Evaluation methods, systems, equipment and storage media for electricity metering devices

Abstract

This invention discloses an evaluation method, system, equipment, and storage medium for power metering devices. It belongs to the field of industrial big data processing technology. The method includes acquiring multi-source data capable of evaluating the operating status of the power metering device and determining the corresponding indicators for each data type in the multi-source data; determining the basic weights of each indicator for the power metering device to be evaluated; introducing a first coefficient characterizing the operating scenario of the power metering device to be evaluated and a second coefficient reflecting the life cycle stage of the power metering device to be evaluated, adjusting the basic weights to determine the dynamic weights of each indicator; determining the proximity of the power metering device to be evaluated using an approximation ideal solution ranking method; and determining the operating status level of the power metering device to be evaluated based on the proximity. By adjusting the basic weights of each indicator using coefficients characterizing the operating scenario and life cycle stage of the power metering device, the accuracy of the operating status evaluation is improved.

Description

Technical Field

[0001] This invention relates to the field of industrial big data processing technology, specifically to an evaluation method, system, equipment, and storage medium for power metering devices. Background Technology

[0002] Electricity metering devices (such as electricity meters and instrument transformers) are core equipment for electricity metering and billing in power systems. Their operational status directly affects the economic interests of power grid companies and electricity users, and plays a crucial role in the safe and stable operation of the power system (for example, large fluctuations in the readings of electricity metering devices may be caused by power grid faults). Therefore, there is an urgent need to assess the operational status of electricity metering devices.

[0003] Currently, the evaluation methods for electricity metering devices typically employ a multi-parameter approach, which includes: obtaining the values ​​of each parameter; determining the importance of each parameter based on empirical values ​​or a predefined algorithm; determining the corresponding weights based on the importance of the parameters; and finally, determining the evaluation result of the electricity metering device by weighted summation of the parameters.

[0004] In the aforementioned evaluation methods for electricity metering devices, the weights of each parameter are often fixed. However, factors such as the operating conditions and environmental conditions of the electricity metering device can affect its operational status. The existing method of fixing the weights of each parameter fails to consider these influencing factors, resulting in low accuracy of the final operational status evaluation results. Summary of the Invention

[0005] The purpose of this invention is to provide an evaluation method, system, device, and storage medium for power metering devices. By using a first coefficient characterizing the operating scenario of the power metering device and a second coefficient representing its life cycle stage, the basic weights are adjusted to determine the dynamic weights of each indicator to adapt to different operating conditions and other influencing factors. This solves the problem of low accuracy in operating status evaluation caused by fixed weights.

[0006] This invention is achieved through the following technical solution:

[0007] The first aspect of this application provides a method for evaluating an electricity metering device, including:

[0008] Acquire multi-source data that can assess the operating status of power metering devices, and determine the corresponding indicators for each data type in the multi-source data based on the preset mapping relationship between data types and indicators.

[0009] For each indicator of the power metering device to be evaluated, the entropy weight method is used to determine the basic weight of each indicator.

[0010] A first coefficient representing the operating scenario of the power metering device to be evaluated, and a second coefficient reflecting the life cycle stage of the power metering device to be evaluated are introduced to adjust the basic weights in order to determine the dynamic weights of each indicator.

[0011] For the constructed weighted matrix, the proximity of the power metering device to be evaluated is determined by the approximation of the ideal solution ranking method; the elements in the weighted matrix are determined by the product of the index value and the corresponding dynamic weight; the proximity characterizes the degree to which the evaluation quantity of the power metering device to be evaluated is close to the optimal solution.

[0012] Based on the preset mapping relationship between proximity and operating status level, the operating status level of the power metering device to be evaluated is determined.

[0013] In one feasible implementation, the multi-source data includes at least technical parameter data characterizing the inherent characteristics of the power metering device, operational data characterizing the real-time operating performance of the power metering device, environmental monitoring data characterizing the environment in which the power metering device is located, maintenance record data characterizing the maintenance of the power metering device, and lifecycle data characterizing the aging and risk characteristics of the power metering device.

[0014] In one feasible implementation, the determination of the basic weights of each index of the power metering device to be evaluated using the entropy weight method includes:

[0015] Based on the power metering device to be evaluated and the determined indicators, a data matrix is ​​constructed; the elements in the data matrix represent the indicator values ​​of the power metering device to be evaluated.

[0016] Based on the data matrix, the weight of each indicator of the power metering device to be evaluated is calculated; when calculating the weight, the sum of each indicator value and the preset smoothing coefficient is used for the weight calculation.

[0017] Based on the weight of each indicator and the number of power metering devices to be evaluated, the entropy value of each indicator is determined.

[0018] The basic weight of each indicator is determined based on its entropy value and the number of indicators.

[0019] In one feasible implementation, the basic weights are adjusted to determine the dynamic weights of each indicator, including:

[0020] The basic weights are multiplied by the first coefficient and the second coefficient respectively to obtain the dynamic weights of each indicator; the first coefficient is the operating condition sensitivity coefficient and the second coefficient is the time decay coefficient.

[0021] The operating condition sensitivity coefficient is determined based on the weighted sum of the load rate, electromagnetic interference intensity, and temperature and humidity deviation values ​​of the operating scenario; the time decay coefficient is determined based on the ratio of the service life of the power metering device to its standard service life.

[0022] In one feasible implementation, the method further includes:

[0023] Based on a preset sampling time window, real-time multi-source data are acquired, and the multi-source data acquired within the sampling time window is used as a sample point of the power metering device to be evaluated.

[0024] Based on the local anomaly factor algorithm, the LOF value of each sample point of the power metering device to be evaluated is calculated; the LOF value represents the degree to which the current sample point deviates from its neighboring sample points.

[0025] By comparing the LOF value of a sample point with the pre-calculated thresholds, it is determined whether the sample point is in an abnormal state; the thresholds are determined based on the baseline threshold and the dynamic weights of each indicator.

[0026] In one feasible implementation, the method further includes:

[0027] The remaining service life of the power metering device to be evaluated is determined based on the standard service life of the device and the influence coefficients of key factors affecting the service life. The key factors include at least operating temperature, operating load, maintenance quality, and electromagnetic interference intensity.

[0028] The influence coefficients of the key factors are determined by fitting a gradient boosting regression model to multi-source data.

[0029] In one feasible implementation, the method further includes:

[0030] Based on the remaining service life and operating status level of the power metering device to be evaluated, the fault risk points of the power metering device and the optimal replacement cycle are determined.

[0031] A second aspect of this application provides an evaluation system for an electricity metering device, comprising:

[0032] The multi-source data acquisition unit is used to acquire multi-source data that can be used to evaluate the operating status of the power metering device, and to determine the corresponding indicators for each data type in the multi-source data based on the preset mapping relationship between data types and indicators.

[0033] The basic weight determination unit uses the entropy weight method to determine the basic weight of each indicator for the power metering device to be evaluated.

[0034] The dynamic weight determination unit is used to introduce a first coefficient representing the operating scenario of the power metering device to be evaluated, and a second coefficient reflecting the life cycle stage of the power metering device to be evaluated, and adjust the basic weights to determine the dynamic weights of each indicator.

[0035] The proximity determination unit is used to determine the proximity of the power metering device to be evaluated by using the ideal solution ranking method on the constructed weighted matrix; the elements in the weighted matrix are determined by the product of the index value and the corresponding dynamic weight; the proximity characterizes the degree to which the evaluation quantity of the power metering device to be evaluated is close to the optimal solution.

[0036] The operation status level determination unit determines the operation status level of the power metering device to be evaluated based on a preset mapping relationship between proximity and operation status level.

[0037] A third aspect of this application provides an electronic device, including: a processor, a memory, and a program or instructions stored in the memory and executable on the processor, wherein the program or instructions, when executed by the processor, implement the steps of the above-described method.

[0038] A fourth aspect of this application provides a storage medium, comprising: storing a program or instructions on the storage medium, wherein the program or instructions, when executed by a processor, implement the steps of the above-described method.

[0039] Compared with the prior art, the present invention has the following advantages and beneficial effects:

[0040] This application utilizes multi-source data from power metering devices for operational status assessment and determines the dynamic weights of each indicator corresponding to the multi-source data. Based on the indicator values ​​and corresponding dynamic weights, the operational status level of the power metering device is determined. Furthermore, the basic weights are adjusted using a first coefficient characterizing the operating scenario of the power metering device and a second coefficient representing its lifecycle stage to determine the dynamic weights. Because the determination of the dynamic weights considers the influencing factors of different operating conditions, such as the operating scenario and lifecycle stage of the power metering device, the determined dynamic weights can adapt to power metering devices under different operating conditions. This ensures that the final operational status level assessment result is adapted to the operating conditions of the power metering device being assessed, solving the problem of low accuracy in operational status assessment caused by fixed weights. Attached Figure Description

[0041] To more clearly illustrate the technical solutions of the exemplary embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly described below. It should be understood that the following drawings only show some embodiments of the present invention and should not be considered as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort. In the drawings:

[0042] Figure 1 A flowchart illustrating an evaluation method for an electricity metering device provided in this application embodiment;

[0043] Figure 2 A schematic diagram of the structure of an evaluation system for an electricity metering device provided in this application embodiment;

[0044] Figure 3 This is a schematic diagram of the structure of a computing device provided in an embodiment of this application. Detailed Implementation

[0045] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to embodiments and accompanying drawings. The illustrative embodiments and descriptions of this invention are for explanation only and are not intended to limit the invention. All other embodiments obtained by those skilled in the art based on the embodiments in this application without creative effort are within the scope of protection of this application.

[0046] As will be known to those skilled in the art, with the development of technology and the emergence of new scenarios, the technical solutions provided in the embodiments of this application are also applicable to similar technical problems.

[0047] The terms “comprising” and “having”, and any variations thereof, in the specification, claims, and accompanying drawings of this application are intended to cover non-exclusive inclusion, so that a process, method, system, product, or apparatus that comprises a series of elements is not necessarily limited to those elements, but may include other elements not expressly listed or inherent to such process, method, product, or apparatus.

[0048] Example 1:

[0049] Embodiment 1 of this application provides an evaluation method for power metering devices to solve the problem of low accuracy in operational status evaluation caused by fixed weights.

[0050] The subject executing this method can be any computing device capable of implementing the method, such as a server, mobile phone, personal computer, smart wearable device, smart robot, etc.

[0051] Furthermore, the embodiments of this application do not limit the execution order of different steps. When using the method provided in the embodiments of this application, the execution order of different steps can be adjusted according to actual needs.

[0052] For ease of description, the following uses an evaluation device for an electricity metering device as the subject of this method to provide a detailed description of the method provided in this application embodiment.

[0053] like Figure 1 The diagram shown is a flowchart illustrating the specific implementation of an evaluation method for an electricity metering device according to an embodiment of this application, including the following steps 11-15:

[0054] Step 11: Obtain multi-source data that can assess the operating status of the power metering device, and determine the corresponding indicators for each data type in the multi-source data based on the preset mapping relationship between data types and indicators.

[0055] Multi-source data refers to data that can reflect the operating status of power metering devices from multiple dimensions.

[0056] Multi-source data includes at least the technical parameter data characterizing the inherent characteristics of the power metering device, the operation data characterizing the real-time operation performance of the power metering device, the environmental monitoring data characterizing the environment in which the power metering device is located, the operation and maintenance record data characterizing the maintenance of the power metering device, and the life cycle data characterizing the aging and risk characteristics of the power metering device.

[0057] Among them, technical parameter data This includes data such as the model, rated voltage, rated current, accuracy class, and factory test data of the power metering device; and operational data. This includes data such as real-time metering error of power metering devices, voltage / current measurements, power factor, operating temperature, and operating time; environmental monitoring data. This includes data such as temperature, humidity, altitude, electromagnetic interference intensity, and dust concentration at the installation location of the power metering device; and operation and maintenance record data. This includes data such as the number of times the power metering device has been repaired, the type of fault, the repair time, calibration records, and information on replaced parts; lifecycle data. This includes data such as fault statistics, aging pattern data, and service life data for similar power metering devices.

[0058] After preprocessing the collected multi-source data, a multi-source dataset D is formed: The preprocessing of multi-source data can include conventional source data processing methods such as removing outliers, filling in missing values, and deleting duplicate data; standardization processing can be used to convert indicator data of different dimensions into a unified scale to ensure data comparability; and a unified data index can be established to link and store multi-source data to provide data support for subsequent evaluation.

[0059] The preset mapping relationship between data types and indicators refers to the correspondence between the types of multi-source data (technical parameter data, operational data, environmental monitoring data, operation and maintenance record data, and lifecycle data) and the preset indicator types, and one type of multi-source data corresponds to multiple indicator types.

[0060] Based on the mapping relationship, the corresponding indicators for each data type in the multi-source data are determined, including: technical parameter data corresponding to indicators such as accuracy level, rated parameter matching degree, and factory inspection pass rate; operational data corresponding to indicators such as measurement error stability, operational parameter compliance rate, and fault-free operation time; environmental monitoring data corresponding to indicators such as temperature and humidity adaptability, electromagnetic interference resistance, and environmental corrosion impact; maintenance record data corresponding to indicators such as maintenance timeliness rate, calibration pass rate, and fault repair quality; and life cycle data corresponding to indicators such as remaining service life prediction, aging rate, and failure risk probability.

[0061] In one feasible implementation, this embodiment further includes determining the quantified value of each indicator, i.e., each indicator value, based on the mapping relationship. Specifically, this includes determining the indicator value of each corresponding indicator based on data of each data type.

[0062] For technical parameter data, the data is directly mapped from the factory parameters of the power metering device. For example, the quantified value of the accuracy class directly corresponds to the labeled data of the accuracy class of the power metering device at the factory, such as 0.2, 0.5, and 1.0; the quantified value of the rated parameter matching degree is determined by the ratio of the actual grid rated value to the rated value of the power metering device; the quantified value of the factory inspection pass rate is determined by the ratio of the factory inspection data corresponding to the qualified inspection items (such as error detection, insulation monitoring, etc.) to the total factory inspection data corresponding to the total inspection items.

[0063] For operational data, based on real-time and historical operational monitoring data from power metering devices, corresponding indicator values ​​are determined through statistical analysis, stability analysis, and other methods. For example, the quantified value of metering error stability is determined by the ratio of the standard deviation of the metering error to the maximum allowable value of the metering error; the quantified value of the compliance rate of operational parameters is determined by the ratio of the number of compliant data points for real-time data such as voltage / current measurements, power factor, and operating temperature to the total number of collected data points; and the quantified value of fault-free operation time is determined by the continuous operation time from the completion of the most recent fault repair to the present.

[0064] For environmental monitoring data, based on real-time environmental monitoring data at the installation location of the power metering device, and in conjunction with the environmental adaptability standards of the power metering device, the corresponding index values ​​are determined through adaptability analysis. For example, the quantitative value of temperature and humidity adaptability is determined by the ratio of the time spent within the rated range in the real-time temperature and humidity data at the installation location to the total monitoring time; the quantitative value of electromagnetic interference resistance is determined by the upper and lower limits of the real-time electromagnetic interference intensity data at the installation location and the electromagnetic interference tolerance threshold; the quantitative value of environmental corrosion impact is determined by the quantitative results of the industry corrosion level standards corresponding to the dust concentration, corrosive gas content, and other data at the installation location (e.g., dust concentration ≤ 0.5 mg / m³ is considered mild corrosion, with a quantitative result of 0.9).

[0065] For operation and maintenance record data, based on the operation, maintenance, and calibration records of the power metering device throughout its entire lifecycle, indicator values ​​are calculated through timeliness and quality analysis. For example, the quantitative value of timely maintenance rate is determined by the ratio of the number of faults that were repaired on time to the total number of faults; the quantitative value of calibration pass rate is determined by the ratio of the number of times the error met the standard after calibration to the total number of calibrations; and the quantitative value of fault repair quality is determined by the ratio of the running time without similar faults after repair to the average operating cycle.

[0066] For lifecycle data, predictions are made based on multi-source data from power metering devices using algorithms (such as gradient boosting regression trees) or preset formulas to determine the corresponding indicator values. For example, the quantified value of the remaining service life prediction is determined by the standard service life and the various influence coefficients on the service life determined by the gradient boosting regression tree model; the quantified value of the aging rate is determined by the ratio of the actual aging degree to the average aging degree of similar devices under the same operating conditions; and the quantified value of the failure risk probability is determined by fitting the multi-source data using the gradient boosting regression tree algorithm.

[0067] In this step, by acquiring multi-source data, including technical parameter data, operational data, environmental monitoring data, operation and maintenance record data, and lifecycle data, a more comprehensive range of data dimensions that can characterize the operational status of power metering data can be covered, thereby improving the credibility and accuracy of the final evaluation results.

[0068] Step 12: For each index of the power metering device to be evaluated, the entropy weight method is used to determine the basic weight of each index.

[0069] The specific implementation of this step includes the following sub-steps 1201-1204:

[0070] Step 1201: Based on the power metering device to be evaluated and the determined indicators, construct a data matrix; the elements in the data matrix represent the indicator values ​​of the power metering device to be evaluated.

[0071] Assuming there are m electricity metering devices to be evaluated and n indicators, then based on the dataset D determined in step 11, construct a standardized data matrix X:

[0072] ;

[0073] In the formula: Let j be the j-th index of the i-th power metering device to be evaluated; i is an integer from 1 to m, and j is an integer from 1 to n.

[0074] Step 1202: Based on the data matrix, calculate the weight of each indicator of the power metering device to be evaluated; when calculating the weight, the sum of each indicator value and the preset smoothing coefficient is used for the weight calculation.

[0075] The smoothing coefficient ε is a constant, such as ε = 0.001. Introducing the smoothing coefficient avoids zero values ​​in entropy calculations. The weight of the i-th power metering device to be evaluated in the j-th indicator. for:

[0076] .

[0077] Step 1203: Determine the entropy value of each indicator based on the weight of each indicator and the number of power metering devices to be evaluated.

[0078] Entropy value of index j Represented as:

[0079] .

[0080] ln represents the logarithm of the exponent; weight The value of the j-th indicator of the i-th power metering device to be evaluated is the proportion of the sum of the j-th indicator values ​​of all power metering devices to be evaluated.

[0081] Step 1204: Determine the basic weight of each indicator based on its entropy value and the number of indicators.

[0082] First, calculate the difference coefficient g. j : It is evident that the smaller the entropy value, the larger the difference coefficient, and the richer the information content of the corresponding indicator.

[0083] Then, the difference coefficients are normalized to obtain the basic weights of each indicator. :

[0084] .

[0085] Step 13: Introduce a first coefficient representing the operating scenario of the power metering device to be evaluated, and a second coefficient reflecting the life cycle stage of the power metering device to be evaluated, and adjust the basic weights to determine the dynamic weights of each indicator.

[0086] The basic weights are multiplied by the first and second coefficients, respectively, to obtain the dynamic weights of each indicator. Specifically, the dynamic weight of indicator j... Represented as: ;in, Indicates the first coefficient. This represents the second coefficient. The first coefficient is the operating condition sensitivity coefficient, and the second coefficient is the time decay coefficient.

[0087] The operating condition sensitivity coefficient is based on the load rate of the operating scenario. Electromagnetic interference intensity and temperature and humidity deviation values The weighted sum and determination.

[0088] The value range of the operating condition sensitivity coefficient is θ∈[0.8,1.2], and its calculation formula can be:

[0089] The more complex the working conditions, the closer θ is to 1.2.

[0090] The time decay factor is based on the service life (t) of the power metering device and its standard service life. The ratio is determined.

[0091] The longer the service life, the lower the η value, thus achieving a reasonable reduction of data for aging equipment.

[0092] In step 13, dynamic weights are generated by adjusting the basic weights, so that the weights can be optimized in real time according to factors such as working conditions and environment, thereby improving the pertinence and adaptability of the assessment.

[0093] Step 14: For the constructed weighted matrix, determine the proximity of the power metering device to be evaluated by the approximation of the ideal solution sorting method; the elements in the weighted matrix are determined by the product of the index value and the corresponding dynamic weight; the proximity characterizes the degree to which the evaluation quantity of the power metering device to be evaluated is close to the optimal solution.

[0094] TOPSIS, a technique for order preference by similarity to the ideal solution.

[0095] The specific implementation of this step includes:

[0096] Construct a weighted (standardized) matrix , represented as ;in, For the first The dynamic weight of each indicator.

[0097] Determine the ideal solution With negative ideal solution :

[0098] The positive ideal solution, representing the optimal solution among all sampled data of each power metering device to be evaluated, can be expressed as: ;

[0099] The negative ideal solution represents the worst solution among all sampled data of each power metering device to be evaluated, corresponding to index j, and can be expressed as: .

[0100] Calculate the Euclidean distance, including the distance from the electricity metering device to be evaluated to the positive ideal solution and the distance to the negative ideal solution:

[0101] The distance to the ideal solution can be expressed as: ;

[0102] The distance to the negative ideal solution can be expressed as: .

[0103] Euclidean distance is used as an evaluation metric for power metering equipment.

[0104] Calculate (relative) proximity : Proximity The closer the value is to 1, the better the operating status of the power metering device being evaluated.

[0105] Step 15: Based on the preset mapping relationship between proximity and operating status level, determine the operating status level of the power metering device to be evaluated.

[0106] The mapping relationship between proximity and operating status level is shown in Table 1 below. Based on proximity... The range of values ​​is used to classify the operating status of power metering devices into five levels: excellent, good, qualified, warning, and unqualified.

[0107] Table 1. Mapping relationship between proximity and operating status level:

[0108] grade Proximity scope Status Description excellent All indicators are excellent, the remaining lifespan is sufficient, and there is no risk of failure. good The core indicators meet the standards, while the secondary indicators show slight deviations, and the remaining lifespan meets the usage requirements. qualified Key indicators meet the requirements, but some indicators show some fluctuations and require enhanced monitoring. Warning Several indicators are approaching their thresholds, indicating a potential risk of failure, and rectification is required within a specified period. Unqualified The core indicators are seriously substandard, the risk of failure is high, and immediate replacement or repair is required.

[0109] In one feasible implementation, to further pinpoint the time of failure of the power metering device, this embodiment also includes the identification and early warning of abnormal time points. Specifically, this includes the following steps 1-4:

[0110] Step 1: Based on the preset sampling time window, acquire real-time multi-source data respectively, and use the multi-source data acquired in the sampling time window as a sample point of the power metering device to be evaluated.

[0111] Using real-time multi-source data collected within a sliding time window as samples, for example, if the sampling time window is set to 5 seconds, then multi-source data from the power metering device is collected every 5 seconds, and the collected multi-source data is used to form a sample point, that is, a sample point is formed every 5 seconds.

[0112] Step 2: Calculate the LOF value of each sample point of the power metering device to be evaluated based on the local anomaly factor algorithm.

[0113] The Local Outlier Factor (LOF) algorithm determines the LOF value by calculating the ratio of the local reachability density of each sample point to the local reachability density of its neighboring sample points. The LOF value characterizes the degree to which the current sample point deviates from its neighboring sample points; the larger the LOF value, the greater the deviation of the sample point from its neighboring sample points, and the higher the probability of an anomaly.

[0114] Step 3: By comparing the LOF value of the sample point with the pre-calculated thresholds, determine whether the sample point is in an abnormal state; the thresholds are determined based on the baseline threshold and the dynamic weights of each indicator.

[0115] benchmark threshold The baseline threshold is determined based on the statistical distribution of historical anomaly data from similar devices, and its dimension is consistent with that of the LOF value.

[0116] The pre-calculated thresholds include various anomaly detection thresholds based on dynamic weight adjustments for each indicator. The expression can be:

[0117] ;

[0118] Among them, the indicator with the highest weight (or the top N weights, where N is a preset integer) is called the core indicator, and its corresponding threshold is the smallest, that is, the judgment standard is the strictest.

[0119] By comparing the LOF value of a sample point with the pre-calculated thresholds, it is determined whether the sample point is in an abnormal state. This includes: comparing the LOF value of the sample point with the thresholds corresponding to each indicator; if the LOF value is not greater than the minimum threshold (the threshold corresponding to the indicator with the highest weight), the sample point is considered normal; if the LOF value of the sample point is higher than the threshold corresponding to the core indicator, the sample point is considered to have an abnormal risk related to the core indicator; if the LOF value of the sample point is higher than the thresholds corresponding to multiple (the specific number can be set in advance) non-core indicators, the sample point is considered to have an overall abnormal risk.

[0120] It should be noted that the number of core indicators can be determined based on the value of dynamic weights, such as setting indicators with dynamic weights greater than 0.4 as core indicators; or it can be determined based on a preset number, such as setting the indicators corresponding to the top 3 largest values ​​in the dynamic weight range as core indicators.

[0121] Step 4: Issue an early warning message based on the identified abnormal state.

[0122] The early warning information includes the name of the abnormal indicator, the corresponding indicator value, the time corresponding to the abnormal sample point, the location of the abnormal power metering device, the severity of the abnormality, and preliminary handling suggestions. The severity of the abnormality can be determined by the abnormal risk assessment in step 3. For example, if the LOF value is higher than the threshold corresponding to one core indicator, the severity is low; if the LOF value is higher than the thresholds corresponding to all core indicators, the severity is medium; if the LOF value is higher than the thresholds corresponding to multiple non-core indicators, the severity is high.

[0123] Early warning information is pushed to relevant personnel through the operation and maintenance platform, SMS and other means to ensure timely response and handling.

[0124] In this implementation, multi-source data from real-time power metering devices are used as sample points. The degree to which each sample point deviates from its neighboring samples is determined based on the LOF algorithm, thus identifying sudden abnormal states of the power metering devices. The LOF value determined by the LOF algorithm is compared with each threshold based on the dynamic weight adjustment of each indicator to determine the degree of abnormality of the sample points, thus refining the granularity of abnormality identification. This enables timely, accurate (detailed) capture and early warning of abnormal states, reducing the risk of faults and metering disputes.

[0125] In one feasible implementation, this embodiment also includes predicting the remaining service life of the electricity metering device. Specifically, this includes determining the remaining service life of the electricity metering device to be evaluated based on its standard service life and the influence coefficients of key factors affecting its service life.

[0126] The key factors include at least operating temperature, operating load, maintenance quality, and electromagnetic interference intensity.

[0127] Remaining service life It can be expressed by the following formula:

[0128] ;

[0129] In the formula, The standard service life is determined based on product specifications and industry standards. This indicates the number of key factors affecting lifespan; Indicates the first The influence coefficients of the key factors, with a range of values ​​of [value range missing]. .

[0130] when At that time, this factor accelerates the aging of the device, such as the influence coefficient of the operating temperature corresponding to a high-temperature environment. ;

[0131] when At that time, this factor had no significant effect on lifespan;

[0132] when At that time, this factor is beneficial for extending lifespan.

[0133] The influence coefficients of key factors were determined by fitting a gradient boosting regression tree model to multi-source data. During the fitting process, historical data from the full multi-source dataset were used. Construct a dataset; by screening key factors affecting lifespan from multi-source data and defining lifespan decay labels, build a gradient boosting regression tree model, use the dataset to iteratively train and optimize the model parameters, determine the trained gradient boosting regression tree model, and output the influence coefficients of each key factor.

[0134] In this implementation method, the remaining service life of the power metering device is predicted, providing a scientific basis for the formulation of operation and maintenance plans and equipment upgrades, thereby improving the economy and rationality of operation and maintenance management.

[0135] In one feasible implementation, this embodiment further includes: determining the fault risk points of the power metering device and recommending the optimal replacement cycle based on the remaining service life and operating status level of the power metering device to be evaluated.

[0136] Specifically, this can be done by: determining the risks associated with the power metering device based on the operating status level and the corresponding status description information in Table 1; predicting the time when the risk will occur based on the remaining service life, such as when the remaining service life of the power metering device is 30 days, then predicting the time when the risk will occur is about 30 days; in addition, extracting the installation point of the power metering device from multi-source data to determine when the power metering device at a specific location will be at risk.

[0137] The optimal replacement cycle refers to the replacement cycle of electricity metering devices.

[0138] Optimal update cycle The following formula is used to determine it:

[0139]

[0140] Risk-based "security update cycle" (the higher the risk, the higher the risk adjustment factor). The smaller the value, the shorter the update cycle); risk correction coefficient. Determined based on the current state level, reflecting the "probability of premature failure";

[0141] : "Economic upgrade cycle" based on operation and maintenance costs (the faster the cost growth, the higher the operation and maintenance cost coefficient) The larger the value, the shorter the update cycle); operation and maintenance cost coefficient. Based on historical operation and maintenance data of similar devices, this reflects the "growth rate of maintenance costs for continued use of the device".

[0142] The optimal update cycle determined by this implementation method ensures that "both the risk of failure and the waste of resources are avoided", achieving a balance between safety and economy.

[0143] In one feasible implementation, this embodiment also includes outputting an evaluation report. The generated evaluation report may include the following:

[0144] Basic information: device model, installation location, service life, and evaluation time;

[0145] Overall evaluation results: relative relevance, status level, and performance of core indicators;

[0146] Anomaly information: anomaly list, severity, and handling recommendations;

[0147] Lifecycle forecasting: remaining useful life, potential risks, and recommended replacement cycles;

[0148] Maintenance and operation plan: Specific measures such as targeted inspection, calibration, and replacement.

[0149] This embodiment also includes iterative optimization of algorithms such as determining the coefficients of dynamic weights and gradient boosting regression tree model involved in the above implementation process, and establishing a feedback-optimization closed-loop mechanism.

[0150] Specifically, this could involve regularly collecting actual operation and maintenance data (such as fault handling results, calibration effects, and post-replacement operating status).

[0151] Based on the accuracy of the evaluation results (operational status, abnormal status, remaining lifespan, etc.) verified by operation and maintenance data, the evaluation index system was optimized (adding key indicators and eliminating redundant indicators), dynamic weight coefficients (calculation logic of θ and η) and life cycle prediction model (fitting parameters of influence coefficients) were optimized; the iteration cycle was determined according to the application scale, with small-scale application scenarios iterated once a quarter and large-scale application scenarios iterated once a month to ensure that the model continuously adapts to actual needs.

[0152] In summary, this is a complete embodiment of the evaluation method of this application.

[0153] This application utilizes multi-source data from power metering devices for operational status assessment and determines the dynamic weights of each indicator corresponding to the multi-source data. Based on the indicator values ​​and corresponding dynamic weights, the operational status level of the power metering device is determined. Furthermore, the basic weights are adjusted using a first coefficient characterizing the operating scenario of the power metering device and a second coefficient representing its lifecycle stage to determine the dynamic weights. Because the determination of the dynamic weights considers the influencing factors of different operating conditions, such as the operating scenario and lifecycle stage of the power metering device, the determined dynamic weights can adapt to power metering devices under different operating conditions. This ensures that the final operational status level assessment result is adapted to the operating conditions of the power metering device being assessed, solving the problem of low accuracy in operational status assessment caused by fixed weights.

[0154] Example 2:

[0155] To address the problem of low accuracy in operational status assessment caused by fixed weights in existing technologies, and based on the same inventive concept as Embodiment 1, this application also provides an assessment system for power metering devices.

[0156] The specific structural diagram of the system is as follows: Figure 2 As shown, it includes the following functional units 21-25:

[0157] The multi-source data acquisition unit 21 is used to acquire multi-source data that can evaluate the operating status of the power metering device, and to determine the corresponding indicators for each data type in the multi-source data based on the preset mapping relationship between data types and indicators.

[0158] Multi-source data includes at least the technical parameter data characterizing the inherent characteristics of the power metering device, the operation data characterizing the real-time operation performance of the power metering device, the environmental monitoring data characterizing the environment in which the power metering device is located, the operation and maintenance record data characterizing the maintenance of the power metering device, and the life cycle data characterizing the aging and risk characteristics of the power metering device.

[0159] The basic weight determination unit 22 uses the entropy weight method to determine the basic weight of each indicator for the power metering device to be evaluated.

[0160] The basic weight determination unit is specifically used for:

[0161] Based on the power metering device to be evaluated and the determined indicators, a data matrix is ​​constructed; the elements in the data matrix represent the indicator values ​​of the power metering device to be evaluated.

[0162] Based on the data matrix, the weight of each indicator of the power metering device to be evaluated is calculated; when calculating the weight, the sum of each indicator value and the preset smoothing coefficient is used for the weight calculation.

[0163] Based on the weight of each indicator and the number of power metering devices to be evaluated, the entropy value of each indicator is determined.

[0164] The basic weight of each indicator is determined based on its entropy value and the number of indicators.

[0165] The dynamic weight determination unit 23 is used to introduce a first coefficient representing the operating scenario of the power metering device to be evaluated, and a second coefficient reflecting the life cycle stage of the power metering device to be evaluated, and adjust the basic weights to determine the dynamic weights of each indicator.

[0166] The dynamic weight determination unit is specifically used for:

[0167] The basic weights are multiplied by the first coefficient and the second coefficient respectively to obtain the dynamic weights of each indicator; the first coefficient is the operating condition sensitivity coefficient and the second coefficient is the time decay coefficient.

[0168] The operating condition sensitivity coefficient is determined based on the weighted sum of the load rate, electromagnetic interference intensity, and temperature and humidity deviation values ​​of the operating scenario; the time decay coefficient is determined based on the ratio of the service life of the power metering device to its standard service life.

[0169] The proximity determination unit 24 is used to determine the proximity of the power metering device to be evaluated by using the approximation ideal solution ranking method on the constructed weighted matrix; the elements in the weighted matrix are determined by the product of the index value and the corresponding dynamic weight; the proximity characterizes the degree to which the evaluation quantity of the power metering device to be evaluated is close to the optimal solution.

[0170] The operation status level determination unit 25 determines the operation status level of the power metering device to be evaluated based on a preset mapping relationship between proximity and operation status level.

[0171] In one feasible implementation, the system of this embodiment further includes: an abnormal state identification unit, used to identify the abnormal state of the power metering device to be evaluated; specifically used for:

[0172] Based on a preset sampling time window, real-time multi-source data is acquired, and the multi-source data acquired within the sampling time window is used as a sample point of the power metering device to be evaluated. Based on the local anomaly factor algorithm, the LOF value of each sample point of the power metering device to be evaluated is calculated. The LOF value represents the degree to which the current sample point deviates from its neighboring sample points. By comparing the LOF value of the sample point with the pre-calculated thresholds, it is determined whether the sample point is in an abnormal state. The thresholds are determined based on the baseline threshold and the dynamic weights of each indicator.

[0173] In one feasible implementation, the system of this embodiment further includes a remaining lifetime prediction unit; specifically used for:

[0174] Based on the standard service life of the power metering device to be evaluated and the influence coefficients of key factors affecting the service life, the remaining service life of the power metering device to be evaluated is determined; the key factors include at least operating temperature, operating load, maintenance quality and electromagnetic interference intensity; the influence coefficients of the key factors are determined by fitting a gradient boosting regression model to multi-source data.

[0175] In one feasible implementation, the system of this embodiment further includes a fault risk determination unit, specifically used to: determine the fault risk points of the power metering device and the optimal update cycle recommendation based on the remaining service life and operating status level of the power metering device to be evaluated.

[0176] This application utilizes multi-source data from power metering devices for operational status assessment and determines the dynamic weights of each indicator corresponding to the multi-source data. Based on the indicator values ​​and corresponding dynamic weights, the operational status level of the power metering device is determined. Furthermore, the basic weights are adjusted using a first coefficient characterizing the operating scenario of the power metering device and a second coefficient representing its lifecycle stage to determine the dynamic weights. Because the determination of the dynamic weights considers the influencing factors of different operating conditions, such as the operating scenario and lifecycle stage of the power metering device, the determined dynamic weights can adapt to power metering devices under different operating conditions. This ensures that the final operational status level assessment result is adapted to the operating conditions of the power metering device being assessed, solving the problem of low accuracy in operational status assessment caused by fixed weights.

[0177] Based on the same inventive concept as the foregoing embodiments of this application, this application also provides a computing device.

[0178] like Figure 3 As shown, the computing device includes a memory 31 and a processor 32. The memory 31 can be configured to store various other data to support operation on the electronic device. Examples of such data include instructions for any application or method used to operate on the electronic device. The memory 31 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0179] The processor 32, coupled to the memory 31, is used to execute the computer program stored in the memory 31 to perform an evaluation method for an electricity metering device as described in the foregoing embodiments.

[0180] When processor 32 executes the computer program to perform an evaluation method for a power metering device, it uses multi-source data from the power metering device to evaluate its operating status and determines the dynamic weights of each indicator corresponding to the multi-source data. Based on the indicator values ​​and corresponding dynamic weights, it determines the operating status level of the power metering device. Furthermore, it adjusts the basic weights using a first coefficient characterizing the operating scenario of the power metering device and a second coefficient representing its life cycle stage to determine the dynamic weights. Because the determination of the dynamic weights considers the influence of different operating conditions, such as the operating scenario and life cycle stage of the power metering device, the determined dynamic weights can adapt to power metering devices under different operating conditions. This ensures that the final evaluation result of the operating status level is adapted to the operating conditions of the power metering device being evaluated, solving the problem of low accuracy in operating status evaluation caused by fixed weights.

[0181] When the processor 32 executes the computer program in the memory 31, in addition to the functions described above, it can also perform other functions, as detailed in the descriptions of the preceding embodiments.

[0182] Furthermore, such as Figure 3 As shown, the computing device also includes other components such as a display 34, a communication component 33, a power supply component 35, and an audio component 36. Figure 3 The diagram only shows some components and does not mean that the computing device includes only these components. Figure 3 The components shown.

[0183] Accordingly, embodiments of this application also provide a computer-readable storage medium storing a computer program, which, when executed by a computer, can implement the methods provided in the above embodiments.

[0184] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0185] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in various embodiments or some parts of the embodiments.

[0186] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method of evaluating an electric power metering device, characterized by, include: Acquire multi-source data that can assess the operating status of power metering devices, and determine the corresponding indicators for each data type in the multi-source data based on the preset mapping relationship between data types and indicators. For each indicator of the power metering device to be evaluated, the entropy weight method is used to determine the basic weight of each indicator. A first coefficient representing the operating scenario of the power metering device to be evaluated, and a second coefficient reflecting the life cycle stage of the power metering device to be evaluated are introduced to adjust the basic weights in order to determine the dynamic weights of each indicator. For the constructed weighted matrix, the proximity of the power metering device to be evaluated is determined by the approximation of the ideal solution ranking method; the elements in the weighted matrix are determined by the product of the index value and the corresponding dynamic weight; the proximity characterizes the degree to which the evaluation quantity of the power metering device to be evaluated is close to the optimal solution. Based on the preset mapping relationship between proximity and operating status level, the operating status level of the power metering device to be evaluated is determined.

2. The evaluation method of the electric power metering device according to claim 1, characterized by, The multi-source data includes at least the technical parameter data characterizing the inherent characteristics of the power metering device, the operation data characterizing the real-time operation performance of the power metering device, the environmental monitoring data characterizing the environment in which the power metering device is located, the maintenance record data characterizing the maintenance of the power metering device, and the life cycle data characterizing the aging and risk characteristics of the power metering device.

3. The evaluation method of the electric power metering device according to claim 1, characterized by, For each index of the power metering device to be evaluated, the entropy weight method is used to determine the basic weight of each index, including: Based on the power metering device to be evaluated and the determined indicators, a data matrix is ​​constructed; the elements in the data matrix represent the indicator values ​​of the power metering device to be evaluated. Based on the data matrix, the weight of each indicator of the power metering device to be evaluated is calculated; when calculating the weight, the sum of each indicator value and the preset smoothing coefficient is used for the weight calculation. Based on the weight of each indicator and the number of power metering devices to be evaluated, the entropy value of each indicator is determined. The basic weight of each indicator is determined based on its entropy value and the number of indicators.

4. The evaluation method of the electric power metering device according to claim 1, characterized by, The basic weights are adjusted to determine the dynamic weights of each indicator, including: The basic weights are multiplied by the first coefficient and the second coefficient respectively to obtain the dynamic weights of each indicator; the first coefficient is the operating condition sensitivity coefficient and the second coefficient is the time decay coefficient. The operating condition sensitivity coefficient is determined based on the weighted sum of the load rate, electromagnetic interference intensity, and temperature and humidity deviation values ​​of the operating scenario; the time decay coefficient is determined based on the ratio of the service life of the power metering device to its standard service life.

5. The method of evaluating a power metering device according to claim 1, wherein, The method further includes: Based on a preset sampling time window, real-time multi-source data are acquired, and the multi-source data acquired within the sampling time window is used as a sample point of the power metering device to be evaluated. Based on the local anomaly factor algorithm, the LOF value of each sample point of the power metering device to be evaluated is calculated; the LOF value represents the degree to which the current sample point deviates from its neighboring sample points. By comparing the LOF value of a sample point with the pre-calculated thresholds, it is determined whether the sample point is in an abnormal state; the thresholds are determined based on the baseline threshold and the dynamic weights of each indicator.

6. The method of evaluating a power metering device according to claim 1, wherein, The method further includes: The remaining service life of the power metering device to be evaluated is determined based on the standard service life of the device and the influence coefficients of key factors affecting the service life. The key factors include at least operating temperature, operating load, maintenance quality, and electromagnetic interference intensity. The influence coefficients of the key factors are determined by fitting a gradient boosting regression model to multi-source data.

7. The method of evaluating a power metering device according to claim 6, wherein, The method further includes: Based on the remaining service life and operating status level of the power metering device to be evaluated, the fault risk points of the power metering device and the optimal replacement cycle are determined.

8. An evaluation system for an electricity metering device, characterized in that, include: The multi-source data acquisition unit is used to acquire multi-source data that can be used to evaluate the operating status of the power metering device, and to determine the corresponding indicators for each data type in the multi-source data based on the preset mapping relationship between data types and indicators. The basic weight determination unit uses the entropy weight method to determine the basic weight of each indicator for the power metering device to be evaluated. The dynamic weight determination unit is used to introduce a first coefficient representing the operating scenario of the power metering device to be evaluated, and a second coefficient reflecting the life cycle stage of the power metering device to be evaluated, and adjust the basic weights to determine the dynamic weights of each indicator. The proximity determination unit is used to determine the proximity of the power metering device to be evaluated by using the ideal solution ranking method on the constructed weighted matrix; the elements in the weighted matrix are determined by the product of the index value and the corresponding dynamic weight; the proximity characterizes the degree to which the evaluation quantity of the power metering device to be evaluated is close to the optimal solution. The operation status level determination unit determines the operation status level of the power metering device to be evaluated based on a preset mapping relationship between proximity and operation status level.

9. An electronic device, characterized in that, include: A processor, a memory, and a program or instructions stored in the memory and executable on the processor, wherein the program or instructions, when executed by the processor, implement the steps of the method as claimed in any one of claims 1-7.

10. A storage medium, characterized in that, include: The storage medium stores a program or instructions that, when executed by a processor, implement the steps of the method as described in any one of claims 1-7.

Images