Transformer substation holographic safety assessment method and system based on system dynamics

Abstract

The invention relates to a transformer substation holographic safety assessment method and system based on system dynamics. The method comprises the following steps that representative monitoring variables corresponding to key equipment of a transformer substation are obtained; classifying the representative monitoring variable into a plurality of dimensions, and modeling the fault probability of the representative monitoring variable to form a fault probability model of the key equipment of the single transformer substation; based on the non-electrical monitoring variables of the key equipment of the single transformer substation, modeling a non-electrical connection relationship between the key equipment of the transformer substation through symbolic regression based on a genetic algorithm to form an equipment comprehensive fault probability model; and based on the equipment comprehensive fault probability model, constructing a substation holographic safety evaluation system dynamic model, and realizing substation safety monitoring. Compared with the prior art, the method has the advantages that the non-electrical incidence relation between different devices is fully considered, and the fault early warning accuracy is high.

Description

Technical Field

[0001] The present invention relates to the technical field of power systems, and in particular, to a method and system for holographic safety assessment of substations based on system dynamics. Background Art

[0002] As an important part of the power system, the safe operation of substations has a significant impact on the power system. With the development of substation holography, the number of electrical and non-electrical variable data acquisition and monitoring devices in substations has gradually increased, and the operation data that can be obtained by substations has also increased explosively. These data can well reflect the real-time operation of substations and their internal equipment.

[0003] Chinese Patent Application Publication No. CN119180004A discloses a method for holographic safety assessment of substation system dynamics considering mutual verification, but only considers the mutual verification relationship between multi-dimensional monitoring variables of single equipment and the electrical connection relationship between different equipment, without considering the non-electrical connection between different equipment, and the connection between equipment in the substation is not comprehensive enough. Chinese Patent Application Publication No. CN118644946A discloses a substation fire monitoring system based on image recognition, which identifies whether a transformer catches fire according to the operation sound signal of the substation and the image information monitored by the camera, and issues a safety warning if a fire occurs. However, this system has certain limitations in identifying the substation status only based on sound and image signals.

[0004] However, the above applications do not fully consider the non-electrical correlation relationship between different equipment. Summary of the Invention

[0005] The purpose of the present invention is to overcome the above-mentioned defects existing in the prior art and provide a method and system for holographic safety assessment of substations based on system dynamics, so as to solve or partially solve the problem that the non-electrical correlation relationship between different equipment, that is, the mutual influence relationship of variables between non-directly contacting equipment, is not fully considered, resulting in unsatisfactory accuracy of subsequent substation safety assessment and early warning.

[0006] The purpose of the present invention can be achieved by the following technical solutions:

[0007] In one aspect of the present invention, a method for holographic safety assessment of substations based on system dynamics is provided, including the following steps:

[0008] Obtain representative monitoring variables corresponding to key equipment in the substation;

[0009] Classify the representative monitoring variables into multiple dimensions, model the failure probability of the representative monitoring variables, and form a failure probability model of a single substation key equipment;

[0010] Based on the non - electrical monitoring variables of key equipment in a single substation, through symbolic regression based on the genetic algorithm, the non - electrical connection relationship between key equipment in the substation is modeled to form an equipment comprehensive failure probability model;

[0011] Based on the equipment comprehensive failure probability model, a dynamic model of the substation holographic security assessment system is constructed to realize substation security monitoring.

[0012] As an optimal technical solution, during the process of modeling the failure probability of the representative monitoring variables,

[0013] The failure probability modeling of the electrical signal dimension is:

[0014]

[0015] In the above formula, \(p_f\) i (t) is the failure probability function of the electrical signal characteristics, is the working threshold of the \(i\) - th representative monitoring variable of the key equipment \(s\) in the substation, are respectively the thresholds of the \(i\) - th representative monitoring variable of the key equipment \(s\) in the substation at time \(t\). A key equipment has a total of \(h\) monitoring variables in the electrical signal dimension, \(p_f\) g (t) is the failure probability of the electrical signal dimension of the key equipment \(g\),

[0016] The failure probability modeling of the equipment state dimension is:

[0017] \(p_l(t)=1 - e\) -l(t)

[0018] \(l(t)=Ke\) -100C·μ(t)·HI'(t)

[0019]

[0020] In the above formula, \(p_l(t)\) is the failure probability of the key equipment at time \(t\), \(l(t)\) is the failure rate of the key equipment, \(K\) and \(C\) are proportionality coefficients, \(\mu(t)\) is the equipment aging coefficient, \(HI'\) r (t) is the deviation between the health state index and the standard value, is the threshold of the \(i\) - th key equipment state index of the key equipment \(g\) in the substation, is the value corresponding to the \(i\) - th key equipment state index at time \(t\). A key equipment has a total of \(m\) key equipment state indicators, \(B\) i is the influence coefficient of the \(i\) - th key equipment state index,

[0021] The failure probability modeling of the operating environment dimension is:

[0022]

[0023]

[0024] In the above formula, pe(t) is the failure probability function of the operating environment dimension, n is the number of operating environment indicators, pe j (t) is the critical equipment failure probability caused by the jth environmental factor to the equipment at time t, M is the undetermined coefficient of the model, λ j (t) is the equipment failure rate caused by the jth environmental monitoring variable to the key at time t, pe j (t) is the equipment failure probability caused by the jth environmental factor to the critical equipment at time t.

[0025] As a preferred technical solution, the symbolic regression modeling is as follows:

[0026]

[0027] Among them, f(X) is the symbolic regression expression, L(f(x), D) is the fitness function for judging the accuracy of f(x), X is the independent variable from the data set D, F is the function set, F = {+, -, ×, ÷, sin, cos}, and M is the symbolic expression space including independent variables, functions, and constant terms.

[0028] As a preferred technical solution, the process of modeling the non - electrical connection relationship between key equipment in a substation includes the following steps:

[0029] Iteratively solve the symbolic regression problem through the genetic algorithm to fit the functional relationship between the temperature of key equipment g and the temperature of key equipment g + 1;

[0030] Based on the fitted functional relationship, calculate the influence coefficient of the failure of key equipment g on the associated key equipment (g + 1);

[0031] Based on the failure probability model of a single key equipment in the substation and the influence coefficient, calculate the failure probability function of a single key equipment g's failure on the lower - level key equipment (g + 1) to realize the modeling of the non - electrical connection relationship of the substation's key equipment;

[0032] Model the electrical connection relationship of the substation's key equipment;

[0033] Based on the non - electrical connection relationship of the substation's key equipment and the electrical connection relationship of the substation's key equipment, construct an equipment comprehensive failure probability model.

[0034] As a preferred technical solution, the failure probability function modeling of a single key equipment g's failure on the lower - level key equipment (g + 1) is as follows:

[0035]

[0036] Among them, is the failure probability function of a single key device g on the subordinate key device (g + 1), is the influence coefficient of the failure of key device g on the associated key device (g + 1), is the functional relationship between the temperature of key device g and the temperature of device (g + 1) obtained by fitting. Through this functional relationship, the predicted value of the temperature of key device (g + 1) can be calculated based on the temperature of key device g, x g+1 is the monitored value of the temperature of key device (g + 1).

[0037] As a preferred technical solution, the comprehensive failure probability model of the device is modeled as:

[0038]

[0039] Among them, is the comprehensive failure probability of key device (g + 1) under the interconnection of other key devices, is the influence probability of other key devices on device (g + 1) under non - electrical connection relationship, is the influence probability of other key devices on device (g + 1) under electrical connection relationship, P g+1 (t) is the failure probability of the change of its own monitoring variable, ω fdq and ω dq and ω are respectively the corresponding coefficients, is the failure probability of the i - th subordinate key device. There are v subordinate key devices for key device (g + 1).

[0040] As a preferred technical solution, based on the comprehensive failure probability model of the device, the process of constructing the dynamic model of the substation holographic security assessment system includes the following steps:

[0041] Based on the comprehensive failure probability model of the device, construct the system dynamics equation;

[0042] Use solid lines to represent the electrical connection relationships between monitoring variables and key devices, and between key devices, and use dashed lines to represent the non - electrical connection relationships between key devices in the substation to construct the dynamic model of the substation holographic security assessment system;

[0043] Build the application architecture and physical architecture of the substation holographic security assessment application system, and through collecting electrical and non - electrical characteristic data, realize data pre - processing, monitoring and query, and issue alarms for abnormal monitoring data.

[0044] As a preferred technical solution, the process of iteratively solving the symbolic regression problem by the genetic algorithm includes the following steps:

[0045] Initialize the formula;

[0046] Use the fitness function to evaluate whether the current formula result meets the preset requirements. If not, update the individuals through selection, crossover, and mutation to obtain a new generation of population, and re-execute this step until the population reaches the optimum or the maximum number of loop iterations is reached.

[0047] As a preferred technical solution, the key equipment of the substation includes cable lines, 110 kV busbars, transformers, 35 kV busbars, feeders, and switchgear.

[0048] As a preferred technical solution, the classifying the representative monitoring variables into multiple dimensions includes the following steps:

[0049] Classify the representative monitoring variables into an electrical signal dimension, an equipment status dimension, and an operating environment dimension. Among them, the representative monitoring variables in the electrical signal dimension include load current, operating voltage, active power, and reactive power; the representative monitoring variables in the equipment status dimension include core grounding current, clamp grounding current, oil level, oil temperature, partial discharge, equipment temperature, and SF6 gas pressure; the representative monitoring variables in the operating environment dimension include water level, humidity, and temperature.

[0050] Another aspect of the present invention provides a substation holographic safety assessment system based on system dynamics for implementing the foregoing substation holographic safety assessment method based on system dynamics. The safety assessment system includes:

[0051] A data acquisition module for collecting and monitoring electrical data and auxiliary control data;

[0052] A system dynamics flow diagram model construction module for constructing a causal relationship flow chart, electrical / non-electrical correlation relationships, and system dynamics function relationships to form a substation holographic safety assessment system dynamics model;

[0053] A basic configuration module for realizing ledger configuration and acquisition data point configuration;

[0054] A safety monitoring module for on-line equipment safety monitoring and equipment dynamic safety warning.

[0055] Compared with the prior art, the present invention has at least one of the following beneficial effects:

[0056] (1) Fully consider the non-electrical correlation relationships between different equipment: By fully considering the electrical connections between key equipment in the substation and the correlation relationships between non-electrical monitoring variables, the present invention improves the safety assessment level of the equipment and the substation in the substation.

[0057] (2) High accuracy of fault warning: Considering the characteristics that non-electrical variables have strong anti-interference ability and slow change speed, the present invention uses non-electrical variables to conduct safety assessment on key equipment, which can effectively improve the accuracy of pre-fault warning.

[0058] (3) No need to preset function form: The present invention uses the symbolic regression method based on genetic algorithm to establish the relationship between non-electrical variables, overcoming the deficiency that other regression methods need to preset function form in advance. Description of the drawings

[0059] Figure 1 It is a schematic diagram of holographic safety assessment of a substation in the embodiment;

[0060] Figure 2 It is a flow chart of symbolic regression in the embodiment;

[0061] Figure 3 It is a schematic diagram of equipment association relationship in the embodiment;

[0062] Figure 4 It is a schematic diagram of constructing a system dynamics model of a substation system in the embodiment;

[0063] Figure 5 It is a schematic diagram of a holographic safety assessment system of a substation based on system dynamics in the embodiment;

[0064] Figure 6 It is a schematic diagram of an electronic device in the embodiment. Detailed implementation manners

[0065] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0066] Embodiment 1

[0067] In view of the problems existing in the foregoing prior art, this embodiment provides a method for holographic safety assessment of a substation based on system dynamics. Considering the characteristics that non-electrical variables (that is, the relationship of mutual influence between variables of non-directly contacting devices, such as main transformer temperature, oil temperature, etc.) have strong anti-interference ability and slow change speed, this method adds the connection of non-electrical variables between devices on the basis of the electrical connection of devices in the substation. When the fault probability of a certain device is obtained through multi-dimensional monitoring variables, through electrical and non-electrical association, the associated devices of the faulty device are alarmed, so as to improve the safety assessment level of the substation.

[0068] See Figure 1, the holographic safety assessment of the substation is gradually deepened at three levels of "monitoring variables - equipment - substation system" to achieve the holographic safety assessment of the substation system. First, key equipment of the substation and important monitoring variables of the equipment are selected; then, according to the selected monitoring variables, a failure probability function of the monitoring variables for the equipment is established to construct a safety assessment model of the substation equipment; next, various regression methods are used to establish the non-electrical connection relationships between the substation equipment, and combined with the electrical connections, the system dynamics equations of various association relationships within the substation are constructed. Finally, a holographic system dynamics model of the substation is built, and then the safety assessment of the substation is carried out.

[0069] This method includes the following steps:

[0070] Step S1, select important equipment of the substation and its key monitoring variables. Specifically, this step includes steps S101 - S102.

[0071] Step S101, the key equipment selected for the substation are: cable lines, 110 kV busbars, transformers, 35 kV busbars, feeders, and switch cabinets.

[0072] Step S102, select representative monitoring variables of the equipment in step S101.

[0073] Specifically, the key variables are divided into three dimensions: electrical signals, equipment status, and operating environment. The key variables in the electrical signal dimension specifically include load current, operating voltage, active power, and reactive power; the equipment status dimension specifically includes core grounding current, clamp grounding current, oil level, oil temperature, partial discharge, equipment temperature, and SF6 gas pressure; the operating environment dimension specifically includes water level, humidity, and temperature.

[0074] Step S2, classify the multi-dimensional monitoring variables, and establish the corresponding failure probability function of the monitoring variables to form a single-equipment safety assessment model. Specifically, step S2 includes steps S201 - S204.

[0075] Step S201, construct the failure probability function of the electrical signal dimension; when the load current, operating voltage, active power, and reactive power of the in-station equipment exceed a certain threshold, the equipment will be damaged or even burned; when the in-station switch signal value is 1, it means the equipment is normal, and when it is 0, it means the equipment is faulty. Therefore, the failure probability function of the electrical signal characteristics is established as pf i (t):

[0076]

[0077] In the formula is the working threshold of the i-th monitoring variable of the in-station equipment s, are respectively the thresholds of the i-th monitoring variable of the in-station equipment s at time t, and an equipment has a total of h monitoring variables in the electrical signal dimension.

[0078] Obtain the failure probability pf of the electrical signal dimension of device g according to the failure probability function of each electrical signal g (t):

[0079]

[0080] Step S202: Construct the failure probability function of the device status dimension;

[0081] Use the deviation between different device health status indicators and the standard values to represent the impact of the indicators on the device, and use HI' r (t) to represent:

[0082]

[0083] In the formula is the threshold of the i-th device status indicator of the in-station device g; is the value corresponding to the i-th device status indicator at time t; a device has a total of m device status indicators, B i is the influence coefficient of the i-th device status indicator.

[0084] During the actual operation of the device, there is an aging process, so the device failure rate l(t) is:

[0085] l(t) = Ke -100C·μ(t)·HI'(t) 4)

[0086] In the formula, K and C are proportionality coefficients, and μ(t) is the device aging coefficient.

[0087] According to the device failure rate in formula (3) and the relationship between the failure rate and the failure occurrence probability, the failure probability function of the device status dimension is:

[0088] pl(t) = 1 - e -l(t) 5)

[0089] In the formula, pl(t) is the device failure probability at time t.

[0090] Step S203: Construct the failure probability function of the operating environment dimension.

[0091] Most of the functions of environmental factors adopt an exponential model with low complexity and high practicality, that is:

[0092]

[0093] In the formula, M is a coefficient to be determined in the model, which can be obtained according to objective historical data and expert experience; λ j (t) is the device failure rate caused by the j-th environmental monitoring variable to the device at time t.

[0094] The failure probability caused by the external environment to the device by the (5) environmental exponential function is as follows:

[0095]

[0096] In the formula: pe j (t) is the device failure probability caused by the j-th environmental factor to the device at time t.

[0097] Considering the influence of the comprehensive operating environment on the device, the failure probability function pe(t) of the operating environment dimension is obtained as follows:

[0098]

[0099] In the formula, n is the number of operating environment indicators.

[0100] Step S204, any abnormal device in the dimensions of electrical signals, device status, and operating environment will issue an alarm. According to the series model and combining steps S201 - S203, the failure probability function P g (t ) :

[0101] P g (t) = 1 - (1 - pf g (t))(1 - pl g (t))(1 - pe g (t))9)

[0102] Step S3, use the symbolic regression method to establish the non - electrical connection relationship of substation electrical equipment and construct the comprehensive device failure probability model. Specifically, this step includes steps S301 - S303.

[0103] Step S301, establish the non - electrical connection relationship of substation electrical equipment.

[0104] Since most faults in the substation will cause temperature rise and then lead to major faults, the non - electrical connection relationship between equipment in the substation, that is, the correlation relationship between the temperatures of electrical equipment, is established to prevent the impact on associated equipment when a certain equipment fails. In this paper, the symbolic regression algorithm is used to train the data in normal and fault operating states, and fit the functional relationship between the temperature of each electrical equipment and that of other equipment. If the temperature of a certain equipment shows an abnormal trend, other equipment under the associated relationship with this temperature will also issue a warning.

[0105] The symbolic regression algorithm obtains an explicit non-linear function relationship expression through symbolic operations, thereby establishing a functional relationship between multiple detection variables. Taking temperature as the non-connected variable for illustration, if the symbolic regression expression is f(X), where L(f(x),D) is the fitness function for judging the accuracy of f(x), X is the independent variable set from the data set D, which includes the temperature variables of all devices, F is the function set, F = { +, -, ×, ÷, sin, cos}, and M is the symbolic expression space composed of independent variables, functions, and constant terms.

[0106]

[0107] The symbolic regression problem is solved using a genetic algorithm, as Figure 2 shown. First, initialize the formula, that is, initialize the population, and evaluate it using the fitness function; judge whether the evaluation result meets the requirements. If it does not meet the requirements, update the individuals using operations such as selection, crossover, and mutation to obtain a new population; loop this process until the population reaches the optimum or reaches the maximum number of iterations of the loop, and finally obtain the optimal functional relationship. Determine the influence coefficient of the failure of device g on the associated device (g + 1) according to the established functional relationship.

[0108]

[0109] In the formula is the functional relationship between the temperature of device g itself and the temperature of device (g + 1). Through this functional relationship, the predicted value of the temperature of device (g + 1) can be calculated from the temperature of device g, and x g+1 is the monitored value of the temperature of device (g + 1).

[0110] When device g fails, the value will increase accordingly, and the influence coefficient will increase, and thus the influence of the faulty device on the related devices will also increase. Therefore, based on the non-electrical connection relationship between devices, the failure probability function of a single device g's failure on the lower-level device g + 1

[0111]

[0112] In the formula, P g (t) is the failure probability of device g, and P g+1 (t) is the failure probability of device (g + 1).

[0113] Step S302, establish the electrical connection relationship of the substation electrical equipment.

[0114] The substation belongs to a multi-device series system. If a certain device in the series system fails, that is, the failure probability of the device is 1, then the devices on the lower side of the device along the power flow direction are also de-energized. The single-device failure probability function calculated in step S204 is used for the failure probability function of the lower-level devices

[0115]

[0116] In the formula is the failure probability of the i-th lower-level device, and the device (g + 1) has a total of v lower-level devices.

[0117] Step S303, as Figure 3 shown, the non-electrical connection relationship function of the substation equipment obtained in step S301 and the electrical connection failure probability function of the substation equipment obtained in step S302 together link different substation equipment. When a certain device fails, early warnings are given to the associated devices of the faulty device through electrical connections and their non-electrical connections, so as to improve the overall safety level of the substation. The comprehensive failure probability of the device (g + 1) under the interconnection of other devices is as follows.

[0118]

[0119] In the formula is the influence probability of other devices on the device (g + 1) under the non-electrical connection relationship, is the influence probability of other devices on the device (g + 1) under the electrical connection relationship, P g+1 (t) is the failure probability of the change of its own monitoring variable, ω fdq 、ω dq and ω are respectively the corresponding coefficients, and the sum of these two is 1.

[0120] Step S4, build a system dynamics model for holographic safety assessment of the substation, and conduct safety monitoring and analysis of the substation. Specifically, this step includes steps S401 - S403.

[0121] Step S401, since the relationship between the devices in the substation satisfies the series model, system dynamics equations are constructed according to steps S301 and S302. The substation failure probability P BDZ (t) is calculated as follows:[[]]

[0122]

[0123] In the formula, d is the total number of substation devices, is the comprehensive failure probability function of the device (g + 1) in the substation.

[0124] Step S402, construct the dynamic model of the substation holographic security assessment system as Figure 4 shown. The solid lines represent the electrical connection relationships between the monitoring variables and the devices, as well as between the devices and devices, while the dashed lines represent the non-electrical connection relationships between the devices in the substation. The internal functional relationships of the model are transformed into system dynamics equations according to the formulas in Step S2, Step S3, and Step S401.

[0125] Step S303, build the application architecture and physical architecture of the substation holographic security assessment application system, and determine that the main functions of the application system are: design the database, collect electrical and non-electrical characteristic data, implement data preprocessing, monitoring, and query functions, and issue alarms for abnormal monitoring data. The schematic diagram of the effect is as Figure 5 shown.

[0126] This method has the following characteristics:

[0127] (1) This method adds the non-electrical connection relationships between different devices in the substation on the basis of the existing substation security assessment, thereby improving the security assessment level of the devices and the substation in the substation.

[0128] (2) Considering the characteristics that non-electrical variables have strong anti-interference ability and slow change speed, using non-electrical variables to conduct security assessment on electrical equipment can effectively improve the accuracy of pre-fault warning.

[0129] (3) Using the symbolic regression method to establish the relationship between non-electricals avoids the deficiencies of other regression methods that require pre-setting the function form.

[0130] Example 2

[0131] On the basis of Example 1, this example provides a substation holographic security assessment system based on system dynamics, which is used to implement the substation holographic security assessment method based on system dynamics in Example 1. See Figure 5 , and the security assessment system includes:

[0132] A data acquisition module, which is used to collect and monitor electrical data and auxiliary control data;

[0133] A system dynamics flow diagram model construction module, which is used to construct the causal relationship flow chart, electrical / non-electrical association relationships, and system dynamics functional relationships, and form the dynamic model of the substation holographic security assessment system by using the method in Example 1;

[0134] A basic configuration module, which is used to implement ledger configuration and collection data point configuration;

[0135] A security monitoring module, which is used for on-line monitoring of equipment security and dynamic security alarm of equipment.

[0136] Embodiment 3

[0137] This embodiment provides an electronic device, including: one or more processors and a memory. One or more programs are stored in the memory, and the one or more programs include instructions for executing the substation holographic security assessment method based on system dynamics as described in Embodiment 1.

[0138] As Figure 6 described, at the hardware level, the electronic device includes a processor, an internal bus, a network interface, a memory, and a non-volatile memory. Of course, it may also include other hardware required for other services. The processor reads the corresponding computer program from the non-volatile memory into the memory and then runs it to implement the above Figure 1 described method. Of course, in addition to the software implementation, the present invention does not exclude other implementation manners, such as logic devices or a combination of software and hardware, etc. That is to say, the execution subject of the following processing flow is not limited to each logic unit, and can also be hardware or a logic device.

[0139] As described above, the above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of various equivalent modifications or substitutions, and these modifications or substitutions should all be covered within the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims

1. A holographic safety assessment method for substations based on system dynamics, characterized in that: The steps include: Obtain representative monitoring variables corresponding to key equipment in substations; Classifying the representative monitoring variables into multiple dimensions, modeling the failure probability of the representative monitoring variables, and forming a failure probability model of key equipment of a single substation; Based on the non-electrical monitoring variables of key equipment in a single substation, the non-electrical connection relationship between key equipment in the substation is modeled through symbolic regression based on genetic algorithm to form a comprehensive equipment failure probability model; Based on the comprehensive equipment failure probability model, a holographic safety assessment system dynamics model of the substation is constructed to realize substation safety monitoring.

2. According to claim 1, a holographic safety assessment method for substations based on system dynamics is characterized in that: In the process of modeling the failure probability of the representative monitoring variables, The failure probability in the electrical signal dimension is modeled as: In the above formula, pf i (t) is the fault probability function of the electrical signal characteristic, is the working threshold of the i-th representative monitoring variable of the key equipment s in the substation, are the thresholds of the i-th representative monitoring variables of the key equipment s in the substation at time t. A key equipment has a total of h monitoring variables in the electrical signal dimension. pf g (t) is the failure probability of the electrical signal dimension of the key equipment g, The failure probability of the equipment status dimension is modeled as: pl(t)=1-e -l(t) l(t)=The -100C·μ(t)·HI′(t) In the above formula, pl(t) is the probability of failure of key equipment at time t, l(t) is the failure rate of key equipment, K and C are proportional coefficients, μ(t) is the equipment aging coefficient, HI′ r (t) is the deviation between the health status index and the standard value, is the threshold value of the i-th key equipment status indicator of the key equipment g in the substation, is the value of the i-th key equipment status indicator at time t. A key equipment has m key equipment status indicators. i is the influence coefficient of the i-th key equipment status indicator, The failure probability of the operating environment dimension is modeled as: In the above formula, pe(t) is the failure probability function of the operating environment dimension, n is the number of operating environment indicators, and pe j (t) is the probability of critical equipment failure caused by the jth environmental factor at time t, M is the unknown coefficient of the model, λ j (t) is the equipment failure rate caused by the jth environmental monitoring variable at time t, pe j (t) is the probability of equipment failure caused by the jth environmental factor at time t on the key equipment.

3. According to claim 1, a holographic safety assessment method for substations based on system dynamics is characterized in that: The symbolic regression model is: Where f(X) is a symbolic regression expression, L(f(x), D) is the fitness function for determining the accuracy of f(x), X is the independent variable from the data set D, F is the function set, F = {+, -, ×, ÷, sin, cos}, and M is the symbolic expression space including independent variables, functions, and constant terms.

4. According to claim 1, a holographic safety assessment method for substations based on system dynamics is characterized in that: The process of modeling the non-electrical connection relationship between key substation equipment includes the following steps: The symbolic regression problem is iteratively solved by genetic algorithm, and the functional relationship between the temperature of key equipment g and the temperature of key equipment g+1 is fitted; Based on the fitted functional relationship, calculate the impact coefficient of the failure of key equipment g on the associated key equipment (g+1); Based on the failure probability model of a single key substation device and the influence coefficient, the failure probability function of a single key device g failure on the lower-level key device (g+1) is calculated to achieve non-electrical connection relationship modeling of key substation devices; Model the electrical connection relationship of key equipment in substations; Based on the non-electrical connection relationship of the key equipment of the substation and the electrical connection relationship of the key equipment of the substation, a comprehensive equipment failure probability model is constructed.

5. According to the system dynamics-based holographic safety assessment method for substations according to claim 1, it is characterized in that: The failure probability function of a single key device g on the lower-level key device (g+1) is modeled as: in, is the failure probability function of a single key device g on the lower key device (g+1), is the impact coefficient of the failure of key equipment g on the associated key equipment (g+1), is the functional relationship between the temperature of key equipment g and the temperature of equipment (g+1) obtained by fitting. Through this functional relationship, the predicted value of the temperature of key equipment (g+1) can be calculated according to the temperature of key equipment g. g+1 It is the monitoring value of the temperature of the key equipment (g+1).

6. A holographic safety assessment method for substations based on system dynamics according to claim 1, characterized in that: The equipment comprehensive failure probability model is modeled as: in, is the comprehensive failure probability of the key equipment (g+1) under the mutual correlation of other key equipment, is the probability of other key equipment affecting equipment (g+1) under non-electrical connection relationship, is the probability of other key equipment affecting equipment (g+1) under electrical connection relationship, P g+1 (t) is the failure probability of the change of the self-monitoring variable, ω fdq ,ω dq and ω are The corresponding coefficients are, is the failure probability of the i-th subordinate key device, and the key device (g+1) has a total of v subordinate key devices.

7. A holographic safety assessment method for substations based on system dynamics according to claim 1, characterized in that: Based on the equipment comprehensive failure probability model, the process of constructing a holographic safety assessment system dynamics model for a substation includes the following steps: Based on the comprehensive failure probability model of the equipment, a system dynamics equation is constructed; Solid lines are used to represent the electrical connection relationship between the monitored variables and key equipment, and between key equipment, and dotted lines are used to represent the non-electrical connection relationship between key equipment in the substation, to build a dynamic model of the substation holographic safety assessment system; Build the application architecture and physical architecture of the holographic safety assessment application system for substations, collect electrical and non-electrical characteristic data, implement data preprocessing, monitoring and query, and issue alarms for abnormal monitoring data.

8. A holographic safety assessment method for substations based on system dynamics according to claim 1, characterized in that: The key equipment of the substation includes cable lines, 110 kV busbars, transformers, 35 kV busbars, feeders and switch cabinets.

9. A holographic safety assessment method for substations based on system dynamics according to claim 8, characterized in that: The classifying of the representative monitoring variables into multiple dimensions comprises the following steps: The representative monitoring variables are classified into electrical signal dimension, equipment status dimension and operating environment dimension, wherein the representative monitoring variables of the electrical signal dimension include load current, operating voltage, active power and reactive power, the representative monitoring variables of the equipment status dimension include core grounding current, clamp grounding current, oil level, oil temperature, partial discharge, equipment temperature and SF6 gas pressure, and the representative monitoring variables of the operating environment dimension include water level, humidity and temperature.

10. A holographic safety assessment system for substations based on system dynamics, characterized in that: Used to implement the holographic safety assessment method for substations based on system dynamics as described in any one of claims 1 to 9, the safety assessment system comprises: Data acquisition module, used to collect and monitor electrical appliance data and auxiliary control data; System dynamics flow chart model building module, used to build causal relationship flow charts, electrical / non-electrical association relationships and system dynamics function relationships, forming a holographic safety assessment system dynamics model for substations; Basic configuration module, used to implement ledger configuration and data collection point configuration; The safety monitoring module is used for online monitoring of equipment safety and dynamic safety alarms of equipment.

Images