Self-healing action analysis method based on distribution automation terminal protection setting value

Abstract

The invention relates to the technical field of power systems, in particular to a distribution automation terminal protection setting value-based self-healing action analysis method, which comprises the following steps of: defining a target and a standard of a self-healing action; the method comprises the following steps: analyzing historical fault data, identifying a fault mode, and constructing a fault identification model; historical data and real-time operation data are combined, and a dynamic protection constant value model is established; constructing a multi-level decision tree structure according to the identified fault mode and the dynamic protection constant value model; performing a self-healing action feasibility test by simulating different fault scenes and self-healing decision logic; all links of the self-healing process are tracked, related data are collected and analyzed in time, and feedback information is formed; the actual effect of the self-healing measure is evaluated by comparing the operation data before and after the self-healing; and establishing and optimizing a knowledge base. The power distribution automation system has the beneficial effects that real-time monitoring and intelligent response can be realized, and the fault identification accuracy and the self-healing capability are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of power systems, and in particular to a self-healing action analysis method based on distribution automation terminal protection setting values. Background Art

[0002] With the continuous growth of electricity demand, the reliability and intelligence level of the distribution system need to be improved urgently. The existing distribution automation terminal protection setting analysis method often relies on static data collection and processing, lacks dynamic adaptability, and is difficult to cope with complex power grid fault scenarios. Traditional methods lag behind in fault mode recognition, protection setting adjustment, and self-healing decision logic, resulting in the inability to respond to faults quickly and effectively under extreme loads and severe weather conditions. In addition, the construction and updating of the knowledge base is not sufficient to support real-time decision-making, which limits the intelligent development of the system. Summary of the invention

[0003] In view of the above problems or problems existing in the prior art, the present invention is proposed.

[0004] Therefore, the object of the present invention is to provide a self-healing action analysis method based on distribution automation terminal protection settings, which can improve fault identification accuracy and self-healing capability.

[0005] To solve the above technical problems, the present invention provides the following technical solutions: a self-healing action analysis method based on distribution automation terminal protection setting, which includes defining the goal and standard of the self-healing action;

[0006] By analyzing historical fault data, identifying fault modes and building fault identification models;

[0007] By combining historical data with real-time operation data, a dynamic protection setting model is established;

[0008] Construct a multi-level decision tree structure based on the identified fault modes and dynamic protection setting models;

[0009] Conduct feasibility tests on self-healing actions by simulating different fault scenarios and self-healing decision logic;

[0010] By tracking each link of the self-healing process, timely collecting and analyzing relevant data, and forming feedback information;

[0011] Evaluate the actual effect of self-healing measures by comparing the operating data before and after self-healing;

[0012] Build and optimize the knowledge base.

[0013] As a preferred solution of the self-healing action analysis method based on the distribution automation terminal protection setting value of the present invention, the goals of the self-healing action include quickly restoring power supply, reducing the impact of faults on users, and improving system reliability;

[0014] The criteria for self-healing actions include response time, fault detection accuracy, and automatic recovery rate.

[0015] As a preferred solution of the self-healing action analysis method based on the distribution automation terminal protection setting value of the present invention, a fault identification model is constructed, including identifying the fault mode of short circuit, overload or equipment failure, to provide basic data support for self-healing analysis, and its formula is as follows:

[0016] F(x)=w1·I 2 +w2·V·R+w3·(P max -P current )+w4·e -λt

[0017] Where F(x) is the fault identification score, and the higher the value, the greater the fault risk; I is the current flowing through the device; V is the device voltage; R is the resistance of the device; P max is the rated power of the equipment; P current is the current power of the device; w1, w2, w3, and w4 are weight parameters, which respectively represent the influence of current, voltage, power, and device status on fault identification; λ is the attenuation factor, which reflects the influence of device aging or environmental factors on fault risk; t is the device operation time;

[0018] The model is used to calculate the fault identification score of the current equipment. When it is higher than a certain threshold, the system determines it as a potential fault state. The threshold is set autonomously based on the actual situation.

[0019] As a preferred solution of the self-healing action analysis method based on the distribution automation terminal protection setting value of the present invention, the dynamic protection setting value model includes automatically adjusting the protection setting value according to the actual operation status, environmental changes and load characteristics of the power grid, and its formula is as follows:

[0020]

[0021] Among them, PD is the dynamic protection setting value; P base is the basic protection setting value, which is set based on the equipment standard; α, β, γ are weight coefficients, which respectively represent the influence of load, temperature and environmental factors on the protection setting value; L is the current load; L max is the maximum load of the equipment; T current is the current temperature; T max is the maximum safe temperature of the equipment; H envIt is the environmental change factor, which is used to reflect the impact of the external environment on the equipment.

[0022] As a preferred solution of the self-healing action analysis method based on the distribution automation terminal protection setting of the present invention, the decision logic includes response strategies under different fault conditions, such as selecting appropriate automatic reclosing, adjusting load or segmented power supply, to ensure that the power supply is restored to the maximum extent in the shortest time.

[0023] As a preferred solution of the self-healing action analysis method based on the distribution automation terminal protection setting value of the present invention, wherein: the decision tree structure includes fault detection, dynamic protection setting value evaluation, decision response strategy selection, and effect evaluation and feedback;

[0024] Based on the decision tree structure, the self-healing decision logic at runtime includes real-time monitoring, dynamic adjustment, and comprehensive evaluation.

[0025] As a preferred solution of the self-healing action analysis method based on the distribution automation terminal protection setting of the present invention, the feedback information includes whether the self-healing action is successful or not, and also includes the above-mentioned standard information of the response time, fault detection accuracy, and automatic recovery rate of the successful self-healing action. Through continuous feedback analysis, the self-healing logic and decision tree structure can be continuously optimized to ensure the efficient self-healing capability of the system.

[0026] As a preferred solution of the current transformer secondary circuit opening detection system without power outages of the present invention, the self-healing effect evaluation includes analyzing the power supply recovery time, user satisfaction, and system response effect by comparing the operating data before and after self-healing, and evaluating the actual effect of the self-healing measures; based on the evaluation results, optimization suggestions are made, including adjusting protection settings, improving decision-making logic or improving monitoring methods, combined with actual operating conditions to achieve continuous improvement and dynamic adaptation of self-healing action analysis.

[0027] As a preferred solution of the current transformer secondary circuit open detection system without power outage of the present invention, the establishment and optimization of the knowledge base includes updating the knowledge base with information on fault types, pattern recognition methods, self-healing decision cases and evaluation results, providing a reference for self-healing actions based on the knowledge base update model, and providing strong support for future fault analysis and decision-making;

[0028] The knowledge base update model is as follows:

[0029] K(t)=K(t-1)+α·E(t)+β·R(t)-γ·O(t)

[0030] Among them, K(t) is the content of the knowledge base at time t; K(t-1) is the content of the knowledge base at time t-1; E(t) is the number of newly obtained valid fault cases; R(t) is the number of evaluated self-healing decision cases; O(t) is the number of outdated or invalid information; α, β, and γ are weight parameters, which respectively represent the influence of valid cases, decision cases, and outdated information on the content of the knowledge base.

[0031] As a preferred solution of the current transformer secondary circuit opening detection system without power outage of the present invention, the knowledge base update model includes data collection, parameter setting, knowledge base update calculation, information screening, knowledge base structure optimization, and continuous feedback mechanism.

[0032] Beneficial effects of the invention: By establishing a dynamic protection setting model, designing self-healing decision logic and constructing a comprehensive knowledge base update model, the distribution automation system can achieve real-time monitoring and intelligent response, improve fault identification accuracy and self-healing ability, which not only ensures the reliability of power supply, but also enhances the adaptability of the system in complex environments, and promotes the development of distribution networks towards a more intelligent and automated direction. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. Among them:

[0034] Figure 1 The figure is a flow chart of the self-healing action analysis method based on the protection setting of distribution automation terminal.

[0035] Figure 2 The figure is a flow chart of fault type and pattern recognition based on the self-healing action analysis method of distribution automation terminal protection setting.

[0036] Figure 3 The present invention is a flowchart of establishing a dynamic protection setting model based on the self-healing action analysis method of distribution automation terminal protection setting.

[0037] Figure 4 The figure is a flow chart of the knowledge base update model of the self-healing action analysis method based on the terminal protection setting of distribution automation. DETAILED DESCRIPTION

[0038] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0039] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0040] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0041] Example 1

[0042] Reference Figure 1 to Figure 4 , which is the first embodiment of the present invention, provides a self-healing action analysis method based on distribution automation terminal protection settings, which can improve fault identification accuracy and self-healing capability.

[0043] Specifically, define the goals and standards of self-healing actions;

[0044] By analyzing historical fault data, identifying fault modes and building fault identification models;

[0045] By combining historical data with real-time operation data, a dynamic protection setting model is established;

[0046] Construct a multi-level decision tree structure based on the identified fault modes and dynamic protection setting models;

[0047] Conduct feasibility tests on self-healing actions by simulating different fault scenarios and self-healing decision logic;

[0048] By tracking each link of the self-healing process, timely collecting and analyzing relevant data, and forming feedback information;

[0049] Evaluate the actual effect of self-healing measures by comparing the operating data before and after self-healing;

[0050] Build and optimize the knowledge base.

[0051] Furthermore, the goals of self-healing actions include quickly restoring power supply, reducing the impact of failures on users, and improving system reliability;

[0052] The criteria for self-healing actions include response time, fault detection accuracy, and automatic recovery rate.

[0053] It should be noted that the definition of the goals and standards for self-healing actions is that the goal requirements of self-healing actions must be specific and quantifiable, and the standard requirements of self-healing actions can be quantified and tested. By setting specific and quantifiable goals, each subsequent step can be adjusted and optimized around these standards, thereby effectively guiding the implementation of self-healing actions.

[0054] Furthermore, a fault identification model is constructed, including identifying the fault modes of short circuit, overload or equipment failure, to provide basic data support for self-healing analysis. The formula is as follows:

[0055] F(x)=w1·I 2 +w2·V·R+w3·(P max -P current )+w4·e -λt

[0056] Where F(x) is the fault identification score, and the higher the value, the greater the fault risk; I is the current flowing through the device; V is the device voltage; R is the resistance of the device; P max is the rated power of the equipment; P current is the current power of the device; w1, w2, w3, and w4 are weight parameters, which respectively represent the influence of current, voltage, power, and device status on fault identification; λ is the attenuation factor, which reflects the influence of device aging or environmental factors on fault risk; t is the device operation time;

[0057] The model is used to calculate the fault identification score of the current equipment. When it is higher than a certain threshold, the system determines it as a potential fault state. The threshold is set autonomously based on the actual situation.

[0058] It should be noted that the fault identification model analyzes historical fault data and identifies fault modes, such as short circuit, overload or equipment failure, to provide basic data support for self-healing analysis, build a fault identification model for real-time analysis and response to possible future fault types, and improve the accuracy and efficiency of fault mode identification. Figure 2 As shown, the fault identification model, when used, includes:

[0059] Data collection: Collect real-time data such as current, voltage, power and equipment operation time to provide a basis for model input;

[0060] Parameter setting: According to historical fault data and expert experience, set the initial values ​​of weight parameters w1, w2, w3, and w4. The weights can be adjusted through experimental methods to achieve the best recognition effect;

[0061] Fault score calculation: The fault identification score of the current device is calculated using the model F(x). When the score is higher than a certain threshold (which can be set according to actual conditions), the system determines it as a potential fault state.

[0062] Dynamic adjustment: Regularly analyze historical fault data and dynamically adjust weight parameters and attenuation factors based on new data to ensure that the model remains efficient as the equipment status and environment change;

[0063] Decision support: Based on the scoring results, self-healing actions are triggered, such as automatic reclosing and load transfer, to optimize the self-healing capability of the power system.

[0064] Furthermore, the dynamic protection setting model includes automatically adjusting the protection setting according to the actual operation status of the power grid, environmental changes and load characteristics. The formula is as follows:

[0065]

[0066] Among them, PD is the dynamic protection setting value; P base is the basic protection setting value, which is set based on the equipment standard; α, β, γ are weight coefficients, which respectively represent the influence of load, temperature and environmental factors on the protection setting value; L is the current load; L max is the maximum load of the equipment; T current is the current temperature; T max is the maximum safe temperature of the equipment; H env It is the environmental change factor, which is used to reflect the impact of the external environment on the equipment.

[0067] It should be noted that if Figure 3 As shown in the figure, the dynamic protection setting model includes the following processes when used:

[0068] Collect data on current load, temperature, and environmental changes in real time to provide input basis for the model;

[0069] Through historical data analysis and expert opinions, the initial values ​​of weight coefficients α, β, and γ are set to ensure that they reflect the importance of each factor;

[0070] The dynamic protection setting value is calculated by using the model PD. As the real-time data changes, the setting value will be automatically adjusted to ensure effectiveness under different conditions;

[0071] Monitor environmental changes and dynamically adjust H env If the value is set to a negative value during extreme weather, it means that the equipment needs to reduce the load protection setting value;

[0072] According to the calculated dynamic protection setting, real-time protection settings are performed and their effects are monitored. If a fault or abnormality is found, self-healing actions are taken in a timely manner.

[0073] Regularly evaluate the effectiveness of protection settings and adjust weight coefficients based on fault data feedback to optimize model performance and ensure efficient self-healing capabilities in complex environments.

[0074] Furthermore, the decision logic includes response strategies under different fault conditions, such as selecting appropriate automatic reclosing, adjusting loads or segmenting power supply, to ensure maximum power supply restoration in the shortest possible time.

[0075] Furthermore, the decision tree structure includes fault detection, dynamic protection setting value evaluation, decision response strategy selection, and effect evaluation and feedback. Specifically, fault detection includes identifying fault types including short circuit faults, overload faults, and equipment faults, wherein the location of the fault includes the trunk line, branch line, and equipment terminal; dynamic protection setting value evaluation includes checking the current protection setting value PD to determine whether it is within the safe range, and if so, continue monitoring, otherwise enter the self-healing logic; decision response strategy selection includes short circuit faults, overload faults, and equipment faults; effect evaluation and feedback includes checking whether the power supply restoration is successful, collecting user feedback, and optimizing the decision rules and response strategies according to the restoration effect and fault type;

[0076] Based on the decision tree structure, the self-healing decision logic includes real-time monitoring, dynamic adjustment, and comprehensive evaluation during operation. Specifically, real-time monitoring includes continuous monitoring of the power grid status, rapid detection of fault types and locations, and ensuring timely entry into the decision-making process; dynamic adjustment includes real-time updating of strategies and thresholds in the decision tree based on operating data and environmental changes; comprehensive evaluation includes evaluating the effectiveness and user satisfaction of each strategy after its implementation, so as to continuously optimize the decision logic in the future.

[0077] It should be noted that in the case of a short-circuit fault, when the automatic reclosing is performed, it is determined whether the number of reclosing times exceeds the threshold. If not, reclosing is performed, and if yes, switching to the backup power supply is performed. In the case of local isolation, the faulty section is isolated and the power supply to other parts is restored.

[0078] In the case of overload fault, the load that can be removed is evaluated during load adjustment, and non-critical users are selected for load reduction; during automatic cut-off, the overload line is cut off when the load exceeds the protection setting value;

[0079] In the event of an equipment failure, during fault identification and assessment, determine whether the faulty equipment is repairable. If it is repairable, mark it and arrange for repair. If it is not repairable, switch to backup equipment. When power supply is divided into sections, isolate the power supply of the section where the faulty equipment is located to maintain normal power supply in other sections.

[0080] Furthermore, the feedback information includes whether the self-healing action is successful or not, as well as the above-mentioned standard information such as the response time of the successful self-healing action, fault detection accuracy, and automatic recovery rate. Through continuous feedback analysis, the self-healing logic and decision tree structure can be continuously optimized to ensure the efficient self-healing capability of the system.

[0081] Furthermore, the self-healing effect evaluation includes analyzing the power supply restoration time, user satisfaction, and system response effect by comparing the operating data before and after self-healing, and evaluating the actual effect of self-healing measures; based on the evaluation results, making optimization suggestions, including adjusting protection settings, improving decision-making logic or improving monitoring methods, combined with actual operating conditions to achieve continuous improvement and dynamic adaptation of self-healing action analysis.

[0082] Furthermore, the establishment and optimization of the knowledge base includes updating the knowledge base with information on fault types, pattern recognition methods, self-healing decision cases, and evaluation results. Based on the knowledge base update model, it provides reference for self-healing actions and provides strong support for future fault analysis and decision-making;

[0083] The knowledge base update model is as follows:

[0084] K(t)=K(t-1)+α·E(t)+β·R(t)-γ·O(t)

[0085] Among them, K(t) is the content of the knowledge base at time t; K(t-1) is the content of the knowledge base at time t-1; E(t) is the number of newly obtained valid fault cases; R(t) is the number of evaluated self-healing decision cases; O(t) is the number of outdated or invalid information; α, β, and γ are weight parameters, which respectively represent the influence of valid cases, decision cases, and outdated information on the content of the knowledge base.

[0086] Further, such as Figure 4 As shown in FIG. 1 , the knowledge base update model includes data collection, parameter setting, knowledge base update calculation, information screening, knowledge base structure optimization, and continuous feedback mechanism. Specifically, data collection includes continuous collection of fault cases, decision results, and evaluation data to provide a basis for model input; parameter setting includes setting the initial values ​​of weight parameters α, β, and γ based on historical data and expert advice, and dynamically adjusting these parameters by analyzing their impact; knowledge base update calculation includes using model K(t) to calculate the content volume of the knowledge base at time t. If K(t) exceeds the set threshold, the optimization or reconstruction of the knowledge base is triggered; information screening includes regularly reviewing the information in the knowledge base based on the evaluation results, eliminating obsolete or invalid information O(t), and ensuring the timeliness and effectiveness of the knowledge base; knowledge base structure optimization includes optimizing the structure and classification method of the knowledge base based on the feedback of newly acquired information and obsolete information, making it easier to query and use; the continuous feedback mechanism includes collecting user feedback after each update, analyzing the usage and actual application effect of the knowledge base, and providing a basis for subsequent updates.

[0087] In summary, by establishing a dynamic protection setting model, designing self-healing decision logic and constructing a comprehensive knowledge base update model, the present invention enables the distribution automation system to achieve real-time monitoring and intelligent response, improves fault identification accuracy and self-healing capability, which not only ensures the reliability of power supply, but also enhances the adaptability of the system in complex environments, and promotes the development of distribution networks towards a more intelligent and automated direction.

[0088] Example 2

[0089] Reference Figure 1 to Figure 4 , which is the second embodiment of the present invention, provides a self-healing action analysis method based on distribution automation terminal protection settings, which can improve fault identification accuracy and self-healing capability.

[0090] Specifically, define the goals and standards of self-healing actions;

[0091] By analyzing historical fault data, identifying fault modes and building fault identification models;

[0092] By combining historical data with real-time operation data, a dynamic protection setting model is established;

[0093] Construct a multi-level decision tree structure based on the identified fault modes and dynamic protection setting models;

[0094] Conduct feasibility tests on self-healing actions by simulating different fault scenarios and self-healing decision logic;

[0095] By tracking each link of the self-healing process, timely collecting and analyzing relevant data, and forming feedback information;

[0096] Evaluate the actual effect of self-healing measures by comparing the operating data before and after self-healing;

[0097] Build and optimize the knowledge base.

[0098] Among them, the feasibility of self-healing actions is tested by simulating different fault scenarios and self-healing decision logic, including the influence of different load conditions, climate factors and equipment status variables.

[0099] Specifically, the feasibility test includes two tests, wherein the feasibility test 1 includes:

[0100] Test objectives: Verify the effectiveness of the self-healing decision logic under different fault scenarios and evaluate the responsiveness under various load conditions, climate factors, and equipment states.

[0101] Test scenarios: short circuit fault, overload fault, equipment failure.

[0102] Test variables: load conditions (low, medium, high), climate factors (normal, severe), equipment status (normal, aging, faulty).

[0103] The test results are shown in Table 1:

[0104]

[0105] Table 1

[0106] The self-healing system shows a high success rate in different fault scenarios, especially under low load and normal temperature conditions, the self-healing success rate of short circuit faults and equipment faults exceeds 90%. However, under high load and harsh environment, the fault response effect is significantly reduced, especially the success rate of equipment failure is only 65%, indicating that the system's ability to cope with extreme conditions still needs to be improved. Therefore, it is necessary to further optimize the decision logic and overload strategy to improve the response effect in complex environments.

[0107] Feasibility test 2 includes:

[0108] Test objective: Verify the performance of the self-healing decision logic under different fault types and environmental conditions, and confirm the accuracy and recovery speed of the self-healing decision.

[0109] Test scenarios: short circuit fault, overload fault, equipment failure.

[0110] Test variables: load conditions (low, medium, high), temperature conditions (normal temperature, high temperature), equipment health status (normal, partially damaged).

[0111] The test results are shown in Table 2:

[0112]

[0113] Table 2

[0114] The performance evaluation of the self-healing system under different temperatures and equipment health conditions shows that although short circuit and overload faults perform well under normal temperature conditions (the success rate is above 90%), the success rate is significantly reduced under high temperature and partial equipment damage, especially under high load, where the success rate of equipment failure is only 62%. This shows that temperature and equipment status have a greater impact on self-healing decisions, and it is recommended to strengthen equipment monitoring and environmental adaptability analysis to improve the overall reliability and recovery capability of the system.

[0115] In summary, by establishing a dynamic protection setting model, designing self-healing decision logic and constructing a comprehensive knowledge base update model, the present invention enables the distribution automation system to achieve real-time monitoring and intelligent response, greatly improving the accuracy of fault identification and self-healing ability, which not only ensures the reliability of power supply, but also enhances the adaptability of the system in complex environments, and promotes the development of distribution networks towards a more intelligent and automated direction.

[0116] Importantly, it should be noted that the construction and arrangement of the present application shown in a plurality of different exemplary embodiments are only exemplary. Although only a few embodiments are described in detail in this disclosure, it should be readily understood by those who refer to this disclosure that many modifications are possible without substantially departing from the novel teachings and advantages of the subject matter described in the application (e.g., mounting arrangements, use of materials, color, changes in orientation, etc.). For example, the element shown as integrally formed may be composed of a plurality of parts or elements, the position of the element may be inverted or otherwise changed, and the nature or number or position of the discrete element may be altered or changed. Therefore, all such modifications are intended to be included within the scope of the present invention. The order or sequence of any process or method steps may be changed or reordered according to an alternative embodiment. In the claims, any "bracket plus function" clause is intended to cover the structure of the execution function described herein, and is not only structurally equivalent but also equivalent structure. Without departing from the scope of the present invention, other replacements, modifications, changes and omissions may be made in the design, operating conditions and arrangement of the exemplary embodiments. Therefore, the present invention is not limited to a specific embodiment, but extends to a variety of modifications that still fall within the scope of the appended claims.

[0117] Additionally, in an effort to provide a concise description of example embodiments, all features of an actual implementation may not be described.

[0118] It should be understood that in the development of any actual implementation, as in any engineering or design project, numerous implementation-specific decisions may be made. Such a development effort may be complex and time-consuming, but for those of ordinary skill having the benefit of this disclosure, the development effort will be a routine task of design, fabrication, and production without undue experimentation.

[0119] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A self-healing action analysis method based on distribution automation terminal protection setting value, characterized by: include, Define goals and standards for self-healing actions; By analyzing historical fault data, identifying fault modes and building fault identification models; By combining historical data with real-time operation data, a dynamic protection setting model is established; Construct a multi-level decision tree structure based on the identified fault modes and dynamic protection setting models; Conduct feasibility tests on self-healing actions by simulating different fault scenarios and self-healing decision logic; By tracking each link of the self-healing process, timely collecting and analyzing relevant data, and forming feedback information; Evaluate the actual effect of self-healing measures by comparing the operating data before and after self-healing; Build and optimize the knowledge base.

2. The self-healing action analysis method based on the distribution automation terminal protection setting value according to claim 1 is characterized in that: The goals of the self-healing action include quickly restoring power supply, reducing the impact of the fault on users, and improving system reliability; The standards for the self-healing action include response time, fault detection accuracy, and automatic recovery rate.

3. The self-healing action analysis method based on the distribution automation terminal protection setting value according to claim 2 is characterized in that: The construction of the fault identification model includes identifying the fault mode of short circuit, overload or equipment failure, and providing basic data support for self-healing analysis. The formula is as follows: F(x)=w1·I 2 +w2·V·R+w3·(P max -P current )+w4·e -λt Where F(x) is the fault identification score, and the higher the value, the greater the fault risk; I is the current flowing through the device; V is the device voltage; R is the resistance of the device; P max is the rated power of the equipment; P current is the current power of the device; w1, w2, w3, and w4 are weight parameters, which respectively represent the influence of current, voltage, power, and device status on fault identification; λ is the attenuation factor, which reflects the influence of device aging or environmental factors on fault risk; t is the device operation time; The model is used to calculate the fault identification score of the current equipment. When it is higher than a certain threshold, the system determines it as a potential fault state. The threshold is set autonomously based on the actual situation.

4. The self-healing action analysis method based on distribution automation terminal protection setting value according to claim 3 is characterized in that: The dynamic protection setting model includes automatically adjusting the protection setting according to the actual operation status of the power grid, environmental changes and load characteristics. The formula is as follows: Among them, PD is the dynamic protection setting value; P base is the basic protection setting value, which is set based on the equipment standard; α, β, γ are weight coefficients, which respectively represent the influence of load, temperature and environmental factors on the protection setting value; L is the current load; L max is the maximum load of the equipment; T current is the current temperature; T max is the maximum safe temperature of the equipment; H env It is the environmental change factor, which is used to reflect the impact of the external environment on the equipment.

5. The self-healing action analysis method based on distribution automation terminal protection setting value according to claim 4 is characterized in that: The decision logic includes response strategies under different fault conditions, such as selecting appropriate automatic reclosing, adjusting loads or segmenting power supply, to ensure maximum restoration of power supply in the shortest time.

6. The self-healing action analysis method based on distribution automation terminal protection setting value according to claim 5 is characterized in that: The decision tree structure includes fault detection, dynamic protection setting value evaluation, decision response strategy selection, and effect evaluation and feedback; Based on the decision tree structure, the self-healing decision logic includes real-time monitoring, dynamic adjustment, and comprehensive evaluation during operation.

7. The self-healing action analysis method based on distribution automation terminal protection setting value according to claim 6 is characterized in that: The feedback information includes whether the self-healing action is successful or not, and also includes the above-mentioned standard information of the response time, fault detection accuracy, and automatic recovery rate of the successful self-healing action. Through continuous feedback analysis, the self-healing logic and decision tree structure can be continuously optimized to ensure the efficient self-healing capability of the system.

8. The self-healing action analysis method based on the distribution automation terminal protection setting value according to claim 7 is characterized in that: The self-healing effect evaluation includes analyzing the power supply restoration time, user satisfaction, and system response effect by comparing the operating data before and after self-healing, and evaluating the actual effect of the self-healing measures; based on the evaluation results, making optimization suggestions, including adjusting protection settings, improving decision-making logic or improving monitoring methods, combined with actual operating conditions to achieve continuous improvement and dynamic adaptation of self-healing action analysis.

9. The self-healing action analysis method based on distribution automation terminal protection setting value according to claim 8 is characterized in that: The establishment and optimization of the knowledge base includes updating the knowledge base with information on fault types, pattern recognition methods, self-healing decision cases and evaluation results, providing reference for self-healing actions based on the knowledge base update model, and providing strong support for future fault analysis and decision-making; The knowledge base update model is as follows: K(t)=K(t-1)+α·E(t)+β·R(t)-γ·O(t) Among them, K(t) is the content of the knowledge base at time t; K(t-1) is the content of the knowledge base at time t-1; E(t) is the number of newly obtained valid fault cases; R(t) is the number of evaluated self-healing decision cases; O(t) is the number of outdated or invalid information; α, β, and γ are weight parameters, which respectively represent the influence of valid cases, decision cases, and outdated information on the content of the knowledge base.

10. The self-healing action analysis method based on distribution automation terminal protection setting value according to claim 9, characterized in that: The knowledge base update model includes data collection, parameter setting, knowledge base update calculation, information screening, knowledge base structure optimization, and continuous feedback mechanism.

Images