A user electricity abnormality detection method based on current analysis

Abstract

This invention provides a user power consumption anomaly detection method based on current analysis, comprising the following steps: (1) collecting the user's power current signal and voltage signal; (2) making a preliminary judgment based on the current signal; (3) retrieving the current signal for two consecutive weeks; (4) further judging whether the user's power consumption is abnormal based on the current signal and issuing an alarm; (5) transmitting the detection result to a remote monitoring center; (6) the remote monitoring center sending the detected abnormality status to the user for timely inspection and maintenance. This invention provides a user power consumption anomaly detection method based on current analysis, which can promptly and comprehensively detect anomalies and ensure the safety and reliability of user power consumption.

Description

Technical Field

[0001] This invention belongs to the field of power detection technology, and specifically relates to a method for detecting abnormal power consumption of users based on current analysis. Background Technology

[0002] With the continuous development of technology, people are using more and more electricity, and their requirements are also getting higher and higher. In order to provide power supply economically and efficiently, it is necessary to reliably detect users' electricity consumption to prevent power supply and distribution system failures and economic losses caused by abnormal user electricity consumption.

[0003] This invention proposes a user power consumption anomaly detection method based on current analysis. It collects basic user power consumption information, performs necessary routine judgments, then performs cluster analysis on the current signal, extracts feature values ​​to determine whether the user's power consumption is abnormal, and promptly alarms and notifies the user, thereby better ensuring the safety of user power consumption. Summary of the Invention

[0004] This invention provides a method for detecting abnormal power consumption in users based on current analysis, which can detect abnormalities in a timely and comprehensive manner and ensure the safety and reliability of power consumption for users.

[0005] This invention specifically relates to a user power consumption anomaly detection method based on current analysis, the user power consumption anomaly detection method comprising the following steps:

[0006] Step (1): Collect the user's current signal and voltage signal;

[0007] Step (2): Make a preliminary judgment based on the current signal;

[0008] Step (3): Retrieve the current signals from two consecutive weeks;

[0009] Step (4): Based on the current signal, further determine whether there is an abnormality in the user's power consumption and issue an alarm;

[0010] Step (5): Transmit the test results to the remote monitoring center;

[0011] Step (6): The remote monitoring center will send the detected abnormal conditions to the user so that timely inspection and maintenance can be carried out.

[0012] The specific method for making a preliminary judgment based on the current signal is as follows:

[0013] First, determine whether the current signal is greater than the current reference value. If so, the user's current consumption is high, indicating an abnormality.

[0014] Secondly, calculate the user's power factor and determine whether the power factor is less than the power factor reference value. If so, the user's power factor is low.

[0015] Next, the harmonic components of the current signal are extracted, and it is determined whether the harmonic components of the current signal are greater than the harmonic component reference value. If so, the harmonic components of the user's power consumption are abnormal.

[0016] The specific method for further determining whether there is an abnormality in the user's electricity consumption based on the current signal is as follows:

[0017] First, calculate the average value of the current signal for each day;

[0018] Next, calculate the standard deviation of the current signal for each day;

[0019] Next, calculate the per-unit value of the current signal for each day;

[0020] Next, the per-unit values ​​of the current signal are used as the clustering input matrix for clustering.

[0021] Next, calculate the percentage of the current signal per day relative to the corresponding point in the cluster center of the same type of load;

[0022] Finally, determine whether there are 20 current signals whose percentage of the corresponding points in the cluster center of the same type of load is less than 25%. If so, the user's power consumption is abnormal.

[0023] The algorithm for calculating the daily standard deviation of the current signal is as follows: in The average value of the current signal is n, and the number of sampling points per day is n.

[0024] The algorithm for calculating the per-unit value of the current signal per day is as follows: Where i n,m This is the nth current signal on day m. Let σ be the average value of the current signal over m days. m Let m be the standard deviation of the current signal.

[0025] Clustering was performed using the K-means clustering method:

[0026] Where τ jk The value is 1 when the current signal is classified into the kth class, and 0 otherwise; μ k It is the cluster center of the k-th class.

[0027] The user communicates with the remote monitoring center via a mobile app, and the app promptly receives the detected abnormality when the user's power consumption is abnormal.

[0028] Compared with existing technologies, the beneficial effects are: the user power consumption anomaly detection method collects user power current and voltage signals daily, performs necessary routine judgments, including current magnitude, power factor, and harmonic component calculations; then performs cluster analysis on the current signals, extracts feature values ​​to determine whether there is an anomaly in the user's power consumption, and promptly alarms and notifies the user, thus better ensuring the safety of user power consumption. Attached Figure Description

[0029] Figure 1 This is a flowchart illustrating the workflow of a user power consumption anomaly detection method based on current analysis according to the present invention. Detailed Implementation

[0030] The following detailed description, in conjunction with the accompanying drawings, illustrates a specific implementation of the present invention's method for detecting abnormal user power consumption based on current analysis.

[0031] like Figure 1 As shown, the user power consumption anomaly detection method of the present invention includes the following steps:

[0032] Step (1): Collect the user's current signal and voltage signal;

[0033] Step (2): Make a preliminary judgment based on the current signal:

[0034] First, determine whether the current signal is greater than the current reference value. If so, the user's current consumption is high, indicating an abnormality.

[0035] Secondly, calculate the user's power factor and determine whether the power factor is less than the power factor reference value. If so, the user's power factor is low.

[0036] Next, extract the harmonic components of the current signal and determine whether the harmonic components of the current signal are greater than the harmonic component reference value. If so, the harmonic components of the user's power consumption are abnormal.

[0037] Step (3): Retrieve the current signals from two consecutive weeks;

[0038] Step (4): Based on the current signal, further determine whether there is an abnormality in the user's power consumption and issue an alarm;

[0039] Step (5): Transmit the test results to the remote monitoring center;

[0040] Step (6): The remote monitoring center sends the detected abnormal situation to the user so that timely inspection and maintenance can be carried out: The user completes communication with the remote monitoring center through the mobile APP. When the user's power consumption is abnormal, the abnormal situation is received in a timely manner.

[0041] The specific method for further determining whether there is an abnormality in the user's electricity consumption based on the current signal is as follows:

[0042] First, calculate the average value of the current signal for each day;

[0043] Next, calculate the daily standard deviation of the current signal: in The average value of the current signal is n, where n is the number of sampling points per day;

[0044] Next, calculate the per-unit value of the current signal for each day: Where i n,m This is the nth current signal on day m. Let σ be the average value of the current signal over m days. m Let m be the standard deviation of the current signal.

[0045] Next, the per-unit values ​​of the current signal are used as the clustering input matrix for clustering:

[0046] Clustering was performed using the K-means clustering method: Where τ jk The value is 1 when the current signal is classified into the kth class, and 0 otherwise; μ k Let be the cluster center of the k-th class;

[0047] Next, calculate the percentage of the current signal per day relative to the corresponding point in the cluster center of the same type of load;

[0048] Finally, determine whether there are 20 current signals whose percentage of the corresponding points in the cluster center of the same type of load is less than 25%. If so, the user's power consumption is abnormal.

[0049] Finally, it should be noted that the above embodiments are merely illustrative of the technical solutions of the present invention and not intended to limit it. Those skilled in the art should understand that modifications or equivalent substitutions can be made to the specific embodiments of the present invention, but such modifications or alterations are all within the scope of protection of the pending claims.

Claims

1. A method for detecting abnormal user power consumption based on current analysis, characterized in that, The method for detecting abnormal power consumption by users includes the following steps: Step (1): Collect the user's current and voltage signals; Step (2): Make a preliminary judgment based on the current signal. The specific method is as follows: First, determine whether the current signal is greater than the current reference value. If so, the user's current consumption is high, indicating an abnormality. Secondly, calculate the user's power factor and determine whether the power factor is less than the power factor reference value. If so, the user's power factor is low. Next, extract the harmonic components of the current signal and determine whether the harmonic components of the current signal are greater than the harmonic component reference value. If so, the harmonic components of the user's power consumption are abnormal. Step (3): Retrieve the current signal for two consecutive weeks; Step (4): Based on the current signal, further determine whether there is any abnormality in the user's power consumption, as follows: First, calculate the average value of the current signal for each day; Next, calculate the standard deviation of the current signal for each day; Next, calculate the per-unit value of the current signal for each day; Next, the per-unit values ​​of the current signal are used as the clustering input matrix for clustering. Next, calculate the percentage of the current signal per day relative to the corresponding point in the cluster center of the same type of load; Finally, determine whether there are 20 current signals whose percentage of the corresponding points of the same type of load cluster center is less than 25%. If so, the user's power consumption is abnormal and an alarm is triggered. Step (5): Transmit the test results to the remote monitoring center; Step (6): The remote monitoring center will send the detected abnormal conditions to the user so that timely inspection and maintenance can be carried out.

2. The user power consumption anomaly detection method based on current analysis according to claim 1, characterized in that, The algorithm for calculating the daily standard deviation of the current signal is as follows: ,in The average value of the current signal. This represents the number of sampling points per day. For the first The current signal at each sampling point.

3. The user power consumption anomaly detection method based on current analysis according to claim 2, characterized in that, The algorithm for calculating the per-unit value of the current signal per day is as follows: ,in for day The aforementioned current signal. for The average value of the current signal mentioned above. for The standard deviation of the current signal mentioned in the text.

4. The user power consumption anomaly detection method based on current analysis according to claim 3, characterized in that, Clustering was performed using the K-means clustering method: ,in The current signal is classified into the first The value is 1 if it is a class, otherwise it is 0; For the first Cluster centers of classes The current signals that need to be clustered are divided into groups based on the number of current signals that need to be clustered. kind, For the first The current signal.

5. The user power consumption anomaly detection method based on current analysis according to claim 4, characterized in that, The user communicates with the remote monitoring center via a mobile app, and the app promptly receives the detected abnormality when the user's power consumption is abnormal.

Images