A fault diagnosis method and system for new energy access to the distribution network

Abstract

This invention discloses a fault diagnosis method and system for new energy sources integrated into a distribution network. The method includes: acquiring distribution network operation data; establishing an initial fault type set based on the distribution network operation data; constructing a multi-level fault knowledge graph including equipment, system, and environmental layers based on the initial fault type set; designing a hybrid reasoning mechanism combining rule-based reasoning and probabilistic reasoning based on the multi-level fault knowledge graph; using the hybrid reasoning mechanism for fault diagnosis to obtain fault diagnosis results; calculating the fault diagnosis coverage rate based on the fault diagnosis results; and optimizing the fault diagnosis process. This invention can continuously improve the coverage and accuracy of fault diagnosis, effectively addressing the challenges brought by a high proportion of new energy sources integrated into the distribution network. The core advantage of this method lies in its dynamic adaptability and multi-dimensional knowledge fusion, enabling the fault diagnosis system to continuously improve itself as the distribution network evolves and new fault types emerge.

Description

Technical Field

[0001] This invention relates to the field of power distribution network fault diagnosis technology, and in particular to a fault diagnosis method and system for new energy access to the power distribution network. Background Art

[0002] With the large-scale integration of new energy sources into distribution networks, the energy composition of these networks has been greatly enriched, and their topology has become increasingly complex and variable. Traditional distribution network structures are relatively simple, and power flow distribution is relatively stable. However, the integration of new energy sources has disrupted this balance, making power flow distribution more difficult to predict and control, thereby affecting the accuracy of fault location.

[0003] Adding to the complexity, the equipment used for connecting renewable energy sources may itself carry new risks of failure. For example, photovoltaic inverters may fail due to overheating or overload, and wind turbines may shut down due to mechanical failures or electrical problems. These types of failures are not common in traditional distribution networks, thus posing new challenges to troubleshooting and repair.

[0004] Furthermore, the high proportion of renewable energy integration makes the operation mode of the distribution network more flexible and diverse. Under certain conditions, the distribution network can operate in islanded mode or achieve interconnection of multiple microgrids. While these new operation modes improve the flexibility and reliability of the distribution network, they also cause significant differences in fault characteristics compared to traditional distribution networks. Traditional fault location methods often fall short when faced with these new fault characteristics, making it difficult to quickly and accurately locate the fault point. Summary of the Invention

[0005] The purpose of this section is to outline some aspects of embodiments of the present invention and to briefly describe some preferred embodiments. Simplifications or omissions may be made in this section, as well as in the abstract and title of this application, to avoid obscuring the purpose of these documents; however, such simplifications or omissions should not be construed as limiting the scope of the invention.

[0006] In view of the aforementioned existing problems, this invention is proposed. Therefore, this invention provides a fault diagnosis method for new energy sources integrated into distribution networks, addressing the uncertainties in the fault diagnosis process for high-proportion new energy sources integrated into distribution networks, as well as the problems of low accuracy and robustness of existing diagnostic methods.

[0007] To solve the above-mentioned technical problems, the present invention provides the following technical solution:

[0008] In a first aspect, the present invention provides a fault diagnosis method for new energy access to a distribution network, comprising:

[0009] Acquire distribution network operation data, and establish an initial fault type set based on the distribution network operation data;

[0010] Based on the initial set of fault types, a multi-level fault knowledge graph containing equipment layer, system layer and environment layer is constructed.

[0011] Based on the multi-level fault knowledge graph, a hybrid reasoning mechanism combining rule-based reasoning and probabilistic reasoning is designed. The hybrid reasoning mechanism is used to perform fault diagnosis and obtain fault diagnosis results.

[0012] Based on the fault diagnosis results, calculate the fault diagnosis coverage and optimize the fault diagnosis process.

[0013] As a preferred embodiment of the fault diagnosis method for new energy access to the distribution network described in this invention, the initial fault type set includes:

[0014] Based on literature review and expert knowledge, an initial set of fault types including traditional distribution network faults and new energy system faults was established;

[0015] Using the Apriori association rule algorithm, new failure modes are discovered from historical failure data, and the support and confidence scores of the Apriori association rule algorithm are calculated.

[0016] When both support and confidence levels meet the preset thresholds, a new fault type is discovered and added to the initial fault type set.

[0017] The K-means clustering algorithm is used to perform cluster analysis on fault data to find potential new fault types. The objective function of the K-means algorithm is:

[0018]

[0019] in, For the i-th data point in the j-th class, c j Let be the cluster center of the j-th class;

[0020] The optimal clustering result is obtained by minimizing the objective function. For newly formed clusters, if the characteristics of the newly formed clusters differ from the existing fault types, they are added as new fault types to the initial fault type set.

[0021] As a preferred embodiment of the fault diagnosis method for new energy access to the distribution network described in this invention, the multi-level fault knowledge graph includes:

[0022] The multi-level fault knowledge graph is formally represented using RDF triples <subject, attribute, object>.

[0023] As a preferred embodiment of the fault diagnosis method for new energy access to the distribution network described in this invention, the equipment layer, system layer, and environment layer include:

[0024] The equipment layer describes the fault characteristics and interrelationships of various types of equipment in the power distribution network;

[0025] The system layer describes the overall topology, operating status, and fault propagation patterns of the distribution network;

[0026] The environmental layer includes external factors that affect the operation of the power distribution network.

[0027] As a preferred embodiment of the fault diagnosis method for new energy access to the distribution network described in this invention, the method includes: designing a hybrid reasoning mechanism that combines rule-based reasoning and probabilistic reasoning, comprising:

[0028] The rule reasoning is based on expert knowledge and fault knowledge graphs, and establishes an IF-THEN rule base.

[0029] Bayesian networks are used for probabilistic reasoning to handle uncertainties in fault diagnosis.

[0030] Combining the results of rule-based reasoning and probabilistic reasoning, the DS evidence theory is used for decision fusion. Let m1 and m2 be the basic probability assignment functions obtained from rule-based reasoning and probabilistic reasoning, respectively. Then the fused result can be expressed as:

[0031]

[0032] Where A, B, and C are subsets of the fault type set, B∩C=A, and k is the normalization factor.

[0033] As a preferred embodiment of the fault diagnosis method for new energy access to the distribution network described in this invention, the calculation of the fault diagnosis coverage rate based on the fault diagnosis results includes:

[0034] Fault diagnosis coverage is the ratio of the number of fault types that the system can correctly diagnose to the total number of fault types, expressed by the formula:

[0035]

[0036] Where, N d N represents the number of fault types that can be correctly diagnosed. t This represents the total number of fault types.

[0037] As a preferred embodiment of the fault diagnosis method for new energy access to the distribution network described in this invention, it further includes:

[0038] Based on the different importance and frequency of occurrence of different fault types, a weighted fault diagnosis coverage rate is introduced, expressed by the formula:

[0039]

[0040] Among them, wi I represents the weight of the i-th fault type; i Let I be the indicator function, representing the state when the i-th type of fault can be correctly diagnosed. i =1, otherwise I i =0.

[0041] Secondly, this invention provides a system for fault diagnosis of new energy access to the distribution network, comprising,

[0042] The data acquisition module is used to acquire power distribution network operation data;

[0043] The fault diagnosis module is used to establish an initial fault type set based on the power distribution network operation data; construct a multi-level fault knowledge graph containing equipment, system, and environment layers based on the initial fault type set; design a hybrid reasoning mechanism combining rule-based reasoning and probabilistic reasoning based on the multi-level fault knowledge graph; and use the hybrid reasoning mechanism to perform fault diagnosis and obtain fault diagnosis results.

[0044] The optimization module is used to calculate the fault diagnosis coverage based on the fault diagnosis results and optimize the fault diagnosis process.

[0045] Thirdly, the present invention provides a computing device, comprising:

[0046] Memory and processor;

[0047] The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions. When the computer-executable instructions are executed by the processor, they implement the steps of the fault diagnosis method for new energy access to the distribution network.

[0048] Fourthly, the present invention provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the steps of the fault diagnosis method for new energy access to the distribution network.

[0049] Compared with the prior art, the beneficial effects of the present invention are as follows: The present invention can continuously improve the coverage and accuracy of fault diagnosis, effectively address the challenges brought about by the high proportion of new energy access to the distribution network. The core advantage of this method lies in its dynamic adaptability and multi-dimensional knowledge integration, which enables the fault diagnosis system to continuously improve itself as the distribution network evolves and new fault types emerge. Attached Figure Description

[0050] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. Wherein:

[0051] Figure 1 This is a schematic diagram of the overall process of a fault diagnosis method for new energy access to the distribution network according to an embodiment of the present invention. Detailed Implementation

[0052] To make the above-mentioned objects, features, and advantages of the present invention more apparent and understandable, specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the protection scope of the present invention.

[0053] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0054] 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 phrase "in one embodiment" appearing in different places in this specification does not necessarily refer to the same embodiment, nor is it a single or selective embodiment that is mutually exclusive with other embodiments.

[0055] This invention is described in detail with reference to the schematic diagrams. When detailing the embodiments of this invention, for ease of explanation, the cross-sectional views illustrating the device structure may be partially enlarged, not adhering to the usual scale. Furthermore, the schematic diagrams are merely examples and should not be construed as limiting the scope of protection of this invention. In actual fabrication, the three-dimensional spatial dimensions of length, width, and depth should be included.

[0056] Furthermore, in the description of this invention, it should be noted that the terms "upper," "lower," "inner," and "outer," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. These terms are used only for the convenience of describing the invention and for simplifying the description, and do not indicate or imply that the system or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on the invention. In addition, the terms "first," "second," or "third" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0057] Unless otherwise explicitly specified and limited, the terms "installation," "connection," and "joining" in this invention should be interpreted broadly. For example, they can refer to fixed connections, detachable connections, or integral connections; similarly, they can refer to mechanical connections, electrical connections, or direct connections, or indirect connections through an intermediate medium, or internal connections between two components. Those skilled in the art can understand the specific meaning of the above terms in this invention based on the specific circumstances.

[0058] Example 1

[0059] Reference Figure 1 As an embodiment of the present invention, a fault diagnosis method for new energy access to the distribution network is provided, comprising:

[0060] S100: Obtain distribution network operation data and establish an initial fault type set based on the distribution network operation data;

[0061] In this embodiment, the distribution network operation data includes, but is not limited to: fault records, real-time measurements of current and voltage, power quality parameters such as power factor and frequency, equipment operation information such as switch status and protection action records, and external environmental factors such as weather conditions and load demand. After obtaining the distribution network operation data, the data is preprocessed, which may include data cleaning, normalization, and outlier handling.

[0062] Preferably, based on literature review and expert knowledge, an initial fault type set including traditional distribution network faults and new energy system faults is established;

[0063] In this embodiment of the application, the initial fault type set is represented as:

[0064] F = {F t ,F n}

[0065] Where F is the set of fault types; F t For a subset of faults in traditional distribution networks; F n This is a subset of faults in the new energy system.

[0066] Preferably, the Apriori association rule algorithm is used to discover new failure modes from historical failure data, and the support and confidence of the Apriori association rule algorithm are calculated. When the support and confidence simultaneously meet the preset threshold, a new failure type is discovered and added to the initial failure type set.

[0067] In this embodiment, let X be the fault feature set and Y be the fault type set. The association rule can be represented as X→Y. The formulas for calculating the support and confidence of the association rule are as follows:

[0068] support(X→Y)=P(X∪Y)

[0069] confidence(X→Y) = P(Y|X)

[0070] Preferably, the K-means clustering algorithm is used to perform cluster analysis on the fault data to find potential new fault types. The objective function of the K-means algorithm is:

[0071]

[0072] in, For the i-th data point in the j-th class, c j Let be the cluster center of the j-th class;

[0073] The optimal clustering result is obtained by minimizing the objective function. For newly formed clusters, if the characteristics of the newly formed clusters differ from the existing fault types, they are added as new fault types to the initial fault type set.

[0074] It should be noted that this invention makes full use of the diversity and richness of distribution network operation data to construct an initial fault type set that includes both traditional distribution network faults and new energy system faults. Through the combined application of the Apriori association rule algorithm and the K-means clustering algorithm, not only are new fault patterns mined from historical data, but also potential unknown fault types are discovered, thereby greatly expanding the coverage and accuracy of the fault type set.

[0075] S102: Based on the initial fault type set, construct a multi-level fault knowledge graph containing the equipment layer, system layer, and environment layer;

[0076] Preferably, RDF triples <subject, attribute, object> are used to formally represent the multi-level fault knowledge graph;

[0077] In this embodiment of the application, the multi-level fault knowledge graph is represented as follows:

[0078] G = (E, R, A)

[0079] Where E is the entity set; R is the relation set; and A is the attribute set.

[0080] Preferably, the equipment layer describes the fault characteristics and interrelationships of various types of equipment in the power distribution network;

[0081] For example, taking a transformer as an example, its knowledge representation may include:

[0082] <Transformer, Type, Oil-immersed>;

[0083] <Transformer, fault type, winding short circuit>;

[0084] <Winding short circuit, fault characteristics, three-phase current imbalance>.

[0085] Preferably, the system layer describes the overall topology, operating status, and fault propagation patterns of the distribution network;

[0086] For example,

[0087] <Power distribution lines, connections, substations>

[0088] <Power distribution line, operating mode, dual circuit>;

[0089] <Fault, impact, power supply reliability>.

[0090] Preferably, the environmental layer includes external factors that affect the operation of the power distribution network;

[0091] In one possible embodiment, external factors may include weather conditions, geographical environment, etc.

[0092] For example,

[0093] Lightning strikes cause insulation breakdown.

[0094] <High temperature affects equipment load capacity>;

[0095] <Marine environment, accelerated corrosion of equipment>.

[0096] In the embodiments of this application, the interaction relationships between different layers are described, for example,

[0097] <Equipment failure, leading to system failure>;

[0098] <Environmental factors, impacts, equipment performance>.

[0099] It should be noted that the multi-level fault knowledge graph constructed based on the initial fault type set in this invention effectively integrates key fault information and interrelationships at the equipment, system, and environment levels through the formal representation of RDF triples. This structured knowledge representation not only improves the readability and understandability of fault information but also facilitates intelligent reasoning and fault analysis. By clearly describing equipment fault characteristics, system operating status, and external environmental influences, the multi-level fault knowledge graph provides strong support for fault prediction, rapid location, and repair in power distribution networks, improving the efficiency and accuracy of fault handling.

[0100] S104: Based on a multi-level fault knowledge graph, a hybrid reasoning mechanism combining rule-based reasoning and probabilistic reasoning is designed. The hybrid reasoning mechanism is used for fault diagnosis to obtain fault diagnosis results.

[0101] Preferably, rule-based reasoning is based on expert knowledge and fault knowledge graphs to establish an IF-THEN rule base;

[0102] In this application embodiment, the general form of the rule is:

[0103] IF (condition 1) AND (condition 2) ... THEN (conclusion)

[0104] For example:

[0105] IF (three-phase current imbalance) AND (transformer oil temperature rise) THEN (transformer winding short circuit fault, CF=0.9)

[0106] Here, CF is the confidence factor, used to represent the uncertainty of the rule.

[0107] Preferably, Bayesian networks are used for probabilistic reasoning to handle uncertainties in fault diagnosis;

[0108] In this embodiment, the Bayesian network consists of a directed acyclic graph (DAG) and a conditional probability table (CPT). Let X be the set of observed variables and Y be the fault type. Then, the posterior probability of fault diagnosis can be expressed as:

[0109]

[0110] Based on the structure of Bayesian networks, the joint probability can be decomposed into a product of conditional probabilities:

[0111]

[0112] Wherein, pa(X) i ) represents X i The set of parent nodes.

[0113] Preferably, combining the results of rule-based reasoning and probabilistic reasoning, the decision fusion is performed using DS evidence theory. Let m1 and m2 be the basic probability assignment functions obtained from rule-based reasoning and probabilistic reasoning, respectively. Then, the fused result can be expressed as:

[0114]

[0115] Where A, B, and C are subsets of the fault type set, B∩C=A, and k is the normalization factor.

[0116] It should be noted that this invention combines a hybrid reasoning mechanism of rule-based reasoning and probabilistic reasoning, providing a more comprehensive and accurate solution for distribution network fault diagnosis based on a multi-level fault knowledge graph. Rule-based reasoning utilizes expert knowledge and IF-THEN rules in the fault knowledge graph to quickly locate common fault modes and expresses the uncertainty of the rules through confidence factors. Meanwhile, Bayesian networks effectively handle the complexity and uncertainty in fault diagnosis through probabilistic reasoning, improving the accuracy and robustness of the diagnosis. By using DS evidence theory to fuse the results of rule-based and probabilistic reasoning, the reliability and consistency of the diagnostic results are further enhanced. This hybrid reasoning mechanism improves the efficiency and accuracy of fault diagnosis, contributing to ensuring the safe and stable operation of the power grid.

[0117] S106: Based on the fault diagnosis results, calculate the fault diagnosis coverage rate and optimize the fault diagnosis process;

[0118] Preferably, the fault diagnosis coverage rate is the ratio of the number of fault types that the system can correctly diagnose to the total number of fault types, expressed by the formula:

[0119]

[0120] Where, N d N represents the number of fault types that can be correctly diagnosed. t This represents the total number of fault types.

[0121] Preferably, a weighted fault diagnosis coverage rate is introduced based on the importance and frequency of different fault types, expressed by the formula:

[0122]

[0123] Among them, w i I represents the weight of the i-th fault type; i Let I be the indicator function, representing the state when the i-th type of fault can be correctly diagnosed. i =1, otherwise I i =0.

[0124] In this embodiment of the application, the following strategy is adopted for optimization based on the diagnostic coverage assessment results:

[0125] a. For fault types with low FDC, focus on collecting relevant data and expanding the knowledge graph;

[0126] b. For fault types that are difficult to diagnose, design specific diagnostic rules or adjust the Bayesian network structure;

[0127] c. Improve the observability of key features by adding sensors or optimizing data acquisition strategies.

[0128] In this embodiment, an iterative optimization process is designed to continuously improve fault diagnosis coverage:

[0129] a. Assess current diagnostic coverage;

[0130] b. Identify fault types with low diagnostic coverage;

[0131] c. Implement targeted optimization strategies;

[0132] d. Reassess diagnostic coverage;

[0133] e. If the preset target is reached or convergence is achieved, the process ends; otherwise, return to step b.

[0134] It should be noted that, through the above steps, the method of the present invention can continuously improve the fault diagnosis coverage of distribution networks with a high proportion of new energy sources, effectively addressing the challenges brought about by the access of new energy sources. The method of the present invention has strong adaptability and scalability, and can be continuously optimized and improved with the development of new energy technologies and the emergence of new fault types.

[0135] The above is an illustrative scheme of a fault diagnosis method for new energy access to the distribution network according to this embodiment. It should be noted that the technical solution of the fault diagnosis system for new energy access to the distribution network is based on the same concept as the technical solution of the fault diagnosis method for new energy access to the distribution network described above. For details not described in detail in the technical solution of the fault diagnosis system for new energy access to the distribution network in this embodiment, please refer to the description of the technical solution of the fault diagnosis method for new energy access to the distribution network described above.

[0136] The fault diagnosis system for new energy access to the distribution network in this embodiment includes:

[0137] The data acquisition module is used to acquire power distribution network operation data;

[0138] The fault diagnosis module is used to establish an initial fault type set based on the distribution network operation data; based on the initial fault type set, a multi-level fault knowledge graph including equipment layer, system layer and environment layer is constructed; based on the multi-level fault knowledge graph, a hybrid reasoning mechanism combining rule reasoning and probabilistic reasoning is designed, and the hybrid reasoning mechanism is used to perform fault diagnosis and obtain fault diagnosis results.

[0139] The optimization module is used to calculate the fault diagnosis coverage based on the fault diagnosis results and optimize the fault diagnosis process.

[0140] This embodiment also provides a computing device suitable for fault diagnosis of new energy access to the distribution network, including:

[0141] The system includes a memory and a processor. The memory stores computer-executable instructions, and the processor executes these instructions to implement the fault diagnosis method for new energy access to the power distribution network as proposed in the above embodiments.

[0142] This embodiment also provides a storage medium storing a computer program, which, when executed by a processor, implements the fault diagnosis method for new energy access to the distribution network as proposed in the above embodiments.

[0143] The storage medium proposed in this embodiment and the fault diagnosis method for realizing the access of new energy to the distribution network proposed in the above embodiments belong to the same inventive concept. Technical details not described in detail in this embodiment can be found in the above embodiments, and this embodiment has the same beneficial effects as the above embodiments.

[0144] Based on the above description of the implementation methods, those skilled in the art can clearly understand that the present invention can be implemented using software and necessary general-purpose hardware, and of course, it can also be implemented using hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as a computer floppy disk, read-only memory (ROM), random access memory (RAM), flash memory, hard disk, or optical disk, etc., including several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods of the various embodiments of the present invention.

[0145] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A fault diagnosis method for new energy access to a distribution network, characterized in that, include: Acquire distribution network operation data, and establish an initial fault type set based on the distribution network operation data; Based on the initial set of fault types, a multi-level fault knowledge graph containing equipment layer, system layer and environment layer is constructed. Based on the multi-level fault knowledge graph, a hybrid reasoning mechanism combining rule-based reasoning and probabilistic reasoning is designed. The hybrid reasoning mechanism is used to perform fault diagnosis and obtain fault diagnosis results. Among them, a hybrid reasoning mechanism combining rule-based reasoning and probabilistic reasoning is designed, including: The rule reasoning is based on expert knowledge and fault knowledge graphs, and establishes an IF-THEN rule base. Bayesian networks are used for probabilistic reasoning to handle uncertainties in fault diagnosis. Combining the results of rule-based reasoning and probabilistic reasoning, the DS evidence theory is used for decision fusion. Let m1 and m2 be the basic probability assignment functions obtained from rule-based reasoning and probabilistic reasoning, respectively. Then the fused result can be expressed as: Where A, B, and C are subsets of the fault type set, B∩C=A, and k is the normalization factor; Based on the fault diagnosis results, calculate the fault diagnosis coverage and optimize the fault diagnosis process; The calculation of fault diagnosis coverage, based on the fault diagnosis results, includes: Fault diagnosis coverage is the ratio of the number of fault types that the system can correctly diagnose to the total number of fault types, expressed by the formula: Where, N d N represents the number of fault types that can be correctly diagnosed. t This represents the total number of fault types.

2. The fault diagnosis method for new energy access to the distribution network as described in claim 1, characterized in that, Establishing the initial fault type set includes, Based on literature review and expert knowledge, an initial set of fault types including traditional distribution network faults and new energy system faults was established; Using the Apriori association rule algorithm, new failure modes are discovered from historical failure data, and the support and confidence scores of the Apriori association rule algorithm are calculated. When both support and confidence levels meet the preset thresholds, a new fault type is discovered and added to the initial fault type set. The K-means clustering algorithm is used to perform cluster analysis on fault data to find potential new fault types. The objective function of the K-means algorithm is: in, For the i-th data point in the j-th class, c j Let j be the cluster center of the j-th class; The optimal clustering result is obtained by minimizing the objective function. For newly formed clusters, if the characteristics of the newly formed clusters differ from the existing fault types, they are added as new fault types to the initial fault type set.

3. The fault diagnosis method for new energy access to the distribution network as described in claim 1 or 2, characterized in that, A multi-level fault knowledge graph includes, The multi-level fault knowledge graph is formally represented using RDF triples <subject, attribute, object>.

4. The fault diagnosis method for new energy access to the distribution network as described in claim 3, characterized in that, The equipment layer, system layer, and environment layer include, The equipment layer describes the fault characteristics and interrelationships of various types of equipment in the power distribution network; The system layer describes the overall topology, operating status, and fault propagation patterns of the distribution network; The environmental layer includes external factors that affect the operation of the power distribution network.

5. The fault diagnosis method for new energy access to the distribution network as described in claim 4, characterized in that, It also includes, Based on the different importance and frequency of occurrence of different fault types, a weighted fault diagnosis coverage rate is introduced, expressed by the formula: Among them, w i I represents the weight of the i-th fault type; i Let I be the indicator function, representing the state when the i-th type of fault can be correctly diagnosed. i =1, otherwise I i =0.

6. A system for fault diagnosis of new energy access to a distribution network, using the method as described in claim 1, characterized in that, include: The data acquisition module is used to acquire power distribution network operation data; The fault diagnosis module is used to establish an initial set of fault types based on the power distribution network operation data; Based on the initial set of fault types, a multi-level fault knowledge graph containing equipment layer, system layer and environment layer is constructed. Based on the multi-level fault knowledge graph, a hybrid reasoning mechanism combining rule-based reasoning and probabilistic reasoning is designed. The hybrid reasoning mechanism is used to perform fault diagnosis and obtain fault diagnosis results. The optimization module is used to calculate the fault diagnosis coverage based on the fault diagnosis results and optimize the fault diagnosis process.

7. An electronic device, comprising: Memory and processor; The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions. When the computer-executable instructions are executed by the processor, they implement the steps of the fault diagnosis method for new energy access to the distribution network as described in any one of claims 1 to 5.

8. A computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the steps of the fault diagnosis method for new energy access to the distribution network as described in any one of claims 1 to 5.

Images