Power grid fault diagnosis method and system based on fuzzy integral multi-source information fusion

Abstract

A power grid fault diagnosis method and system based on fuzzy integral multi-source information fusion, the system includes: power grid data acquisition module, data preprocessing module, fault feature extraction module, central control module, diagnosis model construction module, fault diagnosis module; the association analysis algorithm is used to preprocess the data information of different monitoring points on the current power grid distribution line to obtain a suspicious component set, from which a fault feature parameter set is extracted to construct a power grid multi-objective fault diagnosis model, and the power grid fault is diagnosed based on the fuzzy integral algorithm. The fault processing method based on wavelet transform can more effectively reduce information redundancy, has strong scalability and scope of application, and has high fault diagnosis accuracy; the fuzzy integral theory can effectively integrate multi-source information, perform information fusion fault diagnosis, have stronger robustness, have extremely high fault coverage, and can effectively improve the accuracy of distribution fault detection.

Description

Technical Field

[0001] The present invention relates to the technical field of power grid fault diagnosis, and in particular to a power grid fault diagnosis method and system based on fuzzy integral multi-source information fusion. Background Art

[0002] At present, the power grid is the pillar of the national economy. Economic development is inseparable from the development of the power grid. Once a large-scale power outage occurs, it will cause immeasurable losses. In recent years, my country has ushered in a rapid development stage of power grid construction. The research on power grid fault diagnosis methods has become the focus of research by scholars at home and abroad, and it is also a concern of power equipment manufacturers.

[0003] In the existing technology, the occurrence of power grid failures is unpredictable, the principle of the protection device is extremely complex, and more importantly, with the rapid development of the power system, the integration characteristics of large power grids are becoming increasingly obvious, and the coupling relationship between different elements within the system and the external environment is constantly increasing, making the power grid information multi-source and highly coupled. When facing multi-source information, the traditional power grid fault diagnosis method is difficult to solve and has a low degree of automation. There are often false alarms and missed alarms, and the diagnosis effect is poor. Therefore, there is still a lot of work to be done in power grid fault diagnosis. Real-time and accurate fault diagnosis and timely repair of faulty equipment to restore power supply are of great significance to reducing economic losses and improving power supply reliability. Summary of the invention

[0004] In order to solve the deficiencies in the prior art, the purpose of the present invention is to provide a power grid fault diagnosis method and system based on fuzzy integral multi-source information fusion, to fuse and integrate multi-source information of the power grid, to realize automatic diagnosis of power grid faults, to avoid false alarms and missed alarms, and to effectively improve the accuracy of fault detection.

[0005] The present invention adopts the following technical solution.

[0006] The power grid fault diagnosis system based on fuzzy integral multi-source information fusion includes: power grid data acquisition module, data preprocessing module, fault feature extraction module, central control module, diagnosis model construction module, fault diagnosis module, database construction module, result feedback module, data storage module, update display module;

[0007] A power grid data acquisition module is used to obtain data information of different monitoring points on the current power grid distribution line;

[0008] A data preprocessing module is used to preprocess the data information of different monitoring points on the current power distribution line acquired by using a correlation analysis algorithm to determine the suspicious component set of the fault object;

[0009] A fault feature extraction module, used to extract a fault feature parameter set from the suspicious component set and calculate the fault probability of each component in the suspicious component set;

[0010] A diagnosis model building module is used to build a power grid multi-objective fault diagnosis model based on a fault characteristic parameter set;

[0011] A fault diagnosis module is used to diagnose power grid faults using a power grid multi-objective fault diagnosis model based on a fuzzy integral algorithm;

[0012] A database construction module is used to store historical operation data of different monitoring points on the power distribution line through power grid fault diagnosis;

[0013] A result feedback module, used for providing feedback on the fault detection results;

[0014] A data storage module is used to store the acquired data information of different monitoring points on the current power distribution line, data preprocessing results, fault characteristic parameter sets, fault probabilities, databases, power grid fault areas, power grid multi-objective fault diagnosis models, fault diagnosis results, and result feedback information;

[0015] An update display module is used to update and display the real-time data of the acquired data information of different monitoring points on the current power distribution line, data preprocessing results, fault characteristic parameter sets, fault probabilities, databases, power grid fault areas, power grid multi-objective fault diagnosis models, fault diagnosis results, and result feedback information;

[0016] The central control module is used to coordinate and control the normal operation of the power grid data acquisition module, data preprocessing module, fault feature extraction module, central control module, diagnosis model construction module, fault diagnosis module, database construction module, result feedback module, data storage module, and update display module through the central processor.

[0017] The power grid fault diagnosis method based on fuzzy integral multi-source information fusion includes:

[0018] Step 1: Collect data information from different monitoring points on the current power grid distribution line;

[0019] Step 2: Use the correlation analysis algorithm to pre-process the acquired data information to obtain a set of suspicious components of the fault object;

[0020] Step 3, extracting a set of fault characteristic parameters from the suspicious component set, and calculating the failure probability of each component in the suspicious component set;

[0021] Step 4, constructing an optimization model for multi-objective fault diagnosis of a power grid according to the fault characteristic parameter set, and performing linearization processing on the optimization model for multi-objective fault diagnosis of a power grid to obtain a final multi-objective fault diagnosis model for a power grid;

[0022] Step 5: diagnose power grid faults using a power grid multi-objective fault diagnosis model based on a fuzzy integral algorithm.

[0023] Preferably, in step 1, the data information includes fault alarm information of the current power grid distribution line, distribution network topology information, and historical operation data of different monitoring points on the current power grid distribution line;

[0024] The fault alarm information of the current power grid distribution line includes protection action information and circuit breaker information.

[0025] Preferably, step 2 comprises:

[0026] Step 2.1, establishing a set of association rules for data information; wherein the set of association rules includes the time and location of the fault, the faulty device, and the fault alarm information;

[0027] Step 2.2, according to the association rule set, based on the association analysis algorithm, frequent item sets are screened and association rules are mined, the association confidence of each device failure is calculated, and the devices with a confidence threshold greater than the set association confidence threshold are selected as components in the suspicious component set.

[0028] Preferably, step 3 comprises:

[0029] Step 3.1, perform wavelet analysis on q components in the suspicious component set, and form a p×q-order matrix A with the wavelet analysis results of p scales;

[0030] Step 3.2: For the i-th element in the suspicious element set, calculate the wavelet singularity y using the following relationship: i :

[0031]

[0032] In the formula,

[0033]

[0034] λ i =diag(λ1,λ2,…,λ t ) is the singular value characteristic matrix of the matrix A corresponding to the i-th element in the suspicious element set, where t = min(p,q), i = 1, 2, ..., n,

[0035] The set of wavelet singularities of each component is the extracted fault feature parameter set;

[0036] Step 3.3, at the fault time t0, for the i-th component in the suspicious component set, calculate the wavelet fault degree m using the following relationship: WFD :

[0037]

[0038] In the formula,

[0039] α F For credibility,

[0040] F imax is the maximum amplitude of the electrical signal change of the ith element,

[0041] F′ i is the degree of change in the amplitude of the electrical signal of the i-th component before and after the fault.

[0042] Preferably, in step 4, the objective function in the optimization model of multi-objective fault diagnosis of power grid satisfies the following relationship:

[0043] minE(X)=w1E1(X)+w2E2(X)

[0044] In the formula,

[0045] minE(X) is the optimal objective function with the minimum error index.

[0046] E1(X) is the action logic error indicator, which reflects the deviation between the actual state of the protection device and the expected state.

[0047] E2(X) is the information communication error indicator, which reflects the deviation between the actual state and the alarm state of the protection device.

[0048] w1 is the action logic weight coefficient,

[0049] w2 is the information communication weight coefficient,

[0050] X is the fault hypothesis, which is composed of the states of all power failure components;

[0051] in,

[0052]

[0053]

[0054] In the formula,

[0055] C j is the actual state of the jth circuit breaker, is the expected state of the jth circuit breaker, is the alarm status of the jth circuit breaker,

[0056] r km is the actual status of the kth master protection, is the expected state of the kth primary protection,

[0057] r kp is the actual status of the kth backup protection, is the expected state of the kth station's near backup protection,

[0058] r ks is the actual status of the kth remote backup protection, is the expected state of the k-th remote backup protection,

[0059] r k is the actual state of the k-th protection station, is the alarm status of the kth protection station,

[0060] It is a continuous or operation, that is, as long as one of the following elements is true, the result is true.

[0061] In step 4, the optimization model of the multi-objective fault diagnosis of the power grid is linearized to determine the approximate expression of the power flow value of each line with respect to the output value of each unit, including:

[0062] Step 4.1, through power flow simulation, determine that the power flow values ​​of all lines are linearly related to the output values ​​of each unit;

[0063] Step 4.2: Perform linear fitting and use the least squares fitting method to obtain an approximate expression.

[0064] Preferably, step 5 comprises:

[0065] Step 5.1, obtain the fault characteristic parameters and fault probability of each component in the suspicious component set, that is, the wavelet singularity y of the i-th component i and wavelet fault degree m WFD ;

[0066] Step 5.2: Based on the fuzzy integral algorithm, the wavelet singularity y of the i-th element is i and wavelet fault degree m WFD Perform fusion and obtain a fused data set of all components;

[0067] In step 5.3, based on the fuzzy C-means algorithm, the fusion data set is analyzed using the power grid multi-objective fault diagnosis model to obtain the power grid fault diagnosis results.

[0068] Step 5.2 includes:

[0069] Step 5.2.1, using fault recording information, relay protection information and substation monitoring information as multi-source information;

[0070] Step 5.2.2, according to the λ fuzzy measure algorithm, based on the wavelet singularity y of the i-th element i and wavelet fault degree m WFD Obtain the fuzzy measurement of power grid faults, and calculate the influence coefficient of multi-source information on the fuzzy measurement of power grid faults;

[0071] Step 5.2.3, based on the fuzzy integral algorithm, a fuzzy measurement function is constructed using the value of multi-source information on the influence coefficient, and the fuzzy measurement function is solved to obtain the decision fuzzy value after multi-source information fusion, which is the fault information density;

[0072] Step 5.2.4, store the multi-source information whose decision fuzzy value of each branch of the fault information is greater than or equal to the decision threshold into the fused data set.

[0073] Preferably, the power grid fault diagnosis method based on fuzzy integral multi-source information fusion also includes:

[0074] Step 6.1, storing acquired data information, data preprocessing results, fault characteristic parameter set, fault probability, database, power grid fault area, power grid multi-objective fault diagnosis model, fault diagnosis results and result feedback information;

[0075] Step 6.2, updating and displaying the real-time data of data information, data preprocessing results, fault characteristic parameter set, fault probability, database, power grid fault area, power grid multi-objective fault diagnosis model, fault diagnosis results and result feedback information;

[0076] Step 6.3, use the database construction program to build power grid fault diagnosis and store the historical operation data of different monitoring points on the power grid distribution line.

[0077] The beneficial effects of the present invention are that, compared with the prior art, the method for processing fault information based on wavelet transform can more effectively reduce the redundancy of information, has strong scalability and scope of application, and has high fault diagnosis accuracy; the use of fuzzy integral theory can effectively integrate multi-source information, perform information fusion fault diagnosis, has stronger robustness, has extremely high fault coverage, and can effectively improve the accuracy of distribution fault detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0078] Figure 1 It is a structural block diagram of a power grid fault diagnosis system based on fuzzy integral multi-source information fusion provided by an embodiment of the present invention;

[0079] Figure 2 It is a flow chart of a power grid fault diagnosis method based on fuzzy integral multi-source information fusion provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0080] The present application is further described below in conjunction with the accompanying drawings. The following embodiments are only used to more clearly illustrate the technical solution of the present invention, and cannot be used to limit the protection scope of the present application.

[0081] like Figure 1 ,The power fault diagnosis system based on fuzzy integral multi-source information fusion includes: power grid data acquisition module, data preprocessing module, fault feature extraction module, database construction module, central control module, diagnosis model construction module, fault diagnosis module, result feedback module, data storage module, and update display module.

[0082] The power grid data acquisition module is connected to the data preprocessing module and is used to obtain data information of different monitoring points on the current power grid distribution line through the data acquisition device.

[0083] The data preprocessing module is connected to the fault feature extraction module and is used to preprocess the data information of different monitoring points on the current power distribution line acquired through the data preprocessing program using the Apriori algorithm to determine the suspicious component set of the faulty equipment.

[0084] The fault feature extraction module is connected to the database construction module and is used to extract the fault feature parameter set of the suspicious component set through a feature extraction program and calculate the fault probability of each component in the suspicious component set.

[0085] The database construction module is connected to the central control module and is used for power grid fault diagnosis constructed by the database construction program to store historical operation data of different monitoring points on the power grid distribution line.

[0086] The central control module is connected to the diagnosis model construction module and is used to coordinate and control the normal operation of the power grid data acquisition module, data preprocessing module, fault feature extraction module, database construction module, central control module, diagnosis model construction module, fault diagnosis module, result feedback module, data storage module, and update display module through the central processor.

[0087] The diagnosis model building module is connected to the fault diagnosis module and is used to build a power grid multi-objective fault diagnosis model according to a fault characteristic parameter set through a model building program.

[0088] The fault diagnosis module is connected with the result feedback module and is used to diagnose the power grid fault by using the power grid multi-objective fault diagnosis model based on the fuzzy integral algorithm theory through the fault diagnosis program.

[0089] The result feedback module is connected to the data storage module and is used to provide feedback on the fault detection result through a result feedback program.

[0090] The data storage module is connected to the update display module and is used to store the data information, data preprocessing results, fault characteristic parameter sets, fault probabilities, databases, power grid fault areas, power grid multi-objective fault diagnosis models, fault diagnosis results, and result feedback information of different monitoring points on the current power grid distribution line acquired through the memory.

[0091] The update display module is used to update and display the real-time data of the data information, data preprocessing results, fault characteristic parameter set, fault probability, database, power grid fault area, power grid multi-objective fault diagnosis model, fault diagnosis results and result feedback information of different monitoring points on the current power grid distribution line through the display.

[0092] like Figure 2 , the power grid fault diagnosis method based on fuzzy integral multi-source information fusion includes:

[0093] Step 1: Use the data acquisition device through the power grid data acquisition module to collect data information from different monitoring points on the current power grid distribution line.

[0094] Specifically, in step 1, the data information includes fault alarm information of the current power grid distribution line, distribution network topology information and historical operation data of different monitoring points on the current power grid distribution line; wherein the fault alarm information of the current power grid distribution line includes protection action information and circuit breaker information.

[0095] Step 2: Preprocess the data information of different monitoring points on the current power distribution line acquired by the data preprocessing module using the data preprocessing program and the Apriori algorithm to determine the suspicious component set of the faulty equipment.

[0096] Specifically, step 2 includes:

[0097] Step 2.1, establishing an association rule set for data information; wherein the association rule set includes the time, location, faulty equipment, and fault alarm information of the fault;

[0098] Step 2.2, according to the association rule set, based on the association analysis algorithm, frequent item sets are screened and association rules are mined, the association confidence of each device failure is calculated, and the devices with a confidence threshold greater than the set association confidence threshold are selected as components in the suspicious component set.

[0099] Step 3: extract the fault feature parameter set of the suspicious component set by using the feature extraction program through the fault feature extraction module, and calculate the failure probability of each component in the suspicious component set.

[0100] Specifically, step 3 includes:

[0101] Step 3.1, perform wavelet analysis on q components in the suspicious component set, and form a p×q-order matrix A with the wavelet analysis results of p scales;

[0102] Step 3.2: For the i-th element in the suspicious element set, calculate the wavelet singularity y using the following relationship: i :

[0103]

[0104] In the formula,

[0105]

[0106] λ i =diag(λ1,λ2,…,λ t ) is the singular value characteristic matrix of the matrix A corresponding to the i-th element in the suspicious element set, where t = min(p, q), i = 1, 2, ..., n,

[0107] The set of wavelet singularities of each component is the extracted fault feature parameter set;

[0108] Step 3.3, at the fault time t0, for the i-th component in the suspicious component set, calculate the wavelet fault degree m using the following relationship: WFD :

[0109]

[0110] In the formula,

[0111] α F For credibility,

[0112] F imax is the maximum amplitude of the signal change of the i-th element,

[0113] F′i is the change in the amplitude of the signal of the i-th element before and after the fault, satisfying the following relationship:

[0114]

[0115] In the formula, when t<t0, then F if =max(D(t)); when t≥t0, then F ib =max(D(t)); where D(t) is the detail coefficient,

[0116] The wavelet failure degree of each component is the failure probability of the component.

[0117] Step 4: Use the model building program through the diagnosis model building module to build a power grid multi-objective fault diagnosis model according to the fault characteristic parameter set.

[0118] Specifically, in step 4, the objective function in the optimization model of multi-objective fault diagnosis of power grid satisfies the following relationship:

[0119] minE(X)=w1E1(X)+w2E2(X)

[0120] In the formula,

[0121] minE(X) is the optimal objective function with the minimum error index.

[0122] E1(X) is the action logic error indicator, which reflects the deviation between the actual state of the protection device and the expected state.

[0123] E2(X) is the information communication error indicator, which reflects the deviation between the actual state and the alarm state of the protection device.

[0124] w1 is the action logic weight coefficient,

[0125] w2 is the information communication weight coefficient,

[0126] X is the fault hypothesis, which is composed of the states of all power failure components;

[0127] in,

[0128]

[0129]

[0130] In the formula,

[0131] C j is the actual state of the jth circuit breaker, is the expected state of the jth circuit breaker, is the alarm status of the jth circuit breaker,

[0132] r km is the actual status of the kth master protection, is the expected state of the kth primary protection,

[0133] r kp is the actual status of the kth backup protection, is the expected state of the kth station's near backup protection,

[0134] r ks is the actual status of the kth remote backup protection, is the expected state of the k-th remote backup protection,

[0135] r k is the actual state of the k-th protection station, is the alarm status of the kth protection station,

[0136] It is a continuous or operation, that is, as long as one of the following elements is true, the result is true.

[0137] In step 4, the optimization model of the multi-objective fault diagnosis of the power grid is linearized to determine the approximate expression of the power flow value of each line with respect to the output value of each unit, including:

[0138] Step 4.1, through power flow simulation, determine that the power flow values ​​of all lines are linearly related to the output values ​​of each unit;

[0139] Step 4.2: Perform linear fitting and use the least squares fitting method to obtain an approximate expression.

[0140] Through linear fitting, the goodness of fit of the expression was analyzed and the rationality of the coefficients and constants in the formula was also explained.

[0141] Step 5: diagnose the power grid fault by using the fault diagnosis module, the fault diagnosis program and the power grid multi-objective fault diagnosis model based on the fuzzy integral algorithm theory; and provide feedback on the fault detection result by using the result feedback module and the result feedback program.

[0142] Specifically, step 5 includes:

[0143] Step 5.1, obtain the fault characteristic parameters and fault probability of each component in the suspicious component set, that is, the wavelet singularity y of the i-th component i and wavelet fault degree m WFD .

[0144] Step 5.2: Based on the fuzzy integral algorithm, the wavelet singularity y of the i-th element is i and wavelet fault degree m WFD The fusion is performed and the fused data set of all components is obtained.

[0145] Specifically, step 5.2 includes:

[0146] Step 5.2.1, using fault recording information, relay protection information and substation monitoring information as multi-source information;

[0147] Step 5.2.2, according to the λ fuzzy measure algorithm, based on the wavelet singularity y of the i-th element i and wavelet fault degree m WFD Obtain the fuzzy measurement of power grid faults, and calculate the influence coefficient of multi-source information on the fuzzy measurement of power grid faults;

[0148] Step 5.2.3, based on the fuzzy integral algorithm, a fuzzy measurement function is constructed using the value of multi-source information on the influence coefficient, and the fuzzy measurement function is solved to obtain the decision fuzzy value after multi-source information fusion, which is the fault information density;

[0149] Step 5.2.4, store the multi-source information whose decision fuzzy value of each branch of the fault information is greater than or equal to the decision threshold into the fused data set.

[0150] In step 5.3, based on the fuzzy C-means algorithm, the fusion data set is analyzed using the power grid multi-objective fault diagnosis model to obtain the power grid fault diagnosis results.

[0151] The power grid fault diagnosis method based on fuzzy integral multi-source information fusion also includes:

[0152] Step 6.1, using the memory to store the acquired data information, data preprocessing results, fault characteristic parameter set, fault probability, database, power grid fault area, power grid multi-objective fault diagnosis model, fault diagnosis results and result feedback information of different monitoring points on the current power grid distribution line through the data storage module.

[0153] Step 6.2, by updating the display module, the display is used to update and display the real-time data of the data information, data preprocessing results, fault characteristic parameter set, fault probability, database, power grid fault area, power grid multi-objective fault diagnosis model, fault diagnosis results and result feedback information of different monitoring points on the current power grid distribution line.

[0154] Step 6.3, construct power grid fault diagnosis using a database construction program through a database construction module to store historical operating data of different monitoring points on the power grid distribution lines.

[0155] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When the use is implemented in whole or in part in the form of a computer program product, the computer program product includes one or more computer instructions. When the computer program instructions are loaded or executed on a computer, the process or function described in the embodiment of the present invention is 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 transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from one website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL) or wireless (e.g., infrared, wireless, microwave, etc.) mode) to another website site, computer, server or data center. The computer-readable storage medium may be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integrated. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state hard disk SolidState Disk (SSD)), etc.

[0156] The beneficial effects of the present invention are that, compared with the prior art, the method for processing fault information based on wavelet transform can more effectively reduce the redundancy of information, has strong scalability and scope of application, and has high fault diagnosis accuracy; the use of fuzzy integral theory can effectively integrate multi-source information, perform information fusion fault diagnosis, has stronger robustness, has extremely high fault coverage, and can effectively improve the accuracy of distribution fault detection.

[0157] The applicant of the present invention has made a detailed explanation and description of the implementation examples of the present invention in conjunction with the drawings in the specification. However, those skilled in the art should understand that the above implementation examples are only preferred implementation schemes of the present invention, and the detailed description is only to help readers better understand the spirit of the present invention, but not to limit the scope of protection of the present invention. On the contrary, any improvements or modifications based on the inventive spirit of the present invention should fall within the scope of protection of the present invention.

Claims

1. A power grid fault diagnosis system based on fuzzy integral multi-source information fusion, characterized in that: The system includes: a power grid data acquisition module, a data preprocessing module, a fault feature extraction module, a central control module, a diagnosis model construction module, a fault diagnosis module, a database construction module, a result feedback module, a data storage module, and an update display module; The power grid data acquisition module is used to obtain data information of different monitoring points on the current power grid distribution line; the data information includes fault alarm information of the current power grid distribution line, distribution network topology information and historical operation data of different monitoring points on the current power grid distribution line; The data preprocessing module is used to establish an association rule set for data information, which includes the time, location, faulty equipment and fault alarm information of the fault; according to the association rule set, the frequent item sets are screened and the association rules are mined based on the association analysis algorithm, the association confidence of each device failure is calculated, and the devices with a confidence threshold greater than the set value are selected as the components in the suspicious component set; A fault feature extraction module, used to extract a fault feature parameter set from the suspicious component set and calculate the fault probability of each component in the suspicious component set; The diagnostic model construction module is used to construct a multi-objective fault diagnosis model for a power grid according to a set of fault characteristic parameters; the weighted sum of the action logic error index and the information communication error index is minimized as the objective function in the optimization model for multi-objective fault diagnosis for a power grid, wherein the action logic error index reflects the deviation between the actual state and the expected state of the protection device, and the information communication error index reflects the deviation between the actual state and the alarm state of the protection device; the optimization model for multi-objective fault diagnosis for a power grid is linearized to determine the approximate expression of the power flow value of each line with respect to the output value of each unit; The fault diagnosis module is used to obtain the fault characteristic parameters and fault probability of each component in the suspicious component set. i The wavelet singularity and wavelet fault degree of each component; based on the fuzzy integral algorithm, i The wavelet singularity and wavelet fault degree of each component are fused, and the fusion data set of all components is obtained, including fault recording information, relay protection information and substation monitoring information as multi-source information. Fuzzy measurement algorithm, based on i The wavelet singularity and wavelet fault degree of each element are used to obtain the fuzzy measurement of power grid fault, and the influence coefficient of multi-source information on the fuzzy measurement of power grid fault is calculated. Based on the fuzzy integral algorithm, a fuzzy measurement function is constructed using the value of multi-source information on the influence coefficient. The fuzzy measurement function is solved to obtain the decision fuzzy value after multi-source information fusion, which is the fault information density. The multi-source information whose decision fuzzy value of each branch of the fault information is greater than or equal to the decision threshold is stored in the fused data set; based on the fuzzy C-means algorithm, the fused data set is analyzed using the power grid multi-objective fault diagnosis model to obtain the power grid fault diagnosis result; A database construction module is used to store historical operation data of different monitoring points on the power distribution line through power grid fault diagnosis; A result feedback module, used for providing feedback on the fault detection results; A data storage module is used to store the acquired data information of different monitoring points on the current power distribution line, data preprocessing results, fault characteristic parameter sets, fault probabilities, databases, power grid fault areas, power grid multi-objective fault diagnosis models, fault diagnosis results, and result feedback information; An update display module is used to update and display the real-time data of the acquired data information of different monitoring points on the current power distribution line, data preprocessing results, fault characteristic parameter sets, fault probabilities, databases, power grid fault areas, power grid multi-objective fault diagnosis models, fault diagnosis results, and result feedback information; The central control module is used to coordinate and control the normal operation of the power grid data acquisition module, data preprocessing module, fault feature extraction module, central control module, diagnosis model construction module, fault diagnosis module, database construction module, result feedback module, data storage module, and update display module through the central processor.

2. A power grid fault diagnosis method based on fuzzy integral multi-source information fusion, applicable to the power grid fault diagnosis system based on fuzzy integral multi-source information fusion according to claim 1, characterized in that: The method comprises: Step 1: Collect data information from different monitoring points on the current power grid distribution line; Step 2: Use the correlation analysis algorithm to pre-process the acquired data information to obtain a set of suspicious components of the fault object; Step 3, extracting a set of fault characteristic parameters from the suspicious component set, and calculating the failure probability of each component in the suspicious component set; Step 4, constructing an optimization model for multi-objective fault diagnosis of a power grid according to the fault characteristic parameter set, and performing linearization processing on the optimization model for multi-objective fault diagnosis of a power grid to obtain a final multi-objective fault diagnosis model for a power grid; Step 5: diagnose power grid faults using a power grid multi-objective fault diagnosis model based on a fuzzy integral algorithm.

3. The power grid fault diagnosis method based on fuzzy integral multi-source information fusion according to claim 2 is characterized in that: In step 1, the data information includes fault alarm information of the current power grid distribution line, distribution network topology information, and historical operation data of different monitoring points on the current power grid distribution line; The fault alarm information of the current power grid distribution line includes protection action information and circuit breaker information.

4. The power grid fault diagnosis method based on fuzzy integral multi-source information fusion according to claim 2 is characterized in that: Step 2 includes: Step 2.1, establishing a set of association rules for data information; wherein the set of association rules includes the time and location of the fault, the faulty device, and the fault alarm information; Step 2.2, according to the association rule set, based on the association analysis algorithm, frequent item sets are screened and association rules are mined, the association confidence of each device failure is calculated, and the devices with a confidence threshold greater than the set association confidence threshold are selected as components in the suspicious component set.

5. The power grid fault diagnosis method based on fuzzy integral multi-source information fusion according to claim 4 is characterized in that: Step 3 includes: Step 3.1: Focus on the suspicious components The components are subjected to wavelet analysis. The wavelet analysis results of the scales are composed of Order Matrix ; Step 3.2: For the first The wavelet singularity is calculated using the following relationship : In the formula, ， The first Element corresponding matrix The singular value characteristic matrix of , , The set of wavelet singularities of each component is the extracted fault feature parameter set; Step 3.3, at the moment of failure , for the first The wavelet fault degree is calculated by the following relationship: : In the formula, For credibility, For the The maximum amplitude of the electrical signal change of each element, For the The degree of change in the amplitude of the electrical signal of a component before and after the fault.

6. The power grid fault diagnosis method based on fuzzy integral multi-source information fusion according to claim 2 is characterized in that: In step 4, the objective function in the optimization model of the power grid multi-objective fault diagnosis satisfies the following relationship: In the formula, is the objective function that takes the minimum error index as the optimal one, It is an action logic error indicator, reflecting the deviation between the actual state of the protection device and the expected state. It is an information communication error indicator, reflecting the deviation between the actual state and the alarm state of the protection device. is the action logic weight coefficient, is the information communication weight coefficient, is the fault hypothesis, which is composed of the states of all power failure components; in, In the formula, For the The actual status of the circuit breaker. For the The desired state of the circuit breaker, For the The alarm status of the circuit breaker. For the The actual status of the host protection, For the The expected state of the host protection, For the The actual status of the backup protection. For the The expected state of the near-term backup protection, For the The actual status of Taiyuan backup protection, For the The expected status of remote backup protection, For the The actual status of the protection For the The alarm status of the protection station, It is a continuous or operation, that is, as long as one of the following elements is true, the result is true.

7. The power grid fault diagnosis method based on fuzzy integral multi-source information fusion according to claim 6 is characterized in that: In step 4, the optimization model of the multi-objective fault diagnosis of the power grid is linearized to determine the approximate expression of the power flow value of each line with respect to the output value of each unit, including: Step 4.1, through power flow simulation, determine that the power flow values ​​of all lines are linearly related to the output values ​​of each unit; Step 4.2: Perform linear fitting and use the least squares fitting method to obtain an approximate expression.

8. The power grid fault diagnosis method based on fuzzy integral multi-source information fusion according to claim 2 is characterized in that: Step 5 includes: Step 5.1, obtain the fault characteristic parameters and fault probability of each component in the suspicious component set, that is, The wavelet singularity of the element and wavelet fault degree ; Step 5.2: Based on the fuzzy integral algorithm, The wavelet singularity of the element and wavelet fault degree Perform fusion and obtain a fused data set of all components; In step 5.3, based on the fuzzy C-means algorithm, the fusion data set is analyzed using the power grid multi-objective fault diagnosis model to obtain the power grid fault diagnosis results.

9. The power grid fault diagnosis method based on fuzzy integral multi-source information fusion according to claim 7 is characterized in that: Step 5.2 includes: Step 5.2.1, using fault recording information, relay protection information and substation monitoring information as multi-source information; Step 5.2.2, according to Fuzzy measurement algorithm, based on The wavelet singularity of the element and wavelet fault degree Obtain the fuzzy measurement of power grid faults, and calculate the influence coefficient of multi-source information on the fuzzy measurement of power grid faults; Step 5.2.3, based on the fuzzy integral algorithm, a fuzzy measurement function is constructed using the value of multi-source information on the influence coefficient, and the fuzzy measurement function is solved to obtain the decision fuzzy value after multi-source information fusion, which is the fault information density; Step 5.2.4, store the multi-source information whose decision fuzzy value of each branch of the fault information is greater than or equal to the decision threshold into the fused data set.

10. The power grid fault diagnosis method based on fuzzy integral multi-source information fusion according to claim 2 is characterized in that: The power grid fault diagnosis method based on fuzzy integral multi-source information fusion also includes: Step 6.1, storing acquired data information, data preprocessing results, fault characteristic parameter set, fault probability, database, power grid fault area, power grid multi-objective fault diagnosis model, fault diagnosis results and result feedback information; Step 6.2, updating and displaying the real-time data of data information, data preprocessing results, fault characteristic parameter set, fault probability, database, power grid fault area, power grid multi-objective fault diagnosis model, fault diagnosis results and result feedback information; Step 6.3, use the database construction program to build power grid fault diagnosis and store the historical operation data of different monitoring points on the power grid distribution line.

Images