Method, device and storage medium for determining health condition of user electricity meter

Abstract

The application relates to a health condition determination method, device and equipment of a user electric meter and a storage medium. The method comprises the following steps: obtaining first electric quantity data of a transformer area electric meter at each sampling moment in a target period and second electric quantity data of a user electric meter associated with the transformer area electric meter at each sampling moment; then, according to the first electric quantity data, the second electric quantity data and an electric quantity weight corresponding to each sampling moment, a state representation of the user electric meter at each sampling moment can be determined; and then, according to the state representation of the user electric meter at each sampling moment, the health condition of the user electric meter can be determined. The method does not need to introduce an additional monitoring device, and through sufficient analysis of the data of the transformer area electric meter and the user electric meter associated with the transformer area electric meter, i.e. the electric quantity data at each sampling moment in the target period, the health condition of the user electric meter can be accurately determined, and the monitoring of the health condition of the user electric meter is realized without increasing additional costs.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of computer, in particular to a health condition determination method and device of user electric meter, equipment and storage medium. BACKGROUND

[0002] The user electric meter is an important part of the smart grid, and the measurement result of the health condition of the user electric meter is the basis for the trade settlement of the power grid operation control and power supply and use. The measurement result of the health condition of the user electric meter is directly related to the safety of the power grid and whether the trade settlement is fair and reasonable, so it is crucial to ensure the normal operation of the user electric meter.

[0003] At present, the device capable of measuring the health condition of the user electric meter is additionally installed at the installation site of the user electric meter, so that the real-time remote monitoring of the health condition of the user electric meter can be realized, but this method will increase the additional cost, which needs to be improved. SUMMARY

[0004] Therefore, it is necessary to provide a health condition determination method and device of user electric meter, equipment and storage medium to realize the monitoring of the health condition of the user electric meter without increasing the additional cost.

[0005] In a first aspect, the present application provides a health condition determination method of user electric meter. The method comprises:

[0006] Obtaining first electric quantity data of the area electric meter at each sampling time in a target period, and second electric quantity data of the user electric meter associated with the area electric meter at each sampling time;

[0007] According to the first electric quantity data, the second electric quantity data and the electric quantity weight corresponding to each sampling time, determining the state representation of the user electric meter at each sampling time;

[0008] According to the state representation of the user electric meter at each sampling time, determining the health condition of the user electric meter.

[0009] In one of the embodiments, according to the first electric quantity data, the second electric quantity data and the electric quantity weight corresponding to each sampling time, determining the state representation of the user electric meter at each sampling time, comprises:

[0010] Determining the network loss of the distribution area corresponding to the area electric meter at each sampling time in the target period;

[0011] Removing the network loss from the first electric quantity data to obtain the third electric quantity data of the area electric meter at each sampling time;

[0012] According to the third electric quantity data, the second electric quantity data and the electric quantity weight corresponding to each sampling time, determining the state representation of the user electric meter at each sampling time.

[0013] In one of the embodiments, the network loss of the power distribution area corresponding to the area meter at each sampling time in the target period is determined, comprising:

[0014] According to the second power data, the first power data, and the line resistance of each power distribution line in the power distribution area corresponding to the area meter, the equivalent resistance of the power distribution area at each sampling time is determined.

[0015] According to the equivalent resistance, the first power data, and the current data of the area meter at each sampling time, the network loss of the power distribution area at each sampling time in the target period is determined.

[0016] In one of the embodiments, the state representation of the user meter at each sampling time is determined according to the third power data, the second power data, and the power weight corresponding to each sampling time, comprising:

[0017] According to the second power data and the power forgetting weight corresponding to each sampling time, the power covariance representation at each sampling time is determined.

[0018] According to the third power data, the second power data, and the power covariance representation, the state representation of the user meter at each sampling time is determined.

[0019] In one of the embodiments, the health status of the user meter is determined according to the state representation of the user meter at each sampling time in the target period, comprising:

[0020] According to the state representation of the user meter at each sampling time, a state curve of the user meter is drawn.

[0021] According to the state curve of the user meter, an analysis time is determined.

[0022] According to the state value corresponding to the analysis time, the health status of the user meter is determined.

[0023] In one of the embodiments, the analysis time is determined according to the state curve of the user meter, comprising:

[0024] According to the volatility of the state curve of the user meter, the analysis time is determined.

[0025] In a second aspect, the application further provides a health status determination device of a user meter. The device comprises:

[0026] A data acquisition module is configured to acquire the first power data of the area meter at each sampling time in the target period, and the second power data of the user meter associated with the area meter at each sampling time.

[0027] A state determination module is configured to determine the state representation of the user meter at each sampling time according to the first power data, the second power data, and the power weight corresponding to each sampling time.

[0028] a condition determining module configured to determine the health condition of the user electric meter according to the state representation of the user electric meter at each sampling time.

[0029] In a third aspect, the present application provides a computer device. The computer device comprises a memory and a processor. The memory stores a computer program. The processor implements the following steps when executing the computer program:

[0030] obtaining first electric quantity data of the transformer area electric meter at each sampling time within a target period, and second electric quantity data of the user electric meter associated with the transformer area electric meter at each sampling time;

[0031] determining a state representation of the user electric meter at each sampling time according to the first electric quantity data, the second electric quantity data, and the electric quantity weight corresponding to each sampling time;

[0032] determining the health condition of the user electric meter according to the state representation of the user electric meter at each sampling time within the target period.

[0033] In a fourth aspect, the present application provides a computer readable storage medium. The computer readable storage medium stores a computer program. The computer program is executed by a processor to implement the following steps:

[0034] obtaining first electric quantity data of the transformer area electric meter at each sampling time within a target period, and second electric quantity data of the user electric meter associated with the transformer area electric meter at each sampling time;

[0035] determining a state representation of the user electric meter at each sampling time according to the first electric quantity data, the second electric quantity data, and the electric quantity weight corresponding to each sampling time;

[0036] determining the health condition of the user electric meter according to the state representation of the user electric meter at each sampling time.

[0037] In a fifth aspect, the present application provides a computer program product. The computer program product comprises a computer program. The computer program is executed by a processor to implement the following steps:

[0038] obtaining first electric quantity data of the transformer area electric meter at each sampling time within a target period, and second electric quantity data of the user electric meter associated with the transformer area electric meter at each sampling time;

[0039] determining a state representation of the user electric meter at each sampling time according to the first electric quantity data, the second electric quantity data, and the electric quantity weight corresponding to each sampling time;

[0040] determining the health condition of the user electric meter according to the state representation of the user electric meter at each sampling time.

[0041] The user electric meter health condition determination method, device, equipment and storage medium described above, by obtaining the first electric quantity data of the transformer area electric meter at each sampling time in the target period and the second electric quantity data of the user electric meter associated with the transformer area electric meter at each sampling time, then according to the first electric quantity data, the second electric quantity data and the electric quantity weight corresponding to each sampling time, the state representation of the user electric meter at each sampling time can be determined, and then the health condition of the user electric meter can be determined according to the state representation of the user electric meter at each sampling time. The above scheme does not need to introduce additional monitoring equipment, and by fully analyzing the data of the transformer area electric meter and the user electric meter associated with the transformer area electric meter, that is, the electric quantity data at each sampling time in the target period, the health condition of the user electric meter can be accurately determined, and the monitoring of the health condition of the user electric meter without additional cost is realized. BRIEF DESCRIPTION OF DRAWINGS

[0042] Figure 1 The application environment diagram of the user electric meter health condition determination method in an embodiment;

[0043] Figure 2 The flowchart of the user electric meter health condition determination method in an embodiment;

[0044] Figure 3 The flowchart of determining the state representation of the user electric meter in a target period in an embodiment;

[0045] Figure 4 The flowchart of determining the state representation of the user electric meter in a target period in another embodiment;

[0046] Figure 5 The flowchart of determining the health condition of the user electric meter in an embodiment;

[0047] Figure 6 The flowchart of the user electric meter health condition determination method in another embodiment;

[0048] Figure 7 The comparison diagram of the network loss calculated by the equivalent resistance method and the actual network loss in an embodiment;

[0049] Figure 8 The structural block diagram of the user electric meter health condition determination device in an embodiment;

[0050] Figure 9 The structural block diagram of the state determination module in an embodiment;

[0051] Figure 10 The structural block diagram of the state determination module in an embodiment;

[0052] Figure 11Fig. 1 is a schematic diagram of an internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0053] For the purpose of the present application, technical solutions and advantages, the following will be further described in detail in combination with the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application, and are not used to limit the present application.

[0054] The user electric meter health condition determination method provided by the embodiments of the present application can be applied to the application environment as shown in Figure 1 . The terminal 102 communicates with the server 104 through a network. The data storage system can store data required to be processed by the server 104. The data storage system can be integrated on the server 104, or placed on the cloud or other network servers. Optionally, the server 104 obtains the first electric quantity data of the transformer area electric meter at each sampling time in a target period and the second electric quantity data of the user electric meter associated with the transformer area electric meter at each sampling time, and determines the state representation of the user electric meter at each sampling time based on the obtained first electric quantity data of the transformer area electric meter at each sampling time in the target period, the second electric quantity data of the user electric meter associated with the transformer area electric meter at each sampling time, and the electric quantity weight corresponding to each sampling time. Then, the health condition of the user electric meter can be determined based on the state representation of the user electric meter at each sampling time. Further, the server 104 can send the health condition result of the user electric meter to the terminal 102, so that the relevant personnel can repair the user electric meter with abnormal health condition according to the user electric meter health condition result in the terminal 102. The terminal 102 can be, but is not limited to, various personal computers, notebook computers, smart phones, tablet computers, Internet of Things devices and portable wearable devices. The Internet of Things device can be a smart speaker, a smart television, a smart air conditioner, a smart vehicle device, etc. The portable wearable device can be a smart watch, a smart bracelet, a head-mounted device, etc. The server 104 can be implemented by an independent server or a server cluster composed of multiple servers.

[0055] In one embodiment, as shown in Figure 2 , a user electric meter health condition determination method is provided. Taking the server 104 in Figure 1 as an example, the method includes the following steps:

[0056] S201, obtaining the first electric quantity data of the transformer area electric meter at each sampling time in a target period, and the second electric quantity data of the user electric meter associated with the transformer area electric meter at each sampling time.

[0057] The one power distribution area corresponds to one area electric meter, and the area electric meter can be used to collect the power of the power distribution area corresponding to the area electric meter. One power distribution area can include one power consumption end or multiple power consumption ends, and each power consumption end corresponds to one user electric meter. That is, one area electric meter is associated with one user electric meter or multiple user electric meters, and each user electric meter can be used to collect the power of the power consumption end.

[0058] The target period is a period selected when it is necessary to determine whether the user electric meter in the power distribution area is abnormal. For example, the user electric meter is judged once every day whether it is abnormal, and the corresponding target period can be the time period between the time when the user electric meter is last judged whether it is abnormal and the time when the user electric meter is judged whether it is abnormal this time. The sampling time can be determined according to the pre-set sampling frequency, for example, the target period is 00:00-23:59 on September 21, 2022, and the power is collected once every 15 minutes. At this time, the first sampling time can be 0:15, the second sampling time can be 0:30, etc.

[0059] The power of the entire power distribution area collected by the area electric meter at each sampling time in the target period is taken as the first power data. The power of the power consumption end collected by the user electric meter associated with the area electric meter at each sampling time in the target period is taken as the second power data.

[0060] Specifically, the server 104 can interact with the area electric meter and the user electric meter respectively to obtain the first power data of the entire power distribution area at each sampling time in the target period from the area electric meter, and obtain the second power data of each power consumption end at each sampling time in the target period from the user electric meter.

[0061] S202, according to the first power data, the second power data and the power weight corresponding to each sampling time, determine the state representation of the user electric meter at each sampling time.

[0062] The so-called power weight is a variable introduced to determine whether the user electric meter is abnormal. Optionally, each sampling time corresponds to a power weight, and the power weights corresponding to different sampling times can be the same or different.

[0063] The state representation of the user electric meter at each sampling time is a way to represent the working state of the user electric meter at each sampling time. Optionally, the state representation of the user electric meter at each sampling time can be presented in the form of a vector. Further, the user electric meter at each sampling time can correspond to a state value, and then the state representation of the user electric meter at each sampling time can be constructed based on the state value at each sampling time.

[0064] Optionally, after the server 104 interacts with the transformer meter and the user meter, obtains the first power data of the entire power distribution transformer area in the target period and the second power data of the power consumption end at each sampling time, and based on the set processing logic, the first power data and the second power data obtained, and the power weight corresponding to each sampling time, the state representation of the user meter at each sampling time can be determined. For example, the first power data and the second power data obtained, and the power weight corresponding to each sampling time, can be input into a pre-trained state representation determination model, and the state value of the user meter at each sampling period can be output by the state representation determination model. Then, based on the state value of the user meter at each sampling period, the state representation of the user meter at each sampling time can be determined.

[0065] S203, according to the state representation of the user meter at each sampling time, the health condition of the user meter is determined.

[0066] Among them, the health condition of the user meter is the normal or abnormal condition of the use of the user meter.

[0067] Specifically, a threshold value can be pre-set to determine the health condition of the user meter. Optionally, after determining the state representation of the user meter at each sampling time, a state value of the user meter at a certain time when the state value is relatively stable at each sampling time can be selected from the state representation of the user meter at each sampling time. By comparing the state value at this time with the pre-set threshold value, the health condition of the user meter can be determined based on the comparison result. For example, the pre-set threshold value is x hold , the state value x k is selected from the state representation of the user meter at each sampling time, and x k is compared with x hold to determine the health condition of the user meter; for example, when |x k -1|>x hold , it is considered that the health condition of the user meter is abnormal, and when |x k -1|<x hold , it is considered that the health condition of the user meter is normal.

[0068] It should be noted that in the case where the number of user meters is multiple, the state representation of each user meter at each sampling time can be determined based on the first power data of the transformer meter at each sampling time, the second state representation of each user meter at each sampling time, and the power weight corresponding to each sampling time. Then, based on the state representation of each user meter at each sampling time, the health condition of each user meter can be determined.

[0069] In this embodiment, the first electric quantity data of the transformer electric meter at each sampling time in the target period and the second electric quantity data of the user electric meter associated with the transformer electric meter at each sampling time are obtained. Then, according to the first electric quantity data, the second electric quantity data, and the electric quantity weight corresponding to each sampling time, the state representation of the user electric meter at each sampling time can be determined. Further, the health status of the user electric meter can be determined according to the state representation of the user electric meter at each sampling time. The above scheme does not need to introduce additional monitoring equipment. By fully analyzing the data of the transformer electric meter and the user electric meter associated with the transformer electric meter, that is, the electric quantity data at each sampling time in the target period, the health status of the user electric meter can be accurately determined, and the monitoring of the health status of the user electric meter without additional cost is realized.

[0070] In one embodiment, on the basis of the above embodiment, the S202 of determining the state representation of the user electric meter at each sampling time according to the first electric quantity data, the second electric quantity data, and the electric quantity weight corresponding to each sampling time is further explained and described in detail. As shown in Figure 3 The specific process includes:

[0071] S301, determining the network loss of the power distribution area corresponding to the transformer electric meter at each sampling time in the target period.

[0072] The network loss is the sum of the line losses of all power distribution lines in the power distribution area. Optionally, due to the complexity of the operation process of the power distribution network, the network loss of the power distribution network at different operation times may be different. Therefore, in order to accurately determine the state representation of the user electric meter, the network loss corresponding to each sampling time is determined in this embodiment.

[0073] One implementation manner is that the network loss of the power distribution area corresponding to the transformer electric meter at each sampling time in the reference period can be obtained from the pre-stored network loss database, and directly used as the network loss of the power distribution area corresponding to the transformer electric meter at each sampling time in the target period. The reference period is a period corresponding to the target period, for example, the target period is 12:00-15:00 on September 21, and the corresponding reference period is 12:00-15:00 on September 20.

[0074] Further, in order to ensure the accuracy of the final determination result of whether the user electric meter is abnormal, the network loss can also be calculated in real time, that is, the network loss is determined by the following steps:

[0075] Step A, determining the equivalent resistance of the power distribution area at each sampling time according to the second electric quantity data, the first electric quantity data, and the line resistance of each power distribution line in the power distribution area corresponding to the transformer electric meter.

[0076] The line resistance of each distribution line is the branch line resistance of each distribution line connected to the distribution substation area. Alternatively, the line resistance of each distribution line can be directly obtained by consulting technical data archives.

[0077] The equivalent resistance is the resistance of the entire distribution network line in the entire distribution substation area. Alternatively, an equivalent resistance corresponds to each sampling time.

[0078] Specifically, the calculation of network loss is the relationship between the resistance of each distribution line and the total current flowing through each distribution line. The specific formula is as follows:

[0079]

[0080] Wherein, l(τ) represents the network loss of the distribution substation area corresponding to the substation meter at the τth sampling time; r j represents the resistance of the jth distribution line, i j represents the current flowing through r j , and tp represents the number of all distribution line segments in the distribution substation area.

[0081] Further, the network loss formula is adjusted according to the engineering application requirements. In the case of low calculation requirements, the network loss calculation formula can be simplified, and the specific simplification principles are as follows: (a) assuming that the distribution of the load is proportional to the average power of the user meter; (b) the power factor of each load point is 1; (c) the voltage of each user meter is the same, and the voltage drop is not considered, and the voltage of the substation meter is taken.

[0082] The voltage of the substation meter at the τth sampling time can be represented as:

[0083]

[0084] Wherein, u(τ) represents the voltage of the substation meter at the τth sampling time; p y (τ) and q y (τ) represent the active power and reactive power of the substation meter at the τth sampling time, respectively; I y (τ) represents the current of the substation meter at the τth sampling time. q y (τ) is ignored because the power factor is 1, so the network loss calculation formula of the distribution substation area corresponding to the substation meter at the τth sampling time is as follows:

[0085]

[0086] Wherein, p j (τ) and q j (τ) represent the active power and reactive power flowing through r j at the τth sampling time, respectively. qj (τ) is ignored because the power factor is 1; p y p j The unit is watt. To correspond with the unit of electricity, kWh, a unit conversion factor T can be added based on the actual measurement frequency. K For example, when the measurement frequency is 15 minutes, T K =1 / 0.25×10 -3 Then, the formula for calculating the network loss of the distribution transformer area corresponding to the transformer meter at the τth sampling time can be simplified as follows:

[0087]

[0088] Where y(τ) represents the first electricity data of the transformer substation at the τth sampling time; a rj (τ) represents r j The amount of electricity flowing at the τth sampling time is expressed in kWh. Since the load distribution is assumed to be proportional to the average electricity consumption per user meter, therefore a rj The calculation formula is:

[0089]

[0090] Here, the j-th power distribution line is divided into n (positive integer) sub-segments, mean(a k (τ) represents the average value of the second electricity data of all users' meters located in the k-th sub-segment at the τ-th sampling time.

[0091] Furthermore, the equivalent resistance of the distribution substation at each sampling time within the target time period can be calculated using the network loss calculation formula corresponding to the substation meter. For example, the equivalent resistance R of the distribution substation at the τth sampling time can be determined using the following formula. eq (τ):

[0092]

[0093] Step B: Based on the equivalent resistance, the first power data, and the current data of the transformer substation at each sampling time, determine the network loss of the distribution transformer substation at each sampling time within the target time period.

[0094] Among them, the current data of the transformer substation at each sampling time is the current flowing through the transformer substation at each sampling time within the target time period; optionally, the current data of the transformer substation at each sampling time can be directly obtained by the server 104.

[0095] Specifically, the network loss of the power distribution area at each sampling moment in the target period is determined based on the equivalent resistance, the first electric quantity data, and the current data of the area electric meter at each sampling moment. For example, the network loss of the power distribution area at the τth sampling moment can be determined by the following formula:

[0096] l(τ)=I y 2 (τ)R eq (τ)

[0097] S302, remove the network loss from the first electric quantity data to obtain the third electric quantity data of the area electric meter at each sampling moment.

[0098] The third electric quantity data is the electric quantity of the area electric meter at each sampling moment in the target period after removing the network loss.

[0099] Specifically, the third electric quantity data of the area electric meter at each sampling moment is determined based on the first electric quantity data and the network loss, and the specific calculation formula is as follows:

[0100] y’(τ)=y(τ)-l(τ)

[0101] Where y’(τ) represents the electric quantity of the area electric meter at the τth sampling moment after removing the network loss, i.e., the third electric quantity data; y(τ) represents the first electric quantity data of the area electric meter at the τth sampling moment without removing the network loss.

[0102] S303, determine the state representation of the user electric meter at each sampling moment according to the third electric quantity data, the second electric quantity data, and the electric quantity weight corresponding to each sampling moment.

[0103] Specifically, based on the set processing logic, the third electric quantity data and the second electric quantity data, and the electric quantity weight corresponding to each sampling moment, the state representation of the user electric meter at each sampling moment can be determined. For example, the third electric quantity data and the second electric quantity data obtained, and the electric quantity weight corresponding to each sampling moment, can be input into a pre-trained state representation determination model, and the state value of the user electric meter at each sampling period can be output by the state representation determination model. Then, based on the state value of the user electric meter at each sampling period, the state representation of the user electric meter at each sampling moment can be determined.

[0104] In this embodiment, by introducing the network loss, and using the third electric quantity data obtained by removing the network loss from the first electric quantity data, and the second electric quantity data and the electric quantity weight corresponding to each sampling moment, the state representation of the user electric meter at each sampling moment is determined, so that the determined state representation is more accurate, and the determined health condition of the user electric meter is more accurate.

[0105] In one embodiment, on the basis of the above-mentioned embodiments, the S303 is further explained in detail as follows: determining the state representation of the user electric meter at each sampling time according to the third electric quantity data, the second electric quantity data and the electric quantity weight corresponding to each sampling time. Figure 4 As shown in the following, the specific process includes:

[0106] S401, determining the electric quantity covariance representation at each sampling time according to the second electric quantity data and the electric quantity forgetting weight corresponding to each sampling time.

[0107] The electric quantity forgetting weight is a presentation mode of the above-mentioned electric quantity weight, and is a variable introduced for determining whether the user electric meter is abnormal. Optionally, the electric quantity forgetting weights corresponding to different sampling times are different. Further, the electric quantity forgetting weight of each sampling time can be determined according to a weight coefficient and the electric quantity forgetting weight corresponding to the last sampling time of the sampling time. For example, the electric quantity forgetting weight of the τth sampling time can be represented as wherein the initial electric quantity forgetting weight can be a fixed value, for example, the initial electric quantity forgetting weight W(1) can be 0.7; ρ represents the weight coefficient, which can be a fixed value, such as 0.7.

[0108] The electric quantity covariance representation is another variable introduced for determining whether the user electric meter is abnormal.

[0109] Specifically, the electric quantity covariance representation at each sampling time can be determined based on the second electric quantity data and the electric quantity forgetting weight of each sampling time. For example, the electric quantity covariance representation at the τth sampling time can be determined by the following formula:

[0110] P(τ) = [W(τ)A(τ-1) T A(τ-1) + a(τ) T a(τ)] -1

[0111] wherein P(τ) represents the electric quantity covariance representation at the τth sampling time; W(τ) represents the electric quantity forgetting weight at the τth sampling time; A(τ-1) represents a vector composed of the second electric quantity data of all sampling times before the τth sampling time within the target period of the user electric meter associated with the transformer electric meter; a(τ) represents a vector composed of the second electric quantity data at the τth sampling time of the user electric meter associated with the transformer electric meter. Optionally, in the case that the number of user electric meters is multiple, for example, there are n user electric meters and t sampling times, at this time, a(τ) = (a1(τ)a2(τ)…a n (τ)), wherein a1(τ) represents the second electric quantity data at the τth sampling time of the first user electric meter, and at this time, A(τ-1) can be represented as A(τ-1) = [a(1)a(2)…a(τ-1)]T .

[0112] S402, determine the state representation of the user electricity meter at each sampling moment according to the third electricity data, the second electricity data and the electricity covariance representation.

[0113] Specifically, the state representation of the user electricity meter at each sampling moment within the target period can be determined based on the third electricity data, the second electricity data and the electricity covariance representation at each sampling moment. For example, the state representation at the τth sampling moment can be determined by the following formula:

[0114] X E (τ)=X E (τ-1)+P(τ)a(τ) T (y(τ)-a(τ)X E (τ-1))

[0115] Wherein, X E (τ) represents the state representation of the user electricity meter at the τth sampling moment; X E (τ-1) represents the state representation of the user electricity meter at all sampling moments before the τth sampling moment within the target period.

[0116] It should be noted that in the case of multiple user electricity meters, the state representation of each user electricity meter at each sampling moment can be determined simultaneously based on the third electricity data at each sampling moment, the second electricity data of each user electricity meter at the sampling moment, and the electricity covariance representation at the sampling moment.

[0117] In this embodiment, the electricity covariance representation at each sampling moment can be determined according to the second electricity data and the electricity forgetting weight corresponding to each sampling moment, and the state representation of the user electricity meter at each sampling moment can be further determined according to the third electricity data, the second electricity data and the electricity covariance representation. The above scheme provides an optional way to quickly determine the state representation of the user electricity meter at each sampling moment, which provides data support for subsequent determination of the health condition of the user electricity meter.

[0118] In one embodiment, on the basis of the above embodiment, S203 is further explained in detail according to the state representation of the user electricity meter at each sampling moment to determine the health condition of the user electricity meter. As shown in Figure 5 , the specific process includes:

[0119] S501, draw the state curve of the user electricity meter according to the state representation of the user electricity meter at each sampling moment.

[0120] Specifically, after the state representation of the user electricity meter at each sampling time in the target period is determined, the state representation of the user electricity meter at each sampling time in the target period is connected into a curve by a smooth curve.

[0121] S502, determining an analysis time according to the state curve of the user electricity meter.

[0122] The analysis time is a representative time that can be used to analyze whether the user electricity meter is abnormal.

[0123] Optionally, the analysis time can be determined according to the volatility of the state curve of the user electricity meter. The volatility of the state curve of the user electricity meter is the variability of the state representation of the user electricity meter in the target period. For example, a time with relatively small fluctuations and relatively stable curve can be selected.

[0124] Specifically, after the state curve of the user electricity meter is drawn, the drawn state curve is observed, and a time with relatively small fluctuations and relatively stable curve in the curve is selected as the analysis time.

[0125] S503, determining the health status of the user electricity meter according to the state value corresponding to the analysis time.

[0126] The state value corresponding to the analysis time is the state representation value of the user electricity meter at the analysis time corresponding to the selected analysis time.

[0127] Specifically, the state value corresponding to the analysis time is determined, and the state value is compared with a pre-set threshold value to determine whether the user electricity meter is normal or abnormal. For example, the pre-set threshold value is x hold , and the state value of the determined analysis time is x k , and x k is compared with x hold to obtain the result of the health status of the user electricity meter; for example, when |x k -1|>x hold , it is considered that the health status of the user electricity meter is abnormal, and when |x k -1|<x hold , it is considered that the health status of the user electricity meter is normal.

[0128] In this embodiment, the state curve of the user electricity meter is drawn based on the state representation of the user electricity meter at each sampling time, and the state curve of the user electricity meter can be analyzed, so that the health status of the user electricity meter can be quickly determined, thereby providing an optional way for determining the health status of the user electricity meter.

[0129] In addition, in one embodiment, the application also provides an optional example of a user meter health condition determination method. In combination with the above-mentioned method embodiment, the specific implementation process is as follows: Figure 6 The specific implementation process is as follows:

[0130] S601, acquiring first electric quantity data of the transformer area meter at each sampling time in a target period, and second electric quantity data of the user meter associated with the transformer area meter at each sampling time.

[0131] S602, determining equivalent resistances of the power distribution transformer area at each sampling time according to the second electric quantity data, the first electric quantity data, and line resistances of each power distribution line in the power distribution transformer area corresponding to the transformer area meter.

[0132] S603, determining network losses of the power distribution transformer area at each sampling time in the target period according to the equivalent resistances, the first electric quantity data, and current data of the transformer area meter at each sampling time.

[0133] S604, removing the network losses from the first electric quantity data to obtain third electric quantity data of the transformer area meter at each sampling time.

[0134] S605, determining an electric quantity covariance representation at each sampling time according to the second electric quantity data and an electric quantity forgetting weight corresponding to each sampling time.

[0135] S606, determining a state representation of the user meter at each sampling time according to the third electric quantity data, the second electric quantity data, and the electric quantity covariance representation.

[0136] S607, drawing a state curve of the user meter according to the state representation of the user meter at each sampling time.

[0137] S608, determining an analysis time according to the state curve of the user meter.

[0138] S609, determining a health condition of the user meter according to a state value corresponding to the analysis time.

[0139] The specific process of S601-S609 can be referred to the description of the above-mentioned method embodiment, and the implementation principle and technical effects are similar, which will not be described here.

[0140] Further, in order to verify the effectiveness of the method disclosed in the application, a test is performed on a certain actual transformer area. The transformer area has one transformer area meter and 77 user meters, and now needs to measure and detect the states of the 77 user meters. A total of 353 groups of effective value data of synchronous measurement electric quantity are collected at a frequency of 15 minutes. After correlation verification, the number of data groups meeting the data input requirements is 80. First, the comparison between the network losses calculated by the equivalent resistance method and the actual network losses is as follows: Figure 7As shown in the figure, the dashed line represents the actual value of network loss, and the solid line represents the calculated value of network loss. It can be seen that the actual value of network loss and the calculated value of network loss basically coincide, which means that the network loss calculation result proposed in this invention is basically consistent with the actual network loss. After calculation, the root mean square error between the calculated value and the actual value is 6.3 kWh, which accounts for 7% of the average value of the actual network loss. This verifies the effectiveness of the network loss calculation based on the equivalent resistance method.

[0141] After calculating network losses, these losses were removed from the electricity consumption data of the distribution meters. Status monitoring was then performed on 77 user meters. It can be seen that as the number of measurements increased, the status of each user's meter gradually stabilized. The status values ​​of meters numbered 3, 28, and 49 stabilized at 1.35, 0.80, and 0.65 respectively, while the status values ​​of meters numbered 15, 33, 62, and others were all within the range of 0.9 to 1.1. Now, a threshold x is set. hold To make further judgments, set x hold =0.1. Meters numbered 3, 28, and 49 were identified as abnormal, while the remaining meters were normal. On-site verification revealed that meter number 3 was involved in electricity theft, resulting in a measured value lower than the actual value; meter number 28 had increased wear and tear due to severely aged parts, leading to a measured value higher than the actual value; meter number 49 had a low data return rate due to communication issues; meters numbered 15, 33, and 62, while also experiencing increased metering errors due to aged parts, remained within the normal range and could therefore be considered normal meters. If meters 15, 33, and 62 were considered undetected abnormal meters, the accuracy rate for determining the health status of the user meters proposed in this application reaches 96%, thus demonstrating the effectiveness and engineering applicability of the proposed method.

[0142] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0143] Based on the same inventive concept, the embodiments of the present application further provide a user power meter health condition determination apparatus for implementing the user power meter health condition determination method described above. The apparatus provides a solution to the implementation scheme as described in the above method, and therefore the specific limitations in one or more user power meter health condition determination apparatus embodiments provided below can refer to the limitations of the user power meter health condition determination method described above, and will not be repeated here.

[0144] In one embodiment, as shown in Figure 8 , a user power meter health condition determination apparatus 1 is provided, comprising a data acquisition module 10, a state determination module 20 and a condition determination module 30, wherein:

[0145] The data acquisition module 10 is configured to acquire first power data of the area power meter at each sampling time in a target period, and second power data of the user power meter associated with the area power meter at each sampling time;

[0146] The state determination module 20 is configured to determine a state representation of the user power meter at each sampling time according to the first power data, the second power data and the power weight corresponding to each sampling time.

[0147] The condition determination module 30 is configured to determine the health condition of the user power meter according to the state representation of the user power meter at each sampling time.

[0148] In one embodiment, as shown in Figure 9 , the state determination module 20 in the above Figure 8 may comprise:

[0149] The first determination unit 21 is configured to determine the network loss of the power distribution area corresponding to the area power meter at each sampling time in the target period.

[0150] The second determination unit 22 is configured to remove the network loss from the first power data to obtain third power data of the area power meter at each sampling time.

[0151] The third determination unit 23 is configured to determine the state representation of the user power meter at each sampling time according to the third power data, the second power data and the power weight corresponding to each sampling time.

[0152] In one embodiment, the first determination unit 21 can be configured to:

[0153] Determine the equivalent resistance of the power distribution area at each sampling time according to the second power data, the first power data and the line resistance of each power distribution line in the power distribution area corresponding to the area power meter.

[0154] Based on the equivalent resistance, the first power data, and the current data of the transformer substation at each sampling time, the network loss of the distribution transformer substation at each sampling time within the target time period is determined.

[0155] In one embodiment, the third determining unit 23 can be used to:

[0156] Based on the second energy data and the energy forgetting weights corresponding to each sampling time, the energy covariance representation at each sampling time is determined;

[0157] Based on the third electricity data, the second electricity data, and the electricity covariance representation, the state representation of the user's electricity meter at each sampling time is determined.

[0158] In one embodiment, such as Figure 10 As shown, above Figure 8 The status determination module 30 may include:

[0159] The curve plotting unit 31 is used to plot the state curve of the user's electricity meter based on the state representation of the user's electricity meter at each sampling time.

[0160] The timing determination unit 32 is used to determine the analysis timing based on the status curve of the user's electricity meter;

[0161] The status determination unit 33 is used to determine the health status of the user's electricity meter based on the status value corresponding to the analysis time.

[0162] In one embodiment, the time determination unit 32 is specifically used for:

[0163] The analysis time is determined based on the fluctuations in the state curve of the user's electricity meter.

[0164] The various modules in the aforementioned user meter health status determination device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device in hardware form, or stored in the memory of a computer device in software form, so that the processor can call and execute the corresponding operations of each module.

[0165] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 11As shown in the figure. The computer device includes a processor, a memory and a network interface connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operating system and the computer program in the non-volatile storage medium to run. The database of the computer device is used to store the health condition determination data of the user electric meter. The network interface of the computer device is used to communicate with the external terminal through the network connection. The computer program is executed by the processor to realize a health condition determination method of a user electric meter.

[0166] Those skilled in the art can understand that, Figure 11 The structure shown in the figure is only a block diagram of part of the structure related to the scheme of the present application, and does not constitute a limitation on the computer device to which the scheme of the present application is applied. The specific computer device can include more or fewer components than those shown in the figure, or combine certain components, or have a different component arrangement.

[0167] In one embodiment, a computer device is provided, comprising a memory and a processor, the memory storing a computer program, and the processor executing the computer program to realize the following steps:

[0168] Obtaining first electric quantity data of the electric meter in the target period at each sampling time, and second electric quantity data of the user electric meter associated with the electric meter at each sampling time; determining the state representation of the user electric meter at each sampling time according to the first electric quantity data, the second electric quantity data and the electric quantity weight corresponding to each sampling time; and determining the health condition of the user electric meter according to the state representation of the user electric meter at each sampling time.

[0169] In one embodiment, when the processor executes the logic in the computer program to determine the state representation of the user electric meter at each sampling time according to the first electric quantity data, the second electric quantity data and the electric quantity weight corresponding to each sampling time, the following steps are specifically implemented:

[0170] Determining the network loss of the power distribution area corresponding to the electric meter at each sampling time in the target period; removing the network loss from the first electric quantity data to obtain the third electric quantity data of the electric meter at each sampling time; and determining the state representation of the user electric meter at each sampling time according to the third electric quantity data, the second electric quantity data and the electric quantity weight corresponding to each sampling time.

[0171] In one embodiment, when the processor executes the logic in the computer program to determine the network loss of the power distribution area corresponding to the electric meter at each sampling time in the target period, the following steps are specifically implemented:

[0172] According to the second electric quantity data, the first electric quantity data, and the line resistances of each distribution line in the distribution area corresponding to the distribution area electric meter, equivalent resistances of the distribution area at each sampling moment are determined; and according to the equivalent resistances, the first electric quantity data, and current data of the distribution area electric meter at each sampling moment, network losses of the distribution area at each sampling moment in the target period are determined.

[0173] In one embodiment, when the processor executes the logic in the computer program for determining the state representation of the user electric meter at each sampling moment according to the third electric quantity data, the second electric quantity data, and the electric quantity weight corresponding to each sampling moment, the following steps are specifically implemented:

[0174] According to the second electric quantity data and the electric quantity forgetting weight corresponding to each sampling moment, an electric quantity covariance representation at each sampling moment is determined; and according to the third electric quantity data, the second electric quantity data, and the electric quantity covariance representation, the state representation of the user electric meter at each sampling moment is determined.

[0175] In one embodiment, when the processor executes the logic in the computer program for determining the health condition of the user electric meter according to the state representation of the user electric meter at each sampling moment, the following steps are specifically implemented:

[0176] According to the state representation of the user electric meter at each sampling moment, a state curve of the user electric meter is drawn; according to the state curve of the user electric meter, an analysis moment is determined; and according to the state value corresponding to the analysis moment, the health condition of the user electric meter is determined.

[0177] In one embodiment, when the processor executes the logic in the computer program for determining the analysis moment according to the state curve of the user electric meter, the following steps are specifically implemented:

[0178] According to the volatility of the state curve of the user electric meter, the analysis moment is determined.

[0179] The computer device provided above, which implements the principles and specific processes in the embodiments, can refer to the descriptions in the foregoing embodiment of the method for determining the health condition of the user electric meter, which will not be repeated here.

[0180] In one embodiment, a computer readable storage medium is provided, which stores a computer program, and the computer program is executed by a processor to implement the following steps:

[0181] First electric quantity data of the distribution area electric meter at each sampling moment in a target period, and second electric quantity data of the user electric meter associated with the distribution area electric meter at each sampling moment are acquired; according to the first electric quantity data, the second electric quantity data, and the electric quantity weight corresponding to each sampling moment, a state representation of the user electric meter at each sampling moment is determined; and according to the state representation of the user electric meter at each sampling moment, a health condition of the user electric meter is determined.

[0182] In one embodiment, the logic in the computer program for determining the state representation of the user electric meter at each sampling time according to the first electric quantity data, the second electric quantity data and the electric quantity weight corresponding to each sampling time is implemented by the processor as follows:

[0183] determining the network loss of the distribution area corresponding to the area electric meter at each sampling time within the target period; removing the network loss from the first electric quantity data to obtain third electric quantity data of the area electric meter at each sampling time; and determining the state representation of the user electric meter at each sampling time according to the third electric quantity data, the second electric quantity data and the electric quantity weight corresponding to each sampling time.

[0184] In one embodiment, the logic in the computer program for determining the network loss of the distribution area corresponding to the area electric meter at each sampling time within the target period is implemented by the processor as follows:

[0185] determining the equivalent resistance of the distribution area at each sampling time according to the second electric quantity data, the first electric quantity data and the line resistance of each distribution line in the distribution area corresponding to the area electric meter; and determining the network loss of the distribution area at each sampling time within the target period according to the equivalent resistance, the first electric quantity data and the current data of the area electric meter at each sampling time.

[0186] In one embodiment, the logic in the computer program for determining the state representation of the user electric meter at each sampling time according to the third electric quantity data, the second electric quantity data and the electric quantity weight corresponding to each sampling time is implemented by the processor as follows:

[0187] determining an electric quantity covariance representation at each sampling time according to the second electric quantity data and the electric quantity forgetting weight corresponding to each sampling time; and determining the state representation of the user electric meter at each sampling time according to the third electric quantity data, the second electric quantity data and the electric quantity covariance representation.

[0188] In one embodiment, the logic in the computer program for determining the health status of the user electric meter according to the state representation of the user electric meter at each sampling time is implemented by the processor as follows:

[0189] drawing a state curve of the user electric meter according to the state representation of the user electric meter at each sampling time; determining an analysis time according to the state curve of the user electric meter; and determining the health status of the user electric meter according to the state value corresponding to the analysis time.

[0190] In one embodiment, the logic in the computer program for determining the analysis time according to the state curve of the user electric meter is implemented by the processor as follows:

[0191] determining the analysis time according to the volatility of the state curve of the user electric meter.

[0192] The computer readable storage medium provided in the foregoing can refer to the description in the foregoing embodiment of the method for determining the health status of the user electric meter for the principle and specific process in the embodiments, which will not be repeated here.

[0193] In one embodiment, a computer program product is provided, comprising a computer program which, when executed by a processor, implements the following steps:

[0194] obtaining first electric quantity data of the transformer electric meter at each sampling time in a target period, and second electric quantity data of the user electric meter associated with the transformer electric meter at each sampling time; determining a state representation of the user electric meter at each sampling time according to the first electric quantity data, the second electric quantity data, and an electric quantity weight corresponding to each sampling time; and determining the health status of the user electric meter according to the state representation of the user electric meter at each sampling time.

[0195] In one embodiment, the logic in the computer program for determining the state representation of the user electric meter at each sampling time according to the first electric quantity data, the second electric quantity data, and the electric quantity weight corresponding to each sampling time is executed by the processor to implement the following steps:

[0196] determining network loss of the distribution transformer area corresponding to the transformer electric meter at each sampling time in the target period; removing the network loss from the first electric quantity data to obtain third electric quantity data of the transformer electric meter at each sampling time; and determining the state representation of the user electric meter at each sampling time according to the third electric quantity data, the second electric quantity data, and the electric quantity weight corresponding to each sampling time.

[0197] In one embodiment, the logic in the computer program for determining the network loss of the distribution transformer area corresponding to the transformer electric meter at each sampling time in the target period is executed by the processor to implement the following steps:

[0198] determining an equivalent resistance of the distribution transformer area at each sampling time according to the second electric quantity data, the first electric quantity data, and line resistances of each distribution line in the distribution transformer area corresponding to the transformer electric meter; and determining the network loss of the distribution transformer area at each sampling time in the target period according to the equivalent resistance, the first electric quantity data, and current data of the transformer electric meter at each sampling time.

[0199] In one embodiment, the logic in the computer program for determining the state representation of the user electric meter at each sampling time according to the third electric quantity data, the second electric quantity data, and the electric quantity weight corresponding to each sampling time is executed by the processor to implement the following steps:

[0200] determining an electric quantity covariance representation at each sampling time according to the second electric quantity data and an electric quantity forgetting weight corresponding to each sampling time; and determining the state representation of the user electric meter at each sampling time according to the third electric quantity data, the second electric quantity data, and the electric quantity covariance representation.

[0201] In one embodiment, the logic in the computer program for determining the health condition of the user's electricity meter according to the state representation of the user's electricity meter at each sampling time is implemented as follows when executed by the processor:

[0202] According to the state representation of the user's electricity meter at each sampling time, a state curve of the user's electricity meter is drawn; according to the state curve of the user's electricity meter, a resolving time is determined; and according to the state value corresponding to the resolving time, the health condition of the user's electricity meter is determined.

[0203] In one embodiment, the logic in the computer program for determining the resolving time according to the state curve of the user's electricity meter is implemented as follows when executed by the processor:

[0204] The resolving time is determined according to the volatility of the state curve of the user's electricity meter.

[0205] The computer program product provided above can refer to the descriptions of the user's electricity meter health condition determination method embodiments in the foregoing embodiments for the principles and specific processes in the embodiments, which will not be described herein again.

[0206] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer readable storage medium, and when the computer program is executed, the processes of the above-mentioned embodiments of the methods can be included. Any reference to memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (Read-Only Memory, ROM), magnetic tape, floppy disk, flash memory, optical storage, high-density embedded non-volatile memory, resistive memory (ReRAM), magnetoresistive random access memory (Magnetoresistive Random Access Memory, MRAM), ferroelectric memory (Ferroelectric Random Access Memory, FRAM), phase change memory (Phase Change Memory, PCM), graphene memory, etc. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory, etc. As an illustration but not limitation, RAM can be in various forms, such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), etc. The database involved in the embodiments provided in the present application can include at least one of a relational database and a non-relational database. The non-relational database can include a distributed database based on a block chain, etc., without being limited thereto. The processor involved in the embodiments provided in the present application can be a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., without being limited thereto.

[0207] Any combination of the technical features of the above embodiments can be made. In order to make the description simple, all possible combinations of the technical features in the above embodiments are not described, however, as long as the combination of the technical features does not exist contradictory, it should be considered as the scope of the present application.

[0208] The above embodiments only express several implementation manners of the present application, and the description is more specific and detailed, but it should not be understood as a limitation on the scope of the patent of the present application. It should be pointed out that for ordinary skilled in the art, without departing from the concept of the present application, a number of modifications and improvements can be made, which are within the scope of protection of the present application. Therefore, the protection scope of the present application should be subject to the appended claims.

Claims

1. A method of health condition determination of a user's electricity meter, characterized by, The method comprises: obtaining first electric quantity data of a transformer area electric meter at each sampling time in a target period, and second electric quantity data of a user electric meter associated with the transformer area electric meter at each sampling time; determining equivalent resistances of a power distribution transformer area corresponding to the transformer area electric meter at each sampling time according to the second electric quantity data, the first electric quantity data, and line resistances of each power distribution line in the power distribution transformer area; determining network losses of the power distribution transformer area at each sampling time in the target period according to the equivalent resistances and current data of the transformer area electric meter at each sampling time; removing the network losses from the first electric quantity data to obtain third electric quantity data of the transformer area electric meter at each sampling time; determining state representations of the user electric meter at each sampling time according to the third electric quantity data, the second electric quantity data, and electric quantity weights corresponding to each sampling time; determining a health condition of the user electric meter according to the state representations of the user electric meter at each sampling time; The power distribution district in the first equivalent resistance at the first is expressed by the following equation (1): （1）； In the formula, represents the first electric quantity data of the electric meter in the first sampling moment, represents the electric resistance of the sectional distribution line, represents the electric quantity flowing through in the first sampling moment, in kWh, is expressed by the following formula (2): （2）； In the formula, Indicates that it is located at the th All user meters in each segment are in the first... The average value of the second electrical data at each sampling time; The power distribution district in the first The network loss l(τ) at the first sampling time is expressed by the following equation (3). （3）； In the formula, I y (τ) represents the meter in the transformer area at the τth time. Current at each sampling time; the determining of the state representations of the user electric meter at each sampling time according to the third electric quantity data, the second electric quantity data, and the electric quantity weights corresponding to each sampling time comprises: determining an electric quantity covariance representation at each sampling time according to the second electric quantity data and electric quantity forgetting weights corresponding to each sampling time; wherein the power forgetting weight at the first sampling time is represented as ; wherein the weight coefficient is represented; and the power covariance at the first sampling time is represented as: In the formula, represents the electric quantity forgetting weight at the th sampling moment; A(τ-1) T represents the vector composed of the second electric quantity data of the user electric meter associated with the transformer electric meter before all sampling moments before the th sampling moment in the target period; a(τ) represents the vector composed of the second electric quantity data of the user electric meter associated with the transformer electric meter at the th sampling moment; determining the state representations of the user electric meter at each sampling time according to the third electric quantity data, the second electric quantity data, and the electric quantity covariance representation; At the first sample time, the state is represented as: In the formula, X E (τ) represents the user's electricity meter at the t time. State representation at each sampling time; X E (τ-1) represents the t-th ... The state representation of all sampling times prior to the current sampling time; the determining of the health condition of the user electric meter according to the state representations of the user electric meter at each sampling time comprises: drawing a state curve of the user electric meter according to the state representations of the user electric meter at each sampling time; determining an analysis time according to the state curve of the user electric meter; determining the health condition of the user electric meter by comparing a state value corresponding to the analysis time with a threshold value.

2. The method of claim 1, wherein, the determining of the analysis time according to the state curve of the user electric meter comprises: determining the analysis time according to fluctuation of the state curve of the user electric meter.

3. A health condition determining apparatus of a user's electric meter, characterized by, The device comprises: a data acquisition module configured to obtain first electric quantity data of a transformer area electric meter at each sampling time in a target period, and second electric quantity data of a user electric meter associated with the transformer area electric meter at each sampling time; a state determination module configured to determine equivalent resistances of a power distribution transformer area corresponding to the transformer area electric meter at each sampling time according to the second electric quantity data, the first electric quantity data, and line resistances of each power distribution line in the power distribution transformer area; determine network losses of the power distribution transformer area at each sampling time in the target period according to the equivalent resistances and current data of the transformer area electric meter at each sampling time; remove the network losses from the first electric quantity data to obtain third electric quantity data of the transformer area electric meter at each sampling time; and determine state representations of the user electric meter at each sampling time according to the third electric quantity data, the second electric quantity data, and electric quantity weights corresponding to each sampling time; a condition determination module configured to determine a health condition of the user electric meter according to the state representations of the user electric meter at each sampling time; The power distribution area at the first sample time point is expressed as the following equation (1): （1）； In the formula, represents the first electric quantity data of the electric meter in the section, represents the electric resistance of the section, represents the electric quantity flowing through the section at the sampling time point, in kWh, is represented by the following formula (2):​​​ （2）； In the formula, Indicates that it is located at the th All user meters in each sub-segment are in the first... The average value of the second electrical data at each sampling time; The power distribution district in the first The network loss l(τ) at the first sampling time is expressed by the following equation (3). （3）； In the formula, I y (τ) represents the meter in the transformer area at the τth time. Current at each sampling time; the state determination module comprises: The determining unit is specifically configured to determine an electric quantity covariance representation at each sampling time according to the second electric quantity data and an electric quantity forgetting weight corresponding to each sampling time. wherein the power forgetting weight at the first sampling moment is represented as ; wherein the weight coefficient is represented as; and the power covariance at the first sampling moment is represented as: In the formula, represents the electric quantity forgetting weight at the th sampling moment; A(τ-1) T represents the vector composed of the second electric quantity data of the user electric meter associated with the transformer electric meter before all sampling moments before the th sampling moment in the target period; a(τ) represents the vector composed of the second electric quantity data of the user electric meter associated with the transformer electric meter at the th sampling moment; The second determining unit is specifically configured to determine a state representation of the user electric meter at each sampling time according to the third electric quantity data, the second electric quantity data and the electric quantity covariance representation. At the first sample time, the state is represented as: In the formula, X E (τ) represents the user's electricity meter at the t time. State representation at each sampling time; X E (τ-1) represents the t-th time period of the user's electricity meter within the target time period. The state representation of all sampling times prior to the current sampling time; The condition determining module comprises: The drawing unit is specifically configured to draw a state curve of the user electric meter according to the state representation of the user electric meter at each sampling time. The third determining unit is specifically configured to determine an analysis time according to the state curve of the user electric meter. The fourth determining unit is specifically configured to determine the health condition of the user electric meter by comparing a state value corresponding to the analysis time with a threshold value.

4. The apparatus of claim 3, wherein, The third determining unit is specifically configured to determine the analysis time according to fluctuation of the state curve of the user electric meter. 5.A computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the computer device is configured to perform the method according to any one of claims 1-4 when the computer program is executed by the processor. The computer program is executed by the processor to implement the steps of the method of claim 1 or 2.

6. A computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to implement the steps of the method of claim 1 or 2.

7. A computer program product comprising a computer program, characterized in that, The computer program is executed by the processor to implement the steps of the method of claim 1 or 2.

Images