Safety monitoring method and device of electric energy meter and intelligent electric energy meter

Abstract

The invention relates to the technical field of electric power safety, and particularly discloses a safety monitoring method and device for an electric energy meter and an intelligent electric energy meter, and the safety monitoring method comprises the steps: collecting each type of operation monitoring data in the operation process of the electric energy meter, carrying out the preprocessing of each type of operation monitoring data, and obtaining each type of effective operation monitoring data; when it is judged that abnormal operation monitoring data exists in each type of effective operation monitoring data based on the anomaly detection model, extracting all abnormal operation monitoring data in the corresponding type of effective operation monitoring data; evaluating the safety risk of the electric energy meter based on all abnormal operation monitoring data in all types of effective operation monitoring data and risk evaluation fuzzy logic, and determining the risk level of the electric energy meter; when the risk level of the electric energy meter reaches a risk level threshold value, alarm information is sent out through the wireless communication module; effective monitoring of the operation of the electric energy meter is realized, and the safety and stability of the use of the electric energy meter are improved.

Description

Technical Field

[0001] The present invention relates to the field of electric power safety technology, and in particular to a safety monitoring method and device for an electric energy meter and an intelligent electric energy meter. Background Art

[0002] In today's energy management and power supply field, the accuracy and safety of energy meters, as important equipment for measuring the amount of electricity used, are crucial to the stable operation of the power system and the interests of users and power suppliers. With the continuous development of smart grids, the functions of energy meters are becoming increasingly complex, and the amount of data during their operation is also increasing. In order to ensure the normal operation and safe use of energy meters, they need to be effectively monitored. At present, the common way to monitor energy meters is mainly through regular manual inspections and simple data collection.

[0003] However, this approach has many limitations. Manual inspections are inefficient and difficult to detect problems in real time; simple data collection cannot fully and deeply reflect the operating status of the energy meter. At the same time, with the development of intelligent and information-based power systems, the requirements for the analysis and processing capabilities of energy meter operation data are getting higher and higher. When faced with massive amounts of operation monitoring data, existing monitoring methods are difficult to quickly and accurately extract valuable information, and are unable to timely and effectively identify potential safety hazards and abnormal situations and accurately assess risk levels.

[0004] Therefore, the present invention provides a safety monitoring method and device for an electric energy meter and a smart electric energy meter. Summary of the invention

[0005] The present invention provides a safety monitoring method, device and intelligent electric energy meter for an electric energy meter. By collecting and preprocessing operation monitoring data, accurate and effective data are obtained, providing a reliable basis for subsequent analysis. The abnormal detection model can timely detect abnormal situations in various types of operation monitoring data. The abnormal operation monitoring data is extracted, and the safety risk of the electric energy meter is evaluated in combination with risk assessment fuzzy logic to determine the risk level, making the evaluation more scientific and comprehensive. When the risk level reaches the threshold, an alarm message is issued, which can promptly remind relevant personnel to take measures to prevent risks. Effective monitoring of the operation of the electric energy meter is achieved, and the safety and stability of the use of the electric energy meter are improved.

[0006] The present invention provides a safety monitoring method for an electric energy meter, comprising:

[0007] S1: Collect each type of operation monitoring data during the operation of the electric energy meter, and pre-process each type of operation monitoring data to obtain each type of effective operation monitoring data;

[0008] S2: When it is determined based on the anomaly detection model that there is abnormal operation monitoring data in each category of valid operation monitoring data, all abnormal operation monitoring data in the corresponding category of valid operation monitoring data are extracted;

[0009] S3: Evaluate the safety risk of the electric energy meter based on all abnormal operation monitoring data of all types of effective operation monitoring data and risk assessment fuzzy logic to determine the risk level of the electric energy meter;

[0010] S4: When the risk level of the electric energy meter reaches the risk level threshold, an alarm message is issued.

[0011] Preferably, the safety monitoring method of the electric energy meter, S2: when it is determined based on the abnormality detection model that there is abnormal operation monitoring data in each type of effective operation monitoring data, all abnormal operation monitoring data in the corresponding type of effective operation monitoring data are extracted, including:

[0012] Acquire a preset number of manual judgment instances of electric energy meter monitoring data, and extract abnormal operation monitoring data and complete operation monitoring data contained in each manual judgment instance of electric energy meter monitoring data;

[0013] The abnormal operation monitoring data and the complete operation monitoring data contained in the manual judgment instance of the electric energy meter monitoring data are used to train the neural network model to obtain the abnormality detection model of the electric energy meter;

[0014] Input each type of effective operation monitoring data obtained in real time into the anomaly detection model to determine whether there is abnormal operation monitoring data in each type of effective operation monitoring data;

[0015] If so, all abnormal operation monitoring data in the corresponding class of effective operation monitoring data are obtained based on the output result of the anomaly detection model;

[0016] Otherwise, keep the corresponding model output results.

[0017] Preferably, the safety monitoring method of the electric energy meter, S3: based on all abnormal operation monitoring data in all types of effective operation monitoring data and risk assessment fuzzy logic, the safety risk of the electric energy meter is evaluated to determine the risk level of the electric energy meter, including:

[0018] Extract the performance features of all abnormal operation monitoring data from all types of effective operation monitoring data, and perform feature quantization and normalization on the performance features of all abnormal operation monitoring data to obtain standard quantified values ​​of the performance features of all abnormal operation monitoring data;

[0019] Define all fuzzy sets and corresponding membership functions and all fuzzy rules of risk assessment fuzzy logic;

[0020] Fuzzy reasoning and defuzzification are performed based on the standard quantitative values ​​of the performance characteristics of all abnormal operation monitoring data in all types of effective operation monitoring data, all fuzzy sets and corresponding membership functions of risk assessment fuzzy logic, and all fuzzy rules, and combined with the preset risk level classification standards to determine the risk level of the electric energy meter.

[0021] Preferably, the safety monitoring method of the electric energy meter performs fuzzy reasoning and defuzzification based on the standard quantitative values ​​of the performance characteristics of all abnormal operation monitoring data in all types of effective operation monitoring data, all fuzzy sets of risk assessment fuzzy logic and corresponding membership functions and all fuzzy rules, and determines the risk level of the electric energy meter in combination with the preset risk level classification standard, including:

[0022] Based on the performance characteristic standard quantified values ​​of all abnormal operation monitoring data in all types of effective operation monitoring data, all fuzzy sets of risk assessment fuzzy logic and corresponding membership functions, the membership of each performance characteristic standard quantified value to each fuzzy set is determined;

[0023] Based on the membership of each performance characteristic standard quantization value to each fuzzy set and the premise part of all fuzzy rules, all fuzzy rules activated by each performance characteristic standard quantization value are determined, and the membership of each performance characteristic standard quantization value to all fuzzy sets contained in the premise part of each corresponding activated fuzzy rule is regarded as all activation strengths of the corresponding fuzzy rules;

[0024] Based on all fuzzy rules activated by the quantitative values ​​of all performance feature standards and all corresponding activation intensities, combined reasoning and defuzzification are performed, and the risk level of the electric energy meter is determined in combination with the preset risk level classification standard.

[0025] Preferably, the safety monitoring method of the electric energy meter is based on the combined reasoning and defuzzification of all fuzzy rules activated by all the quantized values ​​of the performance characteristic standards and all the corresponding activation intensities, and combined with the preset risk level classification standard to determine the risk level of the electric energy meter, including:

[0026] Obtain the membership distribution of the fuzzy set of the conclusion part of all fuzzy rules activated by all the standard quantization values ​​of the performance characteristics, take each activation intensity corresponding to each fuzzy rule activated by all the standard quantization values ​​of the performance characteristics as a membership adjustment multiple, perform membership adjustment on the membership distribution of the fuzzy set of the conclusion part of the corresponding fuzzy rule, and obtain the adjusted membership distribution of the fuzzy set of the conclusion part of the corresponding fuzzy rule under each corresponding activation intensity;

[0027] The adjusted membership distributions of the conclusion parts of all fuzzy rules with the same corresponding conclusion parts in all fuzzy rules activated by the quantitative values ​​of all performance characteristic standards are summarized under all corresponding activation intensities to obtain all the adjusted membership distributions of each conclusion;

[0028] Based on all the adjusted membership distributions of all the conclusions, combined reasoning and defuzzification are performed to obtain the fuzzy logic decision value;

[0029] The preset risk level classification standard is retrieved based on the fuzzy logic decision value to determine the risk level of the electric energy meter.

[0030] Preferably, the safety monitoring method of the electric energy meter performs combined reasoning and defuzzification based on all adjusted membership distributions of all conclusions to obtain a fuzzy logic decision value, including:

[0031]

[0032] In the formula, R u is the fuzzy logic decision value, max is the maximum independent variable value in the membership distribution function, n is the total number of conclusions, m is i is the total number of all adjusted membership distributions of the i-th conclusion, θ ij (x) is the function representation of the jth adjusted membership distribution of the ith conclusion, x is the independent variable of the adjusted membership distribution function, α ij is the preset weight of the fuzzy rule corresponding to the jth adjusted membership distribution of the ith conclusion, From 0 to max Perform an integral operation with the integral variable x, From 0 to max Perform an integration operation with the integral variable x.

[0033] Preferably, in the safety monitoring method of the electric energy meter, the alarm information is sent through the wireless communication module.

[0034] Preferably, the safety monitoring method of the electric energy meter further includes:

[0035] All types of operation monitoring data and all abnormal operation monitoring data, all risk assessment results and all alarm information acquired in real time are stored in the monitoring background, among which the risk assessment results include the risk level of the electric energy meter.

[0036] The present invention provides a safety monitoring device for an electric energy meter, which is used to execute any of the above safety monitoring methods for an electric energy meter, comprising:

[0037] The data acquisition and processing module is used to collect each type of operation monitoring data during the operation of the electric energy meter, and pre-process each type of operation monitoring data to obtain each type of effective operation monitoring data;

[0038] The abnormal data extraction module is used to extract all abnormal operation monitoring data in the corresponding class of effective operation monitoring data when it is determined based on the abnormal detection model that there is abnormal operation monitoring data in each class of effective operation monitoring data;

[0039] A safety risk assessment module is used to assess the safety risk of the electric energy meter based on all abnormal operation monitoring data in all types of effective operation monitoring data and risk assessment fuzzy logic, and determine the risk level of the electric energy meter;

[0040] The alarm module is used to issue an alarm message when the risk level of the electric energy meter reaches the risk level threshold.

[0041] The present invention provides an intelligent electric energy meter connected to the above safety monitoring device.

[0042] The beneficial effects of the present invention compared to the prior art are as follows: by collecting and preprocessing operation monitoring data, accurate and effective data can be obtained, providing a reliable basis for subsequent analysis. The abnormal detection model can promptly detect abnormal situations in various types of operation monitoring data. The abnormal operation monitoring data is extracted, and the safety risk of the electric energy meter is evaluated in combination with the risk assessment fuzzy logic to determine the risk level, making the evaluation more scientific and comprehensive. When the risk level reaches the threshold, an alarm message is issued, which can promptly remind relevant personnel to take measures to prevent risks. Effective monitoring of the operation of the electric energy meter is achieved, and the safety and stability of the use of the electric energy meter are improved.

[0043] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures specifically pointed out in this application document.

[0044] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0046] Figure 1 is a flow chart of a safety monitoring method for an electric energy meter in an embodiment of the present invention;

[0047] Figure 2It is a connection diagram of the smart electric energy meter, the safety monitoring device, and the monitoring background in the embodiment of the present invention;

[0048] Figure 3 Schematic diagram of a safety monitoring device for an electric energy meter in an embodiment of the present invention. DETAILED DESCRIPTION

[0049] The preferred embodiments of the present invention are described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0050] Embodiment 1:

[0051] The present invention provides a safety monitoring method for an electric energy meter, referring to Figure 1 ,include:

[0052] S1: Collect each type of operation monitoring data during the operation of the electric energy meter, and pre-process each type of operation monitoring data to obtain each type of effective operation monitoring data;

[0053] S2: When it is determined based on the anomaly detection model that there is abnormal operation monitoring data in each category of valid operation monitoring data, all abnormal operation monitoring data in the corresponding category of valid operation monitoring data are extracted;

[0054] S3: Evaluate the safety risk of the electric energy meter based on all abnormal operation monitoring data of all types of effective operation monitoring data and risk assessment fuzzy logic to determine the risk level of the electric energy meter;

[0055] S4: When the risk level of the electric energy meter reaches the risk level threshold, an alarm message is issued.

[0056] In this embodiment, the operation monitoring data refers to various data collected during the operation of the electric energy meter that reflect its operation status and performance, such as voltage, current, power, etc.

[0057] In this embodiment, effective operation monitoring data refers to data with actual analysis value and accuracy obtained by preprocessing the collected operation monitoring data and removing invalid or erroneous data.

[0058] In this embodiment, the anomaly detection model is a neural network model obtained by training using a preset number of manual judgment instances of electricity meter monitoring data, and is used to determine whether there is an anomaly in the electricity meter operation monitoring data.

[0059] In this embodiment, abnormal operation monitoring data refers to the portion of operation monitoring data that is determined to be inconsistent with the normal operation state after being processed and judged.

[0060] In this embodiment, risk assessment fuzzy logic: a set of fuzzy rules, fuzzy sets and corresponding membership functions for assessing the safety risk of the electric energy meter can comprehensively consider multiple uncertain factors to assess the risk.

[0061] In this embodiment, the risk level of the electric energy meter is a level indicating the degree of safety risk faced by the electric energy meter, such as high, medium, low, etc., divided according to the operation monitoring data of the electric energy meter and the risk assessment result.

[0062] In this embodiment, the risk level threshold is a pre-set threshold used to determine whether the risk level of the electric energy meter has reached a critical level that requires issuing an alarm message.

[0063] In this embodiment, the alarm information is: when the risk level of the electric energy meter reaches or exceeds the risk level threshold, a message is sent through the wireless communication module to prompt relevant personnel to take measures.

[0064] The beneficial effects of the above technology are: by collecting and preprocessing operation monitoring data, accurate and effective data can be obtained, providing a reliable basis for subsequent analysis. The anomaly detection model can promptly detect abnormal situations in various types of operation monitoring data. Extract abnormal operation monitoring data, and combine risk assessment fuzzy logic to evaluate the safety risk of the electric energy meter, determine the risk level, and make the assessment more scientific and comprehensive. When the risk level reaches the threshold, an alarm message is issued, which can promptly remind relevant personnel to take measures to prevent risks. Effective monitoring of the operation of the electric energy meter is achieved, and the safety and stability of the use of the electric energy meter are improved.

[0065] Embodiment 2:

[0066] Based on Example 1, the safety monitoring method of the electric energy meter, S2: when it is determined based on the abnormality detection model that there is abnormal operation monitoring data in each type of effective operation monitoring data, all abnormal operation monitoring data in the corresponding type of effective operation monitoring data are extracted, including:

[0067] Acquire a preset number of manual judgment instances of electric energy meter monitoring data, and extract abnormal operation monitoring data and complete operation monitoring data contained in each manual judgment instance of electric energy meter monitoring data;

[0068] The abnormal operation monitoring data and the complete operation monitoring data contained in the manual judgment instance of the electric energy meter monitoring data are used to train the neural network model to obtain the abnormality detection model of the electric energy meter;

[0069] Input each type of effective operation monitoring data obtained in real time into the anomaly detection model to determine whether there is abnormal operation monitoring data in each type of effective operation monitoring data;

[0070] If so, all abnormal operation monitoring data in the corresponding class of effective operation monitoring data are obtained based on the output result of the anomaly detection model;

[0071] Otherwise, keep the corresponding model output results.

[0072] In this embodiment, the preset number is a preset number value used to specify the number of certain data or instances. For example, if the preset number is 100, it means that 100 electric energy meter monitoring data manual judgment instances are obtained to perform subsequent operations.

[0073] In this embodiment, the manual judgment example of the electric energy meter monitoring data is a specific example of manual judgment and analysis of the electric energy meter monitoring data, including the judgment of whether the data is normal or not and related instructions. For example, an example of manual judgment of the electric energy meter monitoring data may be that within a certain period of time, the electric energy meter voltage data is manually judged to have abnormal fluctuations, and the current data is normal.

[0074] In this embodiment, the complete operation monitoring data covers all aspects of the monitoring data of the electric energy meter during operation, without any missing or omission. For example, the complete operation monitoring data includes the monitoring values ​​of various parameters such as voltage, current, power, power factor, frequency, etc. within a period of time.

[0075] In this embodiment, a neural network model is trained based on abnormal operation monitoring data and complete operation monitoring data contained in manual judgment instances of electric energy meter monitoring data to obtain an abnormal detection model of the electric energy meter: the artificially judged abnormal data and comprehensive normal data are used to train the neural network so that it can learn and identify abnormal conditions in the operation data of the electric energy meter, thereby obtaining a model for detecting abnormalities of the electric energy meter. For example, assuming that 100 manual judgment instances are obtained, including detailed data of 50 abnormal instances and corresponding 50 normal instances, the neural network is trained with these data, and finally a model that can automatically judge whether the operation data of the electric energy meter is abnormal and extract abnormal operation monitoring data is obtained.

[0076] In this embodiment, all abnormal operation monitoring data in the corresponding class of effective operation monitoring data are obtained based on the output result of the abnormal detection model: according to the judgment result given by the abnormal detection model, the data judged to be abnormal are extracted from the processed effective operation monitoring data. For example, if the output result of the abnormal detection model shows that the voltage data in certain time periods are abnormal, then the voltage data in these time periods are extracted from the effective operation monitoring data as abnormal operation monitoring data.

[0077] In this embodiment, the model output result is the result generated by the anomaly detection model, such as the result of determining whether the data is abnormal and marking the abnormal operation monitoring data contained therein. For example, the model output result may be "the current operation data of the electric energy meter is abnormal".

[0078] The beneficial effects of the above technology include: obtaining a preset number of manual judgment instances of electricity meter monitoring data, providing rich sample data for training anomaly detection models. The anomaly detection model is obtained by training the neural network model through these instances, which improves the accuracy and reliability of the model. By inputting real-time data into the model for judgment, anomalies in effective operation monitoring data can be discovered in a timely manner. When anomalies are determined, abnormal operation monitoring data is accurately extracted to provide an accurate basis for subsequent risk assessment. The accuracy and efficiency of abnormal operation monitoring data detection of electricity meters are improved, which helps to conduct more effective safety monitoring.

[0079] Embodiment 3:

[0080] Based on Example 1, the safety monitoring method of the electric energy meter, S3: based on all abnormal operation monitoring data in all types of effective operation monitoring data and risk assessment fuzzy logic, the safety risk of the electric energy meter is evaluated to determine the risk level of the electric energy meter, including:

[0081] Extract the performance features of all abnormal operation monitoring data from all types of effective operation monitoring data, and perform feature quantization and normalization on the performance features of all abnormal operation monitoring data to obtain standard quantified values ​​of the performance features of all abnormal operation monitoring data;

[0082] Define all fuzzy sets and corresponding membership functions and all fuzzy rules of risk assessment fuzzy logic;

[0083] Fuzzy reasoning and defuzzification are performed based on the standard quantitative values ​​of the performance characteristics of all abnormal operation monitoring data in all types of effective operation monitoring data, all fuzzy sets and corresponding membership functions of risk assessment fuzzy logic, and all fuzzy rules, and combined with the preset risk level classification standards to determine the risk level of the electric energy meter.

[0084] In this embodiment, the performance characteristics of the abnormal operation monitoring data refer to the characteristics or attributes presented by the abnormal operation monitoring data that can reflect the abnormal situation, such as the fluctuation amplitude, frequency, duration, etc. of the abnormal data. For example, if the abnormal operation monitoring data is a voltage value, its performance characteristics may be that the voltage suddenly increases by 50V and lasts for 10 seconds.

[0085] In this embodiment, the performance characteristics of all abnormal operation monitoring data are quantified and normalized to obtain the standard quantized values ​​of the performance characteristics of all abnormal operation monitoring data: the performance characteristics of the abnormal operation monitoring data are converted into comparable and calculable values ​​through certain mathematical methods, and normalized so that they have a unified standard and comparability within a specific range. For example, assuming that the performance characteristic is the voltage increase amplitude, it is quantized from the range of 0 to 100V to a value between 0 and 1, such as a 50V increase amplitude is quantized to 0.5, which is the standard quantized value.

[0086] In this embodiment, the standard quantization value of the performance characteristic of the abnormal operation monitoring data is the value of the performance characteristic of the abnormal operation monitoring data after quantization and normalization. For example, in the above example of the voltage increase amplitude, 0.5 is the standard quantization value of the performance characteristic.

[0087] In this embodiment, all fuzzy sets and corresponding membership functions and all fuzzy rules of risk assessment fuzzy logic are defined: various imprecise or ambiguous sets involved in fuzzy logic for assessing the safety risk of electric energy meters, functions of the membership degree of elements in the sets, and evaluation rules are clearly defined. For example, fuzzy sets can be "high risk", "medium risk", and "low risk", and the corresponding membership functions can be the degree to which a certain value belongs to a certain set based on specific data, and the fuzzy rule can be "if the voltage fluctuation is large and lasts for a long time, it is a high risk".

[0088] In this embodiment, a fuzzy set is a set without clear boundaries, and the belonging of elements to the set has a certain degree of ambiguity. For example, the set "voltage fluctuation is large" does not clearly define how much fluctuation is considered large.

[0089] In this embodiment, fuzzy sets and corresponding membership functions: The degree to which an element in a fuzzy set belongs to the set is represented by a membership function. For example, for the fuzzy set "large voltage fluctuation", a voltage value of 150V may have a membership of 0.8, indicating that it has a high degree of belonging to the large fluctuation set.

[0090] In this embodiment, fuzzy rules are rules for judgment and reasoning based on fuzzy concepts and logic, such as "if the current changes quickly and the power is unstable, then it is a medium risk."

[0091] In this embodiment, the preset risk level classification standard is a pre-set criterion for determining the risk level of the electric energy meter, for example, the fuzzy logic decision value may be 0 to 0.3 for low risk, 0.3 to 0.7 for medium risk, and 0.7 to 1 for high risk.

[0092] The beneficial effects of the above technologies include: extracting the performance characteristics of abnormal operation monitoring data and quantifying and normalizing them to make the data more comparable and standardized. Defining the relevant elements of risk assessment fuzzy logic provides clear rules and standards for risk assessment. Through fuzzy reasoning and defuzzification, the impact of multiple uncertain factors on the safety risk of the electric energy meter can be comprehensively considered. Combined with the preset risk level classification standards, the risk level of the electric energy meter is accurately determined, which improves the accuracy and scientificity of the assessment. The comprehensiveness and accuracy of the safety risk assessment of the electric energy meter are enhanced, providing a reliable basis for taking corresponding measures in a timely manner.

[0093] Embodiment 4:

[0094] On the basis of Example 3, the safety monitoring method of the electric energy meter performs fuzzy reasoning and defuzzification based on the standard quantitative values ​​of the performance characteristics of all abnormal operation monitoring data in all types of effective operation monitoring data, all fuzzy sets of risk assessment fuzzy logic and corresponding membership functions, and all fuzzy rules, and determines the risk level of the electric energy meter in combination with the preset risk level classification standard, including:

[0095] Based on the performance characteristic standard quantified values ​​of all abnormal operation monitoring data in all types of effective operation monitoring data, all fuzzy sets of risk assessment fuzzy logic and corresponding membership functions, the membership of each performance characteristic standard quantified value to each fuzzy set is determined;

[0096] Based on the membership of each performance characteristic standard quantization value to each fuzzy set and the premise part of all fuzzy rules, all fuzzy rules activated by each performance characteristic standard quantization value are determined, and the membership of each performance characteristic standard quantization value to all fuzzy sets contained in the premise part of each corresponding activated fuzzy rule is regarded as all activation strengths of the corresponding fuzzy rules;

[0097] Based on all fuzzy rules activated by the quantitative values ​​of all performance feature standards and all corresponding activation intensities, combined reasoning and defuzzification are performed, and the risk level of the electric energy meter is determined in combination with the preset risk level classification standard.

[0098] In this embodiment, the premise part of the fuzzy rule is the part of the fuzzy rule used to determine whether the rule conditions are met. For example, for the fuzzy rule "if the voltage fluctuation amplitude is large and the duration is long, then it is a high risk", "the voltage fluctuation amplitude is large and the duration is long" is the premise part.

[0099] In this embodiment, based on the membership of each standard quantized value of the performance feature to each fuzzy set and the premise part of all fuzzy rules, all fuzzy rules activated by each standard quantized value of the performance feature are determined: according to the degree of membership of the standard quantized value of the performance feature to the fuzzy set and the premise of the fuzzy rule, the fuzzy rule that is satisfied and takes effect is found.

[0100] For example: Assuming that the standard quantitative value of a voltage fluctuation characteristic has a high membership to the fuzzy set "large voltage fluctuation amplitude", and the premise of a fuzzy rule is "large voltage fluctuation amplitude is medium risk", then this rule is activated. In this embodiment, all activation strengths of fuzzy rules: a value used to measure the degree of activation of fuzzy rules. For example, for the activated fuzzy rule "If the voltage fluctuation amplitude is large and the duration is long, it is a high risk", the activation strength can be 0.8, indicating that the activation degree of the rule is high.

[0101] The beneficial effects of the above technology include: by determining the membership of each performance characteristic standard quantization value to each fuzzy set, basic data support is provided for subsequent reasoning. The fuzzy rules activated by each performance characteristic standard quantization value and their activation strength are clarified to make the reasoning process more accurate and targeted. Based on the combined reasoning and defuzzification of all activated fuzzy rules and activation strengths, the impact of various factors on the risk level of the electric energy meter can be comprehensively considered. Combined with the preset risk level classification standards, the risk level of the electric energy meter is accurately determined, which improves the accuracy and reliability of risk assessment. The scientificity and rationality of fuzzy reasoning and defuzzification in the safety risk assessment of electric energy meters are enhanced, providing a more effective decision-making basis for the safety monitoring of electric energy meters.

[0102] Embodiment 5:

[0103] On the basis of Example 4, the safety monitoring method of the electric energy meter performs combined reasoning and defuzzification based on all fuzzy rules activated by all characteristic standard quantization values ​​and all corresponding activation intensities, and determines the risk level of the electric energy meter in combination with the preset risk level classification standard, including:

[0104] Obtain the membership distribution of the fuzzy set of the conclusion part of all fuzzy rules activated by all the standard quantization values ​​of the performance characteristics, take each activation intensity corresponding to each fuzzy rule activated by all the standard quantization values ​​of the performance characteristics as a membership adjustment multiple, perform membership adjustment on the membership distribution of the fuzzy set of the conclusion part of the corresponding fuzzy rule, and obtain the adjusted membership distribution of the fuzzy set of the conclusion part of the corresponding fuzzy rule under each corresponding activation intensity;

[0105] The adjusted membership distributions of the conclusion parts of all fuzzy rules with the same corresponding conclusion parts in all fuzzy rules activated by the quantitative values ​​of all performance characteristic standards are summarized under all corresponding activation intensities to obtain all the adjusted membership distributions of each conclusion;

[0106] Based on all the adjusted membership distributions of all the conclusions, combined reasoning and defuzzification are performed to obtain the fuzzy logic decision value;

[0107] The preset risk level classification standard is retrieved based on the fuzzy logic decision value to determine the risk level of the electric energy meter.

[0108] In this embodiment, the conclusion part of the fuzzy rule is the result part obtained when the premise conditions of the fuzzy rule are met. For example, for the fuzzy rule "if the voltage fluctuation is large and lasts for a long time, it is a high risk", "is a high risk" is the conclusion part.

[0109] In this embodiment, the fuzzy set of the conclusion part of the fuzzy rule is a set of unclear boundaries involved in the conclusion of the fuzzy rule. For example, if the conclusion is "belongs to high risk", then "high risk" is a fuzzy set.

[0110] In this embodiment, the membership distribution of the fuzzy set in the conclusion of the fuzzy rule indicates the distribution of the membership of the elements in the fuzzy set in the conclusion of the fuzzy rule. For example, for the fuzzy set "high risk", its membership distribution may be that the membership gradually increases linearly from 0 to 1 within a certain numerical range.

[0111] In this embodiment, each activation intensity corresponding to each fuzzy rule activated by all the characteristic standard quantization values ​​is used as a membership adjustment multiple, and the membership distribution of the fuzzy set of the conclusion part of the corresponding fuzzy rule is adjusted to obtain the adjusted membership distribution of the fuzzy set of the conclusion part of the corresponding fuzzy rule under each corresponding activation intensity: the activation intensity is used as a coefficient to modify the original membership distribution of the fuzzy set. For example, assuming that the activation intensity of a fuzzy rule is 0.6, the original membership distribution is [0.2, 0.5, 0.8], and the adjusted membership distribution may be [0.12, 0.3, 0.48].

[0112] In this embodiment, the adjusted membership distribution of the fuzzy set of the conclusion part of the fuzzy rule at each corresponding activation strength is: the membership distribution of the fuzzy set after the activation strength adjustment. For example, the above-mentioned adjusted [0.12, 0.3, 0.48] is the adjusted membership distribution.

[0113] In this embodiment, each conclusion is a different final judgment result obtained by different fuzzy rules. For example, "high risk", "medium risk" and "low risk" are three different conclusions.

[0114] In this embodiment, the fuzzy logic decision value is a value used for final decision-making obtained by comprehensive calculation and processing of various adjusted membership distributions. For example, a value such as 0.7 is obtained based on a series of complex calculations to determine the final risk level of the electric energy meter.

[0115] The beneficial effects of the above technology include: by adjusting the membership distribution of the conclusion part of the fuzzy rule, the influence of the activation intensity on the evaluation results is fully considered. The adjusted membership distribution of the fuzzy rules with the same conclusion part is summarized to combine the evaluation results of similar rules. The fuzzy logic decision value is obtained by combined reasoning and defuzzification, making the evaluation results more accurate and reliable. The risk level of the electric energy meter is determined based on the decision value retrieval risk level classification standard, which improves the accuracy and scientificity of the risk level determination. The combined reasoning and defuzzification process in the safety risk assessment of the electric energy meter is optimized, providing a more accurate and effective risk level assessment for the safety monitoring of the electric energy meter.

[0116] Embodiment 6:

[0117] On the basis of Example 5, the safety monitoring method of the electric energy meter performs combined reasoning and defuzzification based on all adjusted membership distributions of all conclusions to obtain a fuzzy logic decision value, including:

[0118]

[0119] In the formula, R u is the fuzzy logic decision value, max is the maximum independent variable value in the membership distribution function, n is the total number of conclusions, m is i is the total number of all adjusted membership distributions of the i-th conclusion, θ ij (x) is the function representation of the jth adjusted membership distribution of the ith conclusion, x is the independent variable of the adjusted membership distribution function, α ij is the preset weight of the fuzzy rule corresponding to the jth adjusted membership distribution of the ith conclusion, From 0 to max Perform an integral operation with the integral variable x, From 0 to max Perform an integration operation with the integral variable x.

[0120] In this embodiment, the maximum independent variable value in the membership distribution function is the maximum value that the independent variable can take in the function describing the membership distribution. For example, assuming that the membership distribution function is θ(x), where x is the independent variable, if the value range of x is [0,1], then 1 is the maximum independent variable value.

[0121] In this embodiment, the preset weight of the fuzzy rule corresponding to the adjusted membership distribution is: when performing fuzzy logic decision calculation, the value of the importance of each fuzzy rule corresponding to the adjusted membership distribution is preset. For example, if there are two fuzzy rules, the preset weight of rule A is 0.7, and the preset weight of rule B is 0.3, indicating that the importance of rule A in decision making is relatively high. And the sum of the preset weights of all fuzzy rules is 1.

[0122] The beneficial effects of the above technology include: through complex mathematical formulas for combined reasoning and defuzzification, the fuzzy logic decision value can be accurately calculated. Multiple factors such as membership distribution, conclusion type, adjustment of the total number of membership distribution and preset weights are taken into account, making the calculation of the decision value more comprehensive and accurate. This precise calculation method helps to more scientifically evaluate the safety risks of the electric energy meter. It provides a reliable numerical basis for accurately determining the risk level of the electric energy meter. It improves the accuracy and reliability of risk assessment in the safety monitoring of the electric energy meter and enhances the effectiveness of safety monitoring.

[0123] Embodiment 7:

[0124] Based on Example 1, in the safety monitoring method of the electric energy meter, the alarm information is sent through the wireless communication module.

[0125] In this embodiment, the wireless communication module is a hardware component that enables wireless data transmission between the electric energy meter and other devices or systems. For example, common wireless communication modules include Bluetooth modules, Wi-Fi modules, Zigbee modules, etc. For example, the electric energy meter sends alarm information to the user's mobile phone through the Bluetooth module, or transmits operation monitoring data to the remote monitoring server through the Wi-Fi module.

[0126] The beneficial effects of the above technologies include: using wireless communication modules to send alarm information, getting rid of the limitations of wired connections, and improving the flexibility and convenience of alarm information transmission. It can quickly send alarm information to the receiving device of relevant personnel, shortening the response time. Wireless communication is easy to integrate with remote monitoring systems to achieve a wider monitoring coverage. It helps to take timely measures to deal with safety issues of electric energy meters and reduce potential risks and losses. It enhances the timeliness and effectiveness of the transmission of electric energy meter safety monitoring alarm information and improves the performance of the safety monitoring system.

[0127] Embodiment 8:

[0128] Based on the first embodiment, the safety monitoring method of the electric energy meter further includes:

[0129] All types of operation monitoring data and all abnormal operation monitoring data, all risk assessment results and all alarm information acquired in real time are stored in the monitoring background, among which the risk assessment results include the risk level of the electric energy meter.

[0130] In this embodiment, the monitoring background is a system or platform for centrally storing and managing all types of operation monitoring data, all abnormal operation monitoring data, all risk assessment results, and all alarm information acquired by the electric energy meter in real time. For example, the monitoring background can be a server-side database system that can store, query, analyze, and perform other operations on a large amount of electric energy meter-related data. For example, the staff can view the operating status and risk assessment of all electric energy meters in a specific area within a certain period of time through the monitoring background, so as to find problems in time and take measures.

[0131] The beneficial effects of the above technologies include: storing various relevant data, evaluation results and alarm information in the monitoring background, realizing centralized management and storage of data. It is convenient to trace back and analyze the operation status of the electric energy meter in the future, providing data support for optimizing monitoring methods and improving the performance of the electric energy meter. It helps to discover potential patterns and problems and provide a reference for preventing similar risks. It can provide comprehensive historical records for regulatory authorities and relevant personnel to facilitate auditing and supervision. It improves the system of safety monitoring of electric energy meters and improves the traceability and management level of monitoring.

[0132] Embodiment 9:

[0133] The present invention provides a safety monitoring device for an electric energy meter, which is used to execute any one of the safety monitoring methods for an electric energy meter in embodiments 1 to 8, comprising:

[0134] The data acquisition and processing module is used to collect each type of operation monitoring data during the operation of the electric energy meter, and pre-process each type of operation monitoring data to obtain each type of effective operation monitoring data;

[0135] The abnormal data extraction module is used to extract all abnormal operation monitoring data in the corresponding class of effective operation monitoring data when it is determined based on the abnormal detection model that there is abnormal operation monitoring data in each class of effective operation monitoring data;

[0136] A safety risk assessment module is used to assess the safety risk of the electric energy meter based on all abnormal operation monitoring data in all types of effective operation monitoring data and risk assessment fuzzy logic, and determine the risk level of the electric energy meter;

[0137] The alarm module is used to issue an alarm message when the risk level of the electric energy meter reaches the risk level threshold.

[0138] The beneficial effects of the above technology are: by collecting and preprocessing operation monitoring data, accurate and effective data can be obtained, providing a reliable basis for subsequent analysis. The anomaly detection model can promptly detect abnormal situations in various types of operation monitoring data. Extract abnormal operation monitoring data, and combine risk assessment fuzzy logic to evaluate the safety risk of the electric energy meter, determine the risk level, and make the assessment more scientific and comprehensive. When the risk level reaches the threshold, an alarm message is issued, which can promptly remind relevant personnel to take measures to prevent risks. Effective monitoring of the operation of the electric energy meter is achieved, and the safety and stability of the use of the electric energy meter are improved.

[0139] Embodiment 10:

[0140] The present invention provides a smart electric energy meter connected to the safety monitoring device of Example 9.

[0141] The beneficial effects of the above technology include: by connecting the safety monitoring device of Example 9, it is possible to monitor the operating status of the electric energy meter in real time, detect and handle abnormal situations in time, and improve the safety and stability of the electric energy meter operation. It provides comprehensive safety protection for smart electric energy meters and reduces losses and risks caused by failures or abnormalities. It helps to improve the reliability and service life of smart electric energy meters and enhance users' trust in electric energy meters. It enables smart electric energy meters to have more powerful self-monitoring and protection capabilities and adapt to complex power consumption environments. It provides strong support for the stable operation of the power system and ensures the accurate measurement and supply of electric energy. It improves the performance and value of smart electric energy meters and promotes technological development and progress in the field of power metering.

[0142] Obviously, those skilled in the art can make various changes and modifications 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 equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A safety monitoring method for an electric energy meter, characterized in that: include: S1: Collect each type of operation monitoring data during the operation of the electric energy meter, and pre-process each type of operation monitoring data to obtain each type of effective operation monitoring data; S2: When it is determined based on the anomaly detection model that there is abnormal operation monitoring data in each category of valid operation monitoring data, all abnormal operation monitoring data in the corresponding category of valid operation monitoring data are extracted; S3: Evaluate the safety risk of the electric energy meter based on all abnormal operation monitoring data of all types of effective operation monitoring data and risk assessment fuzzy logic to determine the risk level of the electric energy meter; S4: When the risk level of the electric energy meter reaches the risk level threshold, an alarm message is issued.

2. The safety monitoring method of an electric energy meter according to claim 1, characterized in that: S2: When it is determined based on the anomaly detection model that there is abnormal operation monitoring data in each category of valid operation monitoring data, all abnormal operation monitoring data in the corresponding category of valid operation monitoring data are extracted, including: Acquire a preset number of manual judgment instances of electric energy meter monitoring data, and extract abnormal operation monitoring data and complete operation monitoring data contained in each manual judgment instance of electric energy meter monitoring data; The abnormal operation monitoring data and the complete operation monitoring data contained in the manual judgment instance of the electric energy meter monitoring data are used to train the neural network model to obtain the abnormality detection model of the electric energy meter; Input each type of effective operation monitoring data obtained in real time into the anomaly detection model to determine whether there is abnormal operation monitoring data in each type of effective operation monitoring data; If so, all abnormal operation monitoring data in the corresponding class of effective operation monitoring data are obtained based on the output result of the anomaly detection model; Otherwise, keep the corresponding model output results.

3. The safety monitoring method of an electric energy meter according to claim 1, characterized in that: S3: Based on all abnormal operation monitoring data in all types of effective operation monitoring data and risk assessment fuzzy logic, the safety risk of the electric energy meter is evaluated to determine the risk level of the electric energy meter, including: Extract the performance features of all abnormal operation monitoring data from all types of effective operation monitoring data, and perform feature quantization and normalization on the performance features of all abnormal operation monitoring data to obtain standard quantified values ​​of the performance features of all abnormal operation monitoring data; Define all fuzzy sets and corresponding membership functions and all fuzzy rules of risk assessment fuzzy logic; Fuzzy reasoning and defuzzification are performed based on the standard quantitative values ​​of the performance characteristics of all abnormal operation monitoring data in all types of effective operation monitoring data, all fuzzy sets and corresponding membership functions of risk assessment fuzzy logic, and all fuzzy rules, and combined with the preset risk level classification standards to determine the risk level of the electric energy meter.

4. The safety monitoring method of an electric energy meter according to claim 3, characterized in that: Based on the standard quantitative values ​​of the performance characteristics of all abnormal operation monitoring data in all types of effective operation monitoring data, all fuzzy sets of risk assessment fuzzy logic and corresponding membership functions and all fuzzy rules, fuzzy reasoning and defuzzification are performed, and combined with the preset risk level classification standards, the risk level of the electric energy meter is determined, including: Based on the performance characteristic standard quantified values ​​of all abnormal operation monitoring data in all types of effective operation monitoring data, all fuzzy sets of risk assessment fuzzy logic and corresponding membership functions, the membership of each performance characteristic standard quantified value to each fuzzy set is determined; Based on the membership of each performance characteristic standard quantization value to each fuzzy set and the premise part of all fuzzy rules, all fuzzy rules activated by each performance characteristic standard quantization value are determined, and the membership of each performance characteristic standard quantization value to all fuzzy sets contained in the premise part of each corresponding activated fuzzy rule is regarded as all activation strengths of the corresponding fuzzy rules; Based on all fuzzy rules activated by the quantitative values ​​of all performance feature standards and all corresponding activation intensities, combined reasoning and defuzzification are performed, and the risk level of the electric energy meter is determined in combination with the preset risk level classification standard.

5. The safety monitoring method of an electric energy meter according to claim 4, characterized in that: Based on all the fuzzy rules activated by the quantitative values ​​of all the performance characteristic standards and all the corresponding activation intensities, the risk level of the electric energy meter is determined by combining the preset risk level classification standards, including: Obtain the membership distribution of the fuzzy set of the conclusion part of all fuzzy rules activated by all the standard quantization values ​​of the performance characteristics, take each activation intensity corresponding to each fuzzy rule activated by all the standard quantization values ​​of the performance characteristics as a membership adjustment multiple, perform membership adjustment on the membership distribution of the fuzzy set of the conclusion part of the corresponding fuzzy rule, and obtain the adjusted membership distribution of the fuzzy set of the conclusion part of the corresponding fuzzy rule under each corresponding activation intensity; The adjusted membership distributions of the conclusion parts of all fuzzy rules with the same corresponding conclusion parts in all fuzzy rules activated by the quantitative values ​​of all performance characteristic standards are summarized under all corresponding activation intensities to obtain all the adjusted membership distributions of each conclusion; Based on all the adjusted membership distributions of all the conclusions, combined reasoning and defuzzification are performed to obtain the fuzzy logic decision value; The preset risk level classification standard is retrieved based on the fuzzy logic decision value to determine the risk level of the electric energy meter.

6. The safety monitoring method of an electric energy meter according to claim 5, characterized in that: Based on all the adjusted membership distributions of all conclusions, combined reasoning and defuzzification are performed to obtain fuzzy logic decision values, including: In the formula, R u is the fuzzy logic decision value, max is the maximum independent variable value in the membership distribution function, n is the total number of conclusions, m is i is the total number of all adjusted membership distributions of the i-th conclusion, θ ij (x) is the function representation of the jth adjusted membership distribution of the ith conclusion, x is the independent variable of the adjusted membership distribution function, α ij is the preset weight of the fuzzy rule corresponding to the jth adjusted membership distribution of the ith conclusion, From 0 to max Perform an integral operation with the integral variable x, From 0 to max Perform an integration operation with the integral variable x.

7. The safety monitoring method of an electric energy meter according to claim 1, characterized in that: The alarm information is sent through the wireless communication module.

8. The safety monitoring method of an electric energy meter according to claim 1, characterized in that: Also includes: All types of operation monitoring data and all abnormal operation monitoring data, all risk assessment results and all alarm information acquired in real time are stored in the monitoring background, among which the risk assessment results include the risk level of the electric energy meter.

9. A safety monitoring device for an electric energy meter, characterized in that: A method for implementing the safety monitoring method of an electric energy meter according to any one of claims 1 to 8, comprising: The data acquisition and processing module is used to collect each type of operation monitoring data during the operation of the electric energy meter, and pre-process each type of operation monitoring data to obtain each type of effective operation monitoring data; The abnormal data extraction module is used to extract all abnormal operation monitoring data in the corresponding class of effective operation monitoring data when it is determined based on the abnormal detection model that there is abnormal operation monitoring data in each class of effective operation monitoring data; A safety risk assessment module is used to assess the safety risk of the electric energy meter based on all abnormal operation monitoring data in all types of effective operation monitoring data and risk assessment fuzzy logic, and determine the risk level of the electric energy meter; The alarm module is used to issue an alarm message when the risk level of the electric energy meter reaches the risk level threshold.

10. A smart electric energy meter, characterized in that: The safety monitoring device according to claim 9 is connected.

Images