree of the first fault line current signal, m2 is the normalized distortion degree of the second fault line current signal, and m L is the normalized distortion degree of the Lth fault line current signal;

[0045] According to the energy spectrum H(w, t) of the fault current signal, the marginal spectrum corresponding to the energy spectrum H(w, t) is obtained, and the expression is:

[0046]

[0047] Where h(ω) is the marginal spectrum and T is the time period;

[0048] Calculate the marginal energy spectrum of the Hilbert transform, the expression is:

[0049]

[0050] Where t2 is the end time, t1 is the start time, and S(ω) is the marginal energy spectrum;

[0051] Calculate the current fault energy measure e of the i-th line at fault based on the marginal energy spectrum i , the expression is:

[0052]

[0053] In the formula, f s is the signal sampling frequency.

[0054] Step S103, acquiring switch quantity information, and using a hierarchical weighted fuzzy Petri net to process and analyze the switch quantity information to obtain a component fuzzy fault degree corresponding to the switch quantity information.

[0055] In this step, the line switch quantity is converted into the corresponding numerical quantity according to the hierarchical weighted fuzzy Petri net, and the failure probability of the line components is recorded as p1, p2, ..., p n ;

[0056] The normalization method is used to process the failure probability of the line components, and the failure probability matrix G = {g1, g2, ..., g n}, that is, the fuzzy fault degree of each line element is obtained, and the normalized expression is:

[0057]

[0058] In the formula, p i is the probability of failure of the ith line element, p j is the failure probability of the jth line element, g i is the normalized failure probability of the ith circuit element.

[0059] Step S104, performing multi-source information fusion on the electrical quantity fault degree and the component fuzzy fault degree according to the improved DS evidence theory to obtain fused data.

[0060] In this step, assume that there are n pieces of evidence, and the absolute credibility of the i-th piece of evidence is R i , normalized, the relative credibility of each evidence body is obtained as follows:

[0061]

[0062] In the formula, R j is the absolute credibility of the jth piece of evidence, n′ is the total number of pieces of evidence, r i is the relative credibility of the ith piece of evidence;

[0063] The basic credibility allocation function is constructed with electrical quantity fault degree and fuzzy fault degree as independent evidence bodies.

[0064] Step S105 , performing fault identification on the fused data according to a fault identification decision method including a Gaussian mixture model to obtain a faulty component.

[0065] In this step, the gamma function is used to initially classify the components, and the initial classification is corrected based on the Gaussian mixture model to obtain the final faulty components. Specifically:

[0066] Assume that the different fault probabilities corresponding to n different components are represented as follows:

[0067] m(F1), m(F2), …, m(F n ),

[0068] In which, let F be the identification framework of power grid fault diagnosis, let F contain n elements, where F i represents the fault state of the i-th component, then m is the basic credibility distribution on the fault identification framework F, m(F i ) is called F i The basic credible number. m(F i ) represents the measure of uncertainty about the fault state of the ith component.

[0069] This type of component is divided into two types, and the gamma function used is:

[0070]

[0071] In the formula, e is the natural exponent, x is the independent variable of the function, and t is the integral variable of the function;

[0072] The gamma function value is solved for different fault probability representations. If the preset conditions are met, they are classified into candidate class Γ1 of faulty components; the rest are classified into candidate class Γ2 of non-faulty components. ε selects a suitable value according to the actual situation, generally 12, and the expression of the preset conditions is:

[0073]

[0074] In the formula, Γ(m(F i )) is m(F i ) is the Γ function of the independent variable;

[0075] Assuming that the number of all components in the fault candidate class is N1, the corresponding gamma function value is defined as The minimum value of the gamma function is defined as the absolute fault component, that is, this component will definitely fail.

[0076] Calculate the Gaussian mixture model of 2 components, the expression is:

[0077]

[0078] Where p(x) is the failure probability of the xth component, Γ(m(F)|μ k ,∑k) is m(F), μ k, ∑k is the Γ function of the variable, m(F) is the basic credible number of F, k is the kth component, N(m(F)|μ k , ∑k) is the Gaussian probability density function, ω k , μ k , ∑k are the weight, mean, and covariance matrix of the kth component in the mixed model respectively;

[0079] The expectation maximization algorithm (EM method) is used to estimate the parameters of the Gaussian mixture model (GMM). The probability of each data point being generated by each component is calculated under the initial parameters, and then the model parameters are continuously updated so that the maximum likelihood function of the GMM can achieve an extreme value. The expression is:

[0080]

[0081] Then the data m(F i )The probability of the pth component generated by the initial classification (Γ1, Γ2) is:

[0082]

[0083] In the formula, ω p is the weight of the pth component, Γ p (m(F i )) is the pth element under Γ(m(F i )) is m(F i ) is the Γ function of the independent variable, N(m(F i )|μ p , ∑p) is the Gaussian probability density function of the p-th component, μp is the mean of the p-th component, and ∑p is the covariance matrix of the p-th component;

[0084] The GMM parameters estimated by EM are expressed as:

[0085]

[0086] In the formula, ∑ p is the covariance matrix of the pth element, ω p is the weight of the pth component, m(F i ) represents the measure of uncertainty about the fault state of the ith component.

[0087] If Γ1(m(F i ))≤Γ2(m(F i )) holds true, then m(F i ) is moved to Γ2.

[0088] Among them, all components in the fault candidate class are faulty components.

[0089] In summary, the method of the present application extracts the corresponding fault features through hierarchical weighted fuzzy Petri nets and Hilbert transform to obtain the electrical quantity fault degree (i.e., amplitude distortion degree, fault energy degree) and fuzzy fault degree; then a fault diagnosis decision model based on a Gaussian mixture model is used to realize the fusion of switch quantity information and electrical quantity signals, thereby realizing the identification of the power grid fault state.

[0090] See also Figure 2 , which shows a structural block diagram of a power grid real fault identification system based on multi-source information fusion of the present application.

[0091] like Figure 2 As shown, the power grid real fault identification system 200 includes a search module 210 , a decomposition module 220 , a processing module 230 , a fusion module 240 and an identification module 250 .

[0092] Among them, the search module 210 is configured to search the fault area of ​​the power grid to form a fault component set; the decomposition module 220 is configured to obtain electrical quantity information, perform modal decomposition on the electrical quantity information, and analyze and process the fault current signal in the fault component set according to the improved Hilbert transform to obtain the electrical quantity fault degree corresponding to the electrical quantity information; the processing module 230 is configured to obtain switch quantity information, and use a hierarchical weighted fuzzy Petri net to process and analyze the switch quantity information to obtain the component fuzzy fault degree corresponding to the switch quantity information; the fusion module 240 is configured to perform multi-source information fusion on the electrical quantity fault degree and the component fuzzy fault degree according to the improved DS evidence theory to obtain fused data; the identification module 250 is configured to perform fault identification on the fused data according to a fault identification decision method including a Gaussian mixture model to obtain a fault component.

[0093] It should be understood that Figure 2 Modules and references documented in Figure 1 Therefore, the operations and features described above for the method and the corresponding technical effects are also applicable to Figure 2 The modules in it will not be described in detail here.

[0094] In some other embodiments, the embodiments of the present invention further provide a computer-readable storage medium having a computer program stored thereon, wherein when the program instructions are executed by a processor, the processor is caused to execute the method for identifying real faults of a power grid based on multi-source information fusion in any of the above method embodiments;

[0095] As an implementation mode, the computer-readable storage medium of the present invention stores computer-executable instructions, and the computer-executable instructions are configured as follows:

[0096] Searching for fault areas in the power grid to form a set of fault components;

[0097] Acquiring electrical quantity information, performing modal decomposition on the electrical quantity information, and analyzing and processing the fault current signal in the fault component set according to an improved Hilbert transform to obtain an electrical quantity fault degree corresponding to the electrical quantity information;

[0098] Acquire switch quantity information, and use a hierarchical weighted fuzzy Petri net to process and analyze the switch quantity information to obtain a fuzzy fault degree of a component corresponding to the switch quantity information;

[0099] According to the improved DS evidence theory, multi-source information fusion is performed on the electrical quantity fault degree and the component fuzzy fault degree to obtain fused data;

[0100] Fault identification is performed on the fused data according to a fault identification decision method including a Gaussian mixture model to obtain a faulty component.

[0101] The computer-readable storage medium may include a program storage area and a data storage area, wherein the program storage area may store an operating system and an application required by at least one function; the data storage area may store data created according to the use of the real fault identification system for the power grid based on multi-source information fusion, etc. In addition, the computer-readable storage medium may include a high-speed random access memory, and may also include a memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some embodiments, the computer-readable storage medium may optionally include a memory remotely arranged relative to the processor, and these remote memories may be connected to the real fault identification system for the power grid based on multi-source information fusion via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0102] Figure 3 is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention, such as Figure 3 As shown, the device includes: a processor 310 and a memory 320. The electronic device may also include: an input device 330 and an output device 340. The processor 310, the memory 320, the input device 330 and the output device 340 may be connected via a bus or other means. Figure 3In the example, the connection through the bus is taken as an example. The memory 320 is the above-mentioned computer-readable storage medium. The processor 310 executes various functional applications and data processing of the server by running the non-volatile software programs, instructions and modules stored in the memory 320, that is, the real fault identification method of the power grid based on multi-source information fusion of the above-mentioned method embodiment is realized. The input device 330 can receive input digital or character information, and generate key signal input related to user settings and function control of the real fault identification system of the power grid based on multi-source information fusion. The output device 340 may include display devices such as display screens.

[0103] The electronic device can execute the method provided by the embodiment of the present invention, and has the functional modules and beneficial effects corresponding to the execution method. For technical details not described in detail in this embodiment, please refer to the method provided by the embodiment of the present invention.

[0104] As an implementation mode, the electronic device is applied to a real fault identification system for a power grid based on multi-source information fusion, and is used for a client, and includes: at least one processor; and a memory connected to the at least one processor in communication; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can:

[0105] Searching for fault areas in the power grid to form a set of fault components;

[0106] Acquiring electrical quantity information, performing modal decomposition on the electrical quantity information, and analyzing and processing the fault current signal in the fault component set according to an improved Hilbert transform to obtain an electrical quantity fault degree corresponding to the electrical quantity information;

[0107] Acquire switch quantity information, and use a hierarchical weighted fuzzy Petri net to process and analyze the switch quantity information to obtain a fuzzy fault degree of a component corresponding to the switch quantity information;

[0108] According to the improved DS evidence theory, multi-source information fusion is performed on the electrical quantity fault degree and the component fuzzy fault degree to obtain fused data;

[0109] Fault identification is performed on the fused data according to a fault identification decision method including a Gaussian mixture model to obtain a faulty component.

[0110] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods of each embodiment or some parts of the embodiment.

[0111] Finally, 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 aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for identifying real faults in a power grid based on multi-source information fusion, characterized in that: include: Searching for fault areas in the power grid to form a set of fault components; Acquiring electrical quantity information, performing modal decomposition on the electrical quantity information, and analyzing and processing the fault current signal in the fault component set according to an improved Hilbert transform to obtain an electrical quantity fault degree corresponding to the electrical quantity information; Acquire switch quantity information, and use a hierarchical weighted fuzzy Petri net to process and analyze the switch quantity information to obtain a fuzzy fault degree of a component corresponding to the switch quantity information; According to the improved DS evidence theory, multi-source information fusion is performed on the electrical quantity fault degree and the component fuzzy fault degree to obtain fused data; Fault identification is performed on the fused data according to a fault identification decision method including a Gaussian mixture model to obtain a faulty component.

2. A method for identifying real faults in a power grid based on multi-source information fusion according to claim 1, characterized in that: The acquiring electrical quantity information and performing modal decomposition on the electrical quantity information comprises: Assume the input original signal is f(t), calculate the extreme point R(t) of the original signal; The linear transformation method is used to transform the extreme point R(t) and generate the corresponding residual r(t), which is expressed as: In the formula, R(t j ) is t j The extreme point of the original signal at time R(t j+1 ) is t j+1 The extreme value point of the original signal at time t is the sampling time, t j is the sampling time corresponding to the jth extreme point, t j+1 is the sampling time corresponding to the j+1th extreme point; The residual r(t) is subtracted from the original signal to obtain an intrinsic mode function of the original signal, and the original signal is decomposed into a plurality of unique intrinsic mode components and a residual according to the intrinsic mode function.

3. A method for identifying real faults in a power grid based on multi-source information fusion according to claim 1, characterized in that: The electrical quantity fault degree includes amplitude distortion degree and current fault energy degree; The analyzing and processing of the fault current signal in the fault component set according to the improved Hilbert transform to obtain the electrical quantity fault degree corresponding to the electrical quantity information includes: Perform Hilbert transform on the first five FIMD components of the fault line current. Assume that the instantaneous amplitude of the jth FIMD component of line i at time k is a according to the definition of instantaneous amplitude. ij (k), according to a ij (k) Calculate the effective value of the instantaneous current amplitude of the jth FIMD component of the i-th line before and after the fault occurs. The expression is: In the formula, A ij1 is the effective value of the instantaneous current amplitude of the jth FIMD component of the i-th line before the fault occurs, A ij2 is the effective value of the instantaneous current amplitude of the jth FIMD component of the i-th line after the fault occurs, N is the number of sampling points corresponding to the end time of one cycle after the fault occurs, and l is the number of sampling points corresponding to the fault moment; Calculate the distortion of the fault line current signal, the expression is: The distortion degree of the fault line current signal is normalized, and the expression is: In the formula, m i is the normalized distortion of the i-th fault line current signal, c j is the jth fault current signal distortion, c i is the distortion degree of the i-th fault current signal, L is the total number of lines; Calculate the matrix of normalized amplitude distortion, the expression is: M=[m1,m2,…,m L ], Where M is the column phase quantity composed of the normalized distortion degree of the fault line current signal, m1 is the normalized distortion degree of the first fault line current signal, m2 is the normalized distortion degree of the second fault line current signal, and m L is the normalized distortion degree of the Lth fault line current signal; According to the energy spectrum H(w, t) of the fault current signal, the marginal spectrum corresponding to the energy spectrum H(w, t) is obtained, and the expression is: Where h(ω) is the marginal spectrum and T is the time period; Calculate the marginal energy spectrum of the Hilbert transform, the expression is: Where t2 is the end time, t1 is the start time, and S(ω) is the marginal energy spectrum; Calculate the current fault energy measure e of the i-th line at fault based on the marginal energy spectrum i , the expression is: In the formula, f s is the signal sampling frequency.

4. The method for identifying real faults in a power grid based on multi-source information fusion according to claim 1, characterized in that: The method of using a hierarchical weighted fuzzy Petri net to process and analyze the switch quantity information to obtain the fuzzy fault degree of the component corresponding to the switch quantity information includes: According to the hierarchical weighted fuzzy Petri net, the line switch quantity is converted into the corresponding numerical quantity, and the failure probability of the line components is recorded as p1, p2, ..., p n ; The normalization method is used to process the failure probability of the line components, and the failure probability matrix G = {g1, g2, ..., g n }, that is, the fuzzy fault degree of each line element is obtained, and the normalized expression is: In the formula, p i is the probability of failure of the ith line element, p j is the failure probability of the jth line element, g i is the normalized failure probability of the ith circuit element.

5. The method for identifying real faults in a power grid based on multi-source information fusion according to claim 1, characterized in that: The multi-source information fusion of the electrical quantity fault degree and the component fuzzy fault degree is performed according to the improved DS evidence theory to obtain fused data including: Assume that there are n pieces of evidence, and the absolute credibility of the i-th piece of evidence is R i , normalized, the relative credibility of each evidence body is obtained as follows: In the formula, R j is the absolute credibility of the jth piece of evidence, n′ is the total number of pieces of evidence, r i is the relative credibility of the ith piece of evidence; The basic credibility allocation function is constructed with electrical quantity fault degree and fuzzy fault degree as independent evidence bodies.

6. A method for identifying real faults in a power grid based on multi-source information fusion according to claim 1, characterized in that: The fault identification decision method including the Gaussian mixture model is used to identify the fused data to obtain the fault component, which includes: The gamma function is used to perform initial classification of components, and the initial classification is corrected based on the Gaussian mixture model to obtain the final faulty components.

7. A real fault identification system for power grid based on multi-source information fusion, characterized in that: include: A search module configured to search for a fault area of ​​the power grid to form a set of fault components; a decomposition module configured to obtain electrical quantity information, perform modal decomposition on the electrical quantity information, and analyze and process the fault current signal in the fault component set according to an improved Hilbert transform to obtain an electrical quantity fault degree corresponding to the electrical quantity information; A processing module is configured to obtain switch quantity information, and process and analyze the switch quantity information using a hierarchical weighted fuzzy Petri net to obtain a component fuzzy fault degree corresponding to the switch quantity information; A fusion module is configured to perform multi-source information fusion on the electrical quantity fault degree and the component fuzzy fault degree according to an improved DS evidence theory to obtain fused data; The identification module is configured to perform fault identification on the fused data according to a fault identification decision method including a Gaussian mixture model to obtain a faulty component.

8. An electronic device, characterized in that: include: At least one processor, and a memory communicatively connected to the at least one processor, wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method described in any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

Images