Substation secondary system failure risk assessment method, device, equipment and medium

Abstract

The invention relates to the technical field of data processing, and discloses a substation secondary system failure risk assessment method and device, equipment and a medium, and the method comprises the steps: obtaining the type test data and daily operation state sample data of secondary equipment; constructing a secondary equipment failure probability model according to the type test data and the daily operation state sample data to obtain the secondary equipment failure probability model; determining an equipment failure probability data set according to the secondary equipment failure probability model; according to the failure probability of each device in the device failure probability data set, constructing a secondary system failure risk assessment model to obtain the secondary system failure risk assessment model; and risk assessment processing is carried out according to the secondary system failure risk assessment model to obtain a target risk assessment result, so that the accuracy of failure risk assessment of the substation secondary system can be effectively improved, and the purpose of more accurately and more efficiently carrying out failure risk assessment on the substation secondary system can be realized.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a method, device, equipment and medium for assessing failure risk of a secondary system of a substation. Background Art

[0002] Substation secondary system risk assessment often lacks comprehensive collection, cleaning, classification and organization of secondary equipment type test data and daily operating status sample data, which may lead to an unstable data foundation when conducting failure risk assessment, affecting the accuracy of the assessment results. At the same time, the failure probability model of the substation secondary system is not accurate. The existing assessment method does not fully consider the characteristics of the secondary equipment, the operating environment and other factors. The selected failure probability model is not accurate enough, which may lead to a large deviation in the estimation of the equipment failure probability and fail to accurately reflect the actual situation. Therefore, how to improve the accuracy of failure risk assessment for substation secondary systems has become a problem that needs to be solved urgently. Summary of the invention

[0003] The present invention provides a substation secondary system failure risk assessment method, device, equipment and medium to solve the technical problem of how to improve the accuracy of failure risk assessment for a substation secondary system.

[0004] In a first aspect, a substation secondary system failure risk assessment method is provided, comprising:

[0005] Obtain type test data and daily operation status sample data of secondary equipment;

[0006] The secondary equipment failure probability model is constructed based on the type test data and the daily operation status sample data to obtain the secondary equipment failure probability model;

[0007] Determine the equipment failure probability data set according to the secondary equipment failure probability model;

[0008] According to the failure probability of each device in the device failure probability data set, a secondary system failure risk assessment model is constructed to obtain a secondary system failure risk assessment model;

[0009] According to the secondary system failure risk assessment model, risk assessment processing is carried out to obtain the target risk assessment result.

[0010] In a second aspect, a substation secondary system failure risk assessment device is provided, comprising:

[0011] Acquisition module, used to obtain type test data and daily operation status sample data of secondary equipment;

[0012] The first processing module is used to construct a secondary equipment failure probability model based on type test data and daily operation status sample data to obtain a secondary equipment failure probability model;

[0013] A determination module, used to determine a data set of equipment failure probability according to a secondary equipment failure probability model;

[0014] The second processing module is used to construct a secondary system failure risk assessment model according to the failure probability of each device in the device failure probability data set to obtain the secondary system failure risk assessment model;

[0015] The third processing module is used to perform risk assessment processing according to the secondary system failure risk assessment model to obtain a target risk assessment result.

[0016] In a third aspect, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above-mentioned substation secondary system failure risk assessment method when executing the computer program.

[0017] In a fourth aspect, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned substation secondary system failure risk assessment method are implemented.

[0018] In the scheme implemented by the above-mentioned substation secondary system failure risk assessment method, device, equipment and medium, by obtaining the type test data and daily operation status sample data of the secondary equipment, a secondary equipment failure probability model can be constructed according to the type test data and the daily operation status sample data to obtain the secondary equipment failure probability model, and further according to the secondary equipment failure probability model, the equipment failure probability data set can be determined; thereby, a secondary system failure risk assessment model can be constructed according to the failure probability of each device in the equipment failure probability data set to obtain the secondary system failure risk assessment model, and then risk assessment processing can be performed according to the secondary system failure risk assessment model to obtain the target risk assessment result, which can effectively improve the accuracy of failure risk assessment of the substation secondary system, and is conducive to achieving the purpose of more accurate and efficient failure risk assessment of the substation secondary system. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments of the present invention will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative labor.

[0020] Figure 1 Schematic diagram of an application environment of a substation secondary system failure risk assessment method according to an embodiment of the present invention;

[0021] Figure 2 It is a flow chart of a method for assessing the failure risk of a secondary system of a substation in one embodiment of the present invention;

[0022] Figure 3 It is a structural schematic diagram of a substation secondary system failure risk assessment device in one embodiment of the present invention;

[0023] Figure 4 is a schematic diagram of a structure of a computer device in one embodiment of the present invention;

[0024] Figure 5 It is another structural schematic diagram of a computer device in one embodiment of the present invention. DETAILED DESCRIPTION

[0025] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0026] Substation relay protection safety measures can regulate the on-site operation of relay protection and safety automatic devices in substations, effectively isolate the equipment to be repaired from the operating equipment, and prevent the equipment to be repaired from affecting other operating equipment. The operation and maintenance work carried out by conventional substations is generally highly targeted, and the target equipment for inspection work is basically primary equipment, such as five-protection host, operation station and telecontrol workstation. However, the existing conventional substation operation and maintenance model generally lacks unified supervision of substation operation. At the same time, due to the large number of equipment, it is common for cables to be repeatedly connected in the secondary circuit. During the fault elimination process, it is very easy to cause other non-fault devices to close or trip due to misoperation. In addition, the functions of each device in a conventional substation are too single and independent of each other. It is difficult to form effective information sharing within it, resulting in a large amount of redundant information accumulation that seriously hinders the operation and maintenance personnel from completing the operation and inspection work. In response to the above problems, the project intends to study the use of logical rehearsal safety isolation and anti-false warning technology, establish a modeled conventional substation secondary safety measure library, build a safe operation rehearsal model, and standardize the behavior of operation and maintenance personnel; study secondary system failure risk assessment technology based on reliability analysis, establish a failure risk assessment model, provide intelligent strategy guidance and accurate time scheduling reference for system maintenance, and improve operation and maintenance efficiency.

[0027] The present invention proposes a failure risk assessment and auxiliary decision-making method for a substation secondary system, which includes three steps: constructing a secondary equipment failure probability model, constructing a secondary system failure risk assessment model, and risk assessment and processing. The accuracy of risk assessment is improved through comprehensive data collection and organization, appropriate failure probability model selection, and consideration of equipment correlation and redundancy. Accurate risk warning, intelligent determination of maintenance priority, and personalized maintenance time scheduling optimize operation and maintenance decisions. Database storage management and data visualization processing facilitate data management and analysis. In addition, multiple implementation methods are optional and easy to improve and combine to adapt to different scenarios. It has strong adaptability and scalability, and ensures the safe and stable operation of the substation secondary system.

[0028] The substation secondary system failure risk assessment method provided by the embodiment of the present invention can be applied in the following aspects: Figure 1 In an application environment, the client communicates with the server through a network. Exemplarily, taking the failure risk assessment scenario for the secondary system of a substation as an example, the target user (R&D personnel or management personnel) can upload the type test data and daily operation status sample data of the secondary equipment through the client. Accordingly, the server can obtain the type test data and daily operation status sample data of the secondary equipment through the client, and can construct a secondary equipment failure probability model based on the type test data and the daily operation status sample data to obtain the secondary equipment failure probability model, and further determine the equipment failure probability data set based on the secondary equipment failure probability model; thereby, the secondary system failure risk assessment model can be constructed based on the failure probability of each device in the equipment failure probability data set to obtain the secondary system failure risk assessment model, and then the risk assessment processing can be performed based on the secondary system failure risk assessment model to obtain the target risk assessment result, and the target risk assessment result is fed back to the client. Accordingly, the client can receive the target risk assessment result from the server, and can display the target risk assessment result on the client for the target user to query or browse. By adopting the substation secondary system failure risk assessment method provided in this application, the accuracy of failure risk assessment of the substation secondary system can be effectively improved, which is conducive to achieving the purpose of more accurate and efficient failure risk assessment of the substation secondary system.

[0029] The client may be, but is not limited to, various personal computers, laptops, smart phones, tablet computers, and portable wearable devices. The server may be implemented by an independent server or a server cluster consisting of multiple servers. The present invention is described in detail below through specific embodiments.

[0030] See also Figure 2 As shown, Figure 2A flow chart of a substation secondary system failure risk assessment method provided by an embodiment of the present invention includes the following steps:

[0031] S10: Obtain type test data and daily operation status sample data of secondary equipment.

[0032] Among them, the type test data of secondary equipment may include but is not limited to the electrical performance parameters of the equipment, such as the mean and standard deviation, fluctuation range and other data of voltage, current and power; mechanical performance parameters, such as specific values ​​and tolerance range of size, weight and seismic strength; environmental adaptability parameters, such as the upper and lower limits of the temperature range, the percentage of the humidity range, the specific value of the altitude, etc.

[0033] The daily operating status sample data of the secondary equipment may include but is not limited to the specific values ​​of the real-time operating temperature and humidity of the equipment, the amplitude and frequency of voltage fluctuations, the curve of current load changes, and the cumulative operating time of the equipment, etc. This application does not impose any restrictions on this.

[0034] S20: constructing a secondary equipment failure probability model according to the type test data and the daily operation status sample data to obtain a secondary equipment failure probability model.

[0035] Among them, the secondary equipment failure probability model can mathematically describe the possibility of failure of secondary equipment under different operating conditions (such as different working hours, environmental parameters, etc.). According to the secondary equipment failure probability model, the failure probability of the equipment in the future can be estimated. For equipment with a high failure probability, maintenance, overhaul or replacement can be arranged in advance to avoid system failure caused by sudden equipment failure.

[0036] It should be understood that constructing a secondary equipment failure probability model based on the type test data and the daily operation status sample data to obtain a secondary equipment failure probability model refers to the process of constructing a secondary equipment failure probability model to obtain a secondary equipment failure probability model. Among them, step S20, that is, constructing a secondary equipment failure probability model based on the type test data and the daily operation status sample data to obtain a secondary equipment failure probability model, includes the following steps:

[0037] S21: using the Laida criterion to perform outlier detection on the type test data and the daily operation status sample data to obtain a first preprocessed data set;

[0038] S22: classifying and sorting each first preprocessed data in the first preprocessed data set to obtain a second preprocessed data set;

[0039] S23: modifying the initial model according to the second preprocessing data set and the temperature correction factor to obtain a modified model;

[0040] S24: performing parameter estimation on the modified model to obtain a secondary equipment failure probability model.

[0041] The server can perform outlier detection on the type test data and the daily operation status sample data to pre-process the initial data. For example, assuming that the data set composed of the type test data and the daily operation status sample data is {x 1, x 2, ...x n,}, the server can first calculate its mean and standard deviation, the specific formula is as follows:

[0042]

[0043]

[0044] in, represents the average value of a data set; n represents the number of data in a data set; i represents the index of data in a data set; x i represents the i-th data; σ represents the standard deviation of the data set.

[0045] It is understandable that if the i-th data x i satisfy Then the i-th data can be considered as an outlier and removed. By calculating the mean and standard deviation of the data set, those data points that deviate too much from the mean are removed, so as to obtain a more accurate first preprocessed data set, providing a reliable data basis for subsequent model construction.

[0046] Each data in the first preprocessed data set is classified and sorted, for example, by factors such as equipment type, operating environment, and service life. Equipment types may include protection devices and measurement and control devices; operating environments may include indoor, outdoor, and high altitude; service life may include 1-5 years and 5-10 years. The classified data helps to better understand the distribution law of the data, and can more specifically consider the characteristics of different categories of data when selecting models and parameter estimation in the subsequent process, and finally obtain the second preprocessed data set.

[0047] Before constructing the secondary equipment failure probability model, the server may select an initial model. Optionally, the server may analyze the characteristics of the failure probability models of the Weibull distribution model, the exponential distribution model, and the normal distribution model.

[0048] Among them, the Weibull distribution model can be used to describe the change of equipment life, and its probability density function can be expressed as follows:

[0049]

[0050] Among them, f(t)1 is the probability density function of the Weibull distribution model, t is time, β is the shape parameter, η is the scale parameter, and e is a natural constant.

[0051] The exponential distribution model can be used to describe devices with a constant failure rate, and its probability density function can be expressed as follows:

[0052] f(t)2=λe -λt

[0053] Among them, f(t)2 is the probability density function of the exponential distribution model, t is time, λ is the failure rate, and e is a natural constant.

[0054] The normal distribution model can be applied to the case where the data approximately obeys the normal distribution, and its probability density function can be expressed as follows:

[0055]

[0056] Among them, f(t)3 is the probability density function of the normal distribution model, t is time, σ is the standard deviation, μ is the mean, e is the natural constant, and π is pi.

[0057] Furthermore, the complexity of the secondary equipment (such as high or low integration), reliability requirements (high reliability, general reliability, etc.), expected service life (long life, short life, etc.) and the operating environment characteristics of the equipment, including electromagnetic interference intensity, temperature range, and humidity level, can be considered to select the model type that best suits the secondary equipment.

[0058] It is understood that for devices that are susceptible to temperature, a temperature correction factor T can be constructed factor , the temperature correction factor can be obtained by fitting experimental data, and this application does not limit this. Optionally, the server implements the step of correcting the initial model according to the second preprocessing data set and the temperature correction factor to obtain the corrected model through the following formula:

[0059] f(t, T) = f(t) × T factor (T)

[0060] T factor (T) = aT 2 +bT+c

[0061] Where f(t, T) represents the modified model; f(t) represents the initial model; Tfactor (T) represents the temperature correction factor; T represents temperature; a represents the fitting parameter, such as being called the first fitting parameter; b represents the fitting parameter, such as being called the second fitting parameter; c represents the fitting parameter, such as being called the third fitting parameter.

[0062] The characteristics of different failure probability models such as Weibull distribution, exponential distribution, and normal distribution are analyzed, and the most suitable model is selected by comprehensively considering the complexity, reliability requirements, service life expectations, and operating environment characteristics of the secondary equipment. For equipment that is easily affected by temperature, a temperature correction factor is also constructed to further improve the accuracy of the model.

[0063] Optionally, the server may further perform parameter estimation on the modified model to obtain a secondary equipment failure probability model. The parameter estimation method may be specifically as follows:

[0064] Average rank method: Arrange the failure data in ascending order. For a sample with n failure data, the rank R of the i-th failure data is i , calculate the empirical distribution function F(t) according to the rank, and then substitute the empirical distribution function into the selected failure probability model, and estimate the model parameters by solving the equation. The specific formula can be as follows:

[0065]

[0066]

[0067] Among them, R i represents the rank of the i-th failure data; n represents the number of samples of failure data; i represents the index of failure data; F(t) represents the empirical distribution function; t represents time; t i Indicates the time corresponding to the i-th failure data.

[0068] The average rank method is more applicable when the data volume is not particularly large and the data distribution is relatively clear. It can use the sequential information of the data to construct an empirical distribution function. For some simple failure probability models or situations where the data patterns are relatively obvious, the model parameters can be estimated more intuitively.

[0069] Least squares estimation: Assume that the actual failure data is t1, t2, ..., t n , the failure probabilities predicted by the model are F(t1, θ), F(t2, θ)..., F(t n , θ), further calculate the error sum of squares S(θ), and obtain the estimated value of the parameter by taking the partial derivative of the error sum of squares and setting it to zero. The specific formula can be as follows:

[0070]

[0071] Where S(θ) is the error sum of squares; θ is the model parameter; n is the number of actual failure data; i is the index of the actual failure data; F(t i ,θ) is the failure probability predicted by the model; t i is the time corresponding to the i-th actual failure data; R i Represents the rank of the i-th failure data.

[0072] The least squares method can be applied to various complex failure probability models, especially when there are many model parameters or the relationship between the model and the data is not intuitive. The optimal parameter estimate can be obtained by minimizing the sum of squared errors between the predicted values ​​and the actual values. It has a good theoretical basis in statistics and can make the model fit the data better as a whole. Even if there is a certain amount of noise or fluctuation in the data, relatively stable parameter estimates can be obtained.

[0073] It is understandable that parameter estimation is a key step in "customizing" the constructed model. Taking the least squares estimation as an example, it obtains the estimated value of the parameter by measuring the sum of squared errors between the failure probability predicted by the model and the actual failure data, taking the partial derivative of the sum of squared errors and setting it to zero. These parameter estimates enable the model to fit the actual data, so that it can be truly used to calculate the failure probability of secondary equipment. For example, when using the exponential distribution model to describe the failure probability of equipment, after obtaining the specific value of the failure rate through parameter estimation, the model can accurately calculate the failure probability of the equipment at that moment according to time.

[0074] By determining the parameter values ​​in the model through appropriate parameter estimation methods (such as the average rank method or the least squares method), a complete secondary equipment failure probability model that can be used for actual calculations can be obtained, so that the model can be personalized and precise, and the model can be closely aligned with the equipment failure laws reflected by the actual data.

[0075] S30: Determine a data set of equipment failure probability according to the secondary equipment failure probability model.

[0076] By using the constructed secondary equipment failure probability model, the corresponding failure probability values ​​can be calculated for different secondary equipment individuals or under different operating conditions, and the failure probability values ​​can constitute the equipment failure probability data set. For example, for different types of secondary equipment such as protection devices and measurement and control devices, their failure probabilities are calculated through the secondary equipment failure probability model under their respective specific operating environments, service life and other conditions, and these probability values ​​are collected to form the data set.

[0077] S40: constructing a secondary system failure risk assessment model according to each device failure probability in the device failure probability data set to obtain a secondary system failure risk assessment model.

[0078] Among them, the secondary system failure risk assessment model can quantitatively calculate the risk probability of secondary system failure, and determine the basic events that lead to system failure (such as single equipment failure events and external environmental factors) and their logical relationships through methods such as fault tree analysis. It can then combine the risk assessment results and equipment importance to provide operation and maintenance personnel with accurate time arrangements and maintenance strategies.

[0079] It should be understood that constructing a secondary system failure risk assessment model based on the failure probability of each device in the device failure probability data set to obtain a secondary system failure risk assessment model refers to the process of constructing a secondary system failure risk assessment model to obtain a secondary system failure risk assessment model. Among them, step S40, that is, constructing a secondary system failure risk assessment model based on the failure probability of each device in the device failure probability data set to obtain a secondary system failure risk assessment model, includes the following steps:

[0080] S41: performing fault tree analysis on each device failure probability in the device failure probability data set to obtain a top event set;

[0081] S42: performing layer-by-layer decomposition processing on each top event in the top event set to obtain an intermediate event set and a bottom event set;

[0082] S43: establishing a logic gate relationship for each top event in the top event set, each intermediate event in the intermediate event set, and each bottom event in the bottom event set to obtain a logic gate relationship set;

[0083] S44: quantitatively calculating and obtaining a secondary system operation risk top event probability distribution function according to the top event set, the intermediate event set, the bottom event set, and the logic gate relationship set;

[0084] S45: constructing and obtaining a secondary system failure risk assessment model according to the secondary system operation risk top event probability distribution function.

[0085] The basic principle of fault tree analysis is to take the system failure event as the top event, and find out the various possible factors that lead to system failure through layer-by-layer decomposition, namely intermediate events and bottom events, and connect them with logic gates. Fault tree analysis is a systematic, top-down analysis method, through which various possible situations of system failure (i.e., top events) can be determined. For example, in a power secondary system, equipment failure may lead to different types of system failures, such as protection malfunction or refusal to operate, etc. These system failures are top events and constitute the top event set.

[0086] Among them, the secondary system failure risk event is regarded as the top event, such as the complete paralysis of the system, the loss of important functions and other events that seriously affect the normal operation of the system. The top event is the core focus of the entire risk assessment, and the subsequent analysis is carried out around the top event to explore the various factors that lead to its occurrence.

[0087] By decomposing the top events layer by layer, we can find out the intermediate links that lead to the top events as the intermediate events, so as to further determine the bottom events as the failure events of a single device and the events affected by external environmental factors. Among them, the intermediate events can be regarded as the transition between the top events and the bottom events, which helps to sort out the logical chain of system failure. The bottom events are usually the most basic and indivisible events, such as the failure of a single device or the influence of external environmental factors. For example, in a substation secondary system, the intermediate event may be the malfunction of a protection device, while the bottom event may be the damage of a component inside the protection device or the external electromagnetic interference.

[0088] Use logic gates (such as AND gates and OR gates) to connect these events. Among them, the AND gate indicates that the output event will only occur when all input events occur at the same time, and the OR gate indicates that the output event will occur as long as one input event occurs. Through this logic gate method, the association between secondary system failure and single device failure can be established. For example, in a redundant system composed of multiple devices, system failure (top event) may require multiple key devices to fail at the same time (bottom events are connected through AND gates); and for some systems with backup devices, as long as the main device or backup device fails (bottom events are connected through OR gates), it may cause partial system function failure.

[0089] It is worth noting that further quantitative calculation of the probability distribution function of the top event of the secondary system operation risk and consideration of the correlation and redundancy between devices can improve the accuracy of risk calculation. The probability distribution function of the top event of the secondary system operation risk can be quantitatively calculated based on the top event set, intermediate event set, bottom event set and logic gate relationship set obtained above. The probability of occurrence of the top event can be further calculated based on the basic principle of fault tree analysis and the known bottom event failure probability and logic gate relationship.

[0090] Among them, the probability distribution function of the top event of the secondary system operation risk can be quantitatively calculated by using the fault tree analysis method combined with the failure probability model of the bottom event. For events connected with the AND gate, the probability of the top event is the product of the probability of all bottom events; for events connected with the OR gate, the probability of the top event is 1 minus the probability that all bottom events do not occur. For example, suppose there are three bottom events A, B, and C, and their failure probabilities are P(A), P(B), and P(C), respectively. They are connected to the top event T through the AND gate, then the probability of the top event T occurring is P(T) = P(A) × P(B) × P(C).

[0091] It should be understood that quantitatively calculating and obtaining the secondary system operation risk top event probability distribution function based on the top event set, the intermediate event set, the bottom event set, and the logic gate relationship set refers to the process of how to obtain the secondary system operation risk top event probability distribution function. Among them, in step S44, that is, quantitatively calculating and obtaining the secondary system operation risk top event probability distribution function based on the top event set, the intermediate event set, the bottom event set, and the logic gate relationship set, includes the following steps:

[0092] S441: Acquire relevant device pairs to obtain a set of relevant device pairs;

[0093] S442: performing joint failure probability calculation on each correlation device pair in the set of correlation device pairs to obtain a set of joint failure probabilities;

[0094] S443: performing top event probability calculation according to the joint failure probability set, the top event set, the intermediate event set, the bottom event set and the logic gate relationship set to obtain a top event probability distribution function;

[0095] S444: Determine the secondary system operation risk top event probability distribution function according to the top event probability distribution function.

[0096] For correlated device pairs, the correlation coefficient method can be used to describe the degree of association between the device pairs. This method can help to more accurately assess the risk of system failure due to mutual influence between devices. For example, in a tightly coupled secondary system, two adjacent devices may be correlated due to shared power or signal interference between them, and this correlation will affect the overall failure probability of the system.

[0097] It is understandable that the above correlation will affect the calculation results of the top event probability distribution function. For example, if device A and device B are highly correlated, the probability of failure of one device will also increase when the other device fails, which will change the probability of occurrence of the top event connected through the logic gate (especially the AND gate). Therefore, considering the device correlation can more accurately calculate the top event probability, thereby avoiding the risk assessment error caused by ignoring the mutual influence between devices.

[0098] For correlated pairs of devices, their joint failure probabilities can be calculated first to determine how the correlation between devices affects the probability of occurrence of the bottom event combination when constructing the system fault tree and calculating the top event probability distribution function. Then, when quantitatively calculating the secondary system operation risk top event probability distribution function based on the logic gate relationship, these joint failure probabilities are substituted into the calculation. With the accurate calculation and substitution of the joint failure probability, the top event probability distribution function of the entire secondary system operation risk is further adjusted, which can more accurately reflect the changes in system failure risk caused by device correlation, so that the top event probability distribution function can truly reflect the actual risk status of the system when considering device correlation.

[0099] Optionally, the step of calculating the joint failure probability for each correlation device pair in the set of correlation device pairs to obtain the joint failure probability set is implemented by the following formula:

[0100] P(A∩B)=P(A)×P(B|A)=P(B)×P(A|B)

[0101] Among them, P(A∩B) represents the joint failure probability of the relevant device pair (i.e., device A and device B) in the joint failure probability set; P(A) represents the failure probability of device A; P(B) represents the failure probability of device B; P(B|A) represents the probability of device B failure when device A fails; P(A|B) represents the probability of device A failure when device B fails.

[0102] For redundant devices, redundancy analysis methods can be used, including hot backup redundancy and cold backup redundancy, to calculate the effect of redundant devices on system reliability. The existence of redundant devices will change the reliability structure of the system. When calculating the top event probability distribution function, it is necessary to consider how redundant devices affect the logical relationship between events. For example, in the case of hot backup redundancy, the backup device can immediately take over after the main device fails, which can reduce the probability of system failure (top event); in the case of cold backup redundancy, the backup device will only start after the main device fails, and its startup success rate and other factors will also affect the reliability of the system. Accurately calculating these effects through redundancy analysis methods can more realistically reflect the actual risk status of the system, thereby more accurately obtaining the secondary system operation risk top event probability distribution function.

[0103] In the secondary system failure risk assessment, the correlation and redundancy between devices are fully considered when quantitatively calculating the probability distribution function of the top event. The correlation coefficient method is used to describe the degree of device association, and the redundancy analysis method is used to calculate the effect of redundant devices on system reliability, making the risk calculation more accurate and able to more truly reflect the actual risk status of the system.

[0104] Finally, a secondary system failure risk assessment model is constructed based on the probability distribution function of the secondary system operation risk top event, so that the model can be used to assess the failure risk of the system under different equipment states and operating conditions, providing an important basis for system maintenance, improvement and risk management.

[0105] S50: Perform risk assessment processing according to the secondary system failure risk assessment model to obtain a target risk assessment result.

[0106] The target risk assessment results may include, but are not limited to, system failure probability information, equipment importance ranking and risk contribution information, risk level classification and warning information, time-related risk information, and recommended measures and strategy information, etc. This application does not impose any restrictions on this.

[0107] The server can use the constructed secondary system failure risk assessment model to analyze and evaluate the actual operation of the secondary system. Optionally, the server can further set risk levels and warning thresholds, and provide operation and maintenance strategy guidance, etc. This application does not limit this.

[0108] The server can set different risk levels (such as low risk, medium risk, high risk, etc.) and determine the corresponding warning thresholds based on the system failure risk probability calculated by the model. When the risk indicator during system operation reaches or exceeds the warning threshold, a warning signal will be issued in a timely manner.

[0109] The server can combine the risk assessment results and the importance of the equipment to formulate accurate time arrangements and operation and maintenance strategies to improve the efficiency of operation and maintenance, thereby ensuring the normal operation of the secondary system. For example, for high-risk equipment or system parts, more frequent inspections and maintenance can be arranged; for low-risk parts, the inspection cycle can be appropriately extended.

[0110] Optionally, the risk assessment and failure risk warning of the treatment steps specifically include:

[0111] The risk matrix method is used to set different risk levels, including high risk, medium risk and low risk. The risk matrix consists of two dimensions: the possibility of risk occurrence (high, medium, low) and the severity of risk consequences (high, medium, low). The combination of possibility and severity is mapped to different risk levels.

[0112] Set the warning threshold. When the risk reaches the warning threshold, the warning signal will be issued in time through sound and light alarm, SMS notification, system pop-up window, etc., and detailed risk information will be provided, including risk level, possible failed equipment, and expected failure time. Use the risk matrix method to set different risk levels, and determine the risk level based on the possibility of risk occurrence and the severity of consequences. When the risk reaches the warning threshold, the warning signal will be issued in time through sound and light alarm, SMS notification, system pop-up window, etc., and detailed risk information will be provided, including risk level, possible failed equipment, and expected failure time. This enables operation and maintenance personnel to respond quickly and take corresponding prevention and control measures.

[0113] Optionally, the server can determine the maintenance priority of the equipment based on the risk assessment results using the Risk Priority Number (RPN) method. The RPN can be composed of three factors: the possibility, severity, and detectability of the risk. The calculation formula is RPN = P × S × D, where P is the possibility, S is the severity, and D is the detectability. This method can be used to comprehensively consider the three factors of the possibility, severity, and detectability of the risk to determine the maintenance priority of the equipment. This helps operation and maintenance personnel give priority to high-risk equipment, improve maintenance efficiency, and reduce the incidence of system failures.

[0114] Combining the risk assessment results and the importance of the equipment, genetic algorithms and simulated annealing algorithms can be used to optimize the maintenance schedule, with the goal of minimizing system risks and maintenance costs, to determine the best maintenance time and sequence, while taking into account the equipment's service life and maintenance history, to develop a personalized maintenance plan. Combining the risk assessment results and the importance of the equipment, genetic algorithms and simulated annealing algorithms can be used to optimize the maintenance schedule, while taking into account the equipment's service life and maintenance history, to develop a personalized maintenance plan, which can meet the maintenance needs of different equipment while minimizing system risks and maintenance costs, extend equipment life, and improve equipment reliability.

[0115] Optionally, a database can be established to store and manage the collected data, which is convenient for subsequent data query, analysis and update. Using data analysis software to visualize the data can help track the operating status and risk changes of the equipment in the long term, and provide data support for continuous improvement of risk assessment and operation and maintenance decision-making. Using data analysis software to visualize the data can more intuitively display the distribution and trend of the data. This enables operation and maintenance personnel to understand the data more quickly, discover potential problems and patterns, and provide stronger support for risk assessment and auxiliary decision-making.

[0116] This application provides a reliable data basis for the establishment of a failure probability model by collecting various parameters of secondary equipment and cleaning, classifying and organizing the data, which can more accurately understand the actual operation of the equipment and thus improve the accuracy of risk assessment.

[0117] The characteristics of different failure probability models such as Weibull distribution, exponential distribution, and normal distribution are further analyzed, and the most suitable model is selected by comprehensively considering the complexity, reliability requirements, service life expectations, and operating environment characteristics of the secondary equipment.

[0118] Using the correlation coefficient method to describe the degree of equipment association and the redundancy analysis method to calculate the effect of redundant equipment on system reliability can make risk calculation more accurate and more realistically reflect the actual risk status of the system.

[0119] Furthermore, the risk matrix method is used to set different risk levels, and the risk level is determined by combining the possibility of risk occurrence and the severity of consequences. When the risk reaches the warning threshold, a warning signal is issued in a timely manner through sound and light alarms, SMS notifications, system pop-ups, etc., and detailed risk information is provided, including risk level, possible failed equipment and expected failure time, which enables operation and maintenance personnel to respond quickly and take corresponding prevention and control measures.

[0120] The present invention improves the accuracy of risk assessment through comprehensive data collection and organization, appropriate failure probability model selection, and consideration of equipment relevance and redundancy; precise risk warning, intelligent determination of maintenance priority, and personalized maintenance time scheduling optimize operation and maintenance decision-making; database storage management and data visualization processing facilitate data management and analysis; and multiple implementation methods are optional and easy to improve and combine to adapt to different scenarios, with strong adaptability and scalability, ensuring the safe and stable operation of the substation secondary system.

[0121] It can be seen that in the above scheme, by obtaining the type test data and daily operation status sample data of the secondary equipment, the secondary equipment failure probability model can be constructed according to the type test data and the daily operation status sample data to obtain the secondary equipment failure probability model, and further according to the secondary equipment failure probability model, the equipment failure probability data set can be determined; thereby, according to the failure probability of each device in the equipment failure probability data set, a secondary system failure risk assessment model can be constructed to obtain a secondary system failure risk assessment model, and then according to the secondary system failure risk assessment model, risk assessment processing can be performed to obtain a target risk assessment result, which can effectively improve the accuracy of failure risk assessment of the secondary system of the substation, and is conducive to achieving the purpose of more accurate and efficient failure risk assessment of the secondary system of the substation.

[0122] It should be understood that the order of execution of the steps in the above embodiment does not necessarily mean 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 embodiment of the present invention.

[0123] In one embodiment, a substation secondary system failure risk assessment device is provided, and the substation secondary system failure risk assessment device corresponds to the substation secondary system failure risk assessment method in the above embodiment. Figure 3 As shown, the substation secondary system failure risk assessment device includes an acquisition module 101, a first processing module 102, a determination module 103, a second processing module 104 and a third processing module 105. Each functional module is described in detail as follows:

[0124] Acquisition module 101, used for acquiring module, used for acquiring type test data and daily operation status sample data of secondary equipment;

[0125] The first processing module 102 is used to construct a secondary equipment failure probability model according to the type test data and the daily operation status sample data to obtain a secondary equipment failure probability model;

[0126] A determination module 103, configured to determine a device failure probability data set according to the secondary device failure probability model;

[0127] The second processing module 104 is used to construct a secondary system failure risk assessment model according to each device failure probability in the device failure probability data set to obtain a secondary system failure risk assessment model;

[0128] The third processing module 105 is used to perform risk assessment processing according to the secondary system failure risk assessment model to obtain a target risk assessment result.

[0129] In one embodiment, the first processing module 102 is used to construct a secondary equipment failure probability model according to the type test data and the daily operation status sample data to obtain a secondary equipment failure probability model, which is specifically used to:

[0130] Using the Laida criterion, performing outlier detection on the type test data and the daily operation status sample data to obtain a first preprocessed data set;

[0131] Classifying and sorting each first preprocessed data in the first preprocessed data set to obtain a second preprocessed data set;

[0132] According to the second preprocessed data set and the temperature correction factor, the initial model is corrected to obtain a corrected model;

[0133] Parameters of the modified model are estimated to obtain a secondary equipment failure probability model.

[0134] In one embodiment, the first processing module 102 is used to modify the initial model according to the second preprocessing data set and the temperature correction factor to obtain a modified model, specifically for:

[0135] The step of correcting the initial model according to the second preprocessed data set and the temperature correction factor to obtain the corrected model is implemented by the following formula:

[0136] f(t, T) = f(t) × T factor (T)

[0137] T factor (T) = aT 2 +bT+c

[0138] Where f(t, T) represents the modified model; f(t) represents the initial model; T factor (T) represents the temperature correction factor; a represents the fitting parameter, such as the first fitting parameter; b represents the fitting parameter, such as the second fitting parameter; c represents the fitting parameter, such as the third fitting parameter.

[0139] In one embodiment, the second processing module 104 is used to construct a secondary system failure risk assessment model according to each device failure probability in the device failure probability data set to obtain a secondary system failure risk assessment model, which is specifically used to:

[0140] Performing fault tree analysis on each device failure probability in the device failure probability data set to obtain a top event set;

[0141] Decomposing each top event in the top event set layer by layer to obtain an intermediate event set and a bottom event set;

[0142] Establishing a logic gate relationship for each top event in the top event set, each intermediate event in the intermediate event set, and each bottom event in the bottom event set to obtain a logic gate relationship set;

[0143] According to the top event set, the intermediate event set, the bottom event set and the logic gate relationship set, quantitatively calculate and obtain the secondary system operation risk top event probability distribution function;

[0144] According to the secondary system operation risk top event probability distribution function, a secondary system failure risk assessment model is constructed and obtained.

[0145] In one embodiment, the second processing module 104 is used to quantitatively calculate and obtain the secondary system operation risk top event probability distribution function according to the top event set, the intermediate event set, the bottom event set and the logic gate relationship set, specifically for:

[0146] Obtaining correlated device pairs to obtain a set of correlated device pairs;

[0147] For each correlation device pair in the set of correlation device pairs, a joint failure probability calculation is performed to obtain a joint failure probability set;

[0148] Calculate the probability of a top event according to the joint failure probability set, the top event set, the intermediate event set, the bottom event set and the logic gate relationship set to obtain a top event probability distribution function;

[0149] Determining a secondary system operation risk top event probability distribution function according to the top event probability distribution function;

[0150] The step of calculating the joint failure probability of each correlation device pair in the correlation device pair set to obtain the joint failure probability set is implemented by the following formula:

[0151] P(A∩B)=P(A)×P(B|A)=P(B)×P(A|B)

[0152] Among them, P(A∩B) represents the joint failure probability of the relevant device pair (i.e., device A and device B) in the joint failure probability set; P(A) represents the failure probability of device A; P(B) represents the failure probability of device B; P(B|A) represents the probability of device B failure when device A fails; P(A|B) represents the probability of device A failure when device B fails.

[0153] The present invention provides a substation secondary system failure risk assessment device. By acquiring type test data and daily operation status sample data of secondary equipment, a secondary equipment failure probability model can be constructed according to the type test data and the daily operation status sample data to obtain the secondary equipment failure probability model, and further according to the secondary equipment failure probability model, a device failure probability data set can be determined; thereby, a secondary system failure risk assessment model can be constructed according to the failure probability of each device in the device failure probability data set to obtain the secondary system failure risk assessment model, and then risk assessment processing can be performed according to the secondary system failure risk assessment model to obtain a target risk assessment result, which can effectively improve the accuracy of failure risk assessment of the substation secondary system, and is conducive to achieving the purpose of more accurate and efficient failure risk assessment of the substation secondary system.

[0154] For the specific definition of the substation secondary system failure risk assessment device, please refer to the definition of the substation secondary system failure risk assessment method mentioned above, which will not be repeated here. Each module in the above-mentioned substation secondary system failure risk assessment device can be implemented in whole or in part by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0155] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 4 As shown. The computer device includes a processor, a memory, a network interface and a database connected via a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile and / or volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external client via a network connection. When the computer program is executed by the processor, it realizes the functions or steps on the service side of a substation secondary system failure risk assessment method.

[0156] In one embodiment, a computer device is provided. The computer device may be a client, and its internal structure diagram may be as follows: Figure 5 As shown. The computer device includes a processor, a memory, a network interface, a display screen and an input device connected via a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external server via a network connection. When the computer program is executed by the processor, it realizes the functions or steps on the client side of a substation secondary system failure risk assessment method.

[0157] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the following steps when executing the computer program:

[0158] Obtain type test data and daily operation status sample data of secondary equipment;

[0159] Constructing a secondary equipment failure probability model according to the type test data and the daily operation status sample data to obtain a secondary equipment failure probability model;

[0160] Determining a data set of equipment failure probability according to the secondary equipment failure probability model;

[0161] According to the failure probability of each device in the device failure probability data set, a secondary system failure risk assessment model is constructed to obtain a secondary system failure risk assessment model;

[0162] According to the secondary system failure risk assessment model, risk assessment processing is performed to obtain a target risk assessment result.

[0163] The present invention provides a computer device, which can construct a secondary equipment failure probability model according to the type test data and the daily operation status sample data of the secondary equipment by acquiring the type test data and the daily operation status sample data, so as to obtain the secondary equipment failure probability model, and further determine the equipment failure probability data set according to the secondary equipment failure probability model; thereby, a secondary system failure risk assessment model can be constructed according to the failure probability of each device in the equipment failure probability data set, so as to obtain the secondary system failure risk assessment model, and then risk assessment processing can be performed according to the secondary system failure risk assessment model to obtain a target risk assessment result, which can effectively improve the accuracy of failure risk assessment of the secondary system of the substation, and is conducive to achieving the purpose of more accurate and efficient failure risk assessment of the secondary system of the substation.

[0164] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0165] Obtain type test data and daily operation status sample data of secondary equipment;

[0166] Constructing a secondary equipment failure probability model according to the type test data and the daily operation status sample data to obtain a secondary equipment failure probability model;

[0167] Determining a data set of equipment failure probability according to the secondary equipment failure probability model;

[0168] According to the failure probability of each device in the device failure probability data set, a secondary system failure risk assessment model is constructed to obtain a secondary system failure risk assessment model;

[0169] According to the secondary system failure risk assessment model, risk assessment processing is performed to obtain a target risk assessment result.

[0170] The present invention provides a computer-readable storage medium. By acquiring type test data and daily operation status sample data of secondary equipment, a secondary equipment failure probability model can be constructed according to the type test data and the daily operation status sample data to obtain the secondary equipment failure probability model, and further according to the secondary equipment failure probability model, a device failure probability data set can be determined; thereby, a secondary system failure risk assessment model can be constructed according to the failure probability of each device in the device failure probability data set to obtain a secondary system failure risk assessment model, and then risk assessment processing can be performed according to the secondary system failure risk assessment model to obtain a target risk assessment result, which can effectively improve the accuracy of failure risk assessment of the secondary system of the substation, and is conducive to achieving the purpose of more accurate and efficient failure risk assessment of the secondary system of the substation.

[0171] It should be noted that the above functions or steps that can be implemented by the computer-readable storage medium or computer device can refer to the relevant descriptions on the server side and the client side in the aforementioned method embodiment. To avoid repetition, they will not be described one by one here.

[0172] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0173] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0174] The embodiments described above are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. A method for assessing the failure risk of a substation secondary system, characterized in that: The substation secondary system failure risk assessment method comprises: Obtain type test data and daily operation status sample data of secondary equipment; Constructing a secondary equipment failure probability model according to the type test data and the daily operation status sample data to obtain a secondary equipment failure probability model; Determining a data set of equipment failure probability according to the secondary equipment failure probability model; According to the failure probability of each device in the device failure probability data set, a secondary system failure risk assessment model is constructed to obtain a secondary system failure risk assessment model; According to the secondary system failure risk assessment model, risk assessment processing is performed to obtain a target risk assessment result.

2. The substation secondary system failure risk assessment method according to claim 1 is characterized in that: The constructing of the secondary equipment failure probability model according to the type test data and the daily operation status sample data to obtain the secondary equipment failure probability model includes: Using the Laida criterion, performing outlier detection on the type test data and the daily operation status sample data to obtain a first preprocessed data set; Classifying and sorting each first preprocessed data in the first preprocessed data set to obtain a second preprocessed data set; According to the second preprocessed data set and the temperature correction factor, the initial model is corrected to obtain a corrected model; Parameters of the modified model are estimated to obtain a secondary equipment failure probability model.

3. The substation secondary system failure risk assessment method according to claim 2 is characterized in that: The step of correcting the initial model according to the second preprocessing data set and the temperature correction factor to obtain a corrected model includes: The step of correcting the initial model according to the second preprocessed data set and the temperature correction factor to obtain the corrected model is implemented by the following formula: f(t,T)=f(t)×T factor (T) T factor (T)=aT 2 +bT+c Where f(t,T) represents the modified model; f(t) represents the initial model; T factor (T) represents the temperature correction factor; a represents the fitting parameter, such as the first fitting parameter; b represents the fitting parameter, such as the second fitting parameter; c represents the fitting parameter, such as the third fitting parameter.

4. The substation secondary system failure risk assessment method according to claim 3 is characterized in that: The secondary system failure risk assessment model is constructed according to each device failure probability in the device failure probability data set to obtain the secondary system failure risk assessment model, including: Performing fault tree analysis on each device failure probability in the device failure probability data set to obtain a top event set; Decomposing each top event in the top event set layer by layer to obtain an intermediate event set and a bottom event set; Establishing a logic gate relationship for each top event in the top event set, each intermediate event in the intermediate event set, and each bottom event in the bottom event set to obtain a logic gate relationship set; According to the top event set, the intermediate event set, the bottom event set and the logic gate relationship set, quantitatively calculate and obtain the secondary system operation risk top event probability distribution function; According to the secondary system operation risk top event probability distribution function, a secondary system failure risk assessment model is constructed and obtained.

5. The substation secondary system failure risk assessment method according to any one of claims 1 to 4, characterized in that: The quantitative calculation and obtaining of the secondary system operation risk top event probability distribution function according to the top event set, the intermediate event set, the bottom event set and the logic gate relationship set includes: Obtaining correlated device pairs to obtain a set of correlated device pairs; For each correlation device pair in the set of correlation device pairs, a joint failure probability calculation is performed to obtain a joint failure probability set; Calculate the probability of a top event according to the joint failure probability set, the top event set, the intermediate event set, the bottom event set and the logic gate relationship set to obtain a top event probability distribution function; Determining a secondary system operation risk top event probability distribution function according to the top event probability distribution function; The step of calculating the joint failure probability of each correlation device pair in the correlation device pair set to obtain the joint failure probability set is implemented by the following formula: P(A∩B)=P(A)×P(B|A)=P(B)×P(A|B) Among them, P(A∩B) represents the joint failure probability of the relevant device pair (i.e., device A and device B) in the joint failure probability set; P(A) represents the failure probability of device A; P(B) represents the failure probability of device B; P(B|A) represents the probability of device B failure when device A fails; P(A|B) represents the probability of device A failure when device B fails.

6. A substation secondary system failure risk assessment device, characterized in that: The substation secondary system failure risk assessment device comprises: Acquisition module, used to obtain type test data and daily operation status sample data of secondary equipment; A first processing module is used to construct a secondary equipment failure probability model according to the type test data and the daily operation status sample data to obtain a secondary equipment failure probability model; A determination module, used to determine a device failure probability data set according to the secondary device failure probability model; A second processing module is used to construct a secondary system failure risk assessment model according to each device failure probability in the device failure probability data set to obtain a secondary system failure risk assessment model; The third processing module is used to perform risk assessment processing according to the secondary system failure risk assessment model to obtain a target risk assessment result.

7. The substation secondary system failure risk assessment device according to claim 6, characterized in that: The first processing module is used to construct a secondary equipment failure probability model according to the type test data and the daily operation status sample data to obtain the secondary equipment failure probability model, which is specifically used to: Using the Laida criterion, performing outlier detection on the type test data and the daily operation status sample data to obtain a first preprocessed data set; Classifying and sorting each first preprocessed data in the first preprocessed data set to obtain a second preprocessed data set; According to the second preprocessed data set and the temperature correction factor, the initial model is corrected to obtain a corrected model; Parameters of the modified model are estimated to obtain a secondary equipment failure probability model.

8. The substation secondary system failure risk assessment device according to claim 7, characterized in that: The first processing module is used to correct the initial model according to the second preprocessing data set and the temperature correction factor to obtain a corrected model, specifically for: The step of correcting the initial model according to the second preprocessed data set and the temperature correction factor to obtain the corrected model is implemented by the following formula: f(t,T)=f(t)×T factor (T) T factor (T)=aT 2 +bT+c Where f(t,T) represents the modified model; f(t) represents the initial model; T factor (T) represents the temperature correction factor; a represents the fitting parameter, such as the first fitting parameter; b represents the fitting parameter, such as the second fitting parameter; c represents the fitting parameter, such as the third fitting parameter.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the substation secondary system failure risk assessment method according to any one of claims 1 to 5 is implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the substation secondary system failure risk assessment method according to any one of claims 1 to 5 is implemented.

Images