Current and voltage monitoring system and monitoring method based on metering device

Abstract

The present invention discloses a current and voltage monitoring system and a monitoring method based on a metering device, and belongs to the technical field of electricity monitoring. A current and voltage monitoring method based on a metering device includes S1, obtaining historical current and voltage data of a designated enterprise and multiple enterprises of the same type; S2, extracting historical feature data from the historical current and voltage data; S3, using a clustering algorithm, performing cluster analysis on the designated enterprise and multiple enterprises of the same type according to the historical feature data, and obtaining the cluster cluster where the designated enterprise is located; S4, calculating the historical similarity between the historical feature data of the enterprises in the cluster cluster; S5, obtaining evaluation parameters according to the similarity between the historical feature data of the enterprises in the cluster cluster; S6, obtaining the current current and voltage data of the enterprises in the cluster cluster; S7, extracting the current feature data of the current current and voltage data of the enterprises in the cluster cluster; S8, calculating the similarity mean of the current feature data of the designated enterprise and the other enterprises in the cluster cluster.

Description

Technical Field

[0001] The present invention relates to the technical field of electricity consumption monitoring, and more specifically, to a current and voltage monitoring system and a monitoring method based on a metering device. Background Art

[0002] With the rapid development of industrial automation and intelligence, electricity, as an important energy source for production and life, is particularly important for monitoring and management. Traditional current and voltage monitoring methods rely on manual inspections and simple data recording, which is difficult to meet the needs of modern enterprises for real-time monitoring, data analysis and abnormal warning. Monitoring methods based on metering devices usually combine smart meters and data acquisition systems to achieve real-time monitoring, storage and analysis of current and voltage. This type of method can not only provide accurate electricity metering, but also monitor current and voltage fluctuations, helping enterprises to detect potential electrical faults and power consumption anomalies in a timely manner.

[0003] After searching, the existing patent document with publication number CN118396223A provides a method for intelligent analysis and detection of abnormal electricity consumption in enterprises. This method performs abnormal detection on the newly added data by calculating the similarity between the time-sharing data and the total electricity consumption data. When the factory changes production, its electricity consumption data will also change, thereby changing the similarity and causing abnormal warning.

[0004] Since the production and operation activities of enterprises are affected by external factors, their electricity consumption data will also fluctuate over time. Using the historical data of a single enterprise cannot effectively reduce the non-periodic impact of external factors, and abnormal alarms are prone to occur, affecting the accuracy of abnormal monitoring of enterprise electricity consumption. In view of this, we propose a current and voltage monitoring system and monitoring method based on a metering device. Summary of the invention

[0005] 1. Technical problems to be solved

[0006] The object of the present invention is to provide a current and voltage monitoring system and a monitoring method based on a metering device to solve the problems raised in the above background technology.

[0007] 2. Technical solution

[0008] The present invention is achieved through the following technical solutions:

[0009] A current and voltage monitoring system and a monitoring method based on a metering device, comprising the following steps:

[0010] S1. Obtain historical current and voltage data of a specified enterprise and multiple enterprises of the same type;

[0011] S2, extracting historical characteristic data from historical current and voltage data;

[0012] S3. Using a clustering algorithm, perform cluster analysis on the designated enterprise and multiple enterprises of the same type according to historical feature data to obtain the cluster to which the designated enterprise belongs;

[0013] S4, calculating the historical similarity between the historical feature data of enterprises in the cluster;

[0014] S5. Obtaining evaluation parameters according to the similarity between the historical feature data of enterprises in the cluster;

[0015] S6, obtaining current current and voltage data of enterprises in the cluster;

[0016] S7, extracting current characteristic data of current current and voltage data of enterprises in the cluster;

[0017] S8, calculating the mean similarity between the current feature data of the specified enterprise and the other enterprises in the cluster;

[0018] S9. Obtain the abnormal alarm information of the designated enterprise, and perform abnormal analysis on the designated enterprise by calculating the evaluation index. The evaluation index is calculated using the following formula:

[0019] ;

[0020] Among them, T is the evaluation index of the specified enterprise, is the mean similarity between the current feature data of the specified enterprise and the other enterprises in the cluster, To evaluate the parameters, is the weight coefficient, and f is the abnormal alarm frequency.

[0021] As an optional solution of the technical solution of this application document, the historical characteristic data includes the mean, standard deviation, skewness and kurtosis of historical current and voltage data.

[0022] As an optional solution of the technical solution of the present application document, S2 specifically includes: scaling the historical current and voltage data to the interval [-1, 1], and then extracting the historical feature data of the scaled historical current and voltage data.

[0023] As an optional solution of the technical solution of this application document, the mean, standard deviation, skewness and kurtosis of the historical current and voltage data are calculated using the following formulas:

[0024] ;

[0025] ;

[0026] ;

[0027] ;

[0028] in, is the mean value of current or voltage, n is the amount of current or voltage data, is the current or voltage value, is the standard deviation of current or voltage, is the skewness of current or voltage, is the peak of current or voltage.

[0029] As an optional solution of the technical solution of this application document, in S3, the K-means clustering method is used to perform cluster analysis on enterprises of the same type, and the number of enterprises in the cluster is not less than 3.

[0030] As an optional solution of the technical solution of this application document, in S4, the calculation formula of historical similarity is as follows:

[0031] ;

[0032] in, is the historical similarity, is the i-th data in the historical feature data of enterprise A in the cluster; is the i-th historical feature data of enterprise B in the cluster.

[0033] As an optional solution of the technical solution of the present application document, in S5, the evaluation parameter is the minimum similarity between the historical feature data of enterprises in the cluster where the specified enterprise is located.

[0034] As an optional solution of the technical solution of this application document, in S8, the similarity mean of the current feature data of the designated enterprise and the other enterprises in the cluster is calculated using the following formula:

[0035] ;

[0036] Where N is the number of enterprises in the cluster, is the jth data in the current feature data of the specified enterprise, is the jth data in the current feature data of the i-th enterprise in the cluster except the specified enterprise.

[0037] A current and voltage monitoring system based on a metering device, comprising:

[0038] Metering devices are installed at key nodes of the enterprise power grid to collect the enterprise's current and voltage data;

[0039] A data acquisition module, connected to the metering device, for receiving and processing the enterprise current and voltage data collected by the metering device;

[0040] A data analysis module, connected to the data acquisition module, is used to perform abnormal analysis on a designated enterprise based on the received enterprise current and voltage data;

[0041] The alarm module is connected to the data analysis module and triggers an alarm signal when abnormal current and voltage data of a specified enterprise are detected;

[0042] The display module is used to display the current and voltage conditions, analysis results and alarm information of the specified enterprise.

[0043] 3. Beneficial effects

[0044] Compared with the prior art, the present invention has the following beneficial effects:

[0045] 1. This application uses the current and voltage data of the same type of enterprises to analyze the specified current and voltage data, which can effectively reduce the situation where the fluctuations in the current and voltage data of the specified enterprise caused by fluctuations in the external environment are judged as abnormal fluctuations, reduce false alarms, and increase the monitoring accuracy of the specified enterprise.

[0046] 2. This application further screens out similar companies with higher similarity through cluster analysis, increases the reliability of this method by controlling the number of companies in the cluster, and reduces the impact of accidental factors on the identification of abnormal situations of companies; and can appropriately increase or weaken the standards for abnormal identification in combination with the company's historical abnormal alarm information, and urge companies to solve abnormal problems in a timely manner. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 The invention is a logic block diagram of a current and voltage monitoring method based on a metering device. DETAILED DESCRIPTION

[0048] The technical solution of the present invention will be clearly and completely described below in conjunction with the accompanying drawings.

[0049] Embodiment 1:

[0050] See also Figure 1 The present invention provides a current and voltage monitoring method based on a metering device, comprising:

[0051] S1. Obtain historical current and voltage data of a specified enterprise and multiple enterprises of the same type;

[0052] S2, extracting historical characteristic data from historical current and voltage data;

[0053] S3. Using a clustering algorithm, perform cluster analysis on the designated enterprise and multiple enterprises of the same type according to historical feature data to obtain the cluster to which the designated enterprise belongs;

[0054] S4, calculating the historical similarity between the historical feature data of enterprises in the cluster;

[0055] S5. Obtaining evaluation parameters according to the similarity between the historical feature data of enterprises in the cluster;

[0056] S6, obtaining current current and voltage data of enterprises in the cluster;

[0057] S7, extracting current characteristic data of current current and voltage data of enterprises in the cluster;

[0058] S8, calculating the mean similarity between the current feature data of the specified enterprise and the other enterprises in the cluster;

[0059] S9. Obtain the abnormal alarm information of the designated enterprise, and perform abnormal analysis on the designated enterprise by calculating the evaluation index. The evaluation index is calculated using the following formula:

[0060] ;

[0061] Among them, T is the evaluation index of the specified enterprise, is the mean similarity between the current feature data of the specified enterprise and the other enterprises in the cluster, To evaluate the parameters, is the weight coefficient, and f is the abnormal alarm frequency.

[0062] The production and operation activities of an enterprise are affected by external factors. When facing changes in external market demand, the production and operation activities of enterprises of the same type have similar fluctuations, and the fluctuations in their historical current and voltage data over time are also similar. By obtaining the current and voltage data of enterprises of the same type, it is possible to determine whether there are any abnormalities in the current and voltage data fluctuations of a specified enterprise.

[0063] In S2, when extracting historical characteristic data from historical current and voltage data, it is necessary to preprocess the historical current and voltage data to remove abnormal values ​​from the historical current and voltage data; then uniformly scale the historical current and voltage data of multiple enterprises of the same type, and scale the historical current and voltage data to the range of [-1,1] according to the maximum floating range of the historical current and voltage data of multiple enterprises of the same type, to obtain the preprocessed current and voltage data;

[0064] The pre-processed current and voltage data are respectively calculated to obtain historical characteristic data, wherein the historical characteristic data includes mean, standard deviation, skewness, kurtosis, etc.

[0065] Current and voltage averages are used to reflect the company's basic electricity usage patterns; if these values ​​deviate significantly from the normal range during a specific time period, it may indicate power theft or inefficient equipment.

[0066] The standard deviation of current and voltage can measure the stability of current and voltage fluctuations; high variance may indicate an unstable power system or abnormal electrical equipment in an enterprise.

[0067] The current-voltage skewness reflects the asymmetry of the current-voltage distribution; if the skewness is too high, it may indicate an abnormal unilateral deviation in the power consumption pattern, which may be due to abnormal operation of some equipment in a specific time period.

[0068] Current and voltage kurtosis measures how sharp or flat the current and voltage distributions are; abnormal kurtosis can indicate extreme changes in power usage patterns, which could indicate a malfunction in a business's equipment.

[0069] The mean is calculated using the following formula:

[0070] ;

[0071] in, is the mean value of current or voltage, n is the amount of current or voltage data, is the current or voltage value;

[0072] The standard deviation is calculated using the following formula:

[0073] ;

[0074] in, is the standard deviation of current or voltage;

[0075] ;

[0076] in, is the deflection of current or voltage;

[0077] ;

[0078] in, is the peak of current or voltage.

[0079] Since differences in scale and operating conditions will lead to differences in power data among different enterprises of the same type, it is impossible to directly use the acquired historical feature data, and it is necessary to perform cluster analysis on the acquired historical feature data.

[0080] In S3, the K-means clustering method can be used to perform cluster analysis on historical feature data, so that multiple enterprises corresponding to the historical feature data in the same cluster cluster are similar not only in type, but also in other dimensions. This can be used to evaluate the electricity consumption of enterprises in the same cluster cluster and reduce the impact of abnormal fluctuations in enterprise electricity consumption data in different time periods on enterprise abnormal analysis.

[0081] During the cluster analysis process, it is necessary to ensure that the number of enterprises in the cluster where the specified enterprise is located is not less than 3 to reduce the impact of abnormal data. Therefore, the number of clusters needs to be determined based on the number of samples collected from the same type of enterprises.

[0082] In S4, the historical similarity calculation formula is as follows:

[0083] ;

[0084] in, is the historical similarity, is the i-th data in the historical feature data of enterprise A in the cluster; is the i-th historical feature data of enterprise B in the cluster.

[0085] In S5, the minimum similarity value between the historical feature data of the enterprises in the cluster where the specified enterprise is located can be determined as the evaluation parameter, that is:

[0086] .

[0087] In S7, the calculation method of the current feature data is the same as the calculation method of the historical feature data, which will not be described in detail here.

[0088] In S8, the mean similarity between the current feature data of the specified enterprise in the cluster and the rest of the enterprises is calculated using the following formula;

[0089] ;

[0090] in, The similarity mean of the current feature data between the enterprise specified in the cluster and the other enterprises in the cluster, N is the number of enterprises in the cluster, is the jth data in the current feature data of the specified enterprise, is the jth data in the current feature data of the i-th enterprise in the cluster except the specified enterprise.

[0091] In S9, the abnormal alarm frequency is calculated using the following formula:

[0092] Abnormal alarm times / monitoring cycle;

[0093] The monitoring period can be set to 30 days.

[0094] The weight coefficient needs to be determined based on the company's electricity consumption. It is positively correlated with the electricity consumption of the enterprise and can generally be taken as 1.5. When T is an evaluation index greater than 1, it can be considered that the enterprise has abnormal electricity consumption behavior.

[0095] Embodiment 2:

[0096] The present invention provides a current and voltage monitoring system based on a metering device, comprising:

[0097] Metering devices are installed at key nodes of the enterprise power grid to collect the enterprise's current and voltage data;

[0098] A data acquisition module, connected to the metering device, for receiving and processing the enterprise current and voltage data collected by the metering device;

[0099] A data analysis module, connected to the data acquisition module, is used to perform abnormal analysis on a designated enterprise based on the received enterprise current and voltage data;

[0100] The alarm module is connected to the data analysis module and triggers an alarm signal when abnormal current and voltage data of a specified enterprise are detected;

[0101] The display module is used to display the current and voltage conditions, analysis results and alarm information of the specified enterprise.

[0102] The metering device is installed at the key nodes of the enterprise power grid, such as transformers, distribution cabinets or near key equipment, to collect the enterprise's current and voltage data in real time. The data acquisition module selects the appropriate interface according to the output type of the metering device. For analog signals, an analog-to-digital converter is usually used for acquisition; for digital signals, data can be received directly through the digital interface. According to the communication requirements between the data acquisition module and the data analysis module, a suitable wireless communication protocol is selected. Before the data is sent, the data is encrypted using an encryption algorithm. After receiving the data, the data analysis module first decrypts the data, and then processes and analyzes the data through the built-in algorithm; when the data analysis module detects that the current and voltage data of the specified enterprise are abnormal, the alarm module will be triggered, and the alarm module can send alarm information to relevant personnel by issuing sound and light alarms, sending SMS notifications, automatically making phone calls, or other communication methods to complete the monitoring task of the current and voltage of the specified enterprise.

Claims

1. A current and voltage monitoring method based on a metering device, characterized in that: The following steps are involved: S1. Obtain historical current and voltage data of a specified enterprise and multiple enterprises of the same type; S2, extracting historical characteristic data from historical current and voltage data; S3. Using a clustering algorithm, perform clustering analysis on the designated enterprise and multiple enterprises of the same type according to historical feature data to obtain the cluster to which the designated enterprise belongs; S4, calculating the historical similarity between the historical feature data of enterprises in the cluster; S5. Obtaining evaluation parameters according to the similarity between the historical feature data of enterprises in the cluster; S6, obtaining current current and voltage data of enterprises in the cluster; S7, extracting current characteristic data of current current and voltage data of enterprises in the cluster; S8, calculating the mean similarity between the current feature data of the specified enterprise and the other enterprises in the cluster; S9. Obtain the abnormal alarm information of the designated enterprise, and perform abnormal analysis on the designated enterprise by calculating the evaluation index. The evaluation index is calculated using the following formula: ； Among them, T is the evaluation index of the specified enterprise, is the mean similarity between the current feature data of the specified enterprise and the other enterprises in the cluster, To evaluate the parameters, is the weight coefficient, f is the abnormal alarm frequency; In S5, the evaluation parameter is the minimum similarity between the historical feature data of the enterprises in the cluster where the specified enterprise is located.

2. A current and voltage monitoring method based on a metering device according to claim 1, characterized in that: The historical characteristic data includes the mean, standard deviation, skewness, and kurtosis of historical current and voltage data.

3. A current and voltage monitoring method based on a metering device according to claim 1, characterized in that: S2 specifically includes: scaling the historical current and voltage data to the interval of [-1, 1], and then extracting the historical feature data of the scaled historical current and voltage data.

4. A current and voltage monitoring method based on a metering device according to claim 2, characterized in that: The mean, standard deviation, skewness, and kurtosis of the historical current and voltage data are calculated using the following formulas: ； ； ； ； in, is the mean value of current or voltage, n is the amount of current or voltage data, is the current or voltage value, is the standard deviation of current or voltage, is the skewness of current or voltage, is the peak of current or voltage.

5. The current and voltage monitoring method based on a metering device according to claim 1, characterized in that: In S3, a K-means clustering method is used to perform cluster analysis on enterprises of the same type, and the number of enterprises in the cluster is not less than 3.

6. The current and voltage monitoring method based on a metering device according to claim 1, characterized in that: In S4, the calculation formula of historical similarity is as follows: ； in, is the historical similarity, is the i-th data in the historical feature data of enterprise A in the cluster; is the i-th historical feature data of enterprise B in the cluster.

7. The current and voltage monitoring method based on a metering device according to claim 1 is characterized in that: In S8, the mean similarity between the current feature data of the specified enterprise and the other enterprises in the cluster is calculated using the following formula: ； Where N is the number of enterprises in the cluster, is the jth data in the current feature data of the specified enterprise, is the jth data in the current feature data of the i-th enterprise in the cluster except the specified enterprise.

8. A current and voltage monitoring system based on a metering device, using a current and voltage monitoring method based on a metering device as claimed in any one of claims 1 to 7, characterized in that: include: Metering devices are installed at key nodes of the enterprise power grid to collect the enterprise's current and voltage data; A data acquisition module, connected to the metering device, for receiving and processing the enterprise current and voltage data collected by the metering device; A data analysis module, connected to the data acquisition module, is used to perform abnormal analysis on a designated enterprise based on the received enterprise current and voltage data; The alarm module is connected to the data analysis module and triggers an alarm signal when abnormal current and voltage data of a specified enterprise are detected; The display module is used to display the current and voltage conditions, analysis results and alarm information of the specified enterprise.

Images