A remote operation control system for outdoor metering boxes based on the Internet of Things

Abstract

The present invention relates to the field of power monitoring technology, and more specifically to an Internet of Things-based remote operation control system for outdoor meter boxes. The system comprises a data acquisition module for collecting equipment parameters of the meter box and environmental parameters at the meter box installation location, and combining the equipment parameters and environmental parameters to construct a basic data set X(t); and a data processing module for performing data cleaning, noise reduction, and format standardization on the basic data set to convert it into a standard data set S(t). The present invention effectively identifies anomalies in the data collected by the meter box by quantitatively calculating dynamic and random external interference and, in combination with historical data, reasonably setting anomaly detection thresholds for parameters. Targeted corrections are then made to the source of the anomaly to ensure that the data received by the user end is closer to the true value.

Description

Technical Field

[0001] The present invention relates to the technical field of power monitoring, and in particular to an outdoor meter box remote operation control system based on the Internet of Things. Background Art

[0002] With the rapid development of urbanization and smart grids, electricity, as a vital form of energy, has become a crucial component of power system operation and maintenance. During power transmission and distribution, power meter boxes are key devices for measuring, recording, and controlling power consumption, and are widely used in industrial, commercial, and residential applications. Traditional outdoor power meter boxes typically provide basic energy metering capabilities, but their lack of intelligent and remote control support poses numerous limitations in operation, management, and maintenance.

[0003] Especially in outdoor environments where no one is on duty for a long time, the performance of the equipment may be degraded due to severe weather, which may cause the electronic components in the meter box to drift, age, or even fail. In addition, when the meter box is in use in the wild, the activities of animals and plants will also cause chain problems for the detection of the meter box. These problems may include animals building nests at the meter box, causing the vents to be blocked, the heat dissipation performance to be reduced, and even causing the equipment to overheat. Alternatively, the roots of plants may extend into the meter box through underground cable ducts, causing damage to the cable sheath, causing exposed conductors to contact or short-circuit with external metal parts. Due to the above problems, when the meter box detects data and performs anomaly analysis, the traditional fixed threshold value is difficult to adapt to the fluctuation of parameters, resulting in frequent false alarms or omissions of parameter anomalies. After uploading to the user end, the data received by the user end has serious deviations.

[0004] Therefore, a remote operation control system for outdoor metering boxes based on the Internet of Things is proposed to solve the above problems. Summary of the Invention

[0005] Technical problems solved

[0006] In response to the above-mentioned shortcomings of the prior art, the present invention provides an outdoor meter box remote operation control system based on the Internet of Things, which can effectively solve the problem in the prior art that the meter box in the field environment is affected by bad weather and plant activities, resulting in deviations in measurement results.

[0007] Technical Solution

[0008] To achieve the above objectives, the present invention is implemented through the following technical solutions:

[0009] The present invention provides an outdoor meter box remote operation control system based on the Internet of Things. The present invention adopts the following technical solutions: comprising a data acquisition module for collecting device parameters of the meter box and environmental parameters at the installation location of the meter box, and combining the device parameters and environmental parameters to construct a basic data set X(t); further comprising:

[0010] The data processing module is used to preprocess the basic data set and convert it into a standard data set S(t);

[0011] The data analysis module is used to filter abnormal data from the standard data set S(t) and merge them into the abnormal data set A(t); it is also used to extract the comprehensive interference index and health assessment index from the standard data set S(t); build an equipment health assessment model based on the standard data set S(t) to obtain the health assessment index of the electrical components; and build a dynamic abnormality analysis model based on the abnormal data set A(t) to obtain the comprehensive interference index.

[0012] The abnormal diagnosis module calculates the dynamic anti-interference threshold based on the extracted comprehensive interference index and health assessment index, and then extracts the confirmed data in the abnormal data set A(t) based on the dynamic anti-interference threshold and constructs the confirmed data set D(t);

[0013] The data repair module is used to correct the confirmed data, obtain the repaired parameter data and transmit it to the user end.

[0014] Among them, the environmental parameters include temperature, humidity, wind speed, box tilt angle, rainfall, lightning activity and whether there is biological infestation; equipment parameters include current, voltage, and maintenance records and cumulative operating time of corresponding electrical components.

[0015] The method of filtering abnormal data is as follows:

[0016] Extract parameter data from the standard data set S(t), compare the parameter data with the pre-set static threshold range, and record the parameter data within the static threshold range as normal data; compare the parameter data outside the static threshold range with the pre-set dynamic threshold range, and record the parameter data outside the dynamic threshold range as risk data;

[0017] A collaborative analysis model is constructed based on risk data to obtain abnormal data and abnormal sources; the abnormal sources are merged to construct the abnormal source collection AEC(t).

[0018] The dynamic threshold range is set as follows:

[0019] Collect parameter data within a fixed period of time in the past and construct it into a historical data set {x1, x2, ..., x N}; where x is the name index of the parameter data, and N is the number of samples of the parameter data;

[0020] Calculate the mean of parameter data using the formula: Where, represents the mean of parameter data; x i is the i-th parameter data;

[0021] Calculate the standard deviation of the parameter data using the formula: Where σ x represents the standard deviation of parameter data;

[0022] Set the dynamic threshold range for abnormal data based on the mean and standard deviation of parameter data in, is the lower limit of the dynamic threshold, is the upper limit of the dynamic threshold; ω is the threshold coefficient.

[0023] The collaborative analysis model is constructed as follows:

[0024] Extract the parameter data with correlation between the basic data sets X(t) and construct it into the current state vector XV=[D x1 , D x2 ,...,D xM ]; among them, D x1 , D x2 ,...,D xM represents different parameter data with associated relationships, and M is the number of collected parameter data with associated relationships;

[0025] Then extract the parameter data within a fixed time in the past and construct it into a historical state vector

[0026] Calculate the deviation DEV between the current state vector and the historical state vector. The calculation formula is: Where, is the Euclidean distance between the current state vector and the historical state vector; D xi is the current value of the i-th parameter data, is the historical value of the i-th parameter data;

[0027] Compare the deviation DEV with a preset deviation threshold, and mark the current state vector whose deviation DEV is greater than the deviation threshold as an abnormal state;

[0028] Extract all parameter data in abnormal state and calculate the deviation ΔD of each parameter data xi , the calculation formula is:

[0029] Then calculate the total deviation

[0030] For each parameter data, calculate its contribution ratio in the total deviation value. The calculation formula is: Then calculate the contribution ratio threshold TH of each data parameter xi , the calculation formula is: Where, is the mean of the historical contribution ratio of the i-th parameter data; μ xi is the standard deviation of the historical contribution ratio of the i-th parameter data; τ is the discrete range factor;

[0031] The contribution ratio of all parameter data in abnormal state is Cont xi And the corresponding contribution ratio threshold TH xi Compare and calculate the contribution ratio Cont xi Greater than the contribution ratio threshold TH xi The parameter data is marked as abnormal data.

[0032] The method for determining the source of the abnormality is as follows:

[0033] Extract the contribution ratio of all abnormal data Cont xi , calculate the main anomaly threshold and the associated anomaly threshold, the calculation formula is:

[0034]

[0035]

[0036] Where TH main is the main anomaly threshold, and the abnormal data with a contribution ratio greater than the main anomaly threshold is the main anomaly source; TH rel is the associated anomaly threshold, and the abnormal data with a contribution ratio greater than the associated anomaly threshold and less than the main anomaly threshold is the secondary anomaly source; is the average contribution ratio of all abnormal data; is the contribution ratio of abnormal data arranged in descending order; E is the total number of abnormal data; u is the dynamic adjustment coefficient; and v is the fixed offset part.

[0037] The device health assessment model is constructed as follows:

[0038] Extract disturbance parameters from the standard data set S(t), including the temperature variation amplitude ΔT env , humidity change range ΔH env 、Wind speed fluctuation max(W speed ), cumulative rainfall ΔP rain , lightning frequency F lgt 、Frequency of animal and plant activities ap、Area A blocked by plants and animals ap and meter box offset angle θ tilt ; All interference parameters are combined to form the interference set Z;

[0039] The comprehensive interference index is calculated based on the interference set. The calculation formula is:

[0040]

[0041] Where, CII is the comprehensive interference index; z is the name index of the interference parameter; S z is the normalized value of the interference parameter; λ is the nonlinear adjustment index; is the nonlinear adjustment factor; γ z is the importance coefficient of the interference parameter, and its value range is: 0<γ z ≤1;η z is the normalized weight of the interference parameter, satisfying Σ z∈Z η z =1;

[0042] The method of constructing the dynamic anomaly analysis model is:

[0043] Extract health score parameters from the standard dataset S(t), including the cumulative running time Historical maintenance times

[0044] Based on cumulative running time Calculate the aging score of electrical components using the following formula: Where, To collect the aging score of the electrical components corresponding to the parameter data; The characteristic life of the corresponding parameter data is collected; b is the shape parameter;

[0045] Based on the historical maintenance times N maint Calculate the maintenance score of electrical components using the following formula: Where, Provide maintenance scores for electrical components for which corresponding parameter data is collected; The maximum number of maintenance times for the electrical component; The time interval between the last maintenance of the electrical component; is the longest allowed maintenance time interval of the electrical component; α1 is the weight coefficient of the maintenance times, and α2 is the weight coefficient of the maintenance time interval;

[0046] The formula for calculating the equipment health assessment index is:

[0047] Where, HAI xis the health assessment index of the electrical component for which the corresponding parameter data is collected; β1 is the weight coefficient of the aging score, and β2 is the weight coefficient of the maintenance score;

[0048] The formula for calculating the dynamic anti-interference threshold is:

[0049] Where (δ1·CII) is the interference correction term, δ1 is the weight coefficient of the comprehensive interference index; (1+δ2(1-HAI x )) is the health correction term, and δ2 is the weight coefficient of the health assessment index.

[0050] The shape parameter b is corrected as follows:

[0051] Under uncertain conditions, the shape parameter b is predicted by prior distribution and observed data. The prediction formula is: P(b)∝P((b prior )P(S(t)|b prior ); where P(b) is the predicted distribution; P(b prior ) is the prior distribution; b prior is the assumed shape parameter; P(St)|b prior ) is the likelihood function;

[0052] Combining the predicted likelihood value and prior distribution, the posterior distribution of the shape parameter b is calculated as follows: P(b post )∝P(S(t)|b)·P(b); where P(b post ) is the posterior distribution;

[0053] The updated posterior distribution P(b post ) is used as the prior distribution for the next round and the above steps are repeated; the calculation expression of the prior distribution is:

[0054]

[0055] The calculation expression of the likelihood function is:

[0056]

[0057] Where μ b is the prior mean; is the prior variance; exp(...) is the exponential function; is the multiplication symbol, J is the total number of data points in the standard data set S(t); S(t) j is the jth data point in the standard data set S(t); σ ε represents the uncertainty of observation data; H(t j | prior ) represents the assumed shape parameter bprior and the predicted j-th time point t j The corresponding health value.

[0058] The data analysis module combines the GAN model to generate extreme condition data in the following way:

[0059] Collect the health indicator set of the standard dataset S(t) at time t and mark it as the real dataset S real ; Define the real data set S real The previous threshold TH UB and the next threshold TH NT ;

[0060] The structure of the GAN model is defined as the generator G and the discriminator D;

[0061] The generator G is used to receive the random noise vector Ψ~N(0,1) and the prior health state distribution P(S real ) as input and output a generated dataset S of extreme health states gen ;

[0062] The discriminator D is used to receive the standard dataset S(t) and the generated distribution from the real dataset as input, and to determine whether the standard dataset S(t) comes from the real distribution.

[0063] Define the loss function of the GNN model:

[0064]

[0065] Where S real ~P(S real ) represents the real data set sampled from the prior health state distribution; logD(S real ) represents the confidence of the real data set; Ψ~P Ψ Represents the random noise distribution P Ψ The random vector sampled in ; G(Ψ) is the generated sample generated by the generator simulating the real data distribution; D(G(Ψ)) is the output of the discriminator for the generated sample;

[0066] Add the boundary loss term L to the loss function bnd , the boundary loss term is calculated as: Where hyp is a hyperparameter that controls the strength of the boundary constraint;

[0067] The generated dataset and the real dataset are fused to construct the extended dataset S ext , and expand the dataset S ext Return to the Bayesian dynamic update correction model.

[0068] The method of correcting the confirmed data is as follows:

[0069] Extract confirmed data from the confirmed data set D(t), and then extract the abnormal sources of the confirmed data from the abnormal source collection AEC(t); the correction formula is:

[0070]

[0071] Where, is the parameter data after repair; For confirmed data; is the anomaly source correction term, where: k Q is the correction coefficient of the corresponding abnormal source, Q is the name index of the abnormal source, is the current value of the exception source, is the optimal value of the anomaly source, is the upper limit value of the abnormal source, is the upper limit value of the abnormal source; is the equipment health correction term, where: ΔHAI x is the equipment health correction value, and the calculation formula is: It is a benchmark assessment index under health status. is the weight coefficient of the device health.

[0072] In summary, due to the adoption of the above technical solution, the beneficial effects of the present invention are:

[0073] 1. In the present invention, by setting a dynamic threshold range, it is possible to meet the personalized threshold of the historical data set of different parameter data, accurately adapt to the volatility of different parameter data, and effectively identify abnormal points in the data collected by the meter box; by statistically analyzing long-term historical data, the normal data distribution range is dynamically quantified, so that the determination of abnormal data has solid data support, rather than relying on manual experience or a single rule, making this solution more applicable to the determination of abnormal data; and in the process of identifying abnormal data, it can not only identify whether the current state is abnormal, but also accurately determine the main source of the problem, analyze the main abnormal data parameters and secondary abnormal parameters, and reduce the ambiguity of abnormal analysis.

[0074] 2. In the present invention, by quantitatively calculating dynamic and random external interference, abnormal data can be effectively extracted from the data detected by the meter box, and compared with the traditional static threshold recognition method, abnormal data can be identified more accurately, avoiding the misjudgment of normal fluctuations as abnormalities when the external environment changes; at the same time, the dynamic threshold adjustment mechanism can achieve personalized optimization by constructing analysis models of electrical components for different detection data, making the overall system more compatible, responding to environmental changes in real time, adapting to various complex scenarios, and realizing unified dynamic anomaly detection.

[0075] 3. In the present invention, by making targeted corrections to the confirmed data and removing the abnormal sources that cause the parameter data abnormalities and the deviations caused by problems with electrical components and equipment, the accuracy of the parameter data collected by the meter box can be effectively improved, ensuring that the data received by the user end is closer to the true value; and when correcting the confirmed data, the specific reasons for the data abnormalities are fully considered, providing a targeted basis for data repair, and effectively improving the credibility of the repaired parameter data. BRIEF DESCRIPTION OF THE DRAWINGS

[0076] Figure 1 It is a schematic diagram of the control system structure of the present invention. DETAILED DESCRIPTION

[0077] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0078] Example,

[0079] Reference Figure 1 This case proposes a remote operation control system for outdoor metering boxes based on the Internet of Things, including a data acquisition module, a data processing module, a data analysis module, an abnormality diagnosis module, and a data repair module; among which:

[0080] The data acquisition module includes a temperature and humidity sensor, an anemometer, a rainfall sensor, a lightning strike sensor, an infrared sensor, a tilt sensor, and a power sensor. The data acquisition module is used to collect environmental parameters and equipment parameters at the meter box. Environmental parameters include temperature, humidity, wind speed, box tilt angle, rainfall, lightning activity, and the presence of biological infestation. Equipment parameters include current, voltage, and maintenance records and accumulated operating time of corresponding electrical components. The data acquisition module collects environmental parameters and equipment parameters at a preset collection frequency (i.e., a set collection interval time t) and combines them to construct a basic data set X(t).

[0081] The data processing module is used to perform data cleaning, noise reduction and format standardization on the basic data set to convert it into a standard data set S(t) for subsequent analysis and monitoring;

[0082] The data analysis module is used to filter out abnormal data in the standard data set S(t) and merge them into the abnormal data set A(t); it is also used to extract the comprehensive interference index and health assessment index from the standard data set S(t);

[0083] The abnormal diagnosis module calculates the dynamic anti-interference threshold based on the extracted comprehensive interference index and health assessment index, extracts the confirmed data in the abnormal data set A(t) based on the dynamic anti-interference threshold, and merges all the confirmed data to construct the confirmed data set D(t);

[0084] The data repair module is used to correct the confirmed data, obtain the repaired parameter data and transmit it to the user end.

[0085] Specifically, in this case, the data analysis module screens abnormal data in the following way:

[0086] Extract parameter data (i.e., collected environmental parameters and equipment parameters) from the standard data set S(t), compare the parameter data with the pre-set static threshold range, and record the parameter data within the static threshold range as normal data; compare the parameter data outside the static threshold range with the pre-set dynamic threshold range, and record the parameter data outside the dynamic threshold range as risk data; the dynamic threshold range is set as follows:

[0087] Collect parameter data within a fixed period of time in the past and construct it into a historical data set {x1, x2, ..., x N}; where x is the name index of the parameter data, and N is the number of samples of the parameter data; first calculate the mean of the parameter data, and the calculation formula is: Where, Represents the mean of a set of parameter data, which is used to reflect the central trend of the parameter data; x i is the i-th parameter data; then calculate the standard deviation of the parameter data, the calculation formula is: Where σ x Represents the standard deviation of a set of parameter data, reflecting the degree of dispersion of the data distribution; sets the dynamic threshold range of abnormal data based on the mean and standard deviation of the parameter data in, is the lower limit of the dynamic threshold, is the upper limit of the dynamic threshold; ω is the threshold coefficient, which determines the width of the dynamic threshold range. In statistics, the fluctuation characteristics of data distribution usually follow the normal distribution, so the threshold coefficient ω is usually taken as 2.0 or 3.0;

[0088] By setting the dynamic threshold range, the personalized threshold of the historical data set of different parameter data can be met, the volatility of different parameter data can be accurately adapted, and anomalies in the data collected by the meter box can be effectively identified.

[0089] More specifically, in this case, the anomaly of a single parameter data (i.e., risk data) cannot be used to determine the abnormal collaborative fluctuation of meter boxes in complex abnormal scenarios. The data analysis module builds a collaborative analysis model based on the basic data set X(t), and then identifies abnormal correlation patterns between multiple parameter data under specific conditions. The collaborative analysis model is constructed in the following way:

[0090] Extract the parameter data with correlation between the basic data sets X(t) and construct it into the current state vector XV=[D x1 , D x2 ,...,D xM ]; among them, D x1 , D x2 ,...,D xM Represents different parameter data with correlation, M is the number of parameter data collected with correlation; for example, when the temperature in the meter box rises, it may cause the current to increase and the voltage to fluctuate; then extract the parameter data within a fixed time in the past and construct it into a historical state vector Then calculate the deviation DEV between the current state vector and the historical state vector. The calculation formula is: Where, is the Euclidean distance between the current state vector and the historical state vector. The larger the distance, the more serious the deviation of the current state from the historical benchmark. xi is the current value of the i-th parameter data, is the historical value of the i-th parameter data; by comparing the deviation DEV with the pre-set deviation threshold, the current state vector whose deviation DEV is greater than the deviation threshold is marked as an abnormal state;

[0091] Extract all parameter data in abnormal state and calculate the deviation ΔD of each parameter data xi , the calculation formula is: Then calculate the total deviation The deviation of each parameter data is ΔD xi The purpose of squaring is to eliminate the influence of positive and negative signs and amplify the influence of large deviations. For each parameter data, its contribution ratio in the total deviation value is calculated using the following formula: Then calculate the contribution ratio threshold TH of each data parameter xi , the calculation formula is: Where, is the mean historical contribution ratio of the i-th parameter data, which is used to reflect the typical level of deviation of the parameter data from the overall abnormality under normal conditions. The formula for obtaining it is: in is the historical contribution ratio of the i-th parameter data, T is the total number of sampling time points; μ xiis the standard deviation of the historical contribution ratio of the i-th parameter data, which measures the volatility of the contribution ratio of the i-th parameter data in the historical normal data; τ is the discrete range factor, which is used to define the range width of the parameter anomaly and is generally set to 2.0 or 3.0 based on experience;

[0092] The contribution ratio of all parameter data in abnormal state is Cont xi And the corresponding contribution ratio threshold TH xi Compare and calculate the contribution ratio Cont xi Greater than the contribution ratio threshold TH xi The parameter data is marked as abnormal data, and all abnormal data are divided into two groups according to the contribution ratio Cont xi and contribution ratio threshold TH xi The difference between them is sorted from high to low to determine the main and secondary abnormal sources; all abnormal data are merged to construct the abnormal data set A(t), and all abnormal sources are merged to construct the abnormal source collection AEC(t).

[0093] By statistically analyzing long-term historical data and dynamically quantifying the distribution range of normal data, the determination of abnormal data is supported by solid data, rather than relying on manual experience or a single rule. This makes this solution more applicable to the determination of abnormal data. In the process of identifying abnormal data, it can not only determine whether the current state is abnormal, but also accurately determine the main source of the problem, analyze the main and secondary sources of abnormality, and reduce the ambiguity of abnormal analysis.

[0094] It is worth noting that in this case, the method of identifying the main and secondary sources of abnormality is:

[0095] Extract the contribution ratio of all abnormal data Cont xi , calculate the main anomaly threshold and the associated anomaly threshold, the calculation formula is:

[0096]

[0097] Where TH main is the main anomaly threshold, and the abnormal data with a contribution ratio greater than the main anomaly threshold is the main anomaly source; TH rel is the associated anomaly threshold, and the abnormal data with a contribution ratio greater than the associated anomaly threshold and less than the main anomaly threshold is the secondary anomaly source; is the average contribution ratio of all abnormal data; is the contribution ratio of abnormal data arranged in descending order (from large to small), indicating the abnormal data with the greatest impact on the overall abnormality; E is the total number of abnormal data; u is the dynamic adjustment coefficient; if u is higher, it is more sensitive to the coordinated anomalies of multi-parameter data and is suitable for critical equipment systems; conversely, if u is lower, it is more inclined to ignore minor coordinated anomalies and is more suitable for stable working scenarios; v is the fixed offset part, which represents the benchmark value for the judgment of coordinated anomalies.

[0098] Furthermore, in this case, the contribution ratio threshold value set based on historical data may be affected by external environmental interference. For example, severe weather and animal and plant activities can significantly affect the monitoring data of electronic components in the meter box, resulting in false positives or missed positives in anomaly detection. The data analysis module constructs a dynamic anomaly analysis model based on the standard data set S(t) and the abnormal data set A(t) to obtain a comprehensive interference index, which is used to correct the contribution ratio threshold value, thereby improving the accuracy of abnormal data diagnosis. The dynamic anomaly analysis model is constructed as follows:

[0099] Extract disturbance parameters from the standard data set S(t), including the temperature variation amplitude ΔT env (affects the accuracy of electrical components), humidity change range ΔH env (causing detection deviation of electrical components and even electrical insulation problems), wind speed fluctuation max (W speed ) (causing physical interference to electrical components), cumulative rainfall ΔP rain (affects humidity and temperature related errors), lightning frequency F lgt (Electromagnetic interference causes abnormalities in electrical signals such as current and voltage), frequency of animal and plant activities F ap (direct contact, biting, vibration impact on electrical components), animal and plant shielding area A ap (affects the measurement of optical sensors in electrical components) and meter box offset angle θ tilt (affecting the measurement accuracy of the sensor and possibly causing abnormal operation of the equipment); all interference parameters are combined to form an interference set Z;

[0100] The comprehensive interference index is calculated based on the interference set. The calculation formula is:

[0101]

[0102] Where, CII is the comprehensive interference index, which quantifies the degree of influence of all interference parameters on the operation of the meter box; z is the name index of the interference parameter; S z is the standardized value of the interference parameter, and the calculation formula is: Among them C z is the current value of the interference parameter, is the historical mean of the interference parameter, σ zis the historical standard deviation of the interference parameter; by adjusting different interference parameters to a dimensionless standardized range, it is convenient to compare the impact of different interference factors; λ is a nonlinear adjustment index, which is generally set based on experience; is the nonlinear adjustment factor, |S z | is the absolute value of the standardized value of the interference parameter, which can indicate the degree to which the standardized value of the interference parameter deviates from the mean. The nonlinear adjustment factor can smoothly enhance the influence of moderate changes while suppressing the influence of extreme changes, thereby avoiding the unreasonable amplification of the overall index by abnormal values. Specifically, for small changes (i.e. |S z | smaller), The interference factor grows nearly linearly; for extreme changes (i.e. |S z | when larger), The increase in the interference index is limited to avoid excessive amplification of the results by extreme values; γ z is the importance coefficient of the interference parameter, which indicates the influence weight of the interference parameter on the comprehensive interference index. The value range is: 0<γ z ≤1;η z is the normalized weight of the interference parameter, satisfying ∑ z∈Z η z =1;

[0103] Furthermore, in this case, during the long-term operation of the meter box, the internal electrical components will age and may cause problems during operation and require maintenance. The data analysis module constructs an equipment health assessment model based on the standard data set S(t) to obtain the health assessment index of the electrical components, which is used to correct the contribution ratio threshold and thus improve the accuracy of abnormal data diagnosis. The equipment health assessment model is constructed as follows:

[0104] Extract health score parameters from the standard dataset S(t), including the cumulative running time Historical maintenance times Based on cumulative running time Calculate the aging score of electrical components using the following formula: Where, To collect the aging score of the electrical components corresponding to the parameter data; The characteristic life of the corresponding parameter data is collected to measure the typical operating time of the electrical component during its entire life cycle, which is usually obtained based on historical data fitting; b is a shape parameter used to characterize the aging behavior (i.e., health curve) or failure mode of the electrical component. Specifically: when b<1, it means that the electrical component is in early decline (i.e., the probability of aging failure is low), and the aging rate of the electrical component gradually accelerates with the increase of the cumulative operating time; when b=1, it means that the electrical component has a constant failure rate (i.e., the aging change is an exponential function relationship); when b>1, it means that the electrical component is in an accelerated aging stage (i.e., the initial aging rate of the electrical component is slow, but as the cumulative operating time increases, the aging rate accelerates); based on the historical maintenance times N maint Calculate the maintenance score of electrical components using the following formula: Where, Provide maintenance scores for electrical components for which corresponding parameter data is collected; The theoretical maximum number of maintenance times for the electrical component; The time interval between the last maintenance of the electrical component; is the theoretically longest maintenance time interval allowed for the electrical component; α1 is the weight coefficient of the maintenance times, and α2 is the weight coefficient of the maintenance time interval; finally, the equipment health assessment index is calculated Where β1 is the weight coefficient of the aging score, and β2 is the weight coefficient of the maintenance score.

[0105] It is worth mentioning that in this case, the shape parameter b describes the rate at which the health status of an electrical component decays over time and is usually based on historical data fitting activities. However, during the historical data fitting process, the shape parameter b can be interfered with by abnormal events, resulting in errors or deviations, which in turn affect the accuracy of the health curve. Abnormal events include: abnormal voltage and overload shocks during the operation of electrical components, which can cause the health of electrical components to drop significantly in a short period of time; abnormal vibration peaks on electrical components, which cause the electrical components to exhibit random upper limit fluctuations for a certain period of time; and isolated abnormal pairs in the data collected from electrical components, causing the overall trend to deviate significantly from the true value.

[0106] The data analysis module performs fitting correction on the shape parameter b based on the Bayesian dynamic update correction model. The fitting correction method is:

[0107] Under uncertain conditions, the shape parameter b is predicted by prior distribution and observed data. The prediction formula is:

[0108] P(b)∝P(b prior )P(S(t)|b prior); where P(b) is the predicted distribution, which represents the comprehensive inference result of the shape parameter b based on prior knowledge and current observation data; P(b prior ) is the prior distribution, which represents the initial assumption about the shape parameter b based on historical experience before there is any observed data; b prior is the assumed shape parameter used for comparison with the actual observed value (shape parameter b); P(S(t)|b prior ) is the likelihood function, which means that under the assumption of shape parameter b prior The probability of the observed data (i.e., the standard data set S(t) collected under the current state) appearing under the condition of

[0109] Combining the predicted likelihood value and prior distribution, the posterior distribution of the shape parameter b is calculated as follows: P(b post )∝P(S(t)|b)·P(b); where P(b post ) is the posterior distribution, which represents the probability distribution after the shape parameter b is modified under the observed data. It is the updated expected result of the shape parameter b after combining the prior distribution and the observed data;

[0110] The updated posterior distribution P(b post ) is used as the prior distribution for the next round, and the above steps are repeated to implement recursive correction of the shape parameter b, so as to dynamically adjust the shape parameter b and return it to the device health assessment model to update the device health assessment index;

[0111] Among them, the calculation expression of the prior distribution is: Where μ b is the prior mean, which represents the initial assumption value of the shape parameter b, that is, in the absence of any observed data, the shape parameter b is most likely close to the prior mean μ b ; is the prior variance, which indicates the uncertainty range of the initial assumption of the shape parameter b. The larger its value, the greater the impact on the fluctuation range of the shape parameter b. exp(...) is the exponential function.

[0112] The calculation expression of the likelihood function is:

[0113]

[0114] Where, is the multiplication symbol, J is the total number of data points in the standard data set S(t); is the normalization coefficient of the normal distribution, which is used to ensure that the total probability density of the entire distribution is 1, where σ ε Indicates the uncertainty or noise of the observed data. The larger the value, the greater the data error. j |b priorAccording to the assumed shape parameter b prior and the predicted j-th time point t j Corresponding health value; (S(t) j -H(t j |b prior )) represents the deviation between the observed value and the predicted value, reflecting the fitting effect of the actual data; S(t) j is the jth data point in the standard data set S(t);

[0115] By combining observational data and historical experience, and providing recursive iteration to continuously optimize the predicted value of the shape parameter b, the equipment health assessment model can more accurately reflect the actual operating conditions of electrical components, overcoming the limitations of the shape parameter b due to fixed assumptions. At the same time, based on the probability distribution to describe the uncertainty of the parameter, rather than just giving a single fixed value, it allows for real-time dynamic updating of the predicted value and can adjust the results as the environment changes, thereby increasing the adaptability of the equipment health assessment model in nonlinear and uncertain environments, especially in health monitoring applications. In particular, the predicted value of the shape parameter b relies on real-time data iterative updates, which can quickly capture abnormal conditions caused by abnormal emergencies, more promptly reflect equipment degradation problems, and improve the accuracy of the equipment health assessment index results.

[0116] When fitting and correcting the shape parameter b, it is done based on the standard data set S(t). Most of the data in the standard data set S(t) is distributed in the normal operating range, and the distribution under extreme conditions is incomplete and sparse. This results in distribution bias when fitting and correcting the shape parameter b based on normal health status data, and it cannot be generalized to the full distribution range, limiting the application scenarios of the model.

[0117] The data analysis module combines the GAN model to generate extreme condition data and use it to correct and optimize the shape parameter b. The generation method is:

[0118] Collect the health indicator set of the standard dataset S(t) at time t and mark it as the real dataset S real ; Construct boundary conditions based on the normal distribution range and define the real data set S real The previous threshold TH UB and the next threshold TH NT , the extreme conditions will fall outside the upper and lower thresholds;

[0119] Design a GNN model for generating extreme health state distributions, including a generator G and a discriminator D;

[0120] The generator G is used to receive the random noise vector Ψ~N(0,1) and the prior health state distribution P(S real) as input, and then outputs the generated dataset S of extreme health states gen , whose distribution is defined as the healthy state sample under boundary conditions; the generator G is used to minimize the accuracy of the discriminator so that the generated data set S gen Closer to the true distribution;

[0121] The discriminator D is used to receive the standard dataset S(t) and the generated distribution from the real dataset as input, and to determine whether the standard dataset S(t) comes from the real distribution. The discriminator D is used to maximize the correct distinction between the real dataset and make the generated dataset closer to the real distribution.

[0122] Define the loss function of the GNN model:

[0123]

[0124] Where, The goal of the discriminator D in the representation model is to maximize V(D, G) and judge the real data set as real (D(S real )→1), and at the same time judge that the generated data set is false (D(T gen )→0), and minimize V(D, G), generate a data set so that the discriminator D cannot distinguish between true and false (D(G(ψ))→1), and finally let the discriminator D and the generator G confront each other to find the best balance point;

[0125] S real ~P(S real ) represents the real data set sampled from the prior health state distribution; log D(S real Indicates the confidence of the real data set, that is, the more the discriminator is convinced that the data is real, the output D(S real ) is closer to 1, the more log D(S real ) value is larger;

[0126] Ψ~P Ψ Represents the random noise distribution P Ψ The random vector sampled in is used as the input of the generator; G(Ψ) is the generated sample generated by the generator simulating the real data distribution; D(G(Ψ)) is the output of the discriminator for the generated sample, which indicates the probability that the discriminator believes that the generated sample comes from the real data distribution; log(1-D(G(Ψ)) represents the ability of the discriminator to identify fake samples;

[0127] Add the boundary loss term L to the loss function bnd , ensuring that the generated dataset falls in the boundary area; Where hyp is a hyperparameter that controls the strength of the boundary constraint;

[0128] The generated dataset and the real dataset are fused to construct the extended dataset Sext , and expand the dataset S ext Returning to the Bayesian dynamic update correction model, the shape parameter b is optimized and corrected. The generated dataset makes up for the shortcomings of the real dataset, ensuring that the correction of the shape parameter b covers the entire distribution, making the correction of the shape parameter b more robust and able to cope with the state changes of the equipment under extreme aging or fault conditions.

[0129] The data diagnosis module calculates the dynamic anti-interference threshold based on the comprehensive interference index and health assessment index, and further verifies the abnormal data through the dynamic anti-interference threshold to obtain confirmed data; avoid misjudging the normal fluctuation of parameter data as abnormal under the influence of bad weather and animal and plant activities, or when the health status of the equipment changes; dynamic anti-interference threshold The calculation formula is:

[0130] Where (δ1·CII) is the interference correction term, δ1 is the weight coefficient of the comprehensive interference index; (1+δ2(1-HAI x )) is the health correction term, and δ2 is the weight coefficient of the health assessment index;

[0131] All abnormal data in the abnormal data set A(t) are compared with the corresponding dynamic anti-interference threshold in turn, and the abnormal data greater than the dynamic anti-interference threshold are marked as confirmed data. Finally, all confirmed data are merged to construct the confirmed data set D(t).

[0132] By quantifying and calculating dynamic and random external interference, abnormal data can be effectively extracted from the data detected by the meter box. Compared with the traditional static threshold recognition method, it can more accurately identify abnormal data and avoid misjudging normal fluctuations as abnormalities when the external environment changes. At the same time, the dynamic threshold adjustment mechanism can achieve personalized optimization by constructing analysis models of electrical components for different detection data, making the overall system more compatible, responding to environmental changes in real time, adapting to various complex scenarios, and realizing unified dynamic anomaly detection.

[0133] The data repair module corrects the confirmed data in the following way:

[0134] Extract all confirmed data from the confirmed data set D(t), and then extract the abnormal sources of the confirmed data from the abnormal source collection AEC(t); correct the confirmed data based on the abnormal sources, and the correction formula is:

[0135]

[0136] Where, The repaired parameter data reflects the actual measurement value of the meter box under the influence of external interference and equipment problems during the measurement process, removes noise and compensates for abnormal data deviations caused by external interference and equipment problems; For confirmed data; is the anomaly source correction term, where: k Q is the correction coefficient of the corresponding abnormal source, Q is the name index of the abnormal source, is the current value of the exception source, is the optimal value of the anomaly source, is the upper limit value of the abnormal source, is the upper limit value of the abnormal source; is the equipment health correction term, where: ΔHAI x is the equipment health correction value, and the calculation formula is: It is a benchmark assessment index under ideal health conditions. is the weight coefficient of the device health.

[0137] By making targeted corrections to confirmed data, removing the sources of anomalies that cause the parameter data anomalies and deviations caused by problems with electrical components and equipment, the accuracy of the parameter data collected by the meter box can be effectively improved, ensuring that the data received by the user end is closer to the true value; and when correcting confirmed data, the specific causes of the data anomalies are fully considered, providing a targeted basis for data repair, and effectively improving the credibility of the repaired parameter data.

[0138] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A remote operation control system for outdoor metering boxes based on the Internet of Things, characterized in that: It includes a data acquisition module for collecting the device parameters of the meter box and the environmental parameters where the meter box is installed, and combining the device parameters and environmental parameters to construct a basic data set X(t); it also includes: Data processing module, used to preprocess the basic data set and convert it into a standard data set S(t); The data analysis module is used to filter abnormal data from the standard data set S(t) and merge them into the abnormal data set A(t); it is also used to extract the comprehensive interference index and health assessment index from the standard data set S(t); build an equipment health assessment model based on the standard data set S(t) to obtain the health assessment index of the electrical components; and build a dynamic abnormality analysis model based on the abnormal data set A(t) to obtain the comprehensive interference index. The abnormal diagnosis module calculates the dynamic anti-interference threshold based on the extracted comprehensive interference index and health assessment index, and then extracts the confirmed data in the abnormal data set A(t) based on the dynamic anti-interference threshold and constructs the confirmed data set D(t); The data repair module is used to correct the confirmed data, obtain the repaired parameter data and transmit it to the user end; The method for correcting confirmed data is: Extract confirmed data from the confirmed data set D(t), and then extract the abnormal sources of the confirmed data from the abnormal source collection AEC(t); the correction formula is: ； Where, is the parameter data after repair; For confirmed data; It is a correction item for abnormal sources, where: is the correction coefficient of the corresponding abnormal source, Q is the name index of the abnormal source, is the current value of the exception source, is the optimal value of the anomaly source, is the upper limit value of the abnormal source, is the upper limit value of the abnormal source; It is the equipment health correction item, where: is the equipment health correction value, and the calculation formula is: , It is a benchmark assessment index under health status. is the weight coefficient of equipment health, Indicates the device health assessment index.

2. The remote operation control system for an outdoor meter box based on the Internet of Things according to claim 1, characterized in that: The environmental parameters include temperature, humidity, wind speed, cabinet tilt angle, rainfall, lightning activity and whether there is biological infestation; the equipment parameters include current, voltage, and the maintenance records and cumulative operating time of the corresponding electrical components.

3. The remote operation control system for an outdoor meter box based on the Internet of Things according to claim 2, characterized in that: The method of filtering abnormal data is: Extract parameter data from the standard data set S(t), compare the parameter data with the pre-set static threshold range, and record the parameter data within the static threshold range as normal data; Compare the parameter data that exceeds the static threshold range with the pre-set dynamic threshold range, and record the parameter data that exceeds the dynamic threshold range as risk data; A collaborative analysis model is constructed based on risk data to obtain abnormal data and abnormal sources; the abnormal sources are merged to construct the abnormal source collection AEC(t).

4. The remote operation control system for an outdoor meter box based on the Internet of Things according to claim 3, characterized in that: The dynamic threshold range is set as follows: Collect parameter data within a fixed period of time in the past and construct it into a historical data set ; Where x is the name index of the parameter data, and N is the number of samples of the parameter data; Calculate the mean of parameter data using the formula: Where, represents the mean of parameter data; is the i-th parameter data; Calculate the standard deviation of the parameter data using the formula: Where, represents the standard deviation of parameter data; Set the dynamic threshold range for abnormal data based on the mean and standard deviation of parameter data ;in, is the lower limit of the dynamic threshold, is the upper limit of the dynamic threshold; is the threshold coefficient.

5. The remote operation control system for an outdoor meter box based on the Internet of Things according to claim 3, characterized in that: The method of constructing the collaborative analysis model is: Extract the parameter data with correlation between the basic data sets X(t) and construct it into the current state vector ;in, represents different parameter data with associated relationships, and M is the number of collected parameter data with associated relationships; Then extract the parameter data within a fixed time in the past and construct it into a historical state vector ; Calculate the deviation DEV between the current state vector and the historical state vector. The calculation formula is: Where, is the Euclidean distance between the current state vector and the historical state vector; is the current value of the i-th parameter data, is the historical value of the i-th parameter data; Compare the deviation DEV with a preset deviation threshold, and mark the current state vector whose deviation DEV is greater than the deviation threshold as an abnormal state; Extract all parameter data in abnormal state and calculate the deviation of each parameter data , the calculation formula is: ; Then calculate the total deviation ; For each parameter data, calculate its contribution ratio in the total deviation value. The calculation formula is: ; Then calculate the contribution ratio threshold of each data parameter , the calculation formula is: Where, is the mean of the historical contribution ratio of the i-th parameter data; is the standard deviation of the historical contribution ratio of the i-th parameter data; is the discrete range factor; The contribution ratio of all parameter data in abnormal state And the corresponding contribution ratio threshold Compare and compare the contribution Greater than the contribution ratio threshold The parameter data is marked as abnormal data.

6. The remote operation control system for an outdoor meter box based on the Internet of Things according to claim 3, characterized in that: The method for determining the source of the abnormality is as follows: Extract the contribution ratio of all abnormal data , calculate the main anomaly threshold and the associated anomaly threshold, the calculation formula is: ； ； Where, is the main anomaly threshold, and the abnormal data with a contribution ratio greater than the main anomaly threshold is the main anomaly source; is the associated anomaly threshold, and the abnormal data with a contribution ratio greater than the associated anomaly threshold and less than the main anomaly threshold is the secondary anomaly source; is the average contribution ratio of all abnormal data; is the contribution ratio of abnormal data arranged in descending order; E is the total number of abnormal data; u is the dynamic adjustment coefficient; and v is the fixed offset part.

7. The remote operation control system for an outdoor meter box based on the Internet of Things according to claim 3, characterized in that: The method of constructing the equipment health assessment model is as follows: Extract disturbance parameters from the standard data set S(t), including the temperature variation amplitude , humidity change range , wind speed fluctuations , cumulative rainfall , lightning strike frequency , frequency of animal and plant activities , area blocked by animals and plants and meter box offset angle ; All interference parameters are combined to form the interference set Z; The comprehensive interference index is calculated based on the interference set. The calculation formula is: ； Where CII is the comprehensive interference index; z is the name index of the interference parameter; is the normalized value of the interference parameter; is the nonlinear adjustment index; is the nonlinear adjustment factor; is the importance coefficient of the interference parameter, and its value range is: ; is the normalized weight of the interference parameter, satisfying ; The method of constructing the dynamic anomaly analysis model is: Extract health score parameters from the standard dataset S(t), including the cumulative running time , Historical maintenance times ; Based on cumulative running time Calculate the aging score of electrical components using the following formula: Where, To collect the aging score of the electrical components corresponding to the parameter data; Collect characteristic life of corresponding parameter data; b is the shape parameter; Based on historical maintenance times Calculate the maintenance score of electrical components using the following formula: Where, Provide maintenance scores for electrical components for which corresponding parameter data is collected; The maximum number of maintenance times for the electrical component; The time interval between the last maintenance of the electrical component; The maximum allowable maintenance interval for the electrical component; is the weight coefficient of maintenance times, is the weight coefficient of the maintenance time interval; The formula for calculating the equipment health assessment index is: Where, To collect the health assessment index of electrical components corresponding to parameter data; is the weight coefficient of aging score, The weight coefficient for maintenance scoring; The formula for calculating the dynamic anti-interference threshold is: Where, is the interference correction term, is the weight coefficient of the comprehensive interference index; is the health correction item, is the weight coefficient of the health assessment index.

8. The remote operation control system for an outdoor meter box based on the Internet of Things according to claim 7, characterized in that: The fitting correction method of the shape parameter b is: Under uncertain conditions, the shape parameter b is predicted by prior distribution and observed data. The prediction formula is: Where, is the predicted distribution; is the prior distribution; is the assumed shape parameter; is the likelihood function; Combining the predicted likelihood value and prior distribution, the posterior distribution of the shape parameter b is calculated using the following formula: Where, is the posterior distribution; The updated posterior distribution Used as the prior distribution for the next round, repeat the above steps; Among them, the calculation expression of the prior distribution is: ； The calculation expression of the likelihood function is: Where, is the prior mean; is the prior variance; is an exponential function; is the multiplication symbol, J is the total number of data points in the standard data set S(t); is the jth data point in the standard data set S(t); represents the uncertainty of the observation data; According to the assumed shape parameters and the predicted j-th time point The corresponding health value.

9. The remote operation control system for an outdoor meter box based on the Internet of Things according to claim 8, characterized in that: The data analysis module combines with the GAN model to generate extreme condition data in the following way: Collect the health indicator set of the standard dataset S(t) at time t and mark it as the real dataset ; Define the real data set The previous threshold and the next threshold ; The structure of the GAN model is defined as the generator G and the discriminator D; Generator G is used to receive random noise vector and the prior health state distribution As input, it outputs a generated dataset of extreme health states ; The discriminator D is used to receive the standard dataset S(t) and the generated distribution from the real dataset as input, and to determine whether the standard dataset S(t) comes from the real distribution. Define the loss function of the GNN model: ； Where, represents a real dataset sampled from the prior health state distribution; Indicates the confidence of the real data set; Represents a random noise distribution A random vector sampled from ; Generate samples for the generator to simulate the real data distribution; is the output of the discriminator for generating samples; Adding boundary loss terms to the loss function , the boundary loss term is calculated as: , where hyp is a hyperparameter that controls the strength of the boundary constraint; The generated dataset and the real dataset are fused to construct an extended dataset , and will expand the dataset Return to the Bayesian dynamic update correction model.

Images