An unattended substation intelligent monitoring system and method

By analyzing the real-time monitoring information and historical data of the substation area, dynamic inspection routes are generated, and the problem of timeliness and low efficiency of inspection route planning in the existing technology is solved, and effective supervision of the substation and auxiliary decision-making are realized. .

CN118572898BActive Publication Date: 2024-11-15NANJING QIZHENG INFORMATION TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411049115.X
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-08-01
Publication Date
2024-11-15
Estimated Expiration
2044-08-01

AI Technical Summary

Technical Problem

The existing intelligent supervision system of unattended substations has problems of timeliness and low efficiency in patrol route planning, and it is impossible to adjust the patrol route in real time to deal with the dynamic situation of the substation, resulting in poor patrol efficiency and timeliness.

Method used

By obtaining real-time monitoring information and historical data of the substation area, analyzing the risk relationship between regional characteristic information and abnormal states, generating reference decisions for inspection nodes, and optimizing inspection routes in combination with path relationships, realizing dynamic adjustment and auxiliary supervision decisions Early warning.

Benefits of technology

Quantitative risk analysis of the substation inspection area and optimization of inspection routes have been achieved, ensuring the effective supervision of unattended substations and the reliability of auxiliary decision-making.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118572898B_ABST
    Figure CN118572898B_ABST
Patent Text Reader

Abstract

The present invention relates to the field of substation supervision technology, specifically to an unmanned intelligent supervision system and method for substations, the system comprising an inspection interference analysis module, the inspection interference analysis module combines the regional characteristic information corresponding to each node area at the current time and the risk association relationship between the corresponding regional characteristic information and the abnormal state of the substation to be tested, and analyzes the inspection interference coefficient of the regional characteristic information corresponding to each node area at the current time on the corresponding node area. The present invention combines the extraction of regional characteristic information from monitoring information and the risk association relationship between regional characteristic information and the abnormal state of the substation to be tested in historical data, analyzes the inspection interference coefficient of the regional characteristic information corresponding to the current time on the corresponding node area, realizes the preliminary screening and locking of the inspection sequence, and realizes the dynamic analysis of the optimization demand decision of the inspection node in combination with the path conditions between the node areas, to ensure the reliability of the auxiliary supervision decision-making and early warning.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of substation supervision, and in particular to an unmanned intelligent supervision system and method for a substation. Background Art

[0002] As the safety and stability requirements of power production are increasing, the traditional model that relies on manual inspection and management has gradually shown its shortcomings, especially in the key link of substations. In traditional substation management, on-site safety risk control mainly relies on on-site inspection and supervision by work supervisors and managers. However, this method is limited by manpower and material resources, and it is impossible to grasp the on-site work situation in real time. It is difficult to correct and summarize problems such as irregular operations and habitual violations in a timely manner; the rise of inspection robots has improved the efficiency and accuracy of substation safety management to a certain extent.

[0003] However, the existing unmanned substation intelligent supervision system, on the one hand, plans the inspection route according to the abnormal monitoring results of the sensor, and on the other hand, directly executes the fixed inspection route preset in the database; both methods have major defects. Planning the inspection route according to the abnormal monitoring results of the sensor belongs to the verification of the corresponding abnormal equipment when the equipment status is clearly abnormal, and the inspection result is not timely; and directly executing the fixed inspection route will also make it impossible to dynamically adjust the inspection route in combination with the real-time situation of each inspection node, resulting in low inspection efficiency and poor timeliness; therefore, the existing technology has major defects. Summary of the invention

[0004] The purpose of the present invention is to provide an unmanned intelligent monitoring system and method for a substation to solve the problems raised in the above background technology.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions: an unmanned substation intelligent supervision method, the method comprising the following steps:

[0006] S1. The area to which the substation to be tested belongs is divided into different node areas, and the monitoring information in each node area is extracted in real time to obtain the regional characteristic information corresponding to different node areas at different times;

[0007] S2. Extract the regional characteristic information corresponding to the corresponding monitoring information of different node areas within the preset time before the abnormal state from the corresponding historical data of the inspection equipment bound to the substation to be tested, and analyze the risk association relationship between the obtained regional characteristic information and the abnormal state of the substation to be tested;

[0008] S3, combining the regional characteristic information corresponding to each node area at the current time and the risk association relationship between the corresponding regional characteristic information and the abnormal state of the substation to be tested, analyzing the inspection interference coefficient of the regional characteristic information corresponding to each node area at the current time on the corresponding node area;

[0009] S4. Generate an inspection node demand reference decision based on the inspection interference coefficient of the corresponding node area based on the regional characteristic information corresponding to each node area at the current time; and generate each inspection node optimization demand decision corresponding to the inspection node demand reference decision in combination with the path relationship between different node areas in the inspection node demand reference decision; and generate an auxiliary supervision decision warning based on the optimization bias interference value corresponding to each inspection node optimization demand decision.

[0010] Furthermore, the division of different node areas in the area to which the substation to be tested belongs in S1 is preset; the i-th node area of ​​the substation to be tested is recorded as Ai;

[0011] The regional characteristic information includes the number of people in the monitoring screen in the corresponding area, the identification results of each person, and the shortest distance between each person and the equipment belonging to the substation;

[0012] The results of character identification include relevant and non-relevant personnel in the corresponding node area of ​​the substation to be tested. The relevant personnel in each node area of ​​the substation to be tested are determined by the facial information and clothing information bound to the database.

[0013] The result of character identification in the present invention is obtained through face recognition technology. The face information in the monitoring screen is extracted in real time through face recognition technology, and the obtained face information is compared with the face information bound in the database to determine the character's identity. At the same time, the character's clothing information in the monitoring screen is also obtained, and the obtained character's clothing information is compared with the clothing information preset in the database to determine the character's identity (taking into account the differences in clothing between different departments in the enterprise, such as different work clothes in different departments).

[0014] Furthermore, the method for analyzing the risk association relationship between the regional characteristic information obtained in S2 and the abnormal state of the substation to be tested comprises the following steps:

[0015] S21, obtaining regional characteristic information corresponding to corresponding monitoring information of different node areas within a preset time before the abnormal state in the corresponding historical data of the inspection equipment bound to the substation to be tested;

[0016] S22, calculate the characteristic correlation value corresponding to the initial time point of the kth abnormal state of the i-th node area of ​​the substation to be tested, denoted as ,

[0017] when When ;

[0018] when When ,

[0019] in, Indicates the maximum time point at which relevant personnel are included in the regional feature information corresponding to the corresponding monitoring information of the i-th node area within the preset time before the k-th abnormal state in the corresponding historical data of the inspection equipment bound to the substation to be tested; It represents the minimum time point corresponding to the kth abnormal state of the ith node area of ​​the substation to be tested; Indicates the historical data corresponding to the inspection equipment bound to the substation to be tested. to The total number of non-related persons included in the regional feature information within the time interval; Indicates the historical data corresponding to the inspection equipment bound to the substation to be tested. to The minimum value of the shortest distance between each non-related person and the equipment of the substation contained in the regional characteristic information within the time interval; represents the shortest distance between the road in the i-th node area of ​​the substation to be tested and the equipment belonging to the substation; β1, β2 and β3 represent weight coefficients, and β1, β2 and β3 are all constants preset in the database;

[0020] S23. According to the preset table in the database, each characteristic correlation quantity corresponding to the i-th node area of ​​the substation to be tested is divided into different groups, and the risk correlation data pair corresponding to the g-th group corresponding to the i-th node area of ​​the substation to be tested is obtained, which is recorded as (Mig, PVig); each group in the preset table in the database corresponds to a characteristic correlation quantity interval, and the intersection between the characteristic correlation quantity intervals corresponding to different groups is empty; Mig represents the midpoint of the characteristic correlation quantity interval corresponding to the g-th group corresponding to the i-th node area of ​​the substation to be tested; PVig represents the quotient of the ratio of the number of elements in the g-th group corresponding to the i-th node area of ​​the substation to be tested to the total number of characteristic correlation quantities corresponding to the i-th node area of ​​the substation to be tested divided by the length of the corresponding characteristic correlation quantity interval;

[0021] S24. Based on MATLAB software, each risk-related data pair corresponding to the ith node area of ​​the substation to be tested is fitted according to the normal distribution function model, and the fitting function is used as the risk association relationship between the regional characteristic information corresponding to the ith node area of ​​the substation to be tested and the abnormal state of the substation to be tested.

[0022] The risk correlation relationship between the regional characteristic information corresponding to the i-th node area of ​​the substation to be tested and the abnormal state of the substation to be tested obtained in the present invention is essentially the probability distribution of equipment abnormalities when the characteristic correlation quantities in different node areas are present, thereby providing data support for analyzing the regional characteristic information corresponding to each node area at the current time on the inspection interference coefficient of the corresponding node area in the subsequent steps.

[0023] Furthermore, when analyzing the inspection interference coefficient of the regional characteristic information corresponding to each node area at the current time on the corresponding node area in S3, the inspection interference coefficient of the regional characteristic information corresponding to the i-th node area at the current time on the corresponding node area is recorded as PFi,

[0024] ,

[0025] in, represents the characteristic correlation quantity corresponding to the i-th node area of ​​the substation to be tested at the current time; Hi{} represents the function corresponding to the risk correlation relationship between the regional characteristic information corresponding to the i-th node area of ​​the substation to be tested and the abnormal state of the substation to be tested; It represents the function value corresponding to the feature correlation quantity FR in Hi{}.

[0026] Furthermore, when generating the inspection node demand reference decision, the inspection interference coefficients of the corresponding node areas are sorted from large to small according to the area characteristic information corresponding to each node area at the current time, and the obtained sorting result is used as the inspection node demand reference decision;

[0027] When generating each inspection node optimization demand decision corresponding to the inspection node demand reference decision in S4, the element positions in the inspection node demand reference decision are randomly arranged to generate different arrangement sequences, and each arrangement sequence is used as an inspection node optimization demand decision; the corresponding planning path between any two node areas in the inspection node demand reference decision in the database preset form is obtained; the inspection path corresponding to the inspection node optimization demand decision is the splicing result of the corresponding planning paths between any two adjacent elements in the corresponding inspection node optimization demand decision.

[0028] Furthermore, when obtaining the optimized bias interference value corresponding to the optimization demand decision of each inspection node, the optimized bias interference value corresponding to the optimization demand decision of the jth inspection node is recorded as DS j ,

[0029] ,

[0030] Among them, DL jrepresents the total length of the path corresponding to the optimization demand decision of the jth inspection node; DCL represents the total length of the path corresponding to the inspection node demand reference decision; represents the position of the bth element in the jth inspection node optimization demand decision in the inspection node demand reference decision; b1 represents the total number of elements in the inspection node demand reference decision; r1 and r2 are interference coefficients, and r1 and r2 are constants preset in the database;

[0031] The auxiliary supervision decision warning is to optimize the demand decision of the inspection node with the smallest optimization bias interference value and its corresponding inspection route.

[0032] An unmanned substation intelligent supervision system, the system comprising the following modules:

[0033] A region division and feature extraction module, wherein the region division and feature extraction module obtains the region to which the substation to be tested belongs and divides it into different node regions, extracts the monitoring information in each node region in real time, and obtains the regional feature information corresponding to different node regions at different times;

[0034] A risk association analysis module, wherein the risk association analysis module extracts regional feature information corresponding to corresponding monitoring information of different node areas within a preset time before an abnormal state from the corresponding historical data of the inspection equipment bound to the substation to be tested, and analyzes the risk association relationship between the obtained regional feature information and the abnormal state of the substation to be tested;

[0035] An inspection interference analysis module, which combines the regional characteristic information corresponding to each node area at the current time and the risk association relationship between the corresponding regional characteristic information and the abnormal state of the substation to be tested, and analyzes the inspection interference coefficient of the corresponding node area on the regional characteristic information corresponding to each node area at the current time;

[0036] A decision optimization and early warning management module, which generates an inspection node demand reference decision based on the inspection interference coefficient of the corresponding node area based on the regional characteristic information corresponding to each node area at the current time; and generates each inspection node optimization demand decision corresponding to the inspection node demand reference decision in combination with the path relationship between different node areas in the inspection node demand reference decision, and generates an auxiliary supervision decision warning based on the optimization bias interference value corresponding to each inspection node optimization demand decision.

[0037] Furthermore, the decision optimization and early warning management module includes a demand reference decision generation unit, an optimization demand decision generation unit and an auxiliary supervision decision analysis unit.

[0038] The demand reference decision generating unit generates an inspection node demand reference decision based on the inspection interference coefficient of the corresponding node area based on the area characteristic information corresponding to each node area at the current time;

[0039] The optimized demand decision generating unit generates optimized demand decisions for each inspection node corresponding to the inspection node demand reference decision in combination with the path relationship between different node areas in the inspection node demand reference decision;

[0040] The auxiliary supervision decision analysis unit generates an auxiliary supervision decision warning according to the optimized bias interference value corresponding to the optimization demand decision of each inspection node.

[0041] Compared with the prior art, the beneficial effect achieved by the present invention is as follows: in the process of intelligent supervision of substations, the present invention combines the extraction of regional characteristic information from monitoring information and the risk association between regional characteristic information in historical data and the abnormal state of the substation to be tested, analyzes the inspection interference coefficient of the regional characteristic information corresponding to the current time on the corresponding node area, and then realizes quantitative analysis of the abnormal risk conditions corresponding to each inspection area, realizes preliminary screening and locking of the inspection sequence, and combines the path conditions between the node areas to realize dynamic analysis of the optimization demand decision of the inspection node, ensures the reliability of the auxiliary supervision decision-making warning, and realizes effective supervision of unmanned substations. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0043] Figure 1 It is a structural schematic diagram of an unattended substation intelligent supervision system of the present invention;

[0044] Figure 2 The present invention is a flowchart of an unmanned intelligent monitoring method for a substation. DETAILED DESCRIPTION

[0045] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0046] See also Figure 1 The present invention provides a technical solution: In the first embodiment, an unmanned intelligent monitoring system for a substation includes the following modules:

[0047] A region division and feature extraction module, wherein the region division and feature extraction module obtains the region to which the substation to be tested belongs and divides it into different node regions, extracts the monitoring information in each node region in real time, and obtains the regional feature information corresponding to different node regions at different times;

[0048] A risk association analysis module, wherein the risk association analysis module extracts regional feature information corresponding to corresponding monitoring information of different node areas within a preset time before an abnormal state from the corresponding historical data of the inspection equipment bound to the substation to be tested, and analyzes the risk association relationship between the obtained regional feature information and the abnormal state of the substation to be tested;

[0049] An inspection interference analysis module, which combines the regional characteristic information corresponding to each node area at the current time and the risk association relationship between the corresponding regional characteristic information and the abnormal state of the substation to be tested, and analyzes the inspection interference coefficient of the corresponding node area on the regional characteristic information corresponding to each node area at the current time;

[0050] A decision optimization and early warning management module, which generates an inspection node demand reference decision based on the inspection interference coefficient of the corresponding node area based on the regional characteristic information corresponding to each node area at the current time; and generates each inspection node optimization demand decision corresponding to the inspection node demand reference decision in combination with the path relationship between different node areas in the inspection node demand reference decision, and generates an auxiliary supervision decision warning based on the optimization bias interference value corresponding to each inspection node optimization demand decision.

[0051] The decision optimization and early warning management module includes a demand reference decision generation unit, an optimization demand decision generation unit and an auxiliary supervision decision analysis unit.

[0052] The demand reference decision generating unit generates an inspection node demand reference decision based on the inspection interference coefficient of the corresponding node area based on the area characteristic information corresponding to each node area at the current time;

[0053] The optimized demand decision generating unit generates optimized demand decisions for each inspection node corresponding to the inspection node demand reference decision in combination with the path relationship between different node areas in the inspection node demand reference decision;

[0054] The auxiliary supervision decision analysis unit generates an auxiliary supervision decision warning according to the optimized bias interference value corresponding to the optimization demand decision of each inspection node.

[0055] like Figure 2 As shown, in the second embodiment, an unattended substation intelligent supervision method is provided, and the method comprises the following steps:

[0056] S1. The area to which the substation to be tested belongs is divided into different node areas, and the monitoring information in each node area is extracted in real time to obtain the regional characteristic information corresponding to different node areas at different times;

[0057] The division of different node areas in the area to which the substation to be tested belongs in S1 is preset; the i-th node area of ​​the substation to be tested is recorded as Ai;

[0058] The regional characteristic information includes the number of people in the monitoring screen in the corresponding area, the identification results of each person, and the shortest distance between each person and the equipment belonging to the substation;

[0059] The results of character identification include relevant and non-relevant personnel in the corresponding node area of ​​the substation to be tested. The relevant personnel in each node area of ​​the substation to be tested are determined by the facial information and clothing information bound to the database.

[0060] S2. Extract the regional characteristic information corresponding to the corresponding monitoring information of different node areas within the preset time before the abnormal state from the corresponding historical data of the inspection equipment bound to the substation to be tested, and analyze the risk association relationship between the obtained regional characteristic information and the abnormal state of the substation to be tested;

[0061] The method for analyzing the risk association relationship between the regional characteristic information obtained in S2 and the abnormal state of the substation to be tested comprises the following steps:

[0062] S21, obtaining regional characteristic information corresponding to corresponding monitoring information of different node areas within a preset time before the abnormal state in the corresponding historical data of the inspection equipment bound to the substation to be tested;

[0063] S22, calculate the characteristic correlation value corresponding to the initial time point of the kth abnormal state of the i-th node area of ​​the substation to be tested, denoted as ,

[0064] when When ;

[0065] when When ,

[0066] in, Indicates the maximum time point at which relevant personnel are included in the regional feature information corresponding to the corresponding monitoring information of the i-th node area within the preset time before the k-th abnormal state in the corresponding historical data of the inspection equipment bound to the substation to be tested; It represents the minimum time point corresponding to the kth abnormal state of the ith node area of ​​the substation to be tested; Indicates the historical data corresponding to the inspection equipment bound to the substation to be tested. to The total number of non-related persons included in the regional feature information within the time interval; Indicates the historical data corresponding to the inspection equipment bound to the substation to be tested. to The minimum value of the shortest distance between each non-related person and the equipment of the substation contained in the regional characteristic information within the time interval; represents the shortest distance between the road in the i-th node area of ​​the substation to be tested and the equipment belonging to the substation; β1, β2 and β3 represent weight coefficients, and β1, β2 and β3 are all constants preset in the database;

[0067] S23. According to the preset table in the database, each characteristic correlation quantity corresponding to the i-th node area of ​​the substation to be tested is divided into different groups, and the risk correlation data pair corresponding to the g-th group corresponding to the i-th node area of ​​the substation to be tested is obtained, which is recorded as (Mig, PVig); each group in the preset table in the database corresponds to a characteristic correlation quantity interval, and the intersection between the characteristic correlation quantity intervals corresponding to different groups is empty; Mig represents the midpoint of the characteristic correlation quantity interval corresponding to the g-th group corresponding to the i-th node area of ​​the substation to be tested; PVig represents the quotient of the ratio of the number of elements in the g-th group corresponding to the i-th node area of ​​the substation to be tested to the total number of characteristic correlation quantities corresponding to the i-th node area of ​​the substation to be tested divided by the length of the corresponding characteristic correlation quantity interval;

[0068] S24. Based on MATLAB software, each risk-related data pair corresponding to the ith node area of ​​the substation to be tested is fitted according to the normal distribution function model, and the fitting function is used as the risk association relationship between the regional characteristic information corresponding to the ith node area of ​​the substation to be tested and the abnormal state of the substation to be tested.

[0069] S3, combining the regional characteristic information corresponding to each node area at the current time and the risk association relationship between the corresponding regional characteristic information and the abnormal state of the substation to be tested, analyzing the inspection interference coefficient of the regional characteristic information corresponding to each node area at the current time on the corresponding node area;

[0070] When analyzing the inspection interference coefficient of the regional characteristic information corresponding to each node area at the current time on the corresponding node area in S3, the inspection interference coefficient of the regional characteristic information corresponding to the i-th node area at the current time on the corresponding node area is recorded as PFi.

[0071] ,

[0072] in, represents the characteristic correlation quantity corresponding to the i-th node area of ​​the substation to be tested at the current time; Hi{} represents the function corresponding to the risk correlation relationship between the regional characteristic information corresponding to the i-th node area of ​​the substation to be tested and the abnormal state of the substation to be tested; It represents the function value corresponding to the feature correlation quantity FR in Hi{}.

[0073] S4. Generate an inspection node demand reference decision based on the inspection interference coefficient of the corresponding node area based on the regional characteristic information corresponding to each node area at the current time; and generate each inspection node optimization demand decision corresponding to the inspection node demand reference decision in combination with the path relationship between different node areas in the inspection node demand reference decision; and generate an auxiliary supervision decision warning based on the optimization bias interference value corresponding to each inspection node optimization demand decision.

[0074] When generating the inspection node demand reference decision, sort the inspection interference coefficients of the corresponding node areas from large to small according to the regional feature information corresponding to each node area at the current time, and use the sorting result as the inspection node demand reference decision;

[0075] When generating each inspection node optimization demand decision corresponding to the inspection node demand reference decision in S4, the element positions in the inspection node demand reference decision are randomly arranged to generate different arrangement sequences, and each arrangement sequence is used as an inspection node optimization demand decision; the corresponding planning path between any two node areas in the inspection node demand reference decision in the database preset form is obtained; the inspection path corresponding to the inspection node optimization demand decision is the splicing result of the corresponding planning paths between any two adjacent elements in the corresponding inspection node optimization demand decision.

[0076] In this embodiment, when generating each inspection node optimization demand decision corresponding to the inspection node demand reference decision, if the number of elements in the inspection node demand reference decision is n, the position of the elements in the inspection node demand reference decision is randomly arranged to generate n factorials of n different arrangement sequences!, that is, n·(n-1)·(n-2)·...·2·1;

[0077] When obtaining the optimized bias interference value corresponding to the optimization demand decision of each inspection node, the optimized bias interference value corresponding to the optimization demand decision of the jth inspection node is recorded as DS j ,

[0078] ,

[0079] Among them, DL j represents the total length of the path corresponding to the optimization demand decision of the jth inspection node; DCL represents the total length of the path corresponding to the inspection node demand reference decision; represents the position of the bth element in the jth inspection node optimization demand decision in the inspection node demand reference decision; b1 represents the total number of elements in the inspection node demand reference decision; r1 and r2 are interference coefficients, and r1 and r2 are constants preset in the database;

[0080] The auxiliary supervision decision warning is to optimize the demand decision of the inspection node with the smallest optimization bias interference value and its corresponding inspection route.

[0081] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0082] Finally, it should be noted that the above is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. An unmanned substation intelligent supervision method, characterized in that: The method comprises the following steps: S1. The area to which the substation to be tested belongs is divided into different node areas, and the monitoring information in each node area is extracted in real time to obtain the regional characteristic information corresponding to different node areas at different times; S2. Extract the regional feature information corresponding to the corresponding monitoring information of different node areas within the preset time before the abnormal state from the corresponding historical data of the inspection equipment bound to the substation to be tested, and analyze the risk association relationship between the obtained regional feature information and the abnormal state of the substation to be tested; S3, combining the regional characteristic information corresponding to each node area at the current time and the risk association relationship between the corresponding regional characteristic information and the abnormal state of the substation to be tested, analyzing the inspection interference coefficient of the regional characteristic information corresponding to each node area at the current time on the corresponding node area; S4. Generate a patrol node demand reference decision based on the patrol interference coefficient of the corresponding node area based on the regional characteristic information corresponding to each node area at the current time; and generate each patrol node optimization demand decision corresponding to the patrol node demand reference decision in combination with the path relationship between different node areas in the patrol node demand reference decision, and generate an auxiliary supervision decision warning based on the optimization bias interference value corresponding to each patrol node optimization demand decision; The method for analyzing the risk association relationship between the regional characteristic information obtained in S2 and the abnormal state of the substation to be tested comprises the following steps: S21, obtaining regional characteristic information corresponding to corresponding monitoring information of different node areas within a preset time before the abnormal state in the corresponding historical data of the inspection equipment bound to the substation to be tested; S22, calculate the characteristic correlation value corresponding to the initial time point of the kth abnormal state of the i-th node area of ​​the substation to be tested, denoted as , when When ; when When , in, Indicates the maximum time point at which relevant personnel are included in the regional feature information corresponding to the corresponding monitoring information of the i-th node area within the preset time before the k-th abnormal state in the corresponding historical data of the inspection equipment bound to the substation to be tested; It represents the minimum time point corresponding to the kth abnormal state of the ith node area of ​​the substation to be tested; Indicates the historical data corresponding to the inspection equipment bound to the substation to be tested. to The total number of non-related persons included in the regional feature information within the time interval; Indicates the historical data corresponding to the inspection equipment bound to the substation to be tested. to The minimum value of the shortest distance between each non-related person and the equipment of the substation contained in the regional characteristic information within the time interval; represents the shortest distance between the road in the i-th node area of ​​the substation to be tested and the equipment belonging to the substation; β1, β2 and β3 represent weight coefficients, and β1, β2 and β3 are all constants preset in the database; S23. According to the preset table in the database, each characteristic correlation quantity corresponding to the i-th node area of ​​the substation to be tested is divided into different groups, and the risk correlation data pair corresponding to the g-th group corresponding to the i-th node area of ​​the substation to be tested is obtained, which is recorded as (Mig, PVig); each group in the preset table in the database corresponds to a characteristic correlation quantity interval, and the intersection between the characteristic correlation quantity intervals corresponding to different groups is empty; Mig represents the midpoint of the characteristic correlation quantity interval corresponding to the g-th group corresponding to the i-th node area of ​​the substation to be tested; PVig represents the quotient of the ratio of the number of elements in the g-th group corresponding to the i-th node area of ​​the substation to be tested to the total number of characteristic correlation quantities corresponding to the i-th node area of ​​the substation to be tested divided by the length of the corresponding characteristic correlation quantity interval; S24. Based on MATLAB software, each risk-related data pair corresponding to the ith node area of ​​the substation to be tested is fitted according to the normal distribution function model, and the fitting function is used as the risk association relationship between the regional characteristic information corresponding to the ith node area of ​​the substation to be tested and the abnormal state of the substation to be tested.

2. The unmanned substation intelligent supervision method according to claim 1 is characterized in that: The division of different node areas in the area to which the substation to be tested belongs in S1 is preset; the i-th node area of ​​the substation to be tested is recorded as Ai; The regional characteristic information includes the number of people in the monitoring screen in the corresponding area, the identification results of each person, and the shortest distance between each person and the equipment belonging to the substation; The results of character identification include relevant and non-relevant personnel in the corresponding node area of ​​the substation to be tested. The relevant personnel in each node area of ​​the substation to be tested are determined by the facial information and clothing information bound to the database.

3. The unmanned intelligent monitoring method for substations according to claim 1 is characterized in that: When analyzing the inspection interference coefficient of the regional characteristic information corresponding to each node area at the current time on the corresponding node area in S3, the inspection interference coefficient of the regional characteristic information corresponding to the i-th node area at the current time on the corresponding node area is recorded as PFi. , in, represents the characteristic correlation quantity corresponding to the i-th node area of ​​the substation to be tested at the current time; Hi{} represents the function corresponding to the risk correlation relationship between the regional characteristic information corresponding to the i-th node area of ​​the substation to be tested and the abnormal state of the substation to be tested; It represents the function value corresponding to the feature correlation quantity FR in Hi{}.

4. The unmanned intelligent monitoring method for substations according to claim 3 is characterized in that: When generating the inspection node demand reference decision, sort the inspection interference coefficients of the corresponding node areas from large to small according to the regional feature information corresponding to each node area at the current time, and use the sorting result as the inspection node demand reference decision; When generating each inspection node optimization demand decision corresponding to the inspection node demand reference decision in S4, the element positions in the inspection node demand reference decision are randomly arranged to generate different arrangement sequences, and each arrangement sequence is used as an inspection node optimization demand decision; Obtain the corresponding planned path in the database preset form between any two node areas in the inspection node demand reference decision; the inspection path corresponding to the inspection node optimization demand decision is the splicing result of the corresponding planned paths between any two adjacent elements in the corresponding inspection node optimization demand decision.

5. The unmanned intelligent monitoring method for substations according to claim 4 is characterized in that: When obtaining the optimized bias interference value corresponding to the optimization demand decision of each inspection node, the optimized bias interference value corresponding to the optimization demand decision of the jth inspection node is recorded as DS j , , Among them, DL j represents the total length of the path corresponding to the optimization demand decision of the jth inspection node; DCL represents the total length of the path corresponding to the inspection node demand reference decision; represents the position of the bth element in the jth inspection node optimization demand decision in the inspection node demand reference decision; b1 represents the total number of elements in the inspection node demand reference decision; r1 and r2 are interference coefficients, and r1 and r2 are constants preset in the database; The auxiliary supervision decision warning is to optimize the demand decision of the inspection node with the smallest optimization bias interference value and its corresponding inspection route.

6. An unattended intelligent monitoring system for a substation, applying an unattended intelligent monitoring method for a substation as claimed in any one of claims 1 to 5, characterized in that: The system includes the following modules: A region division and feature extraction module, wherein the region division and feature extraction module obtains the region to which the substation to be tested belongs and divides it into different node regions, extracts the monitoring information in each node region in real time, and obtains the regional feature information corresponding to different node regions at different times; A risk association analysis module, wherein the risk association analysis module extracts regional feature information corresponding to corresponding monitoring information of different node areas within a preset time before an abnormal state from the corresponding historical data of the inspection equipment bound to the substation to be tested, and analyzes the risk association relationship between the obtained regional feature information and the abnormal state of the substation to be tested; An inspection interference analysis module, which combines the regional characteristic information corresponding to each node area at the current time and the risk association relationship between the corresponding regional characteristic information and the abnormal state of the substation to be tested, and analyzes the inspection interference coefficient of the corresponding node area on the regional characteristic information corresponding to each node area at the current time; A decision optimization and early warning management module, wherein the decision optimization and early warning management module generates an inspection node demand reference decision based on the inspection interference coefficient of the corresponding node area based on the regional characteristic information corresponding to each node area at the current time; and generates each inspection node optimization demand decision corresponding to the inspection node demand reference decision in combination with the path relationship between different node areas in the inspection node demand reference decision; and generates an auxiliary supervision decision early warning based on the optimization bias interference value corresponding to each inspection node optimization demand decision.

7. The unmanned intelligent monitoring system for substations according to claim 6 is characterized in that: The decision optimization and early warning management module includes a demand reference decision generation unit, an optimization demand decision generation unit and an auxiliary supervision decision analysis unit. The demand reference decision generating unit generates an inspection node demand reference decision based on the inspection interference coefficient of the corresponding node area based on the area characteristic information corresponding to each node area at the current time; The optimized demand decision generating unit generates optimized demand decisions for each inspection node corresponding to the inspection node demand reference decision in combination with the path relationship between different node areas in the inspection node demand reference decision; The auxiliary supervision decision analysis unit generates an auxiliary supervision decision warning according to the optimized bias interference value corresponding to the optimization demand decision of each inspection node.