An intelligent auxiliary monitoring system and method for substations

Abstract

This invention discloses an intelligent auxiliary monitoring system and method for substations, specifically relating to the field of intelligent auxiliary monitoring technology. The system includes the following steps: collecting characteristic information on the degree of danger in different areas within the substation; selecting a membership function matching the characteristic information based on its type and obtaining its membership degree; determining the degree of danger in different areas of the substation using fuzzy logic; defuzzifying using a weighted average decision method; comprehensively analyzing the degree of danger in an area in conjunction with the behavioral information of personnel in that area to generate a monitoring alert evaluation coefficient; marking areas with monitoring alert evaluation coefficients greater than a threshold as alert areas and generating alert signals. This invention uses fuzzy logic to determine the degree of danger in different areas of the substation and combines this with the behavioral information of personnel in those areas, which helps in developing safety measures for different areas and ensuring the safe operation of the substation and the safety of personnel.

Description

Technical Field

[0001] This invention relates to the field of intelligent auxiliary monitoring technology, and more specifically, to an intelligent auxiliary monitoring system and method for substations. Background Technology

[0002] Currently, intelligent auxiliary monitoring of substations often involves collecting various data within the substation using various sensors and monitoring equipment, including electrical parameters, temperature, humidity, and equipment status. However, the collected data may be affected by external environmental factors, thus impacting the accuracy and reliability of the monitoring equipment. Furthermore, even if the electrical parameters, temperature, humidity, and other monitoring data within the substation are within normal limits, the substation still carries certain risks. The operation of a substation involves complex electrical equipment and systems, presenting numerous potential risk factors such as equipment aging, load fluctuations, and power outages. Current intelligent auxiliary monitoring systems for substations do not readily assess the degree of danger in different areas within the substation and do not incorporate information on the behavior of personnel within those areas to take effective measures to ensure the safe operation of the substation and the safety of personnel within the substation.

[0003] To address the aforementioned shortcomings, a technical solution is provided. Summary of the Invention

[0004] In order to overcome the above-mentioned defects of the prior art, embodiments of the present invention provide an intelligent auxiliary monitoring system and method for substations to solve the problems mentioned in the background art.

[0005] To achieve the above objectives, the present invention provides the following technical solution:

[0006] A smart auxiliary monitoring method for substations specifically includes the following steps:

[0007] S1: Collect characteristic information on the degree of danger in different areas within the substation, including information on equipment aging, equipment density, and electrical load.

[0008] S2: Based on the type of feature information, select the membership function that matches the feature information and obtain the membership degree of the feature information. Use fuzzy logic method to determine the degree of danger in different areas of the substation.

[0009] S3: Use the weighted average decision method to defuzzify and generate the danger level coefficients for different areas of the substation. Analyze the danger level of the area in conjunction with the behavioral information of the people in the area to generate monitoring prompt assessment coefficients. The behavioral information of the people in the area includes the lingering abnormality coefficient and the number of people concealed safety coefficient.

[0010] S4: Compare the monitoring prompt evaluation coefficients of different areas within the substation with the monitoring prompt evaluation coefficient thresholds, mark the areas with monitoring prompt evaluation coefficients greater than the monitoring prompt evaluation coefficient thresholds as prompt areas, and generate prompt signals.

[0011] In a preferred embodiment, characteristic information for assessing the hazard level of different areas within the substation is collected, including:

[0012] The feature information includes equipment aging information, equipment density information, and electrical load information;

[0013] The equipment aging information includes an aging coefficient. The logic for obtaining the aging coefficient is as follows: obtain the maximum service life of the equipment in a certain area of ​​the substation, and determine the service life of the equipment based on the historical records of the equipment. Normalize the service life of different equipment to determine the aging degree of different equipment. When the aging degree of each equipment in the area is between 0 and 1, calculate the average value based on the aging degree of each equipment and use the average value to represent the aging coefficient of the area. When there are one or more equipment in the area with an aging degree less than 0, obtain the minimum value of the equipment aging degree and use the minimum value to represent the aging coefficient of the area.

[0014] Equipment density information includes equipment density coefficient. The logic for obtaining the equipment density coefficient is as follows: obtain the area size of the substation area, obtain the number of operating substation equipment in the area, and calculate the equipment density coefficient of the area using a formula.

[0015] Electrical load information includes load fluctuation coefficient. The logic for obtaining the load fluctuation coefficient is as follows: obtain the electrical load of a certain area within the substation in a unit time period, calculate the average value and standard deviation of the electrical load in the area in the unit time period, and obtain the load fluctuation coefficient of the area through a formula.

[0016] In a preferred embodiment, the membership function matching the feature information is selected according to the type of feature information, and the membership degree of the feature information is obtained, including:

[0017] Set membership functions for the aging degree coefficient, equipment density coefficient, and load fluctuation coefficient, and calculate the membership degrees of the aging degree coefficient, equipment density coefficient, and load fluctuation coefficient respectively.

[0018] In a preferred embodiment, a fuzzy logic method is used to determine the degree of danger in different areas of the substation, including:

[0019] Based on the membership degree of different regional feature information within the substation, it is divided into different fuzzy sets. According to the number of types of regional feature information, a corresponding number of fuzzy sets are obtained, and a set of fuzzy rules are formulated to describe the impact of different feature information on the regional hazard level.

[0020] In a preferred embodiment, obtaining information on the degree of danger in the area and the behavior of people in the area includes:

[0021] The degree of danger in a region is represented by a degree of danger coefficient. The weighted average decision method can be used to obtain the specific numerical values ​​of the degree of danger in different regions of the substation. The defuzzified output value is recorded as the degree of danger coefficient.

[0022] The behavioral information of people in the area includes the abnormal lodging coefficient and the safety coefficient for concealing the number of people.

[0023] The logic for obtaining the loitering anomaly coefficient is as follows: Cameras typically use computer vision technology to identify the same person and record the duration of their presence within the camera's view. When a person's image appears within the camera's view, the camera identifies and begins recording the duration of their stay within the view. A loitering duration threshold is set. If the duration of a person's stay within the camera's view equals the loitering duration threshold, the counter is incremented by 1, and the timer for the person's stay is reset. If the camera records the same person, the counter is incremented by 1. The count values ​​of the counters for all cameras within the area are obtained, and the loitering anomaly coefficient is calculated using a formula.

[0024] In a preferred embodiment, the analysis of the degree of danger in the area and the behavioral information of people in the area includes:

[0025] By comprehensively analyzing the degree of danger in a region and the behavioral information of people in the region, a data analysis model is established through the degree of danger coefficient, the abnormal stay coefficient, and the safety coefficient of the number of people concealed, and a monitoring prompt evaluation coefficient is generated.

[0026] In a preferred embodiment, areas where the monitoring prompt evaluation coefficient is greater than the monitoring prompt evaluation coefficient threshold are marked as prompt areas, and prompt signals are generated, including:

[0027] The system obtains the monitoring prompt evaluation coefficients for different areas in the substation, sets the monitoring prompt evaluation coefficient threshold, compares the monitoring prompt evaluation coefficients of different areas with the monitoring prompt evaluation coefficient threshold, identifies areas where the monitoring prompt evaluation coefficient is greater than the monitoring prompt evaluation coefficient threshold, marks these areas as prompt areas, and generates prompt signals.

[0028] In a preferred embodiment, the module includes a data acquisition module, a blurring module, an analysis module, and a prompting signal module, with signal connections between the modules:

[0029] The data acquisition module is used to collect characteristic information of different areas and personnel behavior information within the substation, and transmit the characteristic information of different areas to the fuzzy logic module and the personnel behavior information to the analysis module.

[0030] The fuzzing module is used to fuzzify the feature information within a region to determine the degree of danger in different areas of the substation.

[0031] The analysis module is used to comprehensively analyze the degree of danger in a region and the behavioral information of people in the region to determine the monitoring prompt evaluation coefficient for different regions within the substation.

[0032] The alert signal module is used to generate alert signals based on the comparison between the monitoring alert evaluation coefficient and the monitoring alert evaluation coefficient threshold of different areas within the substation.

[0033] The technical effects and advantages of this invention are as follows:

[0034] 1. This invention uses fuzzy logic to determine the degree of danger in different areas within a substation. By classifying the degree of danger in different areas within a substation, it helps to formulate safety measures for different areas in real time. When someone approaches an area with a higher degree of danger, a timely warning can be issued.

[0035] 2. This invention combines the degree of danger in different areas of a substation with the behavioral information of people in different areas to comprehensively analyze the potential dangers to people in the area. By generating warning signals to staff, it assists in reminding staff to evacuate irrelevant personnel from the area. Attached Figure Description

[0036] To facilitate understanding by those skilled in the art, the present invention will be further described below with reference to the accompanying drawings;

[0037] Figure 1 This is a flowchart illustrating the steps of an intelligent auxiliary monitoring method for substations according to the present invention.

[0038] Figure 2 This is a schematic diagram of the structure of an intelligent auxiliary monitoring system for substations according to the present invention. Detailed Implementation

[0039] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0040] Example 1

[0041] This invention provides, for example Figure 1 The flowchart shown illustrates a method for intelligent auxiliary monitoring of substations, specifically including the following steps:

[0042] S1: Collect characteristic information on the degree of danger in different areas within the substation, including information on equipment aging, equipment density, and electrical load.

[0043] S2: Based on the type of feature information, select the membership function that matches the feature information and obtain the membership degree of the feature information. Use fuzzy logic method to determine the degree of danger in different areas of the substation.

[0044] S3: Use the weighted average decision method to defuzzify and generate the danger level coefficients for different areas of the substation. Analyze the danger level of the area in conjunction with the behavioral information of the people in the area to generate monitoring prompt assessment coefficients. The behavioral information of the people in the area includes the lingering abnormality coefficient and the number of people concealed safety coefficient.

[0045] S4: Compare the monitoring prompt evaluation coefficients of different areas within the substation with the monitoring prompt evaluation coefficient thresholds, mark the areas with monitoring prompt evaluation coefficients greater than the monitoring prompt evaluation coefficient thresholds as prompt areas, and generate prompt signals.

[0046] In step 1, the substation will be divided into multiple areas, which may have different functions and equipment. The division of substation areas helps to manage and monitor the operation of the substation and to maintain or handle faults in specific areas when necessary. For example, the substation may be divided into high-voltage area, low-voltage area, control area, distribution area, etc. Therefore, the degree of danger in different areas of the substation may be different, and different safety standards need to be formulated according to the degree of danger in different areas.

[0047] Determine characteristic information for assessing the degree of danger in different areas within the substation, including information on equipment aging, equipment density, and electrical load.

[0048] It should be noted that there is a lot of characteristic information for assessing the degree of danger of a substation. In this embodiment, the degree of equipment aging, equipment density, and electrical load are used as characteristic information for the degree of danger in different areas.

[0049] The equipment aging information includes an aging degree coefficient, which obtains the maximum service life of the substation equipment in a certain area, and determines the service life of the equipment based on historical records. The service life of different equipment is then normalized to determine the aging degree of each piece of equipment. The calculation formula is as follows: Among them, L nThis represents the aging degree of the nth electrical equipment within a certain area of ​​a substation, where n = 1, 2, 3...N, where N is a positive integer and n is the equipment number within that area of ​​the substation. This represents the maximum service life of the nth electrical equipment within a certain area of ​​the substation. The service life of the nth electrical equipment within a certain area of ​​the substation;

[0050] It should be noted that the maximum service life of power equipment is usually obtained from the manufacturer's instructions, while the actual service life of power equipment is usually determined by professionals each time they inspect the power equipment, taking into account the current usage status and the length of time it has been used.

[0051] Based on the calculation results of the aging degree of each transformer device in a certain area of ​​the substation, the aging degree coefficient of the area is determined. When L n If the aging level of each transformer in the area is greater than or equal to 0, then the average aging level of each transformer is calculated, and this average value represents the aging level coefficient of the area. The formula for calculating the aging level coefficient is as follows: Where i = 1, 2, 3...I, I is a positive integer, and i is the number of different areas within the substation, LH i This refers to the aging degree coefficient for different areas within a substation. When one or more pieces of equipment within an area have an aging degree less than 0, the minimum aging degree of the equipment is obtained, and this minimum value represents the aging degree coefficient for that area, i.e., LH. i =L min , where L min This represents the minimum value for different degrees of aging of electrical equipment.

[0052] Equipment density information includes equipment density coefficients, obtains the area size within the substation, and marks the area size as: S i Obtain the number of operating substation equipment within the area and mark the number of operating substation equipment within the area as: SL i The equipment density coefficient for different areas within a substation is calculated using the following formula: Among them, MD i This refers to the equipment density coefficient in different areas within the substation.

[0053] Electrical load information includes load fluctuation coefficients, obtaining the electrical load of a specific area within the substation over a unit of time, and labeling the electrical load of that specific area within the substation over a unit of time as: FH kWhere k = 1, 2, 3...K, K is a positive integer, and k is the number of times the electrical load is monitored within a unit time period; it should be noted that electrical load fluctuation usually refers to the large fluctuation of the real-time load in a short period of time. Such fluctuation may be caused by various reasons, such as sudden load changes, equipment failures, weather changes, etc. Large electrical load fluctuations may increase the instability of the system and affect the operational safety of the equipment, so timely monitoring and handling are required.

[0054] Calculate the average and standard deviation of the regional electrical load within a unit time period, and label the average and standard deviation of the regional electrical load within a unit time period as: DQ avg And DQ bz ,in, The formula for calculating the load fluctuation coefficient per unit time is as follows:

[0055] As can be seen from the formula, the larger the load fluctuation coefficient, the greater the load variation in the substation area, which increases the instability of the system. High-frequency electrical load fluctuations may increase the operating pressure of the substation equipment, leading to accelerated equipment aging and an increased possibility of failure. Conversely, the smaller the load fluctuation coefficient, the safer the equipment in the substation area.

[0056] In step 2, based on the distribution characteristics of the feature information, a suitable membership function is selected, such as triangular membership function, trapezoidal membership function, Gaussian membership function, etc. Through fuzzy logic method, the fuzzy set of feature information is determined according to the membership degree of the input feature information, and the degree of danger of different areas in the substation is evaluated based on fuzzy rules.

[0057] The membership function for the aging degree coefficient is set, and the membership degree of the aging degree coefficient is calculated using the following formula: Where LS1 is the membership degree of the aging degree coefficient, σ is used to adjust the degree of the aging degree coefficient membership function curve, σ is a positive number, and a represents the inflection point of the aging degree coefficient membership function curve;

[0058] It should be noted that LH i ≤a indicates that the aging degree of the region is relatively high. The membership degree of the aging degree coefficient less than a is set to 0. The larger the aging degree coefficient, the larger the membership degree of the aging degree coefficient, and the lower the aging degree of the region.

[0059] Set the membership function for the equipment density coefficient, and calculate the membership degree of the equipment density coefficient. The calculation formula is as follows: Where LS2 is the membership degree of the equipment density coefficient, α is used to adjust the degree of the membership function curve of the equipment density coefficient, β is usually taken as 2, which can ignore the positive and negative signs to obtain the difference, b represents the inflection point of the membership function curve of the equipment density coefficient, and α and β are greater than 0.

[0060] It should be noted that MD i ≤b indicates that the area has a high equipment density. The membership degree of equipment density coefficients less than b is set to 0. The larger the equipment density coefficient, the larger the membership degree of the equipment density coefficient, and the larger the area's equipment density.

[0061] Set the membership function for the load fluctuation coefficient and calculate the membership degree of the load fluctuation coefficient. The calculation formula is as follows: Where LS3 is the membership degree of the load fluctuation coefficient, γ is used to adjust the degree of the membership function curve of the load fluctuation coefficient, δ is usually taken as 2, which can ignore the positive and negative signs to obtain the difference, c represents the inflection point of the membership function curve of the load fluctuation coefficient, and α and β are greater than 0.

[0062] It should be noted that BD i ≤c indicates that the regional load fluctuation is small. The membership degree of load fluctuation coefficient less than c is set to 1. The larger the load fluctuation coefficient, the smaller the membership degree of the load fluctuation coefficient, and the larger the regional load fluctuation.

[0063] Based on the membership degree of different regional feature information within the substation, it is divided into different fuzzy sets. Based on the number of types of regional feature information, a corresponding number of fuzzy sets are obtained, and a set of fuzzy rules are formulated to describe the impact of different feature information on the degree of regional hazard.

[0064] For example, if the membership degree of the aging degree coefficient of a certain region is 0.1, and the membership degree range of the fuzzy set "Low" of the aging degree coefficient is 0 to 0.2, then the aging degree of that region is represented as "Low".

[0065] The fuzzy rule can be defined as: Rule 1: If (LS1 is Low) And (LS2 is High) And (LS3 is Big) Then (WX is High); where WX represents the danger level of the region, and Low, High, and Big are the fuzzy sets for the division.

[0066] It should be noted that the division of fuzzy sets should be adjusted according to the actual situation. Subdividing fuzzy sets with different feature information makes it easier to describe the specific situation of different areas within the substation. For example, the aging degree of regional equipment can be subdivided into extremely low, low, low-medium, medium, medium-high, high, and extremely high based on the aging degree coefficient. More specific feature information should be selected according to the actual situation of different areas of the substation, which will not be elaborated here.

[0067] This embodiment uses fuzzy logic to determine the degree of danger in different areas within a substation. By classifying the degree of danger in different areas within a substation, it is helpful to formulate safety measures for different areas in real time. When someone approaches an area with a higher degree of danger, a timely warning can be issued.

[0068] Example 2

[0069] The above embodiments comprehensively analyze the equipment aging information, equipment density information, and electrical load information in different areas of the substation, use fuzzy logic methods to determine the degree of danger in the substation, monitor the behavior information of personnel in different areas of the substation through real-time camera devices and image analysis technology, and combine the degree of danger in different areas of the substation to issue early warnings and evacuate people in the area.

[0070] In step 3, the weighted average decision method is a commonly used defuzzification method, which is used to transform the fuzzy output into a specific deterministic value. The fuzzy output is the degree of danger of different areas of the substation obtained by the fuzzy logic method. The weighted average decision method can obtain the specific numerical value of the degree of danger of different areas of the substation, and the defuzzified output value is recorded as the degree of danger coefficient.

[0071] The risk level factor is used to represent the degree of danger of an area. The risk level factor is calculated using the following formula: Among them, WX i μ1, μ2, and μ3 are the risk level coefficients for different areas of the substation, respectively. μ1, μ2, and μ3 are the proportional coefficients of the membership degree of the aging degree coefficient, the membership degree of the equipment density coefficient, and the membership degree of the load fluctuation coefficient. μ1 and μ3 are less than 0, and μ2 is greater than 0.

[0072] It should be noted that the risk level coefficient is only related to the feature information that affects the risk level information. The weight of the feature information is set by professionals in the technical field. The greater the weight of the feature information, the greater its influence on the risk level coefficient.

[0073] As can be seen from the formula, the smaller the membership degree of the aging degree coefficient and the load fluctuation coefficient, and the larger the membership degree of the equipment density coefficient, the larger the danger degree coefficient, indicating that the danger level of the area within the substation is higher. Conversely, the larger the membership degree of the aging degree coefficient and the load fluctuation coefficient, and the smaller the membership degree of the equipment density coefficient, the smaller the danger degree coefficient, indicating that the danger level of the area within the substation is lower.

[0074] High-definition cameras capture information about personnel behavior in different areas of the substation. The cameras can record personnel activities, including their movement, dwell time, and possible operational behaviors in different areas. Different areas of the substation usually have different personnel control requirements. Some areas may only allow personnel with specific training and authorization to enter, while other areas may be open to more personnel. The restrictions on the areas are determined according to the degree of danger in different areas of the substation to ensure the normal operation and safety of the substation.

[0075] Personnel behavior information includes the lingering anomaly coefficient and the number of people concealment safety coefficient. The larger the lingering anomaly coefficient, the longer the same person stays in the same place. Usually, professional personnel inspect different areas in the substation. The time that professional personnel stay in each place is basically fixed. If the same person stays in the same place for too long through monitoring devices such as cameras, there may be an anomaly at that location or the person may not be a professional staff member.

[0076] It should be noted that substations typically have cameras installed at multiple key locations in different areas to monitor personnel behavior. For example, if the same person appears at the same camera frequently and for extended periods, it indicates that an anomaly is likely occurring at the location being monitored.

[0077] The logic for obtaining the loitering anomaly coefficient is as follows: Cameras typically use computer vision technology to identify the same person and record the duration of their presence within the camera's view. When a person's image appears in the camera's view, the camera recognizes and begins recording the duration of that person's stay within the view, marking the duration as: SC. m Where m = 1, 2, 3...M, M is a positive integer, and m is the number of the person appearing in the camera's view;

[0078] Set a dwell time threshold and mark the dwell time threshold as: SC yz If the duration of a person's stay in the camera's view is equal to the dwell time threshold, the counter is incremented by 1, and the dwell time of the person is re-timed. If the camera records the same person, the counter is incremented by 1.

[0079] It should be noted that the duration of a person's stay in the camera's view indicates the length of time the same person continuously appears in the camera's view. The camera periodically clears the recorded images, and the counter is reset to zero periodically to ensure that information is reflected within a relatively short time frame.

[0080] For example, in a specific analysis of a camera, if a person leaves the camera's field of view within the time limit of the dwell time threshold, the counter stops counting and the timer for the person's next stay at the camera is reset. If the person appears in the camera for a duration equal to the dwell time threshold, the counter starts counting, the dwell time of the person at the camera is reset to zero, and the timer is reset. If the person appears in the camera y times, the counter counts y-1 times.

[0081] Obtain the counter values ​​of all cameras within the area, and mark the counter values ​​of all cameras as: JS z Let z = 1, 2, 3...Z, where Z is a positive integer and z is the camera number within the area. Calculate the total number of cameras within the area using the following formula: Among them, JS all This represents the total value within the region.

[0082] The formula for calculating the abnormal retention coefficient is as follows: Where ZL is the regional retention anomaly coefficient;

[0083] As can be seen from the formula, the larger the abnormal retention coefficient, the more abnormal the behavior of people in the area is. It is possible that people stay in a certain location in the area for a long time, or that people frequently appear in a certain location.

[0084] The higher the number of people concealed safety factor, the greater the number of people in the substation area, and the greater the potential safety hazards. This is because a substation is a high-voltage power facility with electrical risks. If the population density is high, the possibility of accidents may increase. Therefore, the number of people concealed safety factor is the number of people in the substation area.

[0085] By comprehensively analyzing the degree of danger in a region and the behavioral information of people in that region, a data analysis model is established using a danger level coefficient, a lingering anomaly coefficient, and a personnel concealment safety coefficient. This model generates a monitoring alert assessment coefficient, the formula for which is: Among them, pg i The monitoring prompt evaluation coefficients are for different areas of the substation, RS is the safety coefficient for concealing the number of people, and ω1, ω2, and ω3 are the proportional coefficients of the danger level coefficient, the abnormal stay coefficient, and the safety coefficient for concealing the number of people, respectively. ω1, ω2, and ω3 are greater than 0.

[0086] As can be seen from the formula, the higher the risk level coefficient, the abnormal stay coefficient, and the safety coefficient for concealed personnel, the higher the monitoring prompt assessment coefficient, indicating that the area has a higher risk of danger. Conversely, the lower the risk level coefficient, the abnormal stay coefficient, and the safety coefficient for concealed personnel, the lower the monitoring prompt assessment coefficient, indicating that the area is safer.

[0087] In step 4, by comprehensively analyzing the degree of danger of the area and the behavior information of the people in the area, the monitoring prompt evaluation coefficient of different areas in the substation is obtained. The monitoring prompt evaluation coefficient threshold is set, and the monitoring prompt evaluation coefficient of different areas is compared with the monitoring prompt evaluation coefficient threshold to obtain the areas where the monitoring prompt evaluation coefficient is greater than the monitoring prompt evaluation coefficient threshold. The areas where the monitoring prompt evaluation coefficient is greater than the monitoring prompt evaluation coefficient threshold are marked as prompt areas, and prompt signals are generated to remind the staff in the substation to evacuate irrelevant personnel in the prompt areas.

[0088] This embodiment combines the degree of danger in different areas of the substation with the behavioral information of people in different areas to comprehensively analyze the potential dangers to people in the area. By generating warning signals to staff, it assists in reminding staff to evacuate irrelevant personnel from the area.

[0089] Example 3

[0090] This invention provides, for example Figure 2 The diagram shows a structural schematic of an intelligent auxiliary monitoring system for substations, including a data acquisition module, a fuzzification module, an analysis module, and an alert signal module, with signal connections between the modules;

[0091] The data acquisition module is used to collect characteristic information of different areas and personnel behavior information within the substation, and transmit the characteristic information of different areas to the fuzzy logic module and the personnel behavior information to the analysis module.

[0092] The fuzzing module is used to fuzzify the feature information within a region to determine the degree of danger in different areas of the substation.

[0093] The analysis module is used to comprehensively analyze the degree of danger in a region and the behavioral information of people in the region to determine the monitoring prompt evaluation coefficient for different regions within the substation.

[0094] The alert signal module is used to generate alert signals based on the comparison between the monitoring alert evaluation coefficient and the monitoring alert evaluation coefficient threshold of different areas within the substation.

[0095] The above formulas are all dimensionless calculations. The formulas are derived from software simulations based on a large amount of collected data to obtain the most recent real-world results. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0096] The above embodiments can be implemented, in whole or in part, by software, hardware, firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more sets of available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. A semiconductor medium can be a solid-state drive.

[0097] It should be understood that in the various embodiments of this application, the order of the above-mentioned processes does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0098] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0099] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0100] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0101] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0102] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. A method for intelligent auxiliary monitoring of substations, characterized in that, Includes the following steps: S1: Collect characteristic information on the degree of danger in different areas within the substation, including information on equipment aging, equipment density, and electrical load. S2: Based on the type of feature information, select the membership function that matches the feature information and obtain the membership degree of the feature information. Use fuzzy logic method to determine the degree of danger in different areas of the substation. S3: Use the weighted average decision method to defuzzify and generate the danger level coefficients for different areas of the substation. Analyze the danger level of the area in conjunction with the behavioral information of the people in the area to generate monitoring prompt assessment coefficients. The behavioral information of the people in the area includes the lingering abnormality coefficient and the number of people concealed safety coefficient. S4: Compare the monitoring prompt evaluation coefficients of different areas within the substation with the monitoring prompt evaluation coefficient thresholds, mark areas with monitoring prompt evaluation coefficients greater than the monitoring prompt evaluation coefficient thresholds as prompt areas, and generate prompt signals; Obtain information on the level of danger in the area and the behavior of people in the area, including: The degree of danger in a region is represented by a degree of danger coefficient. The weighted average decision method can be used to obtain the specific numerical values ​​of the degree of danger in different regions of the substation. The defuzzified output value is recorded as the degree of danger coefficient. The behavioral information of people in the area includes the abnormal lodging coefficient and the safety coefficient for concealing the number of people. The logic for obtaining the loitering anomaly coefficient is as follows: Cameras typically use computer vision technology to identify the same person and record the duration of their presence within the camera's view. When a person's image appears in the camera's view, the camera recognizes and begins recording the duration of their stay. A loitering duration threshold is set. If the duration of a person's stay within the camera's view equals the threshold, a counter is incremented by 1, and the loitering duration is re-timing. If the camera records the same person repeatedly, the counter is incremented by 1. The count values ​​of all camera counters within the area are obtained, and the count values ​​of all camera counters are marked as: JS z Let z = 1, 2, 3...Z, where Z is a positive integer and z is the camera number within the area. Calculate the total number of cameras within the area using the following formula: Among them, JS all This represents the total value within the region. The formula for calculating the abnormal retention coefficient is as follows: Where ZL is the regional retention anomaly coefficient; The analysis combines the level of danger in the area with information on the behavior of people in the area, including: By comprehensively analyzing the degree of danger in a region and the behavioral information of people in that region, a data analysis model is established using a danger level coefficient, a lingering anomaly coefficient, and a personnel concealment safety coefficient to generate a monitoring alert assessment coefficient. The formula for calculating the monitoring alert assessment coefficient is as follows: Among them, pg i WX provides evaluation coefficients for monitoring prompts in different areas of the substation. i ω1, ω2, and ω3 are the risk level coefficients for different areas of the substation, RS is the safety factor for concealing the number of people, and ω1, ω2, and ω3 are the proportional coefficients of the risk level coefficient, the abnormal retention coefficient, and the safety factor for concealing the number of people, respectively, with ω1, ω2, and ω3 being greater than 0.

2. The intelligent auxiliary monitoring method for substations according to claim 1, characterized in that, Collect and assess characteristic information on the degree of danger in different areas within the substation, including: The feature information includes equipment aging information, equipment density information, and electrical load information; The equipment aging information includes an aging coefficient. The logic for obtaining the aging coefficient is as follows: obtain the maximum service life of the equipment in a certain area of ​​the substation, and determine the service life of the equipment based on the historical records of the equipment. Normalize the service life of different equipment to determine the aging degree of different equipment. When the aging degree of each equipment in the area is between 0 and 1, calculate the average value based on the aging degree of each equipment and use the average value to represent the aging coefficient of the area. When there are one or more equipment in the area with an aging degree less than 0, obtain the minimum value of the equipment aging degree and use the minimum value to represent the aging coefficient of the area. Equipment density information includes equipment density coefficient. The logic for obtaining the equipment density coefficient is as follows: obtain the area size of the substation area, obtain the number of operating substation equipment in the area, and calculate the equipment density coefficient of the area using a formula. Electrical load information includes load fluctuation coefficient. The logic for obtaining the load fluctuation coefficient is as follows: obtain the electrical load of a certain area within the substation in a unit time period, calculate the average value and standard deviation of the electrical load in the area in the unit time period, and obtain the load fluctuation coefficient of the area through a formula.

3. The intelligent auxiliary monitoring method for substations according to claim 1, characterized in that, Based on the type of feature information, select the membership function that matches the feature information and obtain the membership degree of the feature information, including: Set membership functions for the aging degree coefficient, equipment density coefficient, and load fluctuation coefficient, and calculate the membership degrees of the aging degree coefficient, equipment density coefficient, and load fluctuation coefficient respectively.

4. The intelligent auxiliary monitoring method for substations according to claim 1, characterized in that, Fuzzy logic methods are used to determine the degree of danger in different areas of a substation, including: Based on the membership degree of different regional feature information within the substation, it is divided into different fuzzy sets. According to the number of types of regional feature information, a corresponding number of fuzzy sets are obtained, and a set of fuzzy rules are formulated to describe the impact of different feature information on the regional hazard level.

5. The intelligent auxiliary monitoring method for substations according to claim 1, characterized in that, Regions with a monitoring alert evaluation coefficient greater than the monitoring alert evaluation coefficient threshold are marked as alert regions, and alert signals are generated, including: The system obtains the monitoring prompt evaluation coefficients for different areas in the substation, sets the monitoring prompt evaluation coefficient threshold, compares the monitoring prompt evaluation coefficients of different areas with the monitoring prompt evaluation coefficient threshold, identifies areas where the monitoring prompt evaluation coefficient is greater than the monitoring prompt evaluation coefficient threshold, marks these areas as prompt areas, and generates prompt signals.

6. An intelligent auxiliary monitoring system for substations, used to implement the intelligent auxiliary monitoring method for substations as described in any one of claims 1-5, characterized in that: It includes a data acquisition module, a fuzzing module, an analysis module, and a prompt signal module, with signal connections between the modules: The data acquisition module is used to collect characteristic information of different areas and personnel behavior information within the substation, and transmit the characteristic information of different areas to the fuzzy logic module and the personnel behavior information to the analysis module. The fuzzing module is used to fuzzify the feature information within a region to determine the degree of danger in different areas of the substation. The analysis module is used to comprehensively analyze the degree of danger in a region and the behavioral information of people in the region to determine the monitoring prompt evaluation coefficient for different regions within the substation. The alert signal module is used to generate alert signals based on the comparison between the monitoring alert evaluation coefficient and the monitoring alert evaluation coefficient threshold of different areas within the substation.

Images