Abnormality alarm method and device for distribution network equipment and storage medium

Abstract

The invention discloses an abnormity alarm method and equipment for distribution network equipment, and a storage medium. The method comprises the following steps: determining to-be-detected distribution network equipment in a power grid; constructing a Gaussian mixture model for the distribution network equipment; initializing an abnormal threshold value for judging an abnormal state for the distribution network equipment according to the Gaussian mixture model; inputting real-time target operation parameters of the distribution network equipment into the Gaussian mixture model for processing to obtain target edge probability density; comparing the target marginal probability density with an abnormal threshold value to judge the real-time abnormal state of the distribution network equipment; and executing an alarm operation on the distribution network equipment according to the abnormal state. According to the embodiment of the invention, health state evaluation of different types of distribution network equipment under different types of operation parameters is realized without depending on data quality, the operation characteristics of the distribution network equipment can be better represented by using the Gaussian mixture model, abnormal defects slowly occurring in the distribution network equipment are effectively captured, and the reliability of the distribution network equipment is improved. And the abnormity diagnosis conclusion has reference and analytic performance.

Description

Technical Field

[0001] The present invention relates to the technical field of power grids, and in particular to an abnormal alarm method, device and storage medium for distribution network equipment. Background Art

[0002] In the context of stable operation of the power grid, it is required to conduct a full life cycle health status assessment of key distribution network equipment in the power grid and issue alarms when abnormalities occur. This will not only help to promptly discover and prevent potential faults and performance degradation problems, but also effectively avoid sudden power outages, thereby extending the service life of distribution network equipment and reducing maintenance costs.

[0003] The current abnormal alarm method is to adopt an evaluation algorithm based on machine learning and big data analysis, build an evaluation model by deeply mining and analyzing the historical operation data of the equipment, and realize dynamic evaluation and prediction of distribution network equipment.

[0004] However, this method relies heavily on high-quality and comprehensive data, while the distribution network equipment in the power grid is widely distributed, which can easily lead to omissions when monitoring the distribution network equipment, affecting the reliability and accuracy of abnormal alarms for the distribution network equipment. Summary of the invention

[0005] In view of this, the present invention provides an abnormal alarm method, device and storage medium for distribution network equipment, so as to improve the reliability and accuracy of abnormal alarm for distribution network equipment.

[0006] A first aspect of the present invention provides an abnormal alarm method for a distribution network device, comprising:

[0007] Determine the distribution network equipment to be detected in the power grid;

[0008] Constructing a Gaussian mixture model for the distribution network equipment;

[0009] Initializing an abnormal threshold for determining an abnormal state of the distribution network device according to the Gaussian mixture model;

[0010] The real-time target operating parameter input of the distribution network equipment is processed according to the Gaussian mixture model to obtain the target edge probability density;

[0011] Comparing the target edge probability density with the abnormal threshold to determine the real-time abnormal state of the distribution network equipment;

[0012] An alarm operation is performed on the distribution network device according to the abnormal state.

[0013] A second aspect of the present invention provides an abnormal alarm device for distribution network equipment, comprising:

[0014] A distribution network equipment determination module, used to determine the distribution network equipment to be detected in the power grid;

[0015] A Gaussian mixture model construction module, used to construct a Gaussian mixture model for the distribution network equipment;

[0016] An abnormal threshold initialization module, used to initialize the abnormal threshold for determining an abnormal state of the distribution network device according to the Gaussian mixture model;

[0017] A target edge probability density calculation module is used to input the real-time target operating parameters of the distribution network equipment into the Gaussian mixture model for processing to obtain the target edge probability density;

[0018] An abnormal state determination module, used for comparing the target edge probability density with the abnormal threshold value to determine the real-time abnormal state of the distribution network equipment;

[0019] An alarm operation execution module is used to execute an alarm operation on the distribution network device according to the abnormal state.

[0020] A third aspect of the present invention provides an electronic device, the electronic device comprising:

[0021] at least one processor; and

[0022] a memory communicatively connected to the at least one processor; wherein,

[0023] The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the abnormal alarm method for distribution network equipment as described in the first aspect above.

[0024] A fourth aspect of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the abnormal alarm method for the distribution network device as described in the first aspect above is implemented.

[0025] A fifth aspect of the present invention provides a computer program product, the computer program product comprising a computer program, and when the computer program is executed by a processor, the abnormal alarm method for the distribution network device as described in the first aspect above is implemented.

[0026] In this embodiment, the distribution network equipment to be detected is determined in the power grid; a Gaussian mixture model is constructed for the distribution network equipment; an abnormal threshold for determining the abnormal state of the distribution network equipment is initialized according to the Gaussian mixture model; the real-time target operating parameters of the distribution network equipment are input into the Gaussian mixture model for processing to obtain the target edge probability density; the target edge probability density is compared with the abnormal threshold to determine the real-time abnormal state of the distribution network equipment; and an alarm operation is performed on the distribution network equipment according to the abnormal state. This embodiment constructs a multi-time scale distribution network equipment health status assessment mechanism with strong applicability and versatility, forms an abnormal monitoring and diagnosis process based on the field measured operating parameters, and realizes the health status assessment of different types of distribution network equipment under different types of operating parameters without relying on data quality. The Gaussian mixture model can better characterize the operating characteristics of the distribution network equipment, effectively capture the abnormal defects that occur slowly inside the distribution network equipment, and the abnormal diagnosis conclusion is more referenceable and analyzable, which improves the recognition accuracy and response speed of the abnormal operating state of the distribution network equipment with high concealment and strong randomness.

[0027] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0029] Figure 1 This is a flow chart of an abnormal alarm method for distribution network equipment provided in Example 1 of the present invention.

[0030] Figure 2 It is a structural diagram of an abnormal alarm device for distribution network equipment provided in Embodiment 2 of the present invention.

[0031] Figure 3 It is a structural schematic diagram of an electronic device provided in Embodiment 3 of the present invention. DETAILED DESCRIPTION

[0032] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0033] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present invention described herein can cover sequential implementations other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0034] Embodiment 1

[0035] See also Figure 1 , shows a flow chart of an abnormal alarm method for a distribution network device provided by the first embodiment of the present invention, the method can be executed by an abnormal alarm device of the distribution network device, the abnormal alarm device of the distribution network device can be implemented in the form of hardware and / or software, and the abnormal alarm device of the distribution network device can be configured in an electronic device. Figure 1 As shown, the method includes:

[0036] Step 101: determine a distribution network device to be detected in the power grid.

[0037] In practical applications, the distribution network equipment in the power grid includes the following types:

[0038] 1. Distribution transformer: A distribution transformer is a device that converts AC power of one voltage and current into AC power of another voltage and current of the same frequency. It is mainly composed of the body, voltage regulating device, oil tank and cooling device, protective device, insulating sleeve and other components. The distribution transformer plays the role of voltage conversion in the distribution network. It is usually not suitable for overload operation and should be operated economically. The maximum load current should not be less than 60% of the rated current.

[0039] 2. Reactive power compensation device: Reactive power compensation devices are used to improve the power factor of the power system and reduce line losses. They are usually installed in places where the load is concentrated or at 3 / 4 of the line, and use fixed capacity wiring. Low-voltage reactive power compensation equipment is often installed at the outlet of the pole-mounted distribution transformer.

[0040] 3. Lightning arrester: Lightning arrester is used to protect electrical equipment from damage caused by lightning overvoltage or operating overvoltage. Metal oxide lightning arresters (such as zinc oxide lightning arresters) are divided into two categories: gapless and with series gap. Gapless zinc oxide lightning arresters are widely used due to their excellent operating performance.

[0041] 4. Insulated wire: Insulated wires are covered with an insulating layer to reduce short circuits and power outages caused by foreign objects, as well as the risk of personal electric shock and casualties. Insulated tension clamps are used to fix insulated wires to ensure that they can withstand tension.

[0042] 5. Grounding ring: The grounding ring is used to test electricity and ground the lines where insulated conductors are installed to ensure safe operation.

[0043] 6. Box transformers and box-type substations: With the development of urbanization, the density of electricity load increases. Box transformers and box-type substations have become important power distribution equipment, providing single-ring network power supply technology to meet the environmental landscape requirements of major urban roads.

[0044] 7. Cable branch box: Cable branch box is used for cable tapping and branch connection. It is often used in urban power distribution systems to improve power supply reliability and flexibility.

[0045] These devices work together in the distribution network to ensure the efficient and safe transmission and distribution of electricity.

[0046] In this embodiment, some key distribution network equipment in the power grid can be screened to detect the health status, and an alarm can be issued when an abnormality is found.

[0047] Step 102: construct a Gaussian mixture model for the distribution network equipment.

[0048] In this embodiment, the distribution network equipment whose health status is to be detected is taken as the object, and suitable operating parameters are selected to construct a data set for modeling, thereby constructing a Gaussian Mixed Model (GMM) of multi-dimensional joint distribution.

[0049] The operating parameters include voltage, current, temperature and other parameters, which can be a single parameter or a combination of multiple parameters.

[0050] In practical applications, GMM has high precision in describing random variables. It is a method that uses Gaussian probability density function (normal distribution curve) to accurately quantify things. It is a model that decomposes things into several parts based on Gaussian probability density function (normal distribution curve).

[0051] First, the superposition property indicates that GMM can characterize variables that obey arbitrary distributions, and there is no restriction on the dimension of the variables. The large number of variables can solve problems such as the large variety of power grid operation parameters, strong randomness and complex probability distribution.

[0052] Secondly, in addition to presenting complete probability distribution characteristics as a whole, GMM's linear invariance, marginal probability invariance, conditional probability invariance and the approximate analyzability of the cumulative distribution function indicate that GMM has strong analyzability. It can be flexibly integrated with knowledge-driven models using its analyzability, and has strong applicability and versatility for different applications.

[0053] In view of this, in the power grid, a GMM with random variable distribution of arbitrary dimensions is introduced to detect the health status of distribution network equipment.

[0054] Step 103: Initialize an abnormal threshold for determining an abnormal state of the distribution network device according to the Gaussian mixture model.

[0055] In this embodiment, the abnormal threshold for determining an abnormal state of the distribution network device may be adaptively initialized according to the Gaussian mixture model.

[0056] In a specific implementation, multiple abnormality levels for characterizing abnormal states may be constructed for the distribution network equipment, and there are certain differences in the abnormal states represented by different abnormality levels.

[0057] Exemplarily, the abnormality levels include a first level, a second level, and a third level.

[0058] Among them, the abnormal state represented by the first level is better than the abnormal state represented by the second level, and the abnormal state represented by the second level is better than the abnormal state represented by the third level.

[0059] In this example, the first level may be called a general abnormality, the second level may be called a severe abnormality, and the third level may be called an emergency abnormality.

[0060] The operating parameters of the distribution network equipment when it is in an abnormal state are collected and recorded as historical operating parameters.

[0061] The historical operating parameters are input into the Gaussian mixture model for processing to obtain the marginal probability density, which is recorded as the historical marginal probability density. Based on the historical marginal probability density, anomaly thresholds are set for each anomaly level according to the historical marginal probability density, where the anomaly threshold can be the upper limit value, lower limit value, etc. of each anomaly level.

[0062] Exemplarily, when the abnormality level includes a first level, a second level, and a third level, the abnormality threshold includes a first boundary threshold, a second boundary threshold, and a third boundary threshold.

[0063] On the one hand, the historical edge probability density with the smallest value is screened out from all historical edge probability densities, and the minimum value between the preset first probability threshold boundary and the historical edge probability density with the smallest value is taken as the first boundary threshold of the first level. At this time, the first boundary threshold is the upper limit value of the first level.

[0064] On the other hand, historical edge probability densities that are greater than a preset first probability threshold boundary and less than or equal to a preset second probability threshold boundary are screened out from all historical edge probability densities as first candidate values.

[0065] The maximum value among all the first candidate values ​​is taken as the second boundary threshold of the second level. At this time, the second boundary threshold is the upper limit value of the second level, and the first boundary threshold is the lower limit value of the second level.

[0066] On the other hand, historical edge probability densities that are greater than a preset second probability threshold boundary and less than or equal to a preset third probability threshold boundary are screened out from all historical edge probability densities as second candidate values.

[0067] The maximum value among all the second candidate values ​​is taken as the third boundary threshold of the third level. At this time, the third boundary threshold is the upper limit value of the third level, and the second boundary threshold is the lower limit value of the third level.

[0068] Among them, the first probability threshold boundary is smaller than the second probability threshold boundary, and the second probability threshold boundary is smaller than the third probability threshold boundary.

[0069] In this example, the anomaly threshold can be expressed as:

[0070] T d =min(a,P min );

[0071] T s =max(a<P≤b);

[0072] T g =max(b<P≤c).

[0073] Among them, T d is the first boundary threshold, T s is the second boundary threshold, T g is the third boundary threshold, P is the edge probability density, P minis the edge probability density with the minimum value, a is the first probability threshold boundary, b is the second probability threshold boundary, and c is the third probability threshold boundary.

[0074] a, b, and c can be customized and adjusted according to the actual situation of the distribution equipment in the power grid, for example, a=0.01, b=0.05, and c=0.1.

[0075] Of course, the above-mentioned abnormality levels and abnormality thresholds are only used as examples. When implementing this embodiment, other abnormality levels and abnormality thresholds can be set according to actual conditions. For example, five abnormality levels and five abnormality thresholds can be set, and this embodiment does not limit this. In addition, in addition to the above-mentioned abnormality levels and abnormality thresholds, those skilled in the art can also adopt other abnormality levels and abnormality thresholds according to actual needs, and this embodiment does not limit this.

[0076] Step 104: input the real-time target operating parameters of the distribution network equipment into a Gaussian mixture model for processing to obtain the target edge probability density.

[0077] In this embodiment, the operating parameters of key distribution network equipment in the power grid can be collected in real time and recorded as target operating parameters. The target operating parameters are input into a Gaussian mixture model for processing to obtain edge probability density, which is recorded as target edge probability density.

[0078] Step 105: Compare the target edge probability density with the abnormal threshold to determine the real-time abnormal state of the distribution network equipment.

[0079] In this embodiment, the target edge probability density of the distribution network device may be compared with each abnormal threshold value, so as to determine the real-time abnormal state of the distribution network device.

[0080] Furthermore, multiple abnormality levels for characterizing abnormal states have been constructed in advance. Then, the target edge probability density of the distribution network equipment can be compared with the abnormal thresholds corresponding to each abnormality level. When the target edge probability density of the distribution network equipment is within the interval composed of the abnormal thresholds corresponding to a certain abnormal level, it can be determined that the real-time abnormal state of the distribution network equipment is the abnormal level.

[0081] Exemplarily, the abnormality levels include a first level, a second level, and a third level, and the abnormality thresholds include a first boundary threshold, a second boundary threshold, and a third boundary threshold.

[0082] In this example, the target edge probability density of the distribution network device may be compared with the first boundary threshold, the second boundary threshold, and the third boundary threshold, respectively.

[0083] If the target edge probability density is less than or equal to the first boundary threshold, it is determined that the real-time abnormal state of the distribution network device is at the first level.

[0084] If the target edge probability density is greater than the first boundary threshold and less than or equal to the second boundary threshold, it is determined that the real-time abnormal state of the distribution network device is the second level.

[0085] If the target edge probability density is greater than the second boundary threshold and less than or equal to the third boundary threshold, it is determined that the real-time abnormal state of the distribution network equipment is the third level.

[0086] Step 106: Perform an alarm operation on the distribution network equipment according to the abnormal state.

[0087] In this embodiment, the overall health status of the distribution network equipment can be evaluated based on one or more abnormal conditions. When a more obvious abnormality occurs in the distribution network equipment, an alarm operation is performed on the distribution network equipment. The alarm operation may include sound and light prompts, text message prompts, email prompts, instant messaging prompts, etc., to notify the operation and maintenance personnel to confirm the working condition of the distribution network equipment.

[0088] In a specific implementation, the frequency of the distribution network equipment being in the same abnormal level can be accumulated. At this time, a counter can be set for each abnormal level. The initial value of the counter is 0. When the distribution network equipment is at a certain abnormal level, the counter of the abnormal level accumulates 1. The counter is cleared when an alarm operation occurs.

[0089] Query the alarm threshold set for the same anomaly level. Different anomalies have different alarm thresholds.

[0090] Generally speaking, the abnormality level is negatively correlated with the alarm threshold, that is, the higher the abnormality level, the worse the health level and the smaller the alarm threshold. Conversely, the lower the abnormality level, the better the health level and the larger the alarm threshold.

[0091] Exemplarily, the abnormality levels include a first level, a second level, and a third level, and the abnormal state represented by the first level is better than the abnormal state represented by the second level, and the abnormal state represented by the second level is better than the abnormal state represented by the third level.

[0092] Then, the alarm threshold set for the first level is greater than the alarm threshold set for the second level, and the alarm threshold set for the second level is greater than the alarm threshold set for the third level.

[0093] For the same abnormality level, its frequency is compared with the alarm threshold.

[0094] If the frequency is less than the alarm threshold, the health status of the distribution network equipment is maintained.

[0095] If the frequency is greater than or equal to the alarm threshold, an alarm operation is performed on the distribution network device. The alarm operations of different abnormal levels may be the same or different, and this embodiment does not impose any limitation on this.

[0096] For example, let T d is the first boundary threshold, T s is the second boundary threshold, T g is the third boundary threshold, when the target edge probability density P is detected r When P r With T d , T s , T g Make a comparison.

[0097] If P r ≤T d , then the abnormal level of the distribution network equipment is determined to be the first level, and the frequency N of the first level d Accumulate 1, that is, N d =N d +1.

[0098] If T d <P r ≤T s , then the abnormal level of the distribution network equipment is determined to be the second level, and the frequency N of the second level s Accumulate 1, that is, N s =N s +1.

[0099] If T s <P r ≤T g , then the abnormal level of the distribution network equipment is determined to be the third level, and the frequency N of the third level g Accumulate 1, that is, N g =N g +1.

[0100] If N d ≥5 (alarm threshold), an alarm operation is triggered.

[0101] If N s ≥3 (alarm threshold), an alarm operation is triggered.

[0102] If N g =1 (alarm threshold), an alarm operation is triggered.

[0103] In one embodiment of the present invention, an alarm problem library may be constructed to maintain the working conditions of key distribution network equipment in the power grid.

[0104] When the operation and maintenance personnel verify the working conditions of the key distribution network equipment in the power grid, feedback information can be triggered. At this time, feedback information triggered by the abnormal status of the distribution network equipment can be received.

[0105] If the feedback information is correction information, the network distribution device is marked as normal, indicating that there is no abnormality in the network distribution device.

[0106] Then, when the Gaussian mixture model is updated subsequently, it will not be filtered out. As its probability of occurrence gradually increases, it will automatically change to a normal state (no abnormality). When it appears subsequently, it will not trigger an alarm, reducing the possibility of false alarms.

[0107] If it is verified to be an abnormal operating condition, it will be marked as abnormal and will be automatically filtered out when the Gaussian mixture model is updated later. The probability of its occurrence will not increase and an alarm will still be triggered the next time it occurs.

[0108] In this way, real abnormal alarm conditions are avoided, because the probability increases after a long period of data accumulation, gradually turning into normal conditions and reducing missed alarms.

[0109] If the feedback information is confirmation information, the process returns to step 102 and step 103 to re-construct the Gaussian mixture model for the distribution network equipment and to re-initialize the abnormal threshold for determining the abnormal state of the distribution network equipment based on the Gaussian mixture model.

[0110] In this way, each time a new monitoring point (i.e., distribution network equipment) is added, the edge probability density is recalculated to rollingly update the abnormal threshold and realize adaptive adjustment of the abnormal threshold. At this time, the abnormal level may float up or down. For example, the second level may adaptively change to the first level or the third level, effectively reducing unnecessary alarms.

[0111] In this embodiment, the distribution network equipment to be detected is determined in the power grid; a Gaussian mixture model is constructed for the distribution network equipment; an abnormal threshold for determining the abnormal state of the distribution network equipment is initialized according to the Gaussian mixture model; the real-time target operating parameters of the distribution network equipment are input into the Gaussian mixture model for processing to obtain the target edge probability density; the target edge probability density is compared with the abnormal threshold to determine the real-time abnormal state of the distribution network equipment; and an alarm operation is performed on the distribution network equipment according to the abnormal state. This embodiment constructs a multi-time scale distribution network equipment health status assessment mechanism with strong applicability and versatility, forms an abnormal monitoring and diagnosis process based on the field measured operating parameters, and realizes the health status assessment of different types of distribution network equipment under different types of operating parameters without relying on data quality. The Gaussian mixture model can better characterize the operating characteristics of the distribution network equipment, effectively capture the abnormal defects that occur slowly inside the distribution network equipment, and the abnormal diagnosis conclusion is more referenceable and analyzable, which improves the recognition accuracy and response speed of the abnormal operating state of the distribution network equipment with high concealment and strong randomness.

[0112] Embodiment 2

[0113] See also Figure 2 , shows a schematic diagram of the structure of an abnormal alarm device for a distribution network device provided by Embodiment 2 of the present invention. Figure 2 As shown, the device comprises:

[0114] A distribution network device determination module 201 is used to determine a distribution network device to be detected in the power grid;

[0115] A Gaussian mixture model building module 202, used to build a Gaussian mixture model for the distribution network device;

[0116] An abnormal threshold initialization module 203, used to initialize the abnormal threshold for determining an abnormal state of the distribution network device according to the Gaussian mixture model;

[0117] A target edge probability density calculation module 204 is used to process the real-time target operating parameters of the distribution network equipment according to the Gaussian mixture model to obtain a target edge probability density;

[0118] The abnormal state determination module 205 is used to compare the target edge probability density with the abnormal threshold to determine the real-time abnormal state of the distribution network device;

[0119] The alarm operation execution module 206 is used to execute an alarm operation on the distribution network device according to the abnormal state.

[0120] In one embodiment of the present invention, the abnormal threshold initialization module 203 includes:

[0121] An abnormality level construction module, used to construct a plurality of abnormality levels for characterizing abnormal states for the distribution network equipment;

[0122] A historical operation parameter collection module, used to collect historical operation parameters of the distribution network equipment when it is in an abnormal state;

[0123] A historical edge probability density calculation module, used for inputting the historical operating parameters into the Gaussian mixture model for processing to obtain the historical edge probability density;

[0124] The abnormality threshold setting module is used to set the abnormality threshold for each abnormality level according to the historical marginal probability density.

[0125] In one embodiment of the present invention, the abnormality level includes a first level, a second level, and a third level;

[0126] The abnormal state represented by the first level is better than the abnormal state represented by the second level, and the abnormal state represented by the second level is better than the abnormal state represented by the third level.

[0127] In one embodiment of the present invention, the abnormal threshold includes a first boundary threshold, a second boundary threshold and a third boundary threshold;

[0128] The abnormal threshold setting module is also used for:

[0129] Taking the minimum value between the preset first probability threshold boundary and the historical edge probability density with the minimum value as the first boundary threshold of the first level;

[0130] Filter out the historical edge probability density greater than a preset first probability threshold boundary and less than or equal to a preset second probability threshold boundary as a first candidate value;

[0131] Taking the maximum value among all the first candidate values ​​as the second boundary threshold of the second level;

[0132] Filter out the historical edge probability density that is greater than a preset second probability threshold boundary and less than or equal to a preset third probability threshold boundary as a second candidate value;

[0133] taking the maximum value among all the second candidate values ​​as the third boundary threshold of the third level;

[0134] Among them, the first probability threshold boundary is smaller than the second probability threshold boundary, and the second probability threshold boundary is smaller than the third probability threshold boundary.

[0135] In one embodiment of the present invention, the abnormal state determination module 205 is further used to:

[0136] If the target edge probability density is less than or equal to the first boundary threshold, determining that the real-time abnormal state of the distribution network device is the first level;

[0137] If the target edge probability density is greater than the first boundary threshold and less than or equal to the second boundary threshold, determining that the real-time abnormal state of the distribution network device is the second level;

[0138] If the target edge probability density is greater than the second boundary threshold and less than or equal to the third boundary threshold, it is determined that the real-time abnormal state of the distribution network device is the third level.

[0139] In one embodiment of the present invention, the alarm operation execution module 206 includes:

[0140] A frequency accumulation module, used for accumulating the frequency of the distribution network equipment being at the same abnormal level;

[0141] An alarm threshold query module, used to query the alarm threshold set for the same abnormality level;

[0142] The cumulative alarm module is used to perform an alarm operation on the distribution network device if the frequency is greater than or equal to the alarm threshold.

[0143] In one embodiment of the present invention, the abnormality level includes a first level, a second level, and a third level;

[0144] The alarm threshold set for the first level is greater than the alarm threshold set for the second level, and the alarm threshold set for the second level is greater than the alarm threshold set for the third level.

[0145] In one embodiment of the present invention, it also includes:

[0146] A feedback information receiving module, used to receive feedback information triggered by the abnormal state of the distribution network device; if the feedback information is correction information, the state marking module is executed; if the feedback information is confirmation information, the Gaussian mixture model construction module 202 and the abnormal threshold initialization module 203 are returned to execute;

[0147] The status marking module is used to mark the distribution network device as being in a normal state.

[0148] The abnormal alarm device for distribution network equipment provided in the embodiment of the present invention can execute the abnormal alarm method for distribution network equipment provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects for executing the abnormal alarm method for distribution network equipment.

[0149] Embodiment 3

[0150] See also Figure 3 , showing a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workbenches, personal digital assistants, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0151] like Figure 3As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0152] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0153] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The processor 11 executes the various methods and processes described above, such as the abnormal alarm method of the distribution network equipment.

[0154] In some embodiments, the abnormal alarm method of the distribution network device can be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the abnormal alarm method of the distribution network device described above can be executed. Alternatively, in other embodiments, the processor 11 can be configured to execute the abnormal alarm method of the distribution network device in any other appropriate manner (for example, by means of firmware).

[0155] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0156] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0157] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0158] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0159] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0160] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0161] Embodiment 4

[0162] An embodiment of the present invention further provides a computer program product, which includes a computer program. When the computer program is executed by a processor, the abnormal alarm method of the distribution network device provided by any embodiment of the present invention is implemented.

[0163] In the process of implementation, the computer program product can be written in one or more programming languages ​​or a combination thereof to perform the computer program code of the present invention, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (for example, using an Internet service provider to connect through the Internet).

[0164] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0165] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for abnormal alarm of distribution network equipment, characterized in that: include: Determine the distribution network equipment to be detected in the power grid; Constructing a Gaussian mixture model for the distribution network equipment; Initializing an abnormal threshold for determining an abnormal state of the distribution network device according to the Gaussian mixture model; The real-time target operating parameter input of the distribution network equipment is processed according to the Gaussian mixture model to obtain the target edge probability density; Comparing the target edge probability density with the abnormal threshold to determine the real-time abnormal state of the distribution network equipment; An alarm operation is performed on the distribution network device according to the abnormal state.

2. The method according to claim 1, characterized in that Initializing the abnormal threshold for determining the abnormal state of the distribution network device according to the Gaussian mixture model includes: Constructing a plurality of abnormal levels for characterizing abnormal states for the distribution network equipment; Collecting historical operating parameters of the distribution network equipment when it is in an abnormal state; Inputting the historical operating parameters into the Gaussian mixture model for processing to obtain historical marginal probability density; An abnormality threshold is set for each of the abnormality levels according to the historical marginal probability density.

3. The method according to claim 2, characterized in that The abnormality levels include the first level, the second level and the third level; The abnormal state represented by the first level is better than the abnormal state represented by the second level, and the abnormal state represented by the second level is better than the abnormal state represented by the third level.

4. The method according to claim 3, characterized in that The abnormal threshold includes a first boundary threshold, a second boundary threshold and a third boundary threshold; The setting of an abnormality threshold for each abnormality level according to the historical edge probability density includes: Taking the minimum value between the preset first probability threshold boundary and the historical edge probability density with the minimum value as the first boundary threshold of the first level; Filter out the historical edge probability density greater than a preset first probability threshold boundary and less than or equal to a preset second probability threshold boundary as a first candidate value; Taking the maximum value among all the first candidate values ​​as the second boundary threshold of the second level; Filter out the historical edge probability density that is greater than a preset second probability threshold boundary and less than or equal to a preset third probability threshold boundary as a second candidate value; taking the maximum value among all the second candidate values ​​as the third boundary threshold of the third level; Among them, the first probability threshold boundary is smaller than the second probability threshold boundary, and the second probability threshold boundary is smaller than the third probability threshold boundary.

5. The method according to claim 4, characterized in that The comparing the target edge probability density with the abnormal threshold to determine the real-time abnormal state of the distribution network device includes: If the target edge probability density is less than or equal to the first boundary threshold, determining that the real-time abnormal state of the distribution network device is the first level; If the target edge probability density is greater than the first boundary threshold and less than or equal to the second boundary threshold, determining that the real-time abnormal state of the distribution network device is the second level; If the target edge probability density is greater than the second boundary threshold and less than or equal to the third boundary threshold, it is determined that the real-time abnormal state of the distribution network device is the third level.

6. The method according to claim 2, characterized in that The performing an alarm operation on the distribution network device according to the abnormal state includes: Accumulating the frequency of the distribution network equipment being in the same abnormal level; Query the alarm threshold set for the same abnormality level; If the frequency is greater than or equal to the alarm threshold, an alarm operation is performed on the distribution network device.

7. The method according to claim 6, characterized in that The abnormality levels include the first level, the second level and the third level; The alarm threshold set for the first level is greater than the alarm threshold set for the second level, and the alarm threshold set for the second level is greater than the alarm threshold set for the third level.

8. The method according to any one of claims 1 to 7, characterized in that Also includes: Receiving feedback information triggered by an abnormal state of the distribution network device; If the feedback information is correction information, marking the distribution network device as a normal state; If the feedback information is confirmation information, the process returns to executing the step of constructing a Gaussian mixture model for the network distribution device, and initializing an abnormal threshold value for determining an abnormal state for the network distribution device according to the Gaussian mixture model.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the abnormal alarm method for distribution network equipment according to any one of claims 1 to 8.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the abnormal alarm method for distribution network equipment according to any one of claims 1 to 8 is implemented.

Images