Meter-based Fault Detection Method and System

Abstract

The present invention discloses a fault detection method and system based on an electric meter, relating to the technical field of electric meter fault detection. The fault detection method based on an electric meter includes the following steps: analyzing and setting an electric meter fault warning level according to the evaluation result of the abnormal degree of the electric meter power parameters; analyzing and setting an electric meter fault warning level according to the evaluation result of the hidden danger of the abnormal level of the electric meter position; analyzing, judging and setting an electric meter fault warning level according to the evaluation result of the abnormal degree of the electric meter magnetic force parameters; and determining a corresponding electric meter fault warning scheme according to the electric meter fault warning level. By detecting the electric meter power parameters, the electric meter position parameters and the electric meter magnetic force parameters, and comprehensively analyzing to obtain the electric meter fault warning level, and then determining the corresponding electric meter fault warning scheme, the present invention achieves the effect of improving the adaptability of the electric meter fault detection method to the detection of exogenous faults, and solves the problem of insufficient adaptability of the electric meter fault detection method to the detection of exogenous faults in the prior art.

Description

Technical Field

[0001] The present invention relates to the technical field of electric meter fault detection, and particularly to a fault detection method and system based on an electric meter. Background Art

[0002] With the growth of energy demand and the development of smart grids, electric meters, as key devices for energy management, are playing an increasingly important role. The main function of traditional electric meters is to measure and record power consumption, while modern smart electric meters can also provide more value-added services, such as real-time monitoring, remote meter reading, fault detection, etc. This provides more accurate data for power companies and a more intelligent and convenient power consumption experience for users. However, smart electric meters are still relatively weak in detecting exogenous faults.

[0003] The fault detection method based on an electric meter is achieved in the following way, including power anomaly detection, where the difference between the real-time power and the baseline power is calculated to determine whether there is a power anomaly.

[0004] For example, the electric meter movement detection method, circuit and device disclosed in the patent application with the publication number: CN110646653A, includes: acquiring the data information collected by the position movement detection unit in the electric meter; calculating the data information to obtain the position change value of the electric meter; comparing the position change value with a preset threshold to determine whether to control the relay to cut off the power.

[0005] For example, a single-phase liquid crystal electric meter for preventing electricity theft disclosed in the invention patent announcement with the announcement number: CN106771440B, includes: a meter case, live wire and neutral wire connection holes for accessing the commercial power supply, a microprocessor installed in the meter case, and a power module, a clock module, a storage module, an electrical parameter comprehensive detection module, a display module, and a communication module connected thereto; characterized in that: a shielding cover is provided in the meter case, the power module, the clock module, the storage module, the electrical parameter comprehensive detection module, and the display module are all installed in the shielding cover, and the communication module is located outside the shielding cover and inside the meter case; it further includes a self-detection module, including a digital control analog switch connected in parallel between the live wire and the neutral wire, a test resistor connected in series with the digital control analog switch, and the signal terminal of the digital control analog switch is connected to the microprocessor.

[0006] However, in the process of implementing the technical solution of the invention in the embodiments of the present application, it is found that the above technologies have at least the following technical problems:

[0007] In the prior art, the method for detecting electric meter faults is generally obtained through the detection and analysis of endogenous power parameters. However, for exogenous factor interferences that cause abnormal detection performance of the electric meter functions, including strong electromagnetic interference, additional wiring, or malicious tampering, etc., the existing smart electric meters have insufficient response to the exogenous fault detection method, and there is a problem that the fault detection method of the electric meter has insufficient adaptability to exogenous faults. Summary of the Invention

[0008] By providing a fault detection method and system based on an electric meter, the embodiments of the present application solve the problem in the prior art that the fault detection method of the electric meter has insufficient adaptability to exogenous faults, and achieve the effect of improving the adaptability of the fault detection method of the electric meter to exogenous faults.

[0009] The embodiments of the present application provide a fault detection method based on an electric meter, including the following steps: performing electric meter power parameter detection, obtaining an evaluation result of the abnormal degree of the electric meter power parameters through the hidden danger evaluation of the abnormal degree of the electric meter power parameters, and analyzing and setting the electric meter fault warning level according to the evaluation result of the abnormal degree of the electric meter power parameters; performing electric meter position parameter detection, obtaining an evaluation result of the hidden danger of the mutation level of the electric meter position through the hidden danger evaluation of the mutation level of the electric meter position parameters, and analyzing and setting the electric meter fault warning level according to the evaluation result of the hidden danger of the mutation level of the electric meter position; performing electric meter magnetic force parameter detection, obtaining an evaluation result of the abnormal degree of the electric meter magnetic force parameters through the hidden danger evaluation of the sudden change state of the electric meter magnetic force parameters, and analyzing and obtaining the evaluation result of the abnormal degree of the electric meter magnetic force parameters by combining the evaluation result of the hidden danger of the mutation level of the electric meter position and the evaluation result of the abnormal degree of the electric meter power parameters, and analyzing, judging, and setting the electric meter fault warning level according to the evaluation result of the abnormal degree of the electric meter magnetic force parameters; determining the corresponding electric meter fault warning plan according to the electric meter fault warning level.

[0010] Further, the specific process of obtaining the evaluation result of the abnormal degree of the electric meter power parameters is as follows: obtaining the electric meter power detection parameters through the electric meter intelligent power parameter detection device, where the electric meter power detection parameters include the electric meter power detection voltage parameter, the electric meter power detection current parameter, the electric meter power detection power parameter, the electric meter power detection power factor parameter, and the electric meter power detection electric energy parameter; obtaining the historical electric meter power detection parameters corresponding to the electric meter, combining the historical electric meter power detection parameters as the training data set of the local outlier factor algorithm, and calculating the average value of the local outlier factor of the historical electric meter power detection parameters through the local outlier factor algorithm; analyzing the electric meter power detection parameters through the local outlier factor algorithm to obtain the average value of the local outlier factor of the electric meter power detection parameters.

[0011] Further, the specific process of analyzing and setting the electricity meter fault warning level according to the evaluation result of the abnormal degree of the electricity meter power parameters is as follows: comparing and analyzing the average value of the local outlier factor of the historical electricity meter power detection parameters with the average value of the local outlier factor of the electricity meter power detection parameters, and recording the difference between the average value of the local outlier factor of the electricity meter power detection parameters and the average value of the local outlier factor of the historical electricity meter power detection parameters as the abnormal degree value of the electricity meter power parameters; the abnormal degree value of the electricity meter power parameters is used to represent the hidden danger level corresponding to the abnormal degree of the electricity meter power parameters; if the abnormal degree value of the electricity meter power parameters exceeds the preset local outlier factor difference threshold, the electricity meter fault warning level is set to the first level of electricity meter fault warning, and if the abnormal degree value of the electricity meter power parameters does not exceed the preset local outlier factor difference threshold, the electricity meter fault warning level is not set; the preset local outlier factor difference threshold is used to describe the limit value of the abnormal degree of the sudden change of the electricity meter power parameters exceeding the fluctuation range of the monitored user electricity consumption habits.

[0012] Further, the specific process of obtaining the hidden danger assessment result of the electricity meter position mutation level is as follows: establishing a three-dimensional coordinate system with the center of the electricity meter as the origin, collecting the three-dimensional coordinate data of the electricity meter through the electricity meter position sensing device, and collecting the real-time timestamp data of the electricity meter movement through the electricity meter time collection device; analyzing the change time of the electricity meter movement state, comparing and analyzing the real-time timestamp data of the electricity meter movement with the historical timestamp data of the electricity meter movement state, and obtaining the abnormal correction factor of the electricity meter position mutation time; analyzing the electricity meter movement state according to the three-dimensional coordinate data through the moving trajectory clustering algorithm, and comprehensively analyzing the hidden danger value of the electricity meter position mutation in combination with the abnormal correction factor of the electricity meter position mutation time; the hidden danger value of the electricity meter position mutation is used to represent the hidden danger level corresponding to the abnormal degree of the mutation of the three-dimensional coordinate data of the electricity meter; the abnormal correction factor of the electricity meter position mutation time is used to describe the correction level of the abnormal degree of the electricity meter position mutation time for the hidden danger value of the electricity meter position mutation.

[0013] Further, the specific process of analyzing and setting the electricity meter fault warning level according to the hidden danger assessment result of the electricity meter position mutation level is as follows: if the hidden danger value of the electricity meter position mutation exceeds the preset electricity meter position mutation hidden danger threshold and the abnormal degree value of the electricity meter power parameters does not exceed the preset local outlier factor difference threshold, the electricity meter fault warning level is set to the first level of electricity meter fault warning; if the hidden danger value of the electricity meter position mutation exceeds the preset electricity meter position mutation hidden danger threshold and the abnormal degree value of the electricity meter power parameters exceeds the preset local outlier factor difference threshold, the electricity meter fault warning level is set to the second level of electricity meter fault warning; the preset electricity meter position mutation hidden danger threshold is used to describe the limit value of the abnormal degree of the sudden change of the three-dimensional coordinate data of the electricity meter exceeding the fluctuation range of the position movement during the normal operation adjustment of the monitored electricity meter.

[0014] Further, the specific steps for analyzing and obtaining the evaluation result of the abnormal degree of the electric meter magnetic force parameter by combining the evaluation result of the hidden danger level of the electric meter position mutation and the evaluation result of the abnormal degree of the electric meter power parameter are as follows: Obtain the electric meter magnetic force detection parameter through the electric meter intelligent magnetic force parameter detection device; perform data denoising and data normalization on the electric meter magnetic force detection parameter to obtain the standardized data of the electric meter magnetic force. Extract abnormal magnetic force data from the historical fault detection library of the electric meter magnetic force parameter to obtain the historical abnormal data set of the electric meter magnetic force parameter. After merging the historical abnormal data set of the electric meter magnetic force parameter and the standardized data of the electric meter magnetic force, perform data segmentation to obtain the training set and test set of the electric meter magnetic force detection data; construct an electric meter magnetic force neural network model, and use the training set and test set of the electric meter magnetic force detection data to train the electric meter magnetic force neural network model; the electric meter magnetic force neural network model predicts the real-time monitored electric meter magnetic force detection parameter, and combines the evaluation result of the hidden danger level of the electric meter position mutation and the calculation formula of the abnormal degree of the electric meter power parameter to obtain the evaluation value of the abnormal degree of the electric meter magnetic force parameter.

[0015] Further, the specific constraint formula for the evaluation value of the abnormal degree of the electric meter magnetic force parameter is: perform data standardization processing on the electric meter magnetic force mutation peak value data to obtain the electric meter magnetic force mutation peak value;

[0016]

[0017] In the formula, η represents the evaluation value of the abnormal degree of the electric meter magnetic force parameter, represents the abnormal degree value of the electric meter power parameter, θ represents the hidden danger value of the electric meter position mutation, and ε represents the electric meter magnetic force mutation peak value.

[0018] Further, the specific process for analyzing, judging, and setting the electric meter fault warning level according to the evaluation result of the abnormal degree of the electric meter magnetic force parameter is as follows: If the evaluation value of the abnormal degree of the electric meter magnetic force parameter exceeds the preset electric meter magnetic force mutation hidden danger threshold, set the electric meter fault warning level to the third level of the electric meter fault warning; the preset electric meter magnetic force mutation hidden danger threshold is used to describe that the abnormal degree of the sudden change of the electric meter magnetic force data exceeds the allowable limit value of the fluctuation range of the magnetic force when the corresponding electric meter is working normally.

[0019] Further, the specific steps for determining the corresponding electricity meter fault warning plan according to the electricity meter fault warning level are as follows: If the electricity meter fault warning level is the first level of electricity meter fault warning, a first-level warning of electricity meter abnormal hidden danger is issued, and relevant personnel are notified to immediately check the power parameters or position parameters of the corresponding electricity meter and feedback the inspection results; if the electricity meter fault warning level is the second level of electricity meter fault warning, a second-level warning of electricity meter abnormal hidden danger is issued, and relevant personnel are notified to immediately check the power parameters and position parameters of the corresponding electricity meter and feedback the inspection results; if the electricity meter fault warning level is the third level of electricity meter fault warning, a second-level warning of electricity meter abnormal hidden danger is issued, and relevant personnel are notified to immediately conduct on-site inspections of the power parameters, position parameters and magnetic force parameters of the corresponding electricity meter and feedback the inspection results.

[0020] The embodiment of the present application provides a fault detection system based on an electricity meter. The fault detection system based on an electricity meter includes: an electricity meter power detection and evaluation module, an electricity meter position detection and evaluation module, an electricity meter magnetic force detection and evaluation module, and an electricity meter fault warning plan module; wherein, the electricity meter power detection and evaluation module is used for detecting the power parameters of the electricity meter, obtaining the evaluation result of the abnormal degree of the electricity meter power parameters through the hidden danger evaluation of the abnormal degree of the electricity meter power parameters, and analyzing and setting the electricity meter fault warning level according to the evaluation result of the abnormal degree of the electricity meter power parameters; the electricity meter position detection and evaluation module is used for detecting the position parameters of the electricity meter, obtaining the evaluation result of the hidden danger of the mutation level of the electricity meter position through the hidden danger evaluation of the mutation level of the electricity meter position parameters, and analyzing and setting the electricity meter fault warning level according to the evaluation result of the hidden danger of the mutation level of the electricity meter position; the electricity meter magnetic force detection and evaluation module is used for detecting the magnetic force parameters of the electricity meter, obtaining the evaluation result of the abnormal degree of the electricity meter magnetic force parameters through the hidden danger evaluation of the sudden change state of the electricity meter magnetic force parameters, combining the evaluation result of the hidden danger of the mutation level of the electricity meter position and the evaluation result of the abnormal degree of the electricity meter power parameters to analyze and obtain the evaluation result of the abnormal degree of the electricity meter magnetic force parameters, and analyzing and judging according to the evaluation result of the abnormal degree of the electricity meter magnetic force parameters to set the electricity meter fault warning level; the electricity meter fault warning plan module is used for determining the corresponding electricity meter fault warning plan according to the electricity meter fault warning level.

[0021] One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:

[0022] 1. Through the detection of the power parameters of the electricity meter, the detection of the position parameters of the electricity meter and the detection of the magnetic force parameters of the electricity meter, the electricity meter fault warning level is comprehensively analyzed, and then the corresponding electricity meter fault warning plan is determined, achieving the effect of improving the adaptability of the electricity meter fault detection method to exogenous fault detection, and solving the problem of insufficient adaptability of the existing electricity meter fault detection method to exogenous fault detection.

[0023] 2. By combining the evaluation results of the hidden danger level of the abnormal position of the electricity meter and the evaluation results of the abnormal degree of the electricity meter power parameters, the evaluation results of the abnormal degree of the electricity meter magnetic force parameters are obtained. The electricity meter magnetic force neural network model is trained using the electricity meter magnetic force detection data training set. The neural network can learn and establish the mapping relationship between the magnetic force parameters and the abnormal degree, providing support for actual prediction. By comprehensively analyzing the position change and power parameters of the electricity meter, a more comprehensive and accurate abnormal evaluation value is obtained, thereby realizing the judgment accuracy of the abnormal state of the electricity meter caused by exogenous electromagnetic interference.

[0024] 3. By determining the corresponding electricity meter fault warning plan according to the electricity meter fault warning level and classifying the warnings, resources and manpower are allocated according to the severity of the electricity meter faults, and the most serious faults are preferentially processed, thereby improving the inspection efficiency and accuracy of dealing with the abnormal state of the electricity meter caused by exogenous factors. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Figure 1 It is a flowchart of a fault detection method based on an electricity meter provided by an embodiment of the present application;

[0026] Figure 2 It is a schematic diagram of a function image of an example of the abnormal degree value of the electricity meter power parameters, the hidden danger value of the abnormal position of the electricity meter, and the evaluation value of the abnormal degree of the electricity meter magnetic force parameters provided by an embodiment of the present application;

[0027] Figure 3 It is a schematic structural diagram of a process for determining a corresponding electricity meter fault warning plan according to the electricity meter fault warning level provided by an embodiment of the present application;

[0028] Figure 4 It is a schematic structural diagram of a fault detection system based on an electricity meter provided by an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0029] By providing a fault detection method and system based on an electricity meter, the embodiment of the present application solves the problem that the fault detection method of the electricity meter in the prior art has insufficient adaptability to exogenous faults, and determines the corresponding electricity meter fault warning plan by combining the results of the electricity meter power parameter detection, the electricity meter position parameter detection, and the electricity meter magnetic force parameter detection, improving the adaptability of the electricity meter fault detection method to exogenous fault detection.

[0030] The technical solution in the embodiment of the present application is to solve the above problem of insufficient adaptability of the electricity meter fault detection method to exogenous fault detection. The general idea is as follows:

[0031] By detecting the power parameters, location parameters, and magnetic parameters of the electric meter, comprehensively analyzing to obtain the fault warning level of the electric meter, and then determining the corresponding electric meter fault warning scheme, the adaptability of the fault detection method of the electric meter to external faults is improved.

[0032] To better understand the above technical solution, the above technical solution will be described in detail below in combination with the accompanying drawings of the specification and specific implementation manners.

[0033] As Figure 1 shown, it is a flowchart of a fault detection method based on an electric meter provided by an embodiment of the present application. This method is applied to a fault detection system based on an electric meter. The method includes the following steps: Detect the power parameters of the electric meter, and obtain the evaluation result of the abnormal degree of the power parameters of the electric meter through the hidden danger assessment of the abnormal degree of the power parameters of the electric meter. Analyze and set the fault warning level of the electric meter according to the evaluation result of the abnormal degree of the power parameters of the electric meter; Detect the location parameters of the electric meter, and obtain the hidden danger assessment result of the mutation level of the location of the electric meter through the hidden danger assessment of the mutation level of the location parameters of the electric meter. Analyze and set the fault warning level of the electric meter according to the hidden danger assessment result of the mutation level of the location of the electric meter; Detect the magnetic parameters of the electric meter, and obtain the evaluation result of the abnormal degree of the magnetic parameters of the electric meter through the hidden danger assessment of the sudden change state of the magnetic parameters of the electric meter, combined with the hidden danger assessment result of the mutation level of the location of the electric meter and the evaluation result of the abnormal degree of the power parameters of the electric meter. Analyze, judge, and set the fault warning level of the electric meter according to the evaluation result of the abnormal degree of the magnetic parameters of the electric meter; Determine the corresponding electric meter fault warning scheme according to the fault warning level of the electric meter.

[0034] Further, the specific process of obtaining the evaluation result of the abnormal degree of the power parameters of the electric meter is as follows: Obtain the power detection parameters of the electric meter through the intelligent power parameter detection device of the electric meter. The power detection parameters of the electric meter include the power detection voltage parameter, power detection current parameter, power detection power parameter, power detection power factor parameter, and power detection electric energy parameter of the electric meter; Obtain the historical power detection parameters corresponding to the electric meter, and combine the historical power detection parameters as the training data set of the local outlier factor algorithm. Calculate the average value of the local outlier factor of the historical power detection parameters through the local outlier factor algorithm for the historical power detection parameters; Analyze the power detection parameters of the electric meter through the local outlier factor algorithm to obtain the average value of the local outlier factor of the power detection parameters of the electric meter.

[0035] In this embodiment, the Local Outlier Factor (LOF) algorithm is a density-based outlier detection algorithm used to identify outliers in a data set. The LOF algorithm evaluates whether a test point is an outlier by comparing the density ratio of the test point to the points in its neighborhood. If the density ratio of the test point is significantly lower than that of other points, it is considered an outlier.

[0036] Further, the specific process of analyzing and setting the electricity meter fault warning level according to the evaluation result of the abnormal degree of the electricity meter power parameters is as follows: Compare and analyze the average value of the local outlier factors of the historical electricity meter power detection parameters with the average value of the local outlier factors of the electricity meter power detection parameters, and record the difference between the average value of the local outlier factors of the electricity meter power detection parameters and the average value of the local outlier factors of the historical electricity meter power detection parameters as the abnormal degree value of the electricity meter power parameters; The abnormal degree value of the electricity meter power parameters is used to represent the hidden danger level corresponding to the abnormal degree of the electricity meter power parameters; If the abnormal degree value of the electricity meter power parameters exceeds the preset local outlier factor difference threshold, set the electricity meter fault warning level to the first level of electricity meter fault warning. If the abnormal degree value of the electricity meter power parameters does not exceed the preset local outlier factor difference threshold, do not set the electricity meter fault warning level; The preset local outlier factor difference threshold is used to describe the limit value at which the abnormal degree of the sudden change of the electricity meter power parameters exceeds the fluctuation range of the monitored user electricity consumption habits.

[0037] In this embodiment, the preset local outlier factor difference threshold is obtained in the following way, including multiplying the standard deviation of the normal fluctuation range of the monitored user electricity consumption habits by a certain coefficient, such as 3 times the standard deviation. This coefficient can be determined according to specific circumstances to ensure that most normal fluctuation situations are covered; Adjust the threshold according to the actual test application results to ensure that abnormalities can be detected in a timely manner without false alarms due to excessive sensitivity; Considering seasonal changes and different electricity consumption habits of users, different thresholds may need to be set for different situations and user groups.

[0038] The abnormal degree value of the electricity meter power parameters can be obtained not only by using a dedicated electricity meter fault diagnosis tool or software to judge the data of the power system and identify possible faults or abnormal analysis, but also by using a calculation formula. The specific calculation formula is as follows:

[0039]

[0040] In the formula, represents the abnormal degree value of the electricity meter power parameters. Set the monitoring points of the electricity meter power parameters and number them in sequence. D0 represents the number of the monitoring point of the electricity meter power parameters, and D represents the total number of the monitoring points of the electricity meter power parameters.

[0041] represents the monitored voltage harmonic value of the D0th monitoring point of the electricity meter power parameters, represents the historical voltage average harmonic value corresponding to the D0th monitoring point of the electricity meter power parameters. An irregular wiring method will introduce harmonics into the voltage waveform, causing harmonic distortion. The greater the amount of electricity affected by exogenous factors, the greater the resulting voltage harmonic change. Dividing the monitored voltage harmonic value by the corresponding historical voltage average harmonic value is used to describe the degree of voltage harmonic change at the current monitoring point of the electricity meter power parameters.

[0042] The voltage harmonics are measured by a TEK series oscilloscope (with harmonic analysis using WAVESTAR software).

[0043] It represents the monitored active power value at the monitoring point of the power parameters of the D0th electric meter. It represents the historical average active power value corresponding to the monitoring point of the power parameters of the D0th electric meter. External faults interfering with the electric meter can cause the active power recorded by the electric meter to be significantly lower than the actual power consumption, resulting in an abnormal decrease in the active power. Dividing the monitored active power value by the corresponding historical average active power value is used to describe the degree of decrease in the active power at the current monitoring point of the power parameters of the electric meter. The greater the degree of decrease in the active power, the higher the abnormal degree value of the power parameters of the electric meter.

[0044] It represents the monitored reactive power value at the monitoring point of the power parameters of the D0th electric meter. It represents the historical average reactive power value corresponding to the monitoring point of the power parameters of the D0th electric meter. External faults affecting the electric meter can cause an increase in the reactive power of the power grid because improper wiring may not correctly compensate for the reactive power. Dividing the monitored active power value by the corresponding historical average active power value is used to describe the degree of change in the reactive power at the current monitoring point of the power parameters of the electric meter. The greater the degree of increase in the reactive power, the higher the abnormal degree value of the power parameters of the electric meter.

[0045] The active power value and the reactive power value are obtained through the active power measurement function of a power analyzer.

[0046] φ represents the user electricity consumption habit correction factor, which is corrected by analyzing the influence of different user electricity consumption habits on the abnormal degree value of the power parameters of the electric meter through big data user portrait related algorithms, and the value is between not less than 0 and not greater than 1.

[0047] The abnormal degree value of the power parameters of the electric meter is affected by multiple factors, including the monitored voltage harmonic value, the degree of decrease in the active power, and the degree of increase in the reactive power. As the degree of change in the degree of decrease in the active power and the degree of increase in the reactive power increases, the degree of change in the voltage harmonic value will also increase. Using the correction factor can make personalized adjustments according to the user's electricity consumption habits and more accurately reflect the abnormal degree. Combining these factors and processing them through a calculation formula helps to centrally analyze the abnormal degree, making the abnormal situation more prominent and facilitating the identification of the abnormal degree of the power parameters of the electric meter. Improving the accuracy and reliability of the abnormal detection of the power parameters of the electric meter helps to timely discover and solve the problems of abnormal power parameters, thereby improving the reliability of the fault detection method based on the electric meter.

[0048] Further, the specific process of obtaining the hidden danger evaluation result of the abnormal change level of the electric meter position is as follows: Establish a three-dimensional coordinate system with the center of the electric meter as the origin. Collect the three-dimensional coordinate data of the electric meter through the electric meter position sensing device, and collect the real-time timestamp data of the electric meter movement through the electric meter time collection device; Analyze the change time of the movement state of the electric meter, compare and analyze the real-time timestamp data of the electric meter movement with the historical timestamp data of the electric meter movement state, and obtain the abnormal correction factor of the electric meter position mutation time; Analyze the movement state of the electric meter according to the three-dimensional coordinate data through the moving trajectory clustering algorithm, and comprehensively analyze the hidden danger value of the electric meter position mutation in combination with the abnormal correction factor of the electric meter position mutation time; The hidden danger value of the electric meter position mutation is used to describe the hidden danger level corresponding to the abnormal degree of the mutation of the three-dimensional coordinate data of the electric meter; The abnormal correction factor of the electric meter position mutation time is used to describe the correction level of the abnormal degree of the electric meter position mutation time for the hidden danger value of the electric meter position mutation.

[0049] In this embodiment, for the three-dimensional coordinate data, compare and analyze the real-time timestamp data of the electric meter movement with the historical timestamp data of the electric meter movement state. For example, if the historical timestamp data of the electric meter movement state indicates that the set time for the electric meter to be re-moved during normal adjustment work is between 12:00 and 13:00 on the 1st of each month, then compare the real-time timestamp data of the electric meter movement with the historical timestamp data of the electric meter movement state. For example, if the real-time timestamp data of the electric meter movement indicates that the current time of the electric meter movement is between 12:00 and 13:00 on the 1st of each month (including any time within 12:00 to 13:00), which coincides with the set time for the electric meter to be re-moved during normal adjustment work between 12:00 and 13:00 on the 1st of each month, then the coincidence is complete. At this time, the abnormal correction factor of the electric meter position mutation time is 1. If the real-time timestamp data of the electric meter movement indicates that the current time of the electric meter movement is between 12:00 and 13:00 on the 15th of each month, which does not coincide with the set time for the electric meter to be re-moved during normal adjustment work between 12:00 and 13:00 on the 1st of each month at all, then the abnormal correction factor of the electric meter position mutation time is 100. If the coincidence degree is between complete coincidence and complete non-coincidence, then as the coincidence degree decreases, the abnormal correction factor of the electric meter position mutation time increases, and the value of the abnormal correction factor of the electric meter position mutation time is between not less than 1 and not greater than 100.

[0050] The hidden danger value of the electric meter position mutation can be obtained not only through the GIS tool to analyze and visualize the change of the electric meter position, but also through the calculation formula. The specific calculation formula is as follows:

[0051]

[0052] Where, θ represents the hidden danger value of the sudden change in the meter position. Monitor points for the meter position parameters are set, and the monitor points for the meter position parameters are numbered in sequence. Z0 represents the number of the monitor point for the meter position parameters, and Z represents the total number of the monitor points for the meter position parameters. represents the abnormal correction factor for the sudden change time of the meter position.

[0053] represents the change value of the meter coordinate at the Z0-th monitor point for the meter position parameters. represents the average historical change value of the meter coordinates at the Z0-th monitor point for the meter position parameters. The external faults of the meter will cause obvious changes in the change value of the meter coordinates relative to the average historical change value of the meter coordinates. Dividing the change value of the meter coordinates by the average historical change value of the meter coordinates is used to describe the degree of change of the meter coordinates at the current monitor point for the meter position parameters. The greater the degree of change of the meter coordinates, the higher the hidden danger value of the sudden change in the meter position. represents the relative change value of the coordinates of the adjacent meter at the Z0-th monitor point for the meter position parameters. represents the allowable value of the relative coordinate change of the adjacent meter at the Z0-th monitor point for the meter position parameters. represents the average historical change value of the relative coordinates of the adjacent meters at the Z0-th monitor point for the meter position parameters. The external faults of the meter will cause obvious changes in the relative change value of the coordinates of the adjacent meters relative to the average historical change value of the relative coordinates of the adjacent meters. However, when the relevant personnel adjust the meter during normal work, they also need to move the meter. Therefore, subtracting the allowable value of the relative coordinate change of the adjacent meters from the relative change value of the coordinates of the adjacent meters makes the evaluation more accurate and avoids misjudgment in the evaluation when the relevant personnel adjust the meter during normal work. The greater the degree of change of the relative coordinates of the adjacent meters, the higher the hidden danger value of the sudden change in the meter position.

[0054] The laser scanner is used to measure the three-dimensional coordinates of the meter. Through scanning, an accurate three-dimensional model of the meter can be obtained, which is suitable for occasions that require high-precision three-dimensional coordinate information. The change value of the meter coordinates and the relative change value of the coordinates of the adjacent meters can be obtained through the laser scanner.

[0055] The hidden danger value of the sudden change in the electricity meter position is affected by multiple factors, including the degree of change in the electricity meter coordinates, the degree of change in the relative coordinates of adjacent electricity meters, and the abnormal correction factor for the time of sudden change in the electricity meter position. When the degree of change in the electricity meter coordinates increases, the degree of change in the relative coordinates of adjacent electricity meters generally also increases. However, when relevant personnel adjust the electricity meters during normal work and adjust all electricity meters at the same time, although the degree of change in the electricity meter coordinates increases, the degree of change in the relative coordinates of adjacent electricity meters is not large. At the same time, the abnormal correction factor for the time of sudden change in the electricity meter position can be adjusted personalized according to the time when relevant personnel adjust the electricity meters during normal work, which can more accurately reflect the abnormal degree of the change in the electricity meter position. By integrating these factors and processing them through a calculation formula to centrally evaluate the abnormal degree, it is convenient to identify the change situation of the electricity meter power parameters, helps to avoid misjudgment problems in the normal work of adjusting the electricity meters, and thus improves the reliability of the fault detection method based on the electricity meter.

[0056] Further, the specific process of analyzing and setting the electricity meter fault warning level according to the evaluation result of the hidden danger of the sudden change in the electricity meter position is as follows: If the hidden danger value of the sudden change in the electricity meter position exceeds the preset hidden danger threshold of the sudden change in the electricity meter position and the abnormal degree value of the electricity meter power parameters does not exceed the preset local outlier factor difference threshold, then set the electricity meter fault warning level to the first level of electricity meter fault warning; If the hidden danger value of the sudden change in the electricity meter position exceeds the preset hidden danger threshold of the sudden change in the electricity meter position and the abnormal degree value of the electricity meter power parameters exceeds the preset local outlier factor difference threshold, then set the electricity meter fault warning level to the second level of electricity meter fault warning; The preset hidden danger threshold of the sudden change in the electricity meter position is used to describe the limit value that the abnormal degree of the sudden change in the three-dimensional coordinate data of the electricity meter exceeds the fluctuation range of the position movement during the normal work adjustment of the corresponding electricity meter.

[0057] In this embodiment, the method for determining the preset local outlier factor difference threshold includes the following steps: According to the normal work data of the electricity meter, establish a mathematical model to describe the parameter distribution of the electricity meter under normal working conditions. The mathematical model is, for example, a normal distribution or a t-distribution. According to the distribution characteristics of the mathematical model and the actual application requirements, set the abnormal threshold of the local outlier factor through a large amount of electricity meter fault data, which is the preset local outlier factor difference threshold. By setting different warning levels, refined management can be carried out according to the severity and urgency of the fault, and the fault handling process can be more effectively guided. Combining the two dimensions of position change and power parameter abnormality can more accurately identify the fault type of the electricity meter, so as to take targeted maintenance measures.

[0058] Further, the specific steps for analyzing and obtaining the evaluation result of the abnormal degree of the meter magnetic force parameter by combining the evaluation result of the meter position mutation level hidden danger and the evaluation result of the abnormal degree of the meter power parameter are as follows: Obtain the meter magnetic force detection parameter through the meter intelligent magnetic force parameter detection device; perform data denoising and data normalization on the meter magnetic force detection parameter to obtain the meter magnetic force standardized data. Extract the abnormal magnetic force data from the meter magnetic force parameter historical fault detection library to obtain the meter magnetic force parameter historical abnormal data set. After merging the meter magnetic force parameter historical abnormal data set and the meter magnetic force standardized data, perform data segmentation to obtain the meter magnetic force detection data training set and the meter magnetic force detection data test set; construct a meter magnetic force neural network model, and use the meter magnetic force detection data training set and the meter magnetic force detection data test set to train the meter magnetic force neural network model; the meter magnetic force neural network model predicts the meter magnetic force detection parameter monitored in real time, and combines the evaluation result of the meter position mutation level hidden danger and the calculation formula of the abnormal degree of the meter power parameter to obtain the evaluation value of the abnormal degree of the meter magnetic force parameter.

[0059] In this embodiment, in order to better train the neural network. Data preprocessing includes operations such as denoising, normalization, and segmentation. Denoising is to eliminate random noise in the data, normalization is to scale the data to a suitable range, and segmentation is to divide the data into a training set and a test set. During the training process of the meter magnetic force neural network model, by adjusting the weights and biases of the neural network, the model can learn the relationship between the meter magnetic force parameter and the abnormal value. In order to improve the generalization ability of the model, methods such as cross-validation can be used.

[0060] Further, the specific constraint formula for the evaluation value of the abnormal degree of the meter magnetic force parameter is: Perform data normalization processing on the meter magnetic force mutation peak value data to obtain the meter magnetic force mutation peak value;

[0061]

[0062] In the formula, η represents the evaluation value of the abnormal degree of the meter magnetic force parameter, represents the abnormal degree value of the meter power parameter, θ represents the meter position mutation hidden danger value, and ε represents the meter magnetic force mutation peak value.

[0063] In this embodiment, the evaluation value of the abnormal degree of the meter magnetic force parameter can also be obtained by using computer simulation software, such as ANSYS and COMSOL Multiphysics, to simulate the magnetic force situation in the meter, and evaluating the abnormal degree of the magnetic force parameter through the simulation results.

[0064] The meter magnetic force mutation peak value is measured by a fluxgate magnetometer, a sensor commonly used to measure the magnetic field intensity, which can accurately measure the magnetic field change and give the meter magnetic force mutation peak value.

[0065] ε represents the peak value of the sudden change in the magnetic force of the electricity meter. The peak value of the sudden change in the magnetic force of the electricity meter can be obtained after data standardization using the magnetization intensity received by the electricity meter, and the value is not less than 0 and not higher than 1. In specific situations, if the external fault interference uses the method of electromagnetic interference, the monitoring means of general smart electricity meters will fail. At this time, a shielding shell, a filter circuit, etc. can be used to reduce the impact of electromagnetic interference, or a filter circuit can be added to the electricity meter or the data transmission line to filter out high-frequency interference signals and other means to reduce or ignore electromagnetic interference. At the same time, the monitoring equipment for the magnetic force of the electricity meter can use such methods to resist interference, and at the same time give an early warning through the hardware circuit, rather than using software communication for early warning, to prevent the inability to communicate normally after being affected by electromagnetic interference; the larger the peak value of the sudden change in the magnetic force of the electricity meter, the higher the degree of the electricity meter's ability to deal with potential external faults, and the larger the evaluation value of the abnormal degree of the magnetic force parameter of the electricity meter.

[0066] The evaluation value of the abnormal degree of the magnetic force parameter of the electricity meter is affected by multiple factors, including the abnormal degree value of the electricity parameters of the electricity meter, the hidden danger value of the sudden change in the position of the electricity meter, and the peak value of the sudden change in the magnetic force of the electricity meter. If the external fault interference directly uses the method of electromagnetic interference to tamper with the electricity meter, the abnormal degree value of the electricity parameters of the electricity meter and the hidden danger value of the sudden change in the position of the electricity meter do not change much. It is necessary to comprehensively analyze in combination with the peak value of the sudden change in the magnetic force of the electricity meter to more accurately reflect the evaluation value of the abnormal degree of the magnetic force parameter of the electricity meter. By combining these factors and processing them through a calculation formula, the evaluation of the abnormal degree can be quickly amplified, which is convenient for identifying the parameter changes in various situations of the electricity meter's response to external fault interference, and helps to comprehensively improve the adaptability effect of the electricity meter's fault detection method for external fault detection. Table 1 is an example table of the evaluation value of the abnormal degree of the magnetic force parameter of the electricity meter, and Table 1 is as follows:

[0067] Table 1 Example Table of the Evaluation Value of the Abnormal Degree of the Magnetic Force Parameter of the Electricity Meter

[0068]

[0069] All the values in the table are reserved to two significant figures. As Figure 2 shown, it is a schematic diagram of the function image of the example values of the abnormal degree value of the electricity parameters of the electricity meter, the hidden danger value of the sudden change in the position of the electricity meter, and the evaluation value of the abnormal degree of the magnetic force parameter of the electricity meter provided by the embodiment of the present application. When the example value of the abnormal degree of the electricity parameters of the electricity meter is 1.2, the example value of the hidden danger value of the sudden change in the position of the electricity meter is 1.2, and the peak value of the sudden change in the magnetic force of the electricity meter changes to 0.1, at this time the example value of the evaluation value of the abnormal degree of the magnetic force parameter of the electricity meter is 1.19. Similarly, when the peak value of the sudden change in the magnetic force of the electricity meter changes to 0.5, at this time the example value of the evaluation value of the abnormal degree of the magnetic force parameter of the electricity meter is 2.386. When the peak value of the sudden change in the magnetic force of the electricity meter changes to 1, at this time the example value of the evaluation value of the abnormal degree of the magnetic force parameter of the electricity meter is 5.693. Figure 2Among them, the abscissa is the peak value of the magnetic force mutation of the electric meter, and the ordinate is the evaluation value of the abnormal degree of the magnetic force parameter of the electric meter. It can be observed that if the external fault interference means do not adopt the common external wiring of the electric meter or directly tamper with the electric meter, but adopt the electromagnetic interference method, as the peak value of the magnetic force mutation of the electric meter increases, the evaluation value of the abnormal degree of the magnetic force parameter of the electric meter also increases rapidly, which is convenient for analyzing and evaluating the abnormal degree of the magnetic force parameter of the electric meter.

[0070] Further, the specific process of analyzing, judging and setting the electric meter fault warning level according to the evaluation result of the abnormal degree of the magnetic force parameter of the electric meter is as follows: if the evaluation value of the abnormal degree of the magnetic force parameter of the electric meter exceeds the preset hidden danger threshold of the magnetic force mutation of the electric meter, the electric meter fault warning level is set to the third level of the electric meter fault warning; the preset hidden danger threshold of the magnetic force mutation of the electric meter is used to describe that the abnormal degree of the sudden change of the magnetic force data of the electric meter exceeds the allowable limit value of the fluctuation range of the magnetic force during the normal operation of the monitored electric meter.

[0071] In this embodiment, by considering the magnetic force parameters of the electric meter, a comprehensive diagnosis of the electric meter fault can be realized, including not only the power parameters and position parameters, but also the magnetic force parameters, so as to more comprehensively evaluate the fault judgment situation of the electric meter when coping with external fault interference; by collecting and analyzing the magnetic force data of a large number of in-use electric meters, the fluctuation range of the magnetic force parameters under normal use conditions can be determined. Combining the magnetic force data of the faulty electric meter, through statistical methods, such as standard deviation, the warning threshold, that is, the preset hidden danger threshold of the magnetic force mutation of the electric meter, is set. If the preset hidden danger threshold of the magnetic force mutation of the electric meter is exceeded, it is judged that the electric meter is abnormal.

[0072] Further, the specific steps for determining the corresponding electric meter fault warning plan according to the electric meter fault warning level are as follows: if the electric meter fault warning level is the first level of the electric meter fault warning, a first-level warning of the electric meter abnormal hidden danger is issued, and relevant personnel are notified to immediately check the power parameters or position parameters of the corresponding electric meter and feedback the inspection results; if the electric meter fault warning level is the second level of the electric meter fault warning, a second-level warning of the electric meter abnormal hidden danger is issued, and relevant personnel are notified to immediately check the power parameters and position parameters of the corresponding electric meter and feedback the inspection results; if the electric meter fault warning level is the third level of the electric meter fault warning, a second-level warning of the electric meter abnormal hidden danger is issued, and relevant personnel are notified to immediately conduct on-site inspections of the power parameters, position parameters and magnetic force parameters of the corresponding electric meter and feedback the inspection results.

[0073] In this embodiment, as Figure 3 shown, it is a schematic structural diagram of the process for determining the corresponding electric meter fault warning plan according to the electric meter fault warning level provided by the embodiment of the present application; once the warning is triggered, relevant personnel can immediately check the power parameters, position parameters and magnetic force parameters of the electric meter to timely detect potential faults. According to the level of the warning, maintenance resources can be reasonably allocated to ensure that key problems are solved first.

[0074] AsFigure 4 As shown in the figure, it is a schematic structural diagram of a fault detection system based on an electric meter provided by an embodiment of the present application. The fault detection system based on an electric meter provided by an embodiment of the present application includes: an electric meter power detection and evaluation module, an electric meter position detection and evaluation module, an electric meter magnetic force detection and evaluation module, and an electric meter fault warning scheme module;

[0075] Among them, the electric meter power detection and evaluation module is used to detect the electric meter power parameters, obtain the evaluation result of the abnormal degree of the electric meter power parameters through the hidden danger evaluation of the abnormal degree of the electric meter power parameters, and analyze and set the electric meter fault warning level according to the evaluation result of the abnormal degree of the electric meter power parameters;

[0076] The electric meter position detection and evaluation module is used to detect the electric meter position parameters, obtain the evaluation result of the hidden danger of the mutation level of the electric meter position through the hidden danger evaluation of the mutation level of the electric meter position parameters, and analyze and set the electric meter fault warning level according to the evaluation result of the hidden danger of the mutation level of the electric meter position;

[0077] The electric meter magnetic force detection and evaluation module is used to detect the electric meter magnetic force parameters, obtain the evaluation result of the abnormal degree of the electric meter magnetic force parameters through the hidden danger evaluation of the sudden change state of the electric meter magnetic force parameters, and analyze and judge according to the evaluation result of the abnormal degree of the electric meter magnetic force parameters to set the electric meter fault warning level in combination with the evaluation result of the hidden danger of the mutation level of the electric meter position and the evaluation result of the abnormal degree of the electric meter power parameters;

[0078] The electric meter fault warning scheme module is used to determine the corresponding electric meter fault warning scheme according to the electric meter fault warning level.

[0079] The technical solutions in the above embodiments of the present application have at least the following technical effects or advantages: Compared with the electric meter movement detection method, circuit and device disclosed in the patent application with the publication number of CN110646653A, in the embodiments of the present application, the evaluation result of the abnormal degree of the electric meter magnetic force parameters is obtained by combining the evaluation result of the hidden danger of the mutation level of the electric meter position and the evaluation result of the abnormal degree of the electric meter power parameters. The electric meter magnetic force neural network model is trained using the electric meter magnetic force detection data training set. The neural network can learn and establish the mapping relationship between the magnetic force parameters and the abnormal degree, providing support for actual prediction. By comprehensively analyzing the position change and power parameters of the electric meter, a more comprehensive and accurate abnormal evaluation value is obtained, thereby realizing the judgment accuracy of the abnormal state of the electric meter caused by exogenous electromagnetic interference; Compared with the single-phase liquid crystal electric meter for preventing electricity theft disclosed in the invention patent announcement with the publication number of CN106771440B, in the embodiments of the present application, by determining the corresponding electric meter fault warning scheme according to the electric meter fault warning level and classifying the warnings, resources and manpower are allocated according to the severity of the electric meter fault, and the most serious faults are processed preferentially, thereby realizing the improvement of the inspection efficiency and accuracy of the abnormal state of the electric meter caused by exogenous fault interference.

[0080] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a system, or a computer program product. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0081] The present invention is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to the embodiments of the present invention. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, as well as the combination of flows and / or blocks in the flowcharts and / or block diagrams, can be realized by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing devices generate means for implementing the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0082] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory generate a manufactured article including instruction means that implement the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0083] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process, so that the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0084] Although the preferred embodiments of the present invention have been described, those skilled in the art can make additional changes and modifications to these embodiments once they know the basic creative concepts. Therefore, the appended claims are intended to be construed as including the preferred embodiments and all changes and modifications falling within the scope of the present invention.

[0085] Obviously, those skilled in the art can make various modifications and variations to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalent technologies, the present invention is also intended to include these modifications and variations.

Claims

1. A fault detection method based on an electricity meter, characterized in that, Including the following steps: Conduct power parameter detection of the electricity meter, obtain the evaluation result of the abnormal degree of the electricity meter power parameters through the hidden danger assessment of the abnormal degree of the electricity meter power parameters, and analyze and set the electricity meter fault warning level according to the evaluation result of the abnormal degree of the electricity meter power parameters; Conduct position parameter detection of the electricity meter, obtain the hidden danger assessment result of the mutation level of the electricity meter position parameters through the hidden danger assessment of the mutation level of the electricity meter position parameters, and analyze and set the electricity meter fault warning level according to the hidden danger assessment result of the mutation level of the electricity meter position parameters; Conduct magnetic parameter detection of the electricity meter, obtain the evaluation result of the abnormal degree of the electricity meter magnetic parameters through the hidden danger assessment of the sudden change state of the electricity meter magnetic parameters, and analyze and judge and set the electricity meter fault warning level by combining the hidden danger assessment result of the mutation level of the electricity meter position parameters and the evaluation result of the abnormal degree of the electricity meter power parameters; Determine the corresponding electricity meter fault warning plan according to the electricity meter fault warning level; The specific steps of obtaining the evaluation result of the abnormal degree of the electricity meter magnetic parameters by combining the hidden danger assessment result of the mutation level of the electricity meter position parameters and the evaluation result of the abnormal degree of the electricity meter power parameters are as follows: Obtain the electricity meter magnetic detection parameters through the electricity meter intelligent magnetic parameter detection device; Perform data denoising and data normalization on the electricity meter magnetic detection parameters to obtain the standardized electricity meter magnetic data, extract abnormal magnetic data from the historical fault detection library of the electricity meter magnetic parameters to obtain the historical abnormal data set of the electricity meter magnetic parameters, and merge the historical abnormal data set of the electricity meter magnetic parameters and the standardized electricity meter magnetic data and then perform data segmentation to obtain the training set and test set of the electricity meter magnetic detection data; Construct an electricity meter magnetic neural network model, and use the training set and test set of the electricity meter magnetic detection data to train the electricity meter magnetic neural network model; The electricity meter magnetic neural network model predicts the electricity meter magnetic detection parameters monitored in real time, and combines the hidden danger assessment result of the mutation level of the electricity meter position parameters and the calculation formula of the evaluation result of the abnormal degree of the electricity meter power parameters to obtain the evaluation value of the abnormal degree of the electricity meter magnetic parameters; The specific constraint formula of the evaluation value of the abnormal degree of the electricity meter magnetic parameters is: perform data standardization processing on the electricity meter magnetic mutation peak data to obtain the electricity meter magnetic mutation peak; In the formula, represents the evaluation value of the abnormal degree of the magnetic force parameter of the electric meter, represents the abnormal degree value of the electric power parameter of the electric meter, represents the hidden danger value of the position mutation of the electric meter, represents the peak value of the magnetic force mutation of the electric meter.

2. The fault detection method based on an electricity meter according to claim 1, wherein The specific process of obtaining the evaluation result of the abnormal degree of the electricity meter power parameters is as follows: Obtain the electricity meter power detection parameters through the electricity meter intelligent power parameter detection device, and the electricity meter power detection parameters include the electricity meter power detection voltage parameter, the electricity meter power detection current parameter, the electricity meter power detection power parameter, the electricity meter power detection power factor parameter, and the electricity meter power detection electric energy parameter; Obtain the historical electricity meter power detection parameters corresponding to the electricity meter, merge the historical electricity meter power detection parameters as the training data set of the local outlier factor algorithm, and calculate the average value of the local outlier factor of the historical electricity meter power detection parameters through the local outlier factor algorithm; Analyze the electricity meter power detection parameters through the local outlier factor algorithm to obtain the average value of the local outlier factor of the electricity meter power detection parameters.

3. The fault detection method based on an electricity meter according to claim 1, characterized in that, The specific process of analyzing and setting the electricity meter fault warning level according to the evaluation result of the abnormal degree of the electricity meter power parameters is as follows: Compare and analyze the average value of the local outlier factor of the historical electricity meter power detection parameters with the average value of the local outlier factor of the electricity meter power detection parameters. Denote the difference between the average value of the local outlier factor of the electricity meter power detection parameters and the average value of the local outlier factor of the historical electricity meter power detection parameters as the abnormal degree value of the electricity meter power parameters; The abnormal degree value of the electricity meter power parameters is used to represent the hidden danger level corresponding to the abnormal degree of the electricity meter power parameters; If the abnormal degree value of the electricity meter power parameters exceeds the preset local outlier factor difference threshold, set the electricity meter fault warning level to the first level of electricity meter fault warning. If the abnormal degree value of the electricity meter power parameters does not exceed the preset local outlier factor difference threshold, do not set the electricity meter fault warning level; The preset local outlier factor difference threshold is used to describe the limit value at which the abnormal degree of the sudden change in the electricity meter power parameters exceeds the fluctuation range of monitoring the corresponding user electricity consumption habits.

4. The fault detection method based on an electric meter according to claim 1, characterized in that The specific process of obtaining the hidden danger assessment result of the electricity meter position mutation level is as follows: Establish a three-dimensional coordinate system with the center of the electricity meter as the origin. Collect the three-dimensional coordinate data of the electricity meter through the electricity meter position sensing device, and collect the real-time timestamp data of the electricity meter movement through the electricity meter time collection device; Analyze the change time of the electricity meter movement state, compare and analyze the real-time timestamp data of the electricity meter movement with the historical timestamp data of the electricity meter movement state, and obtain the abnormal correction factor of the electricity meter position mutation time; Analyze the electricity meter movement state according to the three-dimensional coordinate data through the moving trajectory clustering algorithm, and comprehensively analyze the electricity meter position mutation hidden danger value in combination with the abnormal correction factor of the electricity meter position mutation time; The electricity meter position mutation hidden danger value is used to describe the hidden danger level corresponding to the abnormal degree of the mutation of the three-dimensional coordinate data of the electricity meter; The abnormal correction factor of the electricity meter position mutation time is used to describe the correction level of the abnormal degree of the electricity meter position mutation time for the electricity meter position mutation hidden danger value.

5. The fault detection method based on an electricity meter according to claim 1, wherein, The specific process of analyzing and setting the electricity meter fault warning level according to the hidden danger assessment result of the electricity meter position mutation level is as follows: If the electricity meter position mutation hidden danger value exceeds the preset electricity meter position mutation hidden danger threshold and the abnormal degree value of the electricity meter power parameters does not exceed the preset local outlier factor difference threshold, set the electricity meter fault warning level to the first level of electricity meter fault warning; If the electricity meter position mutation hidden danger value exceeds the preset electricity meter position mutation hidden danger threshold and the abnormal degree value of the electricity meter power parameters exceeds the preset local outlier factor difference threshold, set the electricity meter fault warning level to the second level of electricity meter fault warning; The preset electricity meter position mutation hidden danger threshold is used to describe the limit value at which the abnormal degree of the sudden change in the three-dimensional coordinate data of the electricity meter exceeds the fluctuation range of monitoring the position movement during the normal operation adjustment of the corresponding electricity meter.

6. The fault detection method based on an electricity meter according to claim 1, wherein The specific process of analyzing, judging and setting the electricity meter fault warning level according to the assessment result of the abnormal degree of the electricity meter magnetic force parameters is as follows: If the evaluation value of the abnormal degree of the electricity meter magnetic force parameters exceeds the preset electricity meter magnetic force mutation hidden danger threshold, set the electricity meter fault warning level to the third level of electricity meter fault warning; The preset electricity meter magnetic force mutation hidden danger threshold is used to describe the allowable limit value at which the abnormal degree of the sudden change in the electricity meter magnetic force data exceeds the fluctuation range of monitoring the magnetic force of the corresponding electricity meter during normal operation.

7. The fault detection method based on an electricity meter according to claim 1, wherein The specific steps for determining the corresponding electricity meter fault warning plan according to the electricity meter fault warning level are as follows: If the electricity meter fault warning level is the first-level electricity meter fault warning, issue a first-level warning for potential electricity meter anomalies, and notify relevant personnel to immediately check the power parameters or location parameters of the corresponding electricity meter and feedback the inspection results; If the electricity meter fault warning level is the second-level electricity meter fault warning, issue a second-level warning for potential electricity meter anomalies, and notify relevant personnel to immediately check the power parameters and location parameters of the corresponding electricity meter and feedback the inspection results; If the electricity meter fault warning level is the third-level electricity meter fault warning, issue a second-level warning for potential electricity meter anomalies, and notify relevant personnel to immediately conduct on-site inspections of the power parameters, location parameters, and magnetic force parameters of the corresponding electricity meter and feedback the inspection results.

8. A fault detection system based on an electric meter, which applies the fault detection method based on an electric meter according to any one of claims 1-7, characterized in that, The fault detection system based on the electricity meter includes: an electricity meter power detection and evaluation module, an electricity meter location detection and evaluation module, an electricity meter magnetic force detection and evaluation module, and an electricity meter fault warning plan module; Among them, the electricity meter power detection and evaluation module is used to detect the power parameters of the electricity meter. Through the hidden danger assessment of the abnormal degree of the electricity meter power parameters, the evaluation result of the abnormal degree of the electricity meter power parameters is obtained, and the electricity meter fault warning level is analyzed and set according to the evaluation result of the abnormal degree of the electricity meter power parameters; The electricity meter location detection and evaluation module is used to detect the location parameters of the electricity meter. Through the hidden danger assessment of the mutation level of the electricity meter location parameters, the evaluation result of the hidden danger of the electricity meter location mutation level is obtained, and the electricity meter fault warning level is analyzed and set according to the evaluation result of the hidden danger of the electricity meter location mutation level; The electricity meter magnetic force detection and evaluation module is used to detect the magnetic force parameters of the electricity meter. Through the hidden danger assessment of the sudden change state of the electricity meter magnetic force parameters, combined with the evaluation result of the hidden danger of the electricity meter location mutation level and the evaluation result of the abnormal degree of the electricity meter power parameters, the evaluation result of the abnormal degree of the electricity meter magnetic force parameters is obtained, and the electricity meter fault warning level is analyzed and judged and set according to the evaluation result of the abnormal degree of the electricity meter magnetic force parameters; The electricity meter fault warning plan module is used to determine the corresponding electricity meter fault warning plan according to the electricity meter fault warning level.

Images