A power equipment differentiation early warning method and device based on failure probability

Abstract

The application discloses a power equipment differentiation early warning method and device based on a fault probability. The method comprises the following steps: acquiring online monitoring data of a power equipment to be measured; in the case that the online monitoring data are distinguished according to different operating conditions, a first fault probability of the power equipment to be measured is calculated according to a voltage grade of the power equipment to be measured and a probability density distribution function of a fault threshold value under the voltage grade which is established in advance, and an early warning grade of the power equipment to be measured is determined according to the first fault probability; in the case that the online monitoring data are not distinguished according to different operating conditions, a second fault probability of the power equipment to be measured is calculated through a corrected fault probability function according to an ambient temperature of the power equipment to be measured and a corresponding correction coefficient under the ambient temperature, and an early warning grade of the power equipment to be measured is determined according to the second fault probability.

Description

Technical Field

[0001] This invention relates to the field of power system technology, and more specifically, to a method and apparatus for differentiated early warning of power equipment based on fault probability. Background Technology

[0002] The health status of power transmission and transformation equipment is crucial to the safe operation of the power grid. Poorly maintained equipment can seriously threaten the grid's safety and even trigger grid accidents. Current Chinese standards only provide threshold values ​​for online monitoring parameters of power transmission and transformation equipment based on voltage levels, which is rather crude. Different power transmission and transformation equipment vary significantly in manufacturing processes and operating environments. Uniform diagnostic thresholds cannot accurately reflect the fault risks faced by the equipment, resulting in inaccurate diagnostic results and ultimately, poor effectiveness of online monitoring technology in providing early warnings of equipment risks. Summary of the Invention

[0003] To address the shortcomings of existing technologies, this invention provides a method and apparatus for differentiated early warning of power equipment based on fault probability.

[0004] According to one aspect of the present invention, a differentiated early warning method for power equipment based on fault probability is provided, comprising:

[0005] Acquire online monitoring data of the power equipment under test;

[0006] When online monitoring quantities are differentiated according to different operating conditions, the first fault probability of the power equipment under test is calculated based on the voltage level of the power equipment under test using the probability density distribution function of the fault threshold under the pre-established voltage level, and the warning level of the power equipment under test is determined based on the first fault probability.

[0007] When online monitoring parameters are not differentiated according to different operating conditions, the second fault probability of the power equipment under test is calculated based on the ambient temperature of the power equipment under test and the corresponding correction coefficient at that ambient temperature, using a corrected fault probability function. The warning level of the power equipment under test is then determined based on the second fault probability.

[0008] Optionally, it also includes:

[0009] In the absence of online monitoring data of the power equipment under test, the failure probability of each component of the power equipment under test is determined according to the failure probability curve of each component of the power equipment under test with the years of service, and the third failure probability of the power equipment is determined according to the failure probability of each component of the power equipment with the years of service and the preset ratio.

[0010] The warning level of the power equipment under test is determined based on the third failure probability.

[0011] Optionally, the operation of acquiring the online monitoring data of the power equipment under test includes:

[0012] When the electrical equipment under test is a transformer, the online monitoring quantity is dissolved gas in oil;

[0013] When the power equipment under test is a GIS switch, the online monitoring quantities are SF6 gas moisture and pressure;

[0014] When the power equipment under test is a metal oxide surge arrester, the online monitoring equipment is for both total current and resistive current.

[0015] Optionally, the probability density distribution function of the fault probability threshold at different voltage levels is:

[0016]

[0017] Where, σ D f is the probability density distribution function at a certain voltage level. D Standard deviation, μ D f is the probability density distribution function at a certain voltage level. D The mean value of x0 is the value of the online monitoring quantity, and y is the fault threshold of the power equipment under test.

[0018] Optionally, the modified failure probability function is as follows:

[0019]

[0020] in

[0021]

[0022] Among them, T max T is the maximum deterioration limit specified in the industry standard. D The temperature reference values ​​are those specified in the industry standard, where t is the measured temperature in °C, a is a constant, and σ is the temperature value specified in the standard. D f is the probability density distribution function at a certain voltage level. D Standard deviation, μ D f is the probability density distribution function at a certain voltage level. D The mean value of x0 is the value of the online monitoring quantity, and y is the fault threshold of the power equipment under test.

[0023] Optionally, it also includes:

[0024] The online state variables of historical power equipment are modeled using a two-parameter Weibull distribution to determine the parameter data of each component of the power equipment at different ages.

[0025] Based on parameter data of various components of power equipment at different ages, determine the failure probability curves of each component of power equipment as they change with age.

[0026] According to another aspect of the present invention, a power equipment differentiated early warning device based on fault probability is provided, comprising:

[0027] The acquisition module is used to acquire the online monitoring data of the power equipment under test;

[0028] The first determination module is used to calculate the first fault probability of the power equipment under test based on the voltage level of the power equipment under test, using a pre-established probability density distribution function of the fault threshold under the voltage level, and determine the warning level of the power equipment under test based on the first fault probability when the online monitoring quantity is distinguished according to different operating conditions.

[0029] The second determination module is used when the online monitoring quantity is not distinguished according to different operating conditions. Based on the ambient temperature of the power equipment under test and the corresponding correction coefficient at that ambient temperature, it calculates the second fault probability of the power equipment under test through a corrected fault probability function, and determines the warning level of the power equipment under test based on the second fault probability.

[0030] According to another aspect of the present invention, a computer-readable storage medium is provided, the storage medium storing a computer program for performing the methods described in any of the above aspects of the present invention.

[0031] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising: a processor; a memory for storing executable instructions of the processor; the processor being configured to read the executable instructions from the memory and execute the instructions to implement the method described in any of the preceding aspects of the present invention.

[0032] Therefore, this application proposes a differentiated early warning method for power equipment based on fault probability. The method calculates the fault probability using a strength-stress interference model and achieves differentiated early warning by changing the parameters of the distribution function (i.e., the stress value). For fault probabilities corresponding to types of defects other than those monitored online, runtime is considered, making the early warning more comprehensive and accurate. This contributes to improving the accuracy and scientific rigor of the early warning system. Attached Figure Description

[0033] Exemplary embodiments of the present invention can be more fully understood by referring to the following figures:

[0034] Figure 1 This is a flowchart illustrating a differentiated early warning method for power equipment based on fault probability, provided in an exemplary embodiment of the present invention.

[0035] Figure 2 This is a schematic diagram of a differentiated early warning structure for power equipment based on fault probability, provided in an exemplary embodiment of the present invention.

[0036] Figure 3 This is a schematic diagram of the fault proportions of various components of a transformer provided in an exemplary embodiment of the present invention;

[0037] Figure 4 This is a schematic diagram of probability curves for different components of a transformer provided in an exemplary embodiment of the present invention;

[0038] Figure 5 This is a schematic diagram of the structure of a power equipment differential early warning device based on fault probability provided in an exemplary embodiment of the present invention;

[0039] Figure 6 This is the structure of an electronic device provided in an exemplary embodiment of the present invention. Detailed Implementation

[0040] Hereinafter, exemplary embodiments of the present invention will be described in detail with reference to the accompanying drawings. It is obvious that the described embodiments are merely some embodiments of the present invention, and not all embodiments of the present invention, and it should be understood that the present invention is not limited to the exemplary embodiments described herein.

[0041] It should be noted that, unless otherwise specifically stated, the relative arrangement, numerical expressions, and values ​​of the components and steps described in these embodiments do not limit the scope of the invention.

[0042] Those skilled in the art will understand that the terms "first," "second," etc., in the embodiments of the present invention are only used to distinguish different steps, devices, or modules, and do not represent any specific technical meaning, nor do they indicate a necessary logical order between them.

[0043] It should also be understood that in the embodiments of the present invention, "multiple" can refer to two or more, and "at least one" can refer to one, two or more.

[0044] It should also be understood that any component, data or structure mentioned in the embodiments of the present invention can generally be understood as one or more unless explicitly defined or given contrary instructions in the context.

[0045] Furthermore, the term "and / or" in this invention is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this invention generally indicates that the preceding and following related objects have an "or" relationship.

[0046] It should also be understood that the description of the various embodiments in this invention emphasizes the differences between the various embodiments, and the similarities or similarities can be referred to each other. For the sake of brevity, they will not be described in detail.

[0047] At the same time, it should be understood that, for ease of description, the dimensions of the various parts shown in the accompanying drawings are not drawn according to actual scale.

[0048] The following description of at least one exemplary embodiment is merely illustrative and is in no way intended to limit the invention or its application or use.

[0049] Techniques, methods, and equipment known to those skilled in the art may not be discussed in detail, but where appropriate, they should be considered part of the specification.

[0050] It should be noted that similar labels and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be discussed further in subsequent figures.

[0051] The embodiments of this invention can be applied to electronic devices such as terminal devices, computer systems, and servers, and can operate together with a wide range of other general-purpose or special-purpose computing system environments or configurations. Well-known examples of terminal devices, computing systems, environments, and / or configurations suitable for use with electronic devices such as terminal devices, computer systems, and servers include, but are not limited to: personal computer systems, server computer systems, thin clients, thick clients, handheld or laptop devices, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputer systems, mainframe computer systems, and distributed cloud computing environments including any of the above systems, etc.

[0052] Electronic devices such as terminal devices, computer systems, and servers can be described in the general context of computer system executable instructions (such as program modules) executed by a computer system. Typically, program modules can include routines, programs, object programs, components, logic, data structures, etc., which perform specific tasks or implement specific abstract data types. Computer systems / servers can be implemented in distributed cloud computing environments, where tasks are executed by remote processing devices linked through communication networks. In distributed cloud computing environments, program modules can reside on local or remote computing system storage media, including storage devices.

[0053] Exemplary methods

[0054] Figure 1 This is a flowchart illustrating a differentiated early warning method for power equipment based on fault probability, provided in an exemplary embodiment of the present invention. This embodiment can be applied to electronic devices, such as… Figure 1 As shown, the power equipment differential early warning method 100 based on fault probability includes the following steps:

[0055] Step 101: Obtain the online monitoring data of the power equipment under test;

[0056] Step 102: When online monitoring quantities are differentiated according to different operating conditions, the first fault probability of the power equipment under test is calculated based on the voltage level of the power equipment under test using the probability density distribution function of the fault threshold under the pre-established voltage level, and the warning level of the power equipment under test is determined based on the first fault probability.

[0057] Step 103: If the online monitoring quantity is not differentiated according to different operating conditions, the second fault probability of the power equipment under test is calculated based on the ambient temperature of the power equipment under test and the corresponding correction coefficient at that ambient temperature, through the corrected fault probability function, and the warning level of the power equipment under test is determined based on the second fault probability.

[0058] Optionally, it also includes:

[0059] In the absence of online monitoring data of the power equipment under test, the failure probability of each component of the power equipment under test is determined according to the failure probability curve of each component of the power equipment under test with the years of service, and the third failure probability of the power equipment is determined according to the failure probability of each component of the power equipment with the years of service and the preset ratio.

[0060] The warning level of the power equipment under test is determined based on the third failure probability.

[0061] Users can simultaneously obtain the first fault probability, the second fault probability, and the third fault probability of the power equipment under test according to their needs. The three fault probabilities are then combined through a series model to determine the warning level of the power equipment under test.

[0062] Optionally, the operation of acquiring the online monitoring data of the power equipment under test includes:

[0063] When the electrical equipment under test is a transformer, the online monitoring quantity is dissolved gas in oil;

[0064] When the power equipment under test is a GIS switch, the online monitoring quantities are SF6 gas moisture and pressure;

[0065] When the power equipment under test is a metal oxide surge arrester, the online monitoring equipment is for both total current and resistive current.

[0066] Optionally, the probability density distribution function of the fault probability threshold at different voltage levels is:

[0067]

[0068] Where, σ D f is the probability density distribution function at a certain voltage level. D Standard deviation, μD f is the probability density distribution function at a certain voltage level. D The mean value of x0 is the value of the online monitoring quantity, and y is the fault threshold of the power equipment under test.

[0069] Optionally, the modified failure probability function is as follows:

[0070]

[0071] in

[0072]

[0073] Among them, T max T is the maximum deterioration limit specified in the industry standard. D The temperature reference values ​​are those specified in the industry standard, where t is the measured temperature in °C, a is a constant, and σ is the temperature value specified in the standard. D f is the probability density distribution function at a certain voltage level. D Standard deviation, μ D f is the probability density distribution function at a certain voltage level. D The mean value of x0 is the value of the online monitoring quantity, and y is the fault threshold of the power equipment under test.

[0074] Optionally, it also includes:

[0075] The online state variables of historical power equipment are modeled using a two-parameter Weibull distribution to determine the parameter data of each component of the power equipment at different ages.

[0076] Based on parameter data of various components of power equipment at different ages, determine the failure probability curves of each component of power equipment as they change with age.

[0077] Specifically, refer to Figure 2 As shown, the fault probability prediction of the power equipment under test in this application based on different voltage levels and different temperature levels is a differentiated fault probability calculation based on the strength-stress interference model, as detailed below:

[0078] For insulation faults in power transformers, the dissolved H2 concentration in the oil is chosen as its state variable C. The field-measured data for state variable C is greater than zero, and the larger x is, the greater the probability of the fault occurring in the equipment. It is assumed that the value x of the state variable C for this type of equipment in the field has a probability distribution density function f. CA (x); Assumptions: For the insulation fault mode of the transformer, there exists a fault threshold D, and the fault threshold D and the state variable C have the same dimension; when the measured value x of the equipment state variable C is greater than the specific value y of the fault threshold D, the equipment fails; the specific value y of the fault threshold D of each device is random, and its probability distribution density function is f. D (y,μ,σ2 ), where the unknown μ is the expected value, and the unknown σ is the expected value. 2 Let f be the variance, and f D (y,μ,σ 2 ) and f CA (x) has the same functional form.

[0079] A sample set A is established by randomly selecting power transformers in various states, where the total number of transformers is n and the number of transformers with serious insulation defects is m. This invention defines power equipment failure as the occurrence of critical and serious defects. Using existing sampling theory, hypothesis testing, significance testing, and other mathematical statistical theories, the measured values ​​x of the state variables C of all equipment in sample set A are statistically analyzed to obtain the probability distribution density function f of the state variables C of this type of equipment. CA (x) has a log-normal distribution, as shown in formula (1). The following reasoning and calculation process is based on a patent for a method and system for evaluating the state of power equipment based on failure rate. (x is a state variable)

[0080]

[0081] A sample set B is established by randomly selecting transformers containing both critical and severe defects. Using existing sampling theory, hypothesis testing, significance testing, and other mathematical statistics theories, statistical analysis is performed on the measured field values ​​x of the state variables C of all equipment in sample set B to obtain the probability distribution density function f of the state variables C of the faulty equipment. CB (x), as shown in formula (2):

[0082]

[0083] Then, determine the probability density distribution function f for the fault threshold. D (y,μ,σ 2 It also has the form of a log-normal distribution. Further, by simultaneously solving equations (3) and (4), the particle swarm optimization search algorithm is used to solve for f. D (y,μ,σ 2 Unknown parameters μ and σ 2 :

[0084]

[0085]

[0086] Get f D (y,μ,σ 2 The function is as follows:

[0087]

[0088] For a specific transformer, the dissolved hydrogen (H2) content in its oil is x0. The failure probability F of this transformer can be calculated using formula (6):

[0089]

[0090] 1) Differences in voltage levels

[0091] The probability of failure varies across different voltage levels. Therefore, in the above solution process, the selection of sample sets A and B needs to consider the differences in voltage levels. Transformers with voltage levels of 330kV and above have high requirements for the quality of insulating oil due to their high operating voltage, and the requirements for the values ​​of characteristic components and gas content in the oil are also high. Since online monitoring uses highly sensitive sensors for real-time monitoring, the measurement data may be significantly interfered with due to electromagnetic radiation and other factors as the voltage level increases. Furthermore, because the sampling frequency increases with the voltage level, the aging rate of consumables such as carrier gas and chromatographic columns accelerates, leading to abnormal online monitoring data.

[0092] The most convenient way to solve this problem is to perform hierarchical statistics. Select samples A and B from sets of transformers at different voltage levels, and in each set, count the total number of transformers n and the number of transformers with severe insulation defects m. Then, calculate the probability density distribution function f for the fault threshold at different voltage levels. D (y,μ,σ 2 For a specific transformer, the first fault probability F of the transformer is calculated using formula (6) to achieve differentiated early warning based on voltage level.

[0093] 2) Differences in operating temperature

[0094] During transformer operation, electrical, thermal, and mechanical stresses are generated due to factors such as excessively high operating temperatures. This leads to a decrease in the inter-turn insulation performance of the windings, and in severe cases, complete insulation breakdown, resulting in an inter-turn short-circuit fault. Therefore, the impact of operating temperature on the failure probability of power equipment cannot be ignored. However, actual measured data on operating temperature are difficult to obtain; only a rough distribution can be obtained from ambient temperature and operating conditions. It is impossible to statistically solve for the accurate fault threshold probability density distribution function f. D (y,μ,σ 2 Differentiation can be achieved through this method.

[0095] The inventors proposed a method to change the stress value using a correction coefficient, assuming the fault threshold probability density distribution function f D The functional form of (y,μ,σ2) remains unchanged from the expected value μ, with the introduction of a correction coefficient k. D This makes the standard deviation k Dσ, by changing the flatness of the distribution function, alters the size of the interference region. Through inverse fitting, the relationship between F and σ, along with the parameter table, is obtained as follows:

[0096] As ambient temperature rises, the average withstand strength of electrical equipment decreases, and the stress (fault threshold) corresponding to this strength also decreases accordingly. Therefore, we can assume that the probability density distribution function f of the fault threshold D is... D (y,μ,σ 2 The standard deviation σ remains constant, while the mean μ decreases, and its temperature coefficient k T As shown in the following formula:

[0097]

[0098] Where T max T is the maximum deterioration limit specified in the industry standard. D The temperature reference value is specified in the industry standard, t is the measured temperature, and the unit is ℃; a is a constant. In practical applications, the specific value to be taken needs to be analyzed and calculated based on expert opinions for each state quantity, and feedback adjustments should be made in application practice in order to obtain the optimal value.

[0099] The corrected failure probability function is as follows:

[0100]

[0101] Although obtaining the distribution function accurately is difficult, the differences caused by temperature are not negligible. This method of introducing a correction coefficient can effectively solve this type of problem by changing the parameters to adjust the fault threshold probability density distribution function f. D (y,μ,σ 2 This will achieve the goal of differentiated early warning.

[0102] (2) Calculation of differentiated failure probability based on service life

[0103] The failure probability based on the intensity-interference model is obtained from online monitoring state variables. However, the online monitoring-related defect types are only a part of the defect types. For failure probabilities corresponding to other defect types besides those related to online monitoring, this invention considers runtime. Generally, early-stage operation conforms to the law of accidental failure; later-stage operation conforms to the law of aging failure. Therefore, differentiated early warning can be achieved by utilizing different runtimes.

[0104] The defect data analyzed in this invention comes from transformers in a provincial power grid in my country, covering all 110kV and above voltage levels across the province, spanning from 2000 to 2019. In reliability theory, time-truncation tests and fixed-number truncation tests are commonly used to obtain failure rate distributions or lifetime distributions. Time-truncation tests involve recording the time of failure for each device within a defined time period for a given sample set, and then using theoretical formulas to calculate parameters such as the average lifetime of the devices in that sample set. Different operating years of transformers meet the requirements for time-truncation test data; therefore, transformers with the same test period are grouped into one sample set, i.e., transformers put into operation in each year constitute one sample set. The sample sets are named S1-S10 sequentially. Each sample set corresponds to one time-truncation test from the year of commissioning to 2019. Details of the sample sets are shown in Table 1, where the truncation rate refers to the proportion of samples that did not fail during the test period to the total number of samples, and is closely related to the confidence interval of the failure rate calculation results.

[0105] Table 1

[0106]

[0107] It is undeniable that there are differences in the failure probabilities of different components. In order to make the failure probability calculation more precise, the equipment is broken down into different components, the differentiated failure rates of each component based on the service life are calculated separately, and then they are integrated through a series model.

[0108] The parameters in a distribution function (such as m and t0 in a Weibull distribution) need to be obtained from experimental data. The most common method for estimating the parameters of a distribution function is the maximum likelihood method. Proposed by the British scientist Fisher, the maximum likelihood method is based on the idea that the probability of a sample occurring is maximized within a given random distribution. When the sample follows a certain random distribution but the specific distribution parameters are unknown, the method seeks the extreme value of the parameter that maximizes the probability of the sample occurring and uses this extreme value as an estimate of the distribution parameters.

[0109] This invention models the S1-S10 sample set based on the Weibull distribution function. The maximum likelihood method is then used for parameter estimation, yielding shape and scale parameters, as shown in Table 2. The numbers in parentheses in the table represent the 95% confidence intervals of the parameter estimates.

[0110] Table 2

[0111] Sample set m estimate m confidence interval t estimate <![CDATA[t0 confidence interval]]> S1 2.80 [2.26,3.45] 12.17 [10.97,13.50] S2 2.64 [2.25,3.10] 11.41 [10.51,12.37] S3 1.84 [1.55,2.18] 11.98 [10.70,13.41] S4 1.50 [1.27,1.76] 11.99 [10.52,13.65] S5 1.29 [1.10,1.51] 14.99 [13.00,17.33] S6 1.21 [1.02,1.42] 15.10 [12.87,17.70] S7 1.04 [0.88,1.22] 15.18 [12.68,18.19] S8 0.80 [0.69,0.94] 13.04 [10.53,16.15] S9 0.81 [0.71,0.95] 15.28 [12.42,18.79] S10 1.00 [0.85,1.17] 16.00 [13.17,19.45]

[0112] Transformer components are generally divided into five parts during current maintenance: the main body, non-electrical protection, bushings, tap changers, and the cooler system. The distribution ratio of 1096 faulty components in sample transformers S1-S10 was statistically analyzed, and the results are as follows: Figure 3 As shown.

[0113] The Weibull distribution provides a good fit for modeling transformer failure times, and the Weibull function model yields good results in cost analysis of transformers. The cumulative failure probability distribution function of the two-parameter Weibull distribution is shown in Equation 8. Based on Equation 8 and the distribution parameters in Table 3, the failure probabilities for different years are calculated, resulting in failure probability curves that vary with age. In this invention, it is assumed that failures between components are uncorrelated, and the equipment failure probability is equal to the sum of the probabilities of each component. The failure probabilities of equipment components are adjusted according to the distribution ratio of the failed components. Taking sample S6 as an example, the calculation results are as follows: Figure 4 As shown in the figure. By comparing the statistical results with actual data, it was found that the trend and magnitude of the proportionally calculated failure rate over the years are similar to the actual results.

[0114]

[0115] The warning levels of the power equipment under test are obtained based on the first, second, or third failure probabilities, as shown in Table 3.

[0116] Table 3

[0117]

[0118] Therefore, this application proposes a differentiated early warning method for power equipment based on fault probability. The method calculates the fault probability using a strength-stress interference model and achieves differentiated early warning by changing the parameters of the distribution function (i.e., the stress value). For fault probabilities corresponding to types of defects other than those monitored online, runtime is considered, making the early warning more comprehensive and accurate. This contributes to improving the accuracy and scientific rigor of the early warning system.

[0119] Exemplary device

[0120] Figure 5 This is a schematic diagram of the structure of a power equipment differentiated early warning device based on fault probability provided in an exemplary embodiment of the present invention. Figure 5 As shown, the device 500 includes:

[0121] The acquisition module 510 is used to acquire the online monitoring data of the power equipment under test;

[0122] The first determining module 520 is used to calculate the first fault probability of the power equipment under test based on the voltage level of the power equipment under test and using the probability density distribution function of the fault threshold under the pre-established voltage level, when the online monitoring quantity is distinguished according to different operating conditions, and to determine the warning level of the power equipment under test based on the first fault probability.

[0123] The second determining module 530 is used to calculate the second fault probability of the power equipment under test based on the ambient temperature of the power equipment under test and the corresponding correction coefficient under that ambient temperature, through a corrected fault probability function, and to determine the warning level of the power equipment under test based on the second fault probability when the online monitoring quantity is not distinguished according to different operating conditions.

[0124] Optionally, the device 500 also includes:

[0125] The third determination module is used to determine the failure probability of each component of the power equipment under test based on the failure probability curve of each component of the power equipment under test with the change of the years when the online monitoring data of the power equipment under test cannot be obtained, and to determine the third failure probability of the power equipment based on the failure probability of each component of the power equipment with the years and the preset ratio.

[0126] The fourth determination module is used to determine the early warning level of the power equipment under test based on the third fault probability.

[0127] Optionally, module 510 includes:

[0128] The first acquisition submodule is used to monitor dissolved gas in oil online when the power equipment under test is a transformer.

[0129] The second acquisition submodule is used to monitor SF6 gas moisture and pressure online when the power equipment under test is a GIS switch.

[0130] The third acquisition submodule is used to monitor the total current and resistive current of the online monitoring device when the power equipment under test is a metal oxide surge arrester.

[0131] Optionally, the probability density distribution function of the fault probability threshold at different voltage levels is:

[0132]

[0133] Where, σ D f is the probability density distribution function at a certain voltage level. D Standard deviation, μ D f is the probability density distribution function at a certain voltage level. D The mean value of x0 is the value of the online monitoring quantity, and y is the fault threshold of the power equipment under test.

[0134] Optionally, the modified failure probability function is as follows:

[0135]

[0136] in

[0137]

[0138] Among them, T max T is the maximum deterioration limit specified in the industry standard. D The temperature reference values ​​are those specified in the industry standard, where t is the measured temperature in °C, a is a constant, and σ is the temperature value specified in the standard. D f is the probability density distribution function at a certain voltage level. D Standard deviation, μ D f is the probability density distribution function at a certain voltage level. D The mean value of x0 is the value of the online monitoring quantity, and y is the fault threshold of the power equipment under test.

[0139] Optionally, the device 500 also includes:

[0140] The fifth determination module is used to model the online state variables of historical power equipment using a two-parameter Weibull distribution, and to determine the parameter data of each component of the power equipment at different ages.

[0141] The sixth determination module is used to determine the failure probability curve of each component of the power equipment as it changes with age, based on parameter data of each component at different ages.

[0142] Exemplary electronic devices

[0143] Figure 6 This is the structure of an electronic device provided in an exemplary embodiment of the present invention. For example... Figure 6 As shown, the electronic device 60 includes one or more processors 61 and a memory 62.

[0144] The processor 61 may be a central processing unit (CPU) or other form of processing unit with data processing and / or instruction execution capabilities, and may control other components in the electronic device to perform desired functions.

[0145] The memory 62 may include one or more computer program products, which may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may include, for example, random access memory (RAM) and / or cache memory. The non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium, and the processor 61 may execute the program instructions to implement the methods of the software programs of the various embodiments of the present invention described above, and / or other desired functions. In one example, the electronic device may also include an input device 63 and an output device 64, these components being interconnected via a bus system and / or other forms of connection mechanisms (not shown).

[0146] In addition, the input device 63 may also include, for example, a keyboard, a mouse, etc.

[0147] The output device 64 can output various information to the outside. The output device 64 may include, for example, a display, a speaker, a printer, and a communication network and its connected remote output devices, etc.

[0148] Of course, for the sake of simplicity, Figure 6 Only some of the components of the electronic device relevant to the present invention are shown, omitting components such as buses, input / output interfaces, etc. In addition, the electronic device may include any other suitable components depending on the specific application.

[0149] Exemplary computer program products and computer-readable storage media

[0150] In addition to the methods and apparatus described above, embodiments of the present invention may also be computer program products, which include computer program instructions that, when executed by a processor, cause the processor to perform the steps of the methods according to various embodiments of the present invention described in the "Exemplary Methods" section above.

[0151] The computer program product can be written in any combination of one or more programming languages ​​to perform the operations of the embodiments of the present invention. The programming languages ​​include object-oriented programming languages ​​such as Java and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on the user's computing device, partially on the user's computing device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0152] Furthermore, embodiments of the present invention may also be computer-readable storage media storing computer program instructions thereon, which, when executed by a processor, cause the processor to perform the steps of the methods for information mining of historical change records according to various embodiments of the present invention as described in the "Exemplary Methods" section above.

[0153] The computer-readable storage medium may be any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or any combination thereof. More specific examples (a non-exhaustive list) of readable storage media include: an electrical connection having one or more wires, a portable disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof.

[0154] The basic principles of the present invention have been described above with reference to specific embodiments. However, it should be noted that the advantages, benefits, and effects mentioned in the present invention are merely examples and not limitations, and should not be considered as essential features of each embodiment of the present invention. Furthermore, the specific details disclosed above are for illustrative and facilitative purposes only, and are not limitations. These details do not limit the present invention to the necessity of employing the aforementioned specific details.

[0155] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For system embodiments, since they largely correspond to method embodiments, the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments.

[0156] The block diagrams of devices, systems, devices, and systems involved in this invention are merely illustrative examples and are not intended to require or imply that they must be connected, arranged, or configured in the manner shown in the block diagrams. As those skilled in the art will recognize, these devices, systems, devices, and systems can be connected, arranged, and configured in any manner. Words such as “comprising,” “including,” “having,” etc., are open-ended terms meaning “including but not limited to,” and are used interchangeably with them. The terms “or” and “and” as used herein refer to the terms “and / or,” and are used interchangeably with them unless the context clearly indicates otherwise. The term “such as” as used herein refers to the phrase “such as but not limited to,” and is used interchangeably with it.

[0157] The methods and systems of the present invention may be implemented in many ways. For example, they may be implemented by software, hardware, firmware, or any combination of software, hardware, and firmware. The above-described order of steps for the methods is for illustrative purposes only, and the steps of the methods of the present invention are not limited to the order specifically described above unless otherwise specifically stated. Furthermore, in some embodiments, the present invention may also be implemented as a program recorded on a recording medium, the program comprising machine-readable instructions for implementing the methods according to the present invention. Thus, the present invention also covers recording media storing programs for performing the methods according to the present invention.

[0158] It should also be noted that in the systems, apparatus, and methods of the present invention, the components or steps can be disassembled and / or recombined. These disassemblies and / or recombinations should be considered equivalents of the present invention. The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use the invention. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein can be applied to other aspects without departing from the scope of the invention. Therefore, the invention is not intended to be limited to the aspects shown herein, but rather to be carried out within the widest scope consistent with the principles and novel features disclosed herein.

[0159] The above description has been given for purposes of illustration and description. Furthermore, this description is not intended to limit the embodiments of the invention to the forms disclosed herein. Although numerous exemplary aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, alterations, additions, and sub-combinations therein.

Claims

1. A power equipment differentiated early warning method based on failure probability, characterized in that, include: Acquire online monitoring data of the power equipment under test; When the online monitoring quantities are distinguished according to different operating conditions, the first fault probability of the power equipment under test is calculated based on the voltage level of the power equipment under test using the probability density distribution function of the fault threshold under the voltage level that is established in advance, and the warning level of the power equipment under test is determined based on the first fault probability. When the online monitoring quantities are not differentiated according to different operating conditions, the second fault probability of the power equipment under test is calculated by using the corrected fault probability function based on the ambient temperature of the power equipment under test and the correction coefficient corresponding to that ambient temperature, and the warning level of the power equipment under test is determined based on the second fault probability. In the absence of online monitoring data of the power equipment under test, the failure probability of each component of the power equipment under test is determined according to the failure probability curve of each component of the power equipment under test as a function of years, and the third failure probability of the power equipment is determined according to the failure probability of each component of the power equipment under test as a function of years and a preset ratio. The warning level of the power equipment under test is determined based on the third fault probability. The probability density distribution function of the fault probability threshold at different voltage levels is: wherein, σ D a standard deviation of the probability density distribution function for a voltage level, f D μ D a mean value of the probability density distribution function for a voltage level, f D x 0 a value of the online monitoring quantity, y a failure threshold of the power equipment to be measured.​​ The corrected fault probability function is as follows: in in, T max This is the maximum deterioration limit specified in the industry standard. T D The temperature precaution value is specified in the industry standard. t These are measured temperatures, all in °C, and 'a' is a constant. σ D The probability density distribution function at a certain voltage level f D standard deviation μ D The probability density distribution function at a certain voltage level f D The mean, x 0 The value is the online monitoring quantity. y The fault threshold of the power equipment under test; The method further includes: The online state variables of historical power equipment are modeled using a two-parameter Weibull distribution to determine the parameter data of each component of the power equipment at different ages. Based on the parameter data of each component of the power equipment at different ages, the failure probability curve of each component of the power equipment as it changes with age is determined.

2. The method of claim 1, wherein, The operations for obtaining online monitoring data of the power equipment under test include: When the electrical equipment under test is a transformer, the online monitoring quantity is dissolved gas in oil; When the power equipment under test is a GIS switch, the online monitoring quantity is SF6 gas moisture and pressure; When the power equipment under test is a metal oxide surge arrester, the online monitoring equipment is a total current and resistive current device.

3. A device for differentiated early warning of power equipment based on failure probability, for implementing the method of any one of claims 1-2, characterized in that, include: The acquisition module is used to acquire the online monitoring data of the power equipment under test; The first determining module is used to calculate the first fault probability of the power equipment under test based on the voltage level of the power equipment under test, using a pre-established probability density distribution function of the fault threshold under the voltage level, when the online monitoring quantity is distinguished according to different operating conditions, and to determine the warning level of the power equipment under test based on the first fault probability. The second determining module is used to calculate the second fault probability of the power equipment under test based on the ambient temperature of the power equipment under test and the corresponding correction coefficient at the ambient temperature, and to determine the warning level of the power equipment under test based on the second fault probability, when the online monitoring quantity is not distinguished according to different operating conditions.

4. The apparatus of claim 3, wherein, Also includes: The third determining module is used to determine the failure probability of each component of the power equipment under test based on the failure probability curve of each component of the power equipment under test changing with the years when the online monitoring quantity of the power equipment under test cannot be obtained, and to determine the third failure probability of the power equipment based on the failure probability of each component of the power equipment under test and a preset ratio. The fourth determining module is used to determine the warning level of the power equipment under test based on the third fault probability.

5. The apparatus of claim 3, wherein, The acquisition module includes: When the electrical equipment under test is a transformer, the online monitoring quantity is dissolved gas in oil; When the power equipment under test is a GIS switch, the online monitoring quantity is SF6 gas moisture and pressure; When the power equipment under test is a metal oxide surge arrester, the online monitoring equipment is a total current and resistive current device.

6. The apparatus of claim 3, wherein, The probability density distribution function of the fault probability threshold at different voltage levels is: wherein, σ D a standard deviation of the probability density distribution function for a voltage level, f D μ D a mean value of the probability density distribution function for a voltage level, f D x 0 a value of the online monitoring quantity, y a failure threshold of the power equipment to be measured.​​ 7. The apparatus of claim 3, wherein, The corrected fault probability function is as follows: in in, T max This is the maximum deterioration limit specified in the industry standard. T D The temperature precaution value is specified in the industry standard. t These are measured temperatures, all in °C, and 'a' is a constant. σ D The probability density distribution function at a certain voltage level f D standard deviation μ D The probability density distribution function at a certain voltage level f D The mean, x 0 The value is the online monitoring quantity. y The fault threshold of the power equipment under test.

8. The apparatus of claim 3, wherein, Also includes: The online state variables of historical power equipment are modeled using a two-parameter Weibull distribution to determine the parameter data of each component of the power equipment at different ages. Based on the parameter data of each component of the power equipment at different ages, the failure probability curve of each component of the power equipment as it changes with age is determined.

9. A computer-readable storage medium, characterized in that, The storage medium stores a computer program for performing the method described in any one of claims 1-2.

10. An electronic device, comprising: The electronic device includes: processor; Memory used to store the processor's executable instructions; The processor is configured to read the executable instructions from the memory and execute the instructions to implement the method described in any one of claims 1-2.

Images