A method and system for detecting electric power parameters based on smart electric power

Abstract

The present invention relates to the field of power parameter measurement, and specifically to a power parameter detection method and detection system based on smart power. The method first obtains the power data of different power parameters of each sub-circuit and the current parameters of the main line at each moment in a preset time period, takes the main line or any sub-circuit as the target line, analyzes the fluctuation characteristics of the power data of each power parameter of the target line, obtains the initial load abnormality of each power parameter of the target line at each moment, combines the correlation degree of load abnormality between the sub-circuit and the main line, obtains the real load abnormality of the target line at each moment, and then adjusts the data acquisition frequency of the target line during the load abnormality period, collects the power parameter data of the target line at the adjusted frequency, and detects the collected power parameter data. The present invention improves the accuracy of power parameter detection by adjusting the data acquisition frequency during the load abnormality period.

Description

Technical Field

[0001] The present invention relates to the field of power parameter measurement, and in particular to a power parameter detection method and a detection system based on smart power. Background Art

[0002] Power parameter detection based on smart power is to monitor key power parameters in the power system in real time, such as voltage or current, through intelligent technology. It combines sensors, data acquisition, wireless communication, data analysis and automatic control technologies to achieve efficient management and maintenance of the power system and real-time monitoring of power equipment status, optimize energy use, and improve system safety and reliability.

[0003] In the related art, sensors with a fixed collection frequency are usually used to collect data on various power parameters, and the collected data are used to perform real-time detection of each power parameter. However, during peak power consumption periods, the load of power equipment on the line is abnormally high, resulting in frequent changes in the data of various power parameters of the line. At this time, if the fixed collection frequency is still used to collect power parameter data, some key data will be missed, thereby reducing the accuracy of power parameter detection. Summary of the invention

[0004] In order to solve the technical problem that the existing method of collecting power parameter data using a fixed collection frequency may miss some key data, thereby reducing the accuracy of power parameter detection, the purpose of the present invention is to provide a power parameter detection method and detection system based on smart power. The technical solutions adopted are as follows:

[0005] The present invention proposes a method for detecting power parameters based on smart power, the method comprising:

[0006] Acquire power data of different power parameters of each sub-circuit at each moment in a preset time period, wherein the power parameters at least include current parameters, and simultaneously acquire power data of current parameters of the main line at each moment in the preset time period;

[0007] Taking the main line or any sub-line as the target line, taking any power parameter in the target line as the target power parameter, obtaining the data fluctuation degree of the target power parameter of the target line at each moment according to the difference between the power data at each moment of the target power parameter of the target line and each moment in the preset time domain; based on the data fluctuation degree, screening out the abnormal fluctuation moments of the target power parameter of the target line from all moments; obtaining the initial load abnormality degree of the target power parameter of the target line at each moment according to the data fluctuation degree of the target power parameter of the target line at each moment and the number of the abnormal fluctuation moments in the preset time domain;

[0008] According to the correlation of current parameters between each sub-circuit and the main circuit, the difference of the initial load abnormality of the current parameters between each sub-circuit and the main circuit at the same time, and the initial load abnormality of all power parameters of each sub-circuit at the same time, the real load abnormality of each sub-circuit at each time is obtained; according to the real load abnormality of all sub-circuits at the same time, the real load abnormality of the main circuit at each time is obtained; according to the real load abnormality of the target circuit at each time, the load abnormality period of the target circuit within a preset time period is obtained; according to the real load abnormality of the target circuit at each time in each load abnormality period, the data collection frequency of the target circuit in each load abnormality period is adjusted to obtain the adjustment frequency of the target circuit in each load abnormality period;

[0009] The adjustment frequency is used to collect power parameter data within a preset time period, and the collected power parameter data is tested.

[0010] Furthermore, obtaining the data fluctuation degree of the target power parameter of the target line at each moment includes:

[0011] Taking any moment as the target moment, in the preset time domain of the target moment, taking the absolute value of the difference between the power data of the target power parameter of the target line at the target moment and each other moment except the target moment as the data difference between the target moment and each other moment;

[0012] After analyzing the overall level of the data difference between the target power parameter of the target line at the target moment and all other moments in the preset time domain and performing normalization processing, the data fluctuation degree of the target power parameter of the target line at the target moment is obtained.

[0013] Furthermore, the step of screening out the abnormal fluctuation moments of the target power parameters of the target line from all moments includes:

[0014] The moment when the data fluctuation degree is greater than a preset fluctuation threshold is regarded as the abnormal fluctuation moment of the target power parameter of the target line.

[0015] Further, obtaining the initial load abnormality of the target power parameter of the target line at each moment includes:

[0016] The data fluctuation degree of the target power parameter of the target line at each moment and the number of abnormal fluctuation moments within a preset time domain at each moment are integrated to obtain the initial load abnormality degree of the target power parameter of the target line at each moment.

[0017] Further, obtaining the actual load abnormality of each sub-line at each moment includes:

[0018] Taking any sub-circuit as a target sub-circuit, taking the absolute value of the Spearman correlation coefficient of the power data of the current parameter between the target sub-circuit and the main line as the current correlation coefficient between the target sub-circuit and the main line;

[0019] Performing negative correlation mapping on the absolute value of the difference between the initial load anomaly of the current parameters of the target sub-circuit and the main line at the same time, to obtain the initial anomaly similarity between the target sub-circuit and the main line at each time; taking the average value of the anomaly similarity between the target sub-circuit and the main line at all times as the current anomaly similarity between the target sub-circuit and the main line;

[0020] The current correlation coefficient and the current anomaly similarity are integrated and normalized to obtain a weight parameter of a target sub-circuit;

[0021] Analyzing the overall level of the initial load abnormality of all power parameters of the target sub-circuit at the same time to obtain the overall load abnormality of the target sub-circuit at each time;

[0022] The product value of the weight parameter of the target sub-circuit and the overall load abnormality of the target sub-circuit at each moment is normalized to obtain the real load abnormality of the target sub-circuit at each moment.

[0023] Furthermore, obtaining the actual load abnormality of the main line at each moment includes:

[0024] Taking any time as the time to be tested, if the actual load abnormality of each sub-circuit at the time to be tested is greater than the preset first abnormal threshold, then each sub-circuit is regarded as a high abnormal sub-circuit, otherwise, each sub-circuit is regarded as a low abnormal sub-circuit;

[0025] The average value of the actual load abnormality of all the high abnormal sub-circuits at the time to be tested is used as the average value of the high abnormality at the time to be tested, and the average value of the actual load abnormality of all the low abnormal sub-circuits at the time to be tested is used as the average value of the low abnormality at the time to be tested;

[0026] Using the preset first weight and the preset second weight, the high abnormality mean and the low abnormality mean are weightedly summed to obtain the actual load abnormality of the main line at the time to be tested, wherein the sum of the preset first weight and the preset second weight is equal to the value 1, and the preset first weight is greater than the preset second weight.

[0027] Furthermore, obtaining the load abnormality period of the target line within a preset time period includes:

[0028] If the actual load abnormality of the target line at each moment is greater than the preset second abnormal threshold, each moment is regarded as the load abnormality moment of the target line;

[0029] The period consisting of the continuous load abnormal moments of the target line is used as the load abnormal period of the target line within the preset time period.

[0030] Further, obtaining the adjustment frequency of the target line in each load abnormality period includes:

[0031] The average value of the actual load abnormality of the target line at all times in each load abnormality period is used as the load abnormality parameter of the target line in each load abnormality period;

[0032] The product value of the load abnormality parameter and the original data acquisition frequency is used as the frequency adjustment amount of the target line in each load abnormality period;

[0033] The sum of the original data collection frequency of the target line and the frequency adjustment amount of the target line in each load abnormality period is used as the adjustment frequency of the target line in each load abnormality period.

[0034] Further, the collecting of power parameter data within a preset time period by using the adjustment frequency and detecting the collected power parameter data includes:

[0035] The power parameter data of the target line in each load abnormality period within the preset time period is collected by utilizing the adjustment frequency of the target line in each load abnormality period, and the power parameter data of the target line in the non-load abnormality period within the preset time period is collected by utilizing the original data collection frequency, and among the power parameter data collected at each moment, the data that exceeds the normal data range of the corresponding power parameter is regarded as abnormal data.

[0036] The present invention also proposes an electric power parameter detection system based on smart power, the system comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements any one of the steps of an electric power parameter detection method based on smart power when executing the computer program.

[0037] The present invention has the following beneficial effects:

[0038] The present invention takes into account that the existing use of a fixed collection frequency to collect data on power parameters will miss some key data, thereby reducing the accuracy of power parameter detection. Therefore, the power data of different power parameters of each sub-circuit at each moment in a preset time period is first obtained, and the power data of the current parameters of the main line at each moment in the preset time period is simultaneously obtained. Since there are different numbers and types of power equipment on the main line and each sub-circuit, during peak power consumption, the data changes of power parameters between the main line and each sub-circuit are different, and the changes of different power parameters in the same line are also different. Therefore, it is necessary to analyze specific power parameters in a specific line. Since an abnormally high load will cause obvious fluctuations in power data, the abnormal fluctuation moment can be first extracted according to the degree of data fluctuation. Considering the power data Noise will also cause data fluctuations, but the fluctuations caused by noise usually appear in isolation, and the number of abnormal fluctuation moments caused by noise in a local area is small. Therefore, the initial load abnormality can be further used to preliminarily reflect the possibility of target line load abnormality represented by the target power parameters. Since all sub-lines converge on the main line, different sub-lines have different impacts on the main line, and the current parameter is the most critical power parameter that reflects the power consumption. Therefore, the actual load abnormality can be used to reflect the possibility of load abnormalities in sub-lines and main lines at each moment, and then accurately extract the load abnormality period of the target line, and adjust the data collection frequency of the load abnormality period to improve the accuracy of data collection for the target line during the load abnormality period, so as to capture the subtle changes in power parameter data during the load abnormality period and improve the accuracy of power parameter detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0040] Figure 1 A flow chart of a power parameter detection method based on smart power provided by an embodiment of the present invention;

[0041] Figure 2 A flow chart of a method for obtaining the actual load abnormality degree of each sub-line at each moment provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0042] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following is a detailed description of the specific implementation method, structure, features and effects of a power parameter detection method and detection system based on smart power proposed by the present invention in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0043] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0044] The following is a detailed description of a specific scheme of a power parameter detection method and detection system based on smart power provided by the present invention in conjunction with the accompanying drawings.

[0045] See also Figure 1 , which shows a flow chart of a power parameter detection method based on smart power provided by an embodiment of the present invention, the method comprising:

[0046] Step S1: acquiring power data of different power parameters of each sub-circuit at each moment in a preset time period, where the power parameters at least include current parameters, and acquiring power data of current parameters of the main line at each moment in a preset time period.

[0047] In the manufacturing automation park, multiple sub-controllers are generally connected through a main controller, where the main controller is used to control the main line, and the sub-controller is used to control the sub-line. The control of multi-level lines can improve the reliability of the system and enhance flexibility and scalability.

[0048] Therefore, the embodiment of the present invention first uses different types of power sensors such as current sensors or voltage sensors to collect power data of different power parameters of each sub-circuit at each moment within a preset time period, wherein the power parameters include multiple different types of parameters such as current parameters, voltage parameters and electric power parameters. The preset time period is set to one day, and the time interval for data collection is one minute. That is to say, for each power parameter of the sub-circuit, power data is collected every one minute. The specific values ​​of the preset time period and the time interval for data collection can also be set by the implementer according to the specific implementation scenario, and are not limited here.

[0049] At the same time, since the current parameter is the most critical power parameter to show the power consumption, in order to improve the accuracy of subsequent calculation and analysis, the embodiment of the present invention also needs to use the current sensor to collect the power data of the current parameter of the main line at each moment in the preset time period. At this time, the power data is the current data, wherein the time interval for collecting the data of the current parameter of the main line is the same as the time interval for collecting the data of the sub-line. At this time, the power sensor collects the original data of the main line and each sub-line in the preset time period at a frequency of Hertz, the raw data collection frequency of the power sensor can be adjusted later to improve the accuracy of power parameter data detection.

[0050] Step S2: taking the main line or any sub-line as the target line, taking any power parameter in the target line as the target power parameter, obtaining the data fluctuation degree of the target power parameter of the target line at each moment according to the difference in power data between each moment of the target power parameter of the target line and each moment in the preset time domain; based on the data fluctuation degree, screening out the abnormal fluctuation moments of the target power parameter of the target line from all moments; obtaining the initial load abnormality of the target power parameter of the target line at each moment according to the data fluctuation degree of the target power parameter of the target line at each moment and the number of abnormal fluctuation moments in the preset time domain.

[0051] Since there are different numbers and types of power equipment on the main line and each sub-line, during the peak period of power consumption, the data changes of power parameters between the main line and each sub-line are different, and the changes of different power parameters in the same line are also different. Therefore, it is necessary to analyze the specific power parameters in the specific line. First, the main line or any sub-line is taken as the target line, and any power parameter in the target line is taken as the target power parameter. When the load is abnormally high at a certain moment, the power data of the target power parameter at that moment will fluctuate significantly, so that the power data with large fluctuations is different from other local power data. Therefore, the difference in power data between each moment of the target power parameter of the target line and each moment in the preset time domain can be analyzed. The degree of fluctuation of the target power parameter of the target line at each moment is reflected by the obtained data fluctuation degree. Subsequently, based on the data fluctuation degree, the various moments of abnormal data fluctuation of the target power parameter of the target line can be accurately extracted, and the possibility of load abnormality represented by the target power parameter of the target line can be accurately calculated and analyzed. The length of the preset neighborhood of each moment is set to 19, that is, the preset neighborhood includes the moment and the 18 moments closest to the moment.

[0052] Preferably, in one embodiment of the present invention, the method for acquiring the data fluctuation degree of the target power parameter of the target line at each moment specifically includes:

[0053] First, any moment is taken as the target moment. In the preset time domain of the target moment, the absolute value of the difference in power data between the target power parameter of the target line at the target moment and every other moment except the target moment is taken as the data difference between the target moment and every other moment. The larger the data difference, the greater the data difference between the target power parameter of the target line at the target moment and other moments, and thus the greater the data fluctuation at the target moment.

[0054] Then, the overall level of data difference between the target power parameter of the target line at the target moment and all other moments in the preset time domain is analyzed and normalized to obtain the data fluctuation degree of the target power parameter of the target line at the target moment.

[0055] In an embodiment of the present invention, the overall level of data difference between the target power parameters of the target line at the target moment and all other moments in the preset time domain can be analyzed by calculating the average value or median of the data difference between the target power parameters of the target line at the target moment and all other moments in the preset time domain, which is not limited here.

[0056] In one embodiment of the present invention, the normalization processing can be specifically, for example, maximum and minimum value normalization processing, and the normalization in subsequent steps can all adopt maximum and minimum value normalization processing. In other embodiments of the present invention, other normalization methods can be selected according to the specific range of numerical values, which will not be described in detail.

[0057] As an example, in one embodiment of the present invention, the expression of the data fluctuation degree of the target power parameter of the target line at the target time may be specifically, for example, as follows:

[0058]

[0059] Wherein, W represents the data fluctuation degree of the target power parameter of the target line at the target time; D represents the power data of the target power parameter of the target line at the target time; D i Represents the power data of the target power parameter of the target line at the i-th time other than the target time in the preset time domain of the target time; |DD i | represents the data difference between the target moment and the i-th other moment; I represents the number of other moments except the target moment in the preset time domain of the target moment; norm() represents the normalization function.

[0060] The same method as above can be used to obtain the data fluctuation degree of the target power parameters of the target line at each moment, and then based on the data fluctuation degree, the abnormal fluctuation moments of the target power parameters of the target line can be screened out from all moments. The abnormal fluctuation moment is the moment when the target power parameters of the target line have abnormal data fluctuations which may be caused by load abnormality.

[0061] Preferably, in one embodiment of the present invention, the moment when the data fluctuation degree is greater than a preset fluctuation threshold is taken as the abnormal fluctuation moment of the target power parameter of the target line. The preset fluctuation threshold is set to 0.6. The specific value of the preset fluctuation threshold can also be set by the implementer according to the specific implementation scenario, which is not limited here.

[0062] Taking into account that noise in power data can also cause data fluctuations, but due to the randomness of noise, the data fluctuations caused by it usually appear in isolation, and the number of abnormal fluctuation moments caused by noise in a local area is small, while load abnormalities usually last for a period of time, and the number of abnormal fluctuation moments caused by load abnormalities in a local area is large. Therefore, the number of abnormal fluctuation moments of the target power parameters of the target line in the preset time domain at each moment can be analyzed. At the same time, combined with the degree of data fluctuation at each moment, the initial load abnormality obtained can preliminarily reflect the possibility of load abnormality in the target line shown by the target power parameters at each moment, thereby eliminating the interference of noise on load abnormality analysis, and providing a data basis for the subsequent accurate calculation of the possibility of real load abnormality of the sub-line at each moment.

[0063] Preferably, in one embodiment of the present invention, the method for obtaining the initial load abnormality degree of the target power parameter of the target line at each moment specifically includes:

[0064] The greater the data fluctuation degree of the target power parameter of the target line at each moment, and the greater the number of abnormal fluctuation moments within the preset time domain at each moment, the greater the possibility of load abnormality in the target line represented by the target power parameter at each moment. Therefore, the data fluctuation degree of the target power parameter of the target line at each moment and the number of abnormal fluctuation moments within the preset time domain at each moment can be combined to obtain the initial load abnormality degree of the target power parameter of the target line at each moment.

[0065] In an embodiment of the present invention, the sum or product of the data fluctuation degree of the target power parameter of the target line at each moment and the number of abnormal fluctuation moments within a preset time domain at each moment can be used as the initial load abnormality degree of the target power parameter of the target line at each moment.

[0066] As an example, in one embodiment of the present invention, the expression of the initial load abnormality degree of the target power parameter of the target line at each moment can be specifically, for example, as follows:

[0067] A n =W n +Z n

[0068] Among them, A n W represents the initial load abnormality of the target power parameter of the target line at the nth moment; n Indicates the data fluctuation degree of the target power parameter of the target line at the nth moment; Z n Indicates the number of abnormal fluctuation moments of the target power parameter of the target line within the preset time domain at the nth moment.

[0069] By using the same method as above, the initial load abnormality of each power parameter of each sub-circuit at each moment and the initial load abnormality of the current parameter of the main line at each moment can be obtained.

[0070] Step S3: According to the correlation of current parameters between each sub-circuit and the main line, the difference of initial load abnormality of current parameters between each sub-circuit and the main line at the same time, and the initial load abnormality of all power parameters of each sub-circuit at the same time, the real load abnormality of each sub-circuit at each time is obtained; according to the real load abnormality of all sub-circuits at the same time, the real load abnormality of the main line at each time is obtained; according to the real load abnormality of the target line at each time, the load abnormality period of the target line within a preset time period is obtained; according to the real load abnormality of the target line at each time in each load abnormality period, the data collection frequency of the target line in each load abnormality period is adjusted to obtain the adjustment frequency of the target line in each load abnormality period.

[0071] Since all sub-circuits converge on the main line, the load anomaly of the sub-circuit will directly affect the load anomaly of the main line, and different sub-circuits have different degrees of influence on the load anomaly of the main line. The current parameters are directly related to various other power parameters. The current parameters are the most critical power parameters that reflect the power consumption situation. Therefore, we can first analyze the correlation degree of the load anomaly between each sub-circuit and the main line based on the correlation of the current parameters between each sub-circuit and the main line, and the difference in the initial load anomaly degree of the current parameters between each sub-circuit and the main line at the same time. In addition, combined with the initial load anomaly degree of all power parameters of each sub-circuit at the same time, the actual load anomaly degree of each sub-circuit at each time is obtained to accurately reflect the possibility of load anomaly in each sub-circuit at each time and the correlation degree of load anomaly between each sub-circuit and the main line. Subsequently, the actual load anomaly degree of each sub-circuit at the same time can be combined to accurately calculate the actual load anomaly degree of the main line at each time.

[0072] Preferably, in one embodiment of the present invention, the method for obtaining the actual load abnormality of each sub-line at each moment specifically includes:

[0073] See also Figure 2 , which shows a flow chart of a method for obtaining the actual load abnormality degree of each sub-line at each moment provided by an embodiment of the present invention.

[0074] Step S301: taking any sub-circuit as a target sub-circuit, and taking the absolute value of the Spearman correlation coefficient of the power data of the current parameters between the target sub-circuit and the main circuit as the current correlation coefficient between the target sub-circuit and the main circuit.

[0075] First, any sub-circuit is analyzed and any sub-circuit is taken as the target sub-circuit. The greater the correlation between the current parameters of the target sub-circuit and the main circuit, the more similar the data changes of the current parameters of the two are, and further the greater the correlation between the load abnormalities of the target sub-circuit and the main circuit. Therefore, the absolute value of the Spearman correlation coefficient of the power data of the current parameters between the target sub-circuit and the main circuit can be used as the current correlation coefficient between the target sub-circuit and the main circuit. The calculation method of the Spearman correlation coefficient is a technical means well known to those skilled in the art and is not limited here. In other embodiments of the present invention, the Pearson correlation coefficient can also be used to calculate the current correlation coefficient.

[0076] Step S302: negatively correlate the absolute value of the difference in the initial load anomaly degree of the current parameters between the target sub-circuit and the main line at the same time to obtain the initial anomaly similarity between the target sub-circuit and the main line at each time; and take the average value of the anomaly similarity between the target sub-circuit and the main line at all times as the current anomaly similarity between the target sub-circuit and the main line.

[0077] The smaller the difference in the initial load anomaly degree of the current parameters between the target subcircuit and the main line at the same time, the more similar the load anomaly situations between the target subcircuit and the main line are. Therefore, the absolute value of the difference in the initial load anomaly degree of the current parameters between the target subcircuit and the main line at the same time can be firstly negatively correlated to obtain the initial anomaly similarity between the target subcircuit and the main line at each time. The larger the initial anomaly similarity, the more similar the possibility of load anomaly between the target subcircuit and the main line at the same time is, which further indicates that the greater the correlation between the load anomaly between the target subcircuit and the main line is. Then, the average value of the anomaly similarity between the target subcircuit and the main line at all times is taken as the current anomaly similarity between the target subcircuit and the main line.

[0078] Step S303: The current correlation coefficient and the current anomaly similarity are integrated and normalized to obtain the weight parameter of the target sub-circuit.

[0079] From the above analysis, it can be seen that the greater the current correlation coefficient and the current anomaly similarity, the greater the correlation between the load anomaly of the target sub-line and the main line. Therefore, the current correlation coefficient and the current anomaly similarity can be integrated and normalized to obtain the weight parameter of the target sub-line. The weight parameter can be used to accurately calculate the real load anomaly of the target sub-line at each moment, so that the calculated real load anomaly of the target sub-line at each moment is linked to the main line. Then, the real load anomaly of the main line at each moment can be accurately calculated through the real load anomaly of each sub-line at the same moment.

[0080] In the embodiment of the present invention, the current correlation coefficient and the current anomaly similarity may be integrated by calculating the sum or product of the two, which is not limited herein.

[0081] As an example, in one embodiment of the present invention, the expression of the weight parameter of the target sub-line may be specifically, for example:

[0082]

[0083] Where G represents the weight parameter of the target sub-circuit; ρ represents the Spearman correlation coefficient of the power data of the current parameters between the target sub-circuit and the main line; |ρ| represents the current correlation coefficient between the target sub-circuit and the main line; A′ n Indicates the initial load abnormality of the current parameter of the target sub-circuit at the nth moment; A″ n Indicates the initial load abnormality of the current parameter of the main line at the nth moment; represents the initial anomaly similarity between the target sub-route and the main route at the nth moment; Indicates the similarity of current anomaly between the target sub-circuit and the main circuit; N indicates the number of moments for data collection of current parameters of the target sub-circuit or the main circuit. Since step S1 collects power data of each power parameter of the sub-circuit and the main circuit through the original data collection frequency, the number of collection moments between each power parameter of the sub-circuit and the main circuit is the same; norm() indicates a normalization function; ε indicates a preset adjustment parameter for preventing the denominator from being 0. The value range of ε is [0.001, 0.01]. In one embodiment of the present invention, ε is set to 0.01. The specific value of ε can also be set by the implementer according to the specific implementation scenario, which is not limited here.

[0084] It should be noted that in other embodiments of the present invention, negative correlation mapping may be achieved through other basic mathematical operations, which will not be elaborated herein.

[0085] Step S304: Analyze the overall level of initial load abnormality of all power parameters of the target sub-circuit at the same time to obtain the overall load abnormality of the target sub-circuit at each time.

[0086] Since there are multiple power parameters in the target sub-line, the overall level of the initial load abnormality of all power parameters of the target sub-line at the same time can be analyzed to obtain the overall load abnormality of the target sub-line at each moment. The larger the overall load abnormality, the greater the possibility of load abnormality in the target sub-line at each moment. Subsequently, the overall load abnormality and weight parameters can be combined to accurately calculate the actual load abnormality of the target sub-line at each moment.

[0087] In an embodiment of the present invention, the average value or median of the initial load abnormality of all power parameters of the target sub-circuit at the same time can be used as the overall load abnormality of the target sub-circuit at each time, so as to realize the analysis of the overall level of the initial load abnormality of all power parameters of the target sub-circuit at the same time, which is not limited here.

[0088] Step S305: normalizing the product value of the weight parameter of the target sub-circuit and the overall load abnormality of the target sub-circuit at each moment to obtain the real load abnormality of the target sub-circuit at each moment.

[0089] The larger the weight parameter of the target sub-line is, the greater the correlation between the target sub-line and the main line is. The overall load abnormality of the target sub-line at each moment indicates that the possibility of load abnormality in the target sub-line at each moment is greater. Therefore, the product value of the weight parameter of the target sub-line and the overall load abnormality of the target sub-line at each moment can be normalized to obtain the true load abnormality of the target sub-line at each moment.

[0090] As an example, in one embodiment of the present invention, the expression of the actual load abnormality of the target sub-line at each moment may be specifically, for example, as follows:

[0091]

[0092] Among them, B n represents the actual load abnormality of the target sub-line at the nth moment; G represents the weight parameter of the target sub-line; A (m,n) represents the initial load abnormality of the mth power parameter of the target sub-circuit at the nth moment; represents the overall load abnormality of the target sub-circuit at the nth moment; M represents the number of power parameters in the target sub-circuit; norm() represents the normalization function.

[0093] The same method as above can be used to obtain the true load anomaly of each sub-line at each moment. Since each sub-line converges on the main line, a load anomaly in a sub-line will directly lead to a load anomaly in the main line. Therefore, the true load anomaly of the main line at each moment can be obtained based on the true load anomaly of all sub-lines at the same moment.

[0094] Preferably, in one embodiment of the present invention, the method for obtaining the real load abnormality of the main line at each moment specifically includes:

[0095] First, any moment is taken as the moment to be tested. Since the correlation degree of load anomaly between each sub-line and the main line is different, the greater the actual load degree of the sub-line at the moment to be tested, the greater the possibility of load anomaly in the sub-line at the moment to be tested, and the greater the possibility of load anomaly in the main line. Therefore, based on the actual load anomaly degree of each sub-line at the moment to be tested, each sub-line can be divided into two categories. If the actual load anomaly degree of each sub-line at the moment to be tested is greater than the preset first anomaly threshold, each sub-line is regarded as a high-abnormal sub-line, otherwise, each sub-line is regarded as a low-abnormal sub-line, wherein the preset first anomaly threshold is set to 0.6, and the specific value of the preset first anomaly threshold can also be set by the implementer according to the specific implementation scenario, and is not limited here.

[0096] Then, the average value of the actual load anomaly of all high-abnormal sub-lines at the time to be tested is taken as the average value of the high anomaly at the time to be tested, and the average value of the actual load anomaly of all low-abnormal sub-lines at the time to be tested is taken as the average value of the low anomaly at the time to be tested;

[0097] Compared with the low-abnormal sub-line, the high-abnormal sub-line has a greater impact on the load abnormality of the main line. Therefore, the preset first weight and the preset second weight are used to perform weighted summation on the high abnormality mean and the low abnormality mean to obtain the actual load abnormality of the main line at the time to be tested, wherein the sum of the preset first weight and the preset second weight is equal to the value 1, and the preset first weight is greater than the preset second weight. In one embodiment of the present invention, the preset first weight and the preset second weight are set to 0.8 and 0.2, respectively. The specific values ​​of the preset first weight and the preset second weight can also be set by the implementer according to the specific implementation scenario, which is not limited here.

[0098] As an example, in one embodiment of the present invention, the expression of the actual load abnormality of the main line at the time to be tested can be specifically, for example, as follows:

[0099]

[0100] Wherein, C represents the actual load abnormality of the main line at the time to be tested; It represents the average value of the real load abnormality of all high abnormal sub-lines at the time to be tested, that is, the high abnormality mean value at the time to be tested; It represents the average value of the actual load abnormality of all low-abnormal sub-lines at the time to be tested, that is, the low-abnormality mean at the time to be tested; β1 represents the preset first weight; β2 represents the preset second weight.

[0101] The same method as above can be used to obtain the real load anomaly of the main line at each moment. So far, the real load anomaly of the main line and each sub-line at each moment is obtained.n Indicates the actual load abnormality of the main line or each sub-line at the nth moment.

[0102] Then, the main line or any sub-line is analyzed. The larger the actual load abnormality, the greater the possibility that the main line or sub-line has a load abnormality at that moment. According to the actual load abnormality of the target line at each moment, the load abnormality period of the target line within the preset time period can be obtained, where the target line represents the main line or any sub-line.

[0103] Preferably, in one embodiment of the present invention, the method for obtaining the abnormal load period of the target line within a preset time period specifically includes:

[0104] If the actual load abnormality of the target line at each moment is greater than the preset second abnormal threshold, each moment is regarded as the load abnormality moment of the target line, wherein the preset second abnormal threshold is set to 0.5, and the specific value of the preset second abnormal threshold can also be set by the implementer according to the specific implementation scenario, which is not limited here.

[0105] Under normal circumstances, the peak period of electricity consumption will last for a period of time, so the abnormally high load phenomenon of the target line will also last for a period of time. Therefore, the time period composed of continuous abnormal load moments of the target line can be used as the abnormal load period of the target line within the preset time period. For example, for each moment {a, b, c, d, e, f, g} within the preset time period, where moments a, b, c, f and g are the abnormal load moments of the target line, then the time periods {a, b, c} and {f, g} are the abnormal load periods of the target line within the preset time period, and the time period {d, e} is the non-abnormal load period of the target line.

[0106] Since the data of various power parameters of the target line during the load abnormality period change frequently, in order to capture the subtle changes in the power parameter data during the load abnormality period, it is necessary to adjust the data collection frequency of the target line during the load abnormality period to avoid missing some key power data of the power parameters and improve the accuracy of power parameter detection. At the same time, the target line has different degrees of load abnormality in different load abnormality periods, so it is necessary to adjust the data collection frequency of different load abnormality periods to different degrees. The actual load abnormality degree of the target line at each moment in each load abnormality period can reflect the degree of load abnormality of the target line in each load abnormality period. Therefore, according to the actual load abnormality degree of the target line at each moment in each load abnormality period, the data collection frequency of the target line in each load abnormality period can be adjusted to obtain the adjusted frequency of the target line in each load abnormality period. The adjusted frequency can be used to collect the power parameter data of the target line in each load abnormality period to improve the accuracy of power parameter detection.

[0107] Preferably, in one embodiment of the present invention, the method for acquiring the adjustment frequency of the target line in each load abnormality period specifically includes:

[0108] The average value of the actual load anomaly degree of the target line at all times in each load anomaly period is used as the load anomaly parameter of the target line in each load anomaly period. The larger the load anomaly parameter, the greater the degree of load anomaly of the target line in each load anomaly period, and the greater the adjustment degree of the data acquisition frequency. Then, the product value of the load anomaly parameter and the original data acquisition frequency is used as the frequency adjustment amount of the target line in each load anomaly period. For load anomaly periods with frequent data changes, a higher frequency is required to collect power data in the load anomaly period in order to capture subtle changes in power parameter data. Therefore, the sum of the original data acquisition frequency of the target line and the frequency adjustment amount of the target line in each load anomaly period can be used as the adjustment frequency of the target line in each load anomaly period.

[0109] As an example, in one embodiment of the present invention, the expression of the adjustment frequency of the target line in each load abnormality period may be specifically, for example, as follows:

[0110] f′ h =f+U h ×f

[0111]

[0112] Among them, f′ h represents the adjustment frequency of the target line in the hth load abnormal period; f represents the original data acquisition frequency. In one embodiment of the present invention, Hertz; U h represents the load abnormality parameter of the target line in the hth load abnormality period; E (h,r) represents the actual load abnormality of the target line at the rth moment in the hth load abnormality period; R h Indicates the number of time points included in the hth load abnormality period of the target line.

[0113] Step S4: collecting power parameter data within a preset time period by adjusting the frequency, and detecting the collected power parameter data.

[0114] Through the above process, the adjustment frequency of the target line in each load abnormality period within the preset time period is obtained. Therefore, the adjustment frequency can be used to collect the power parameter data within the preset time period, so that the subtle changes in the power parameter data can be captured more accurately, and then the collected power parameter data can be detected to improve the accuracy of the detection of each power parameter.

[0115] Preferably, in one embodiment of the present invention, the method for detecting the collected power parameter data specifically includes:

[0116] By utilizing the adjustment frequency of the target line in each load abnormality period, the power parameter data of the target line in each load abnormality period within the preset time period is collected, and by utilizing the original data collection frequency, the power parameter data of the target line in the non-load abnormality period within the preset time period is collected. Under normal circumstances, the detection of power parameters is generally anomaly detection. Therefore, in the power parameter data collected at each moment, the data that exceeds the normal data range of the corresponding power parameter can be used as abnormal data. Among them, each power parameter will have a normal data range, so as to judge whether the power data of the power parameter at each moment is abnormal. Since the data collection frequency of the target line in each load abnormality period is improved, it can more accurately capture the subtle changes in the data of each power parameter, so it can more accurately detect the data abnormality of the power parameter.

[0117] An embodiment of the present invention provides an electric parameter detection system based on smart power, the system includes a memory, a processor and a computer program, wherein the memory is used to store the corresponding computer program, the processor is used to run the corresponding computer program, and when the computer program runs in the processor, it can implement the method described in steps S1 to S4.

[0118] It should be noted that the sequence of the above embodiments of the present invention is only for description and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0119] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

Claims

1. A method for detecting power parameters based on smart power, characterized in that: The method comprises: Acquire power data of different power parameters of each sub-circuit at each moment in a preset time period, wherein the power parameters at least include current parameters, and simultaneously acquire power data of current parameters of the main line at each moment in the preset time period; Taking the main line or any sub-line as the target line, taking any power parameter in the target line as the target power parameter, obtaining the data fluctuation degree of the target power parameter of the target line at each moment according to the difference between the power data at each moment of the target power parameter of the target line and each moment in the preset time domain; based on the data fluctuation degree, screening out the abnormal fluctuation moments of the target power parameter of the target line from all moments; obtaining the initial load abnormality degree of the target power parameter of the target line at each moment according to the data fluctuation degree of the target power parameter of the target line at each moment and the number of the abnormal fluctuation moments in the preset time domain; According to the correlation of current parameters between each sub-circuit and the main circuit, the difference of the initial load abnormality of the current parameters between each sub-circuit and the main circuit at the same time, and the initial load abnormality of all power parameters of each sub-circuit at the same time, the real load abnormality of each sub-circuit at each time is obtained; according to the real load abnormality of all sub-circuits at the same time, the real load abnormality of the main circuit at each time is obtained; according to the real load abnormality of the target circuit at each time, the load abnormality period of the target circuit within a preset time period is obtained; according to the real load abnormality of the target circuit at each time in each load abnormality period, the data collection frequency of the target circuit in each load abnormality period is adjusted to obtain the adjustment frequency of the target circuit in each load abnormality period; The adjustment frequency is used to collect power parameter data within a preset time period, and the collected power parameter data is tested.

2. The method for detecting power parameters based on smart power according to claim 1, characterized in that: The step of obtaining the data fluctuation degree of the target power parameter of the target line at each moment includes: Taking any moment as the target moment, in the preset time domain of the target moment, taking the absolute value of the difference between the power data of the target power parameter of the target line at the target moment and each other moment except the target moment as the data difference between the target moment and each other moment; After analyzing the overall level of the data difference between the target power parameter of the target line at the target moment and all other moments in the preset time domain and performing normalization processing, the data fluctuation degree of the target power parameter of the target line at the target moment is obtained.

3. The method for detecting power parameters based on smart power according to claim 1, characterized in that: The abnormal fluctuation moments of the target power parameters of the target line are screened out from all moments, including: The moment when the data fluctuation degree is greater than a preset fluctuation threshold is regarded as the abnormal fluctuation moment of the target power parameter of the target line.

4. The method for detecting power parameters based on smart power according to claim 1, characterized in that: The step of obtaining the initial load abnormality of the target power parameter of the target line at each moment includes: The data fluctuation degree of the target power parameter of the target line at each moment and the number of abnormal fluctuation moments within a preset time domain at each moment are integrated to obtain the initial load abnormality degree of the target power parameter of the target line at each moment.

5. The method for detecting power parameters based on smart power according to claim 1, characterized in that: The obtaining of the actual load abnormality of each sub-circuit at each moment comprises: Taking any sub-circuit as a target sub-circuit, taking the absolute value of the Spearman correlation coefficient of the power data of the current parameter between the target sub-circuit and the main line as the current correlation coefficient between the target sub-circuit and the main line; Performing negative correlation mapping on the absolute value of the difference between the initial load anomaly of the current parameters of the target sub-circuit and the main line at the same time, to obtain the initial anomaly similarity between the target sub-circuit and the main line at each time; taking the average value of the anomaly similarity between the target sub-circuit and the main line at all times as the current anomaly similarity between the target sub-circuit and the main line; The current correlation coefficient and the current anomaly similarity are integrated and normalized to obtain a weight parameter of a target sub-circuit; Analyzing the overall level of the initial load abnormality of all power parameters of the target sub-circuit at the same time to obtain the overall load abnormality of the target sub-circuit at each time; The product value of the weight parameter of the target sub-circuit and the overall load abnormality of the target sub-circuit at each moment is normalized to obtain the real load abnormality of the target sub-circuit at each moment.

6. The method for detecting power parameters based on smart power according to claim 1, characterized in that: The obtaining of the actual load abnormality of the main line at each moment comprises: Taking any time as the time to be tested, if the actual load abnormality of each sub-circuit at the time to be tested is greater than the preset first abnormal threshold, then each sub-circuit is regarded as a high abnormal sub-circuit, otherwise, each sub-circuit is regarded as a low abnormal sub-circuit; The average value of the actual load abnormality of all the high abnormal sub-circuits at the time to be tested is used as the average value of the high abnormality at the time to be tested, and the average value of the actual load abnormality of all the low abnormal sub-circuits at the time to be tested is used as the average value of the low abnormality at the time to be tested; Using the preset first weight and the preset second weight, the high abnormality mean and the low abnormality mean are weightedly summed to obtain the actual load abnormality of the main line at the time to be tested, wherein the sum of the preset first weight and the preset second weight is equal to the value 1, and the preset first weight is greater than the preset second weight.

7. The method for detecting power parameters based on smart power according to claim 1, characterized in that: The step of obtaining the load abnormality period of the target line within the preset time period includes: If the actual load abnormality of the target line at each moment is greater than the preset second abnormal threshold, each moment is regarded as the load abnormality moment of the target line; The period consisting of the continuous load abnormal moments of the target line is used as the load abnormal period of the target line within the preset time period.

8. The method for detecting power parameters based on smart power according to claim 1, characterized in that: The step of obtaining the adjustment frequency of the target line in each load abnormality period includes: The average value of the actual load abnormality of the target line at all times in each load abnormality period is used as the load abnormality parameter of the target line in each load abnormality period; The product value of the load abnormality parameter and the original data acquisition frequency is used as the frequency adjustment amount of the target line in each load abnormality period; The sum of the original data collection frequency of the target line and the frequency adjustment amount of the target line in each load abnormality period is used as the adjustment frequency of the target line in each load abnormality period.

9. The method for detecting power parameters based on smart power according to claim 1, characterized in that: The collecting of power parameter data within a preset time period by using the adjustment frequency and detecting the collected power parameter data includes: The power parameter data of the target line in each load abnormality period within the preset time period is collected by utilizing the adjustment frequency of the target line in each load abnormality period, and the power parameter data of the target line in the non-load abnormality period within the preset time period is collected by utilizing the original data collection frequency, and among the power parameter data collected at each moment, the data that exceeds the normal data range of the corresponding power parameter is regarded as abnormal data.

10. A power parameter detection system based on smart power, the system comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 9 are implemented.

Images