CN111103490A - Load identification event detection method, device and equipment - Google Patents
Load identification event detection method, device and equipment Download PDFInfo
- Publication number
- CN111103490A CN111103490A CN201911368330.5A CN201911368330A CN111103490A CN 111103490 A CN111103490 A CN 111103490A CN 201911368330 A CN201911368330 A CN 201911368330A CN 111103490 A CN111103490 A CN 111103490A
- Authority
- CN
- China
- Prior art keywords
- current effective
- detection window
- detection
- current
- effective value
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R35/00—Testing or calibrating of apparatus covered by the other groups of this subclass
- G01R35/04—Testing or calibrating of apparatus covered by the other groups of this subclass of instruments for measuring time integral of power or current
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Remote Monitoring And Control Of Power-Distribution Networks (AREA)
Abstract
The application discloses a load identification event detection method, a device and equipment, wherein the method comprises the following steps: acquiring a plurality of current effective values meeting the detection time period of a preset load event; calculating a plurality of first direction sub-features corresponding to each current effective value in a detection window; accumulating the plurality of first direction sub-characteristics corresponding to each current effective value to obtain a second direction sub-characteristic of each current effective value; accumulating all the second direction sub-characteristics of the current effective value to obtain the direction characteristics of the current effective value in the detection window; sliding the detection window based on a preset sliding step length, and updating the current effective value in the detection window to obtain the direction characteristic of the sliding detection window; and calculating the confidence coefficient of the current effective value corresponding to the largest direction feature in all the direction features, and outputting an effective load event when the confidence coefficient is smaller than a threshold value. The method and the device solve the technical problems that the prior art cannot take into account of low operation complexity, quick response, detection accuracy and other indexes.
Description
Technical Field
The present application relates to the field of power grid systems, and in particular, to a method, an apparatus, and a device for detecting a load identification event.
Background
The load identification means that monitoring equipment is installed at an electric power inlet, and the type, the running condition, the accumulated power consumption and other power consumption parameters of a single load in a load cluster can be obtained through analysis by monitoring signals such as voltage, current and the like at the position. The electricity utilization information has high application value, can bring benefits to power grid companies, users and other parties, and has the advantages of low economic investment and strong practicability. In addition, products and systems meeting actual requirements can be customized in more non-electric energy metering subdivision scenes, such as monitoring of fire safety of electric fires, analysis and monitoring of illegal electricity stealing behaviors in rural areas and the like.
The load identification technology can be further decomposed into several main steps of event detection, feature extraction, classification identification and the like, and the detection of the load state switching event is the basis of the whole technical scheme and directly influences the performance index of the subsequent link. The existing detection device for the load state switching event is mainly deployed in a single-phase electric energy meter, and cannot give consideration to indexes such as low operation complexity, quick response, detection accuracy and the like.
Disclosure of Invention
The application provides a load identification event detection method, device and equipment, which are used for solving the technical problems that the existing load event detection technology cannot give consideration to indexes such as low operation complexity, quick response and detection accuracy.
In view of the above, a first aspect of the present application provides a load identification event detection method, including:
s1: acquiring a plurality of current effective values meeting the detection time period of a preset load event, wherein the number of the current effective values is constrained by the length of a detection window of the preset load event;
s2: calculating a plurality of first direction sub-characteristics corresponding to each current effective value in the detection window;
s3: accumulating the plurality of first direction sub-characteristics corresponding to each current effective value to obtain a second direction sub-characteristic of each current effective value;
s4: accumulating all the second direction sub-characteristics of the current effective value to obtain the direction characteristics of the current effective value in the detection window;
s5: sliding the detection window based on a preset sliding step length, updating the effective current value in the detection window, and repeating the steps S2-S4 to obtain the direction characteristic of the effective current value in the sliding detection window;
s6: calculating the confidence of the current effective value corresponding to the direction feature which is the largest in the step S4 or the step S5, and outputting a payload event when the confidence is smaller than a threshold value.
Preferably, the obtaining a plurality of current effective values satisfying a detection time period of a preset load event, where the number of the current effective values is constrained by a detection window length of the preset load event, further includes:
initializing parameters for pre-load event detection, the parameters comprising: a detection time period and a detection window length.
Preferably, the calculating a plurality of first-direction sub-features corresponding to each effective current value in the detection window specifically includes:
and solving a plurality of first direction sub-features corresponding to each current effective value through a first direction sub-feature formula, wherein the first direction sub-feature formula is as follows:
wherein A is the effective value of the current in the window, SwFor the length of the detection window, i and j represent the index numbers of different current effective values in the detection window.
Preferably, the calculating a confidence of the current effective value corresponding to the direction feature which is the largest in the step S4, and when the confidence is smaller than a threshold, outputting a payload event includes:
the confidence of the current effective value corresponding to the largest direction feature is obtained through a confidence formula, wherein the confidence formula is as follows:
N＝max(S(x))
C＝X×exp(Y×N2/Sw 3+Sw 2)
P＝e-C
wherein, P is the confidence index, S(x)For the directional feature, x represents the index of the detection window, N is the largest directional feature, X, Y is the preset confidence parameter, SwC is the intermediate quantity of the confidence for the detection window length.
A second aspect of the present application provides a load identification event detection apparatus, including:
the system comprises an acquisition module, a detection module and a control module, wherein the acquisition module is used for acquiring a plurality of current effective values meeting the detection time period of a preset load event, and the number of the current effective values is constrained by the length of a detection window of the preset load event;
the calculation module is used for calculating a plurality of first direction sub-features corresponding to each current effective value in the detection window;
the first accumulation module is used for accumulating the plurality of first direction sub-characteristics corresponding to each current effective value to obtain a second direction sub-characteristic of each current effective value;
the second accumulation module is used for accumulating all the second direction sub-characteristics of the current effective value to obtain the direction characteristics of the current effective value in the detection window;
the updating module is used for sliding the detection window based on a preset sliding step length, updating the effective current value in the detection window, and triggering the calculating module to obtain the direction characteristic of the effective current value in the sliding detection window;
and the judging module is used for calculating the confidence coefficient of the current effective value corresponding to the maximum direction feature in the second accumulation module or the updating module, and outputting an effective load event when the confidence coefficient is smaller than a threshold value.
Preferably, the method further comprises the following steps:
an initialization module configured to initialize parameters for preset load event detection, the parameters including: the detection time period and the length of the detection window.
Preferably, the calculation module comprises:
the first calculation sub-module is configured to obtain, through a first direction sub-feature formula, a plurality of first direction sub-features corresponding to each of the current effective values, where the first direction sub-feature formula is as follows:
wherein A is the effective value of the current in the window, SwFor the length of the detection window, i and j represent the index numbers of different current effective values in the detection window.
Preferably, the judging module includes:
a second calculation submodule, configured to solve the confidence of the current effective value corresponding to the largest directional feature through a confidence formula, where the confidence formula is as follows:
N＝max(S(x))
C＝X×exp(Y×N2/Sw 3+Sw 2)
P＝e-C
wherein, P is the confidence index, S(x)Is the squareThe directional feature, x represents the label of the detection window, N is the largest directional feature, X, Y is the preset confidence parameter, SwC is the intermediate quantity of the confidence for the detection window length.
A third aspect of the present application provides a load recognition event detection device, the device comprising a processor and a memory:
the memory is used for storing program codes and transmitting the program codes to the processor;
the processor is configured to perform any of the load recognition event detection methods of the first aspect in accordance with instructions in the program code.
A fourth aspect of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium is configured to store a program code, and the program code is configured to execute the load identification event detection method according to any one of the first aspects.
According to the technical scheme, the embodiment of the application has the following advantages:
the application provides a load identification event detection method, which comprises the following steps: acquiring a plurality of current effective values meeting the detection time period of a preset load event, wherein the number of the current effective values is constrained by the length of a detection window of the preset load event; calculating a plurality of first direction sub-features corresponding to each current effective value in a detection window; accumulating the plurality of first direction sub-characteristics corresponding to each current effective value to obtain a second direction sub-characteristic of each current effective value; accumulating all the second direction sub-characteristics of the current effective value to obtain the direction characteristics of the current effective value in the detection window; sliding the detection window based on a preset sliding step length, and updating the current effective value in the detection window to obtain the direction characteristic of the current effective value in the sliding detection window; and calculating the confidence coefficient of the current effective value corresponding to the largest direction feature in all the direction features of the detection window after sliding, and outputting an effective load event when the confidence coefficient is smaller than a threshold value. According to the load identification event detection method, the direction sub-characteristics of the current effective value are obtained, then accumulation is carried out, the direction characteristics of the current effective value are obtained, the confidence coefficient is obtained through the maximum direction characteristics, and the load event is detected; whether an effective load event occurs or not is judged by the confidence coefficient, so that the interference of typical pulses can be effectively avoided, and a more accurate judgment result can be obtained.
Drawings
Fig. 1 is a schematic flowchart illustrating an embodiment of a load identification event detection method according to the present application;
FIG. 2 is a schematic flowchart illustrating a load identification event detection method according to another embodiment of the present disclosure;
FIG. 3 is a diagram illustrating an exemplary detection window of a load identification event detection apparatus according to the present disclosure;
fig. 4 is a schematic structural diagram of an embodiment of a load identification event detection apparatus provided in the present application.
Detailed Description
In order to make the technical solutions of the present application better understood, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
For easy understanding, referring to fig. 1, an embodiment of a load identification event detection method provided in the present application includes:
102, calculating a plurality of first direction sub-characteristics corresponding to each current effective value in a detection window;
103, accumulating a plurality of first direction sub-characteristics corresponding to each current effective value to obtain a second direction sub-characteristic of each current effective value;
and 106, calculating the confidence coefficient of the current effective value corresponding to the maximum direction feature in the step 104 or the step 105, and outputting an effective load event when the confidence coefficient is smaller than a threshold value.
It should be noted that the preset load event refers to setting a load event to be identified, which is similar to a fixed-frequency air conditioning equipment starting event, an electric kettle equipment starting event, an induction cooker equipment starting event, and the like, and the final output result is to identify whether the preset load event is valid or not according to the identification of the preset load event, so that the task of identifying the load can be completed.
It should be noted that, obtaining a plurality of current effective values that satisfy the detection time period of the preset load event specifically includes: the current data is collected from the detection environment circuit in real time, and the current effective value is calculated according to the frequency of the detection time period of the preset load event, for example, if the set detection time period is 1, the current effective value is calculated according to a cycle, and if the period is 5, the current effective value is calculated according to 5 cycles. The detection window is in a preset size, and the length value of the detection window is the quantity value of the effective value of the contained current, so that the next calculation operation can be carried out only when the number of the obtained effective values of the current reaches the length of the detection window.
It should be noted that each current effective value in the detection window corresponds to a direction attribute, the direction attribute of each current effective value in each detection window is defined as a first direction sub-feature, the first direction sub-feature is a direction attribute of the currently studied current effective value relative to each current effective value in the corresponding detection window, and includes a direction attribute relative to itself, and therefore, the number of the first direction sub-features of each current effective value is determined by the number of the total current effective values in the detection window.
It should be noted that the second direction sub-feature of each current effective value in the current window can be obtained by adding up the first direction sub-features of the current effective value, so that each current effective value has only one second direction sub-feature with respect to the current corresponding window.
It should be noted that each current effective value in the current window corresponds to one second direction sub-feature, and a direction feature can be obtained by accumulating all the second direction sub-features of the current window, and is used for describing a direction attribute of the current effective value in the current window, where the direction feature is a direction attribute description for the current effective value in the current whole window.
It should be noted that the detection window moves on a chain data of the effective current value, the sliding step length of the detection window is set according to the actual situation, a new direction feature can be obtained every time the window is moved, and the number of window updates is the number of final direction features.
It should be noted that, a certain detection window may be determined according to a maximum value of the directional characteristic, a position of the maximum directional characteristic value is located, a confidence may be obtained by using the maximum directional characteristic value, a value range of the confidence is 0 to 1, a preset threshold is compared with the obtained confidence, and a result of detecting the load event is obtained, where the detection result is for the previous preset load event and is used to identify validity of the preset load event.
According to the load identification event detection method provided by the embodiment, the direction sub-characteristics of the current effective value are solved, then accumulation is carried out, the direction characteristics of the current effective value are obtained, and the load event is detected through the confidence coefficient obtained by the maximum direction characteristics; whether the preset load event is effective or not is judged by the confidence coefficient, so that the interference of typical pulses can be effectively avoided, and a more accurate judgment result can be obtained.
For easy understanding, referring to fig. 2, another embodiment of a load identification event detection method is provided in the present application, including:
It is assumed that the detection window length is SwSetting the detection time period to TrIf T isr1, in cycles, the current effective value is calculated according to a cycle, if T isrWhen the current is 5, the effective value of the current is calculated according to 5 cycles.
It should be noted that, obtaining a plurality of current effective values that satisfy the detection time period of the preset load event specifically includes: collecting current data in real time from the detection environment circuit, calculating current effective value with frequency of detection time period of preset load event, the length of window is the number of current effective values, therefore, only the number of current effective values obtained reaches the length S of windowwThen the next calculation operation can be performed.
And step 203, obtaining a plurality of first direction sub-features corresponding to each current effective value in the detection window through the first direction sub-feature formula.
It should be noted that each current effective value in the detection window corresponds to a direction attribute, the direction attribute of each current effective value in each window is defined as a first direction sub-feature, the first direction sub-feature is a direction attribute of the currently studied current effective value relative to each current effective value in the corresponding detection window, and includes a direction attribute relative to itself, and therefore, the number of the first direction sub-features of each current effective value is determined by the number of total current effective values in the detection window. The first direction sub-feature formula may be expressed as follows:
wherein A is the effective value of the current in the window, SwFor the detection window length, i and j then represent the index numbers of the different current effective values in the detection window.
And 204, accumulating the plurality of direction sub-characteristics corresponding to each current effective value to obtain a second direction sub-characteristic of each current effective value.
It should be noted that, by adding up the first direction sub-features of each current effective value, the second direction sub-features of the current effective value in the current detection window can be obtained, so that each current effective value has only one second direction sub-feature with respect to the current corresponding detection window. The specific cumulative formula is as follows:
wherein D is(i)Representing a second directional sub-characteristic, S, of the effective value of each current under the current detection windowwIs the length of the detection window.
And step 205, accumulating all the second direction sub-characteristics of the current effective value to obtain the direction characteristics of the current effective value in the detection window.
It should be noted that each current effective value in the current detection window corresponds to one second direction sub-feature, and a direction feature can be obtained by accumulating all the second direction sub-features of the current detection window, and is used for describing a direction attribute of the current effective value in the current detection window, where the direction feature is a direction attribute description for the current effective value in the entire window. The specific cumulative formula is as follows:
wherein, S is the direction characteristic of the current effective value of the current detection window, x represents the label of the detection window, and is obtained by accumulating the second direction sub-characteristics corresponding to all the current effective values in the window.
Please refer to fig. 3, an exemplary diagram of the detection window in fig. 3 is divided into a current detection window in a solid frame and a next detection window in a dashed frame, where the window size is preset to be 5, and the window sliding step length is 2; the detection window moves on a chain data of the effective current value, the sliding step length of the detection window is set according to the actual situation, a new direction characteristic can be obtained when the window moves once, the updating times of the window are the number of the final direction characteristics, and x represents the number. The direction characteristic of a specific update window may be expressed as:
the x directional characteristics can be obtained by the formula, and different detection windows can be distinguished according to the value.
And step 207, calculating the confidence of the current effective value corresponding to the maximum direction characteristic in step 205 or step 206 through a confidence formula.
It should be noted that, a corresponding detection window is determined according to the maximum value of one directional feature, the specific position of the maximum value of the directional feature is located, and a confidence level can be obtained by using the maximum value of the directional feature. Firstly, the maximum direction characteristic is obtained, and the formula is as follows:
N＝max(S(x))
wherein S is(x)Is a direction feature, x represents the label of the detection window, and N is the maximum direction feature;
secondly, the confidence coefficient of the current effective value corresponding to the maximum value of the direction characteristic is obtained through a confidence coefficient formula, and the specific calculation formula is as follows:
C＝X×exp(Y×N2/Sw 3+Sw 2)
P＝e-C
wherein, the confidence index P X, Y is a preset detection confidence parameter SwFor detection window length, C is the median amount of confidence.
And step 208, outputting the effective load event when the obtained confidence coefficient is smaller than the threshold value.
It should be noted that, the confidence level is compared with a preset threshold, and whether a payload event occurs can be determined according to a preset load event. In addition, in addition to the detection time period and the length of the monitoring window, initialization is required, and the preset sliding step, the confidence parameter and the threshold in this embodiment also need to be initialized at the same time.
For ease of understanding, referring to fig. 4, the present application further provides an embodiment of a load identification event detection apparatus, including:
an initialization module 301, configured to initialize parameters for detecting a preset load event, where the parameters include: the detection time period and the length of the detection window;
an obtaining module 302, configured to obtain a plurality of current effective values that meet a detection time period of a preset load event, where a number of the current effective values is constrained by a length of a detection window of the preset load event;
a calculating module 303, configured to calculate a plurality of first direction sub-features corresponding to each current effective value in the detection window;
a first accumulation module 304, configured to accumulate a plurality of first direction sub-features corresponding to each current effective value to obtain a second direction sub-feature of each current effective value;
a second accumulation module 305, configured to accumulate all second direction sub-features of the current effective value to obtain a direction feature of the current effective value in the detection window;
an updating module 306, configured to slide the detection window based on a preset sliding step length, update the effective value of the current in the detection window, and trigger the calculating module 303 to obtain a directional characteristic of the effective value of the current in the slid detection window;
and the determining module 307 is configured to calculate a confidence of the current effective value corresponding to the largest direction feature in the second accumulating module 305 or the updating module 306, and output the effective load event when the confidence is smaller than a threshold.
It should be noted that the calculating module 303 further includes a first calculating submodule 3031, configured to obtain, by using a first direction sub-feature formula, a plurality of first direction sub-features corresponding to each effective value of the current, where the first direction sub-feature formula is as follows:
wherein A is the effective value of the current in the window, SwFor the detection window length, i and j then represent the labels of the different current effective values in the detection window.
It should be noted that the determining module 307 further includes a second calculating submodule 3071, configured to find a confidence of the current effective value corresponding to the maximum directional feature through a confidence formula, where the confidence formula is as follows:
N＝max(S(x))
C＝X×exp(Y×N2/Sw 3+Sw 2)
P＝e-C
wherein P is a confidence index, S(x)For directional features, x denotes the label of the detection windowThe number N is the maximum direction characteristic, X, Y is the preset detection confidence parameter, SwC is the intermediate amount of confidence for the length of the detection window.
To facilitate understanding, the present application provides an embodiment of a load recognition event detection device, comprising: a processor and a memory;
the memory is used for storing the program codes and transmitting the program codes to the processor;
the processor is configured to execute any one of the load recognition event detection methods according to instructions in the program code.
The present application further provides a computer-readable storage medium, wherein the computer-readable storage medium is configured to store a program code, and the program code is configured to execute any one of the load identification event detection methods described in the foregoing embodiments.
In the several embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application may be substantially implemented or contributed to by the prior art, or all or part of the technical solution may be embodied in a software product, which is stored in a storage medium and includes instructions for executing all or part of the steps of the method described in the embodiments of the present application through a computer device (which may be a personal computer, a server, or a network device). And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
The above embodiments are only used for illustrating the technical solutions of the present application, and not for limiting the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions in the embodiments of the present application.
Claims (10)
1. A load identification event detection method is characterized by comprising the following steps:
s1: acquiring a plurality of current effective values meeting the detection time period of a preset load event, wherein the number of the current effective values is constrained by the length of a detection window of the preset load event;
s2: calculating a plurality of first direction sub-characteristics corresponding to each current effective value in the detection window;
s3: accumulating the plurality of first direction sub-characteristics corresponding to each current effective value to obtain a second direction sub-characteristic of each current effective value;
s4: accumulating all the second direction sub-characteristics of the current effective value to obtain the direction characteristics of the current effective value in the detection window;
s5: sliding the detection window based on a preset sliding step length, updating the effective current value in the detection window, and repeating the steps S2-S4 to obtain the direction characteristic of the effective current value in the sliding detection window;
s6: calculating the confidence of the current effective value corresponding to the direction feature which is the largest in the step S4 or the step S5, and outputting a payload event when the confidence is smaller than a threshold value.
2. The method according to claim 1, wherein the obtaining a plurality of current effective values satisfying a detection time period of a preset load event, the number of the current effective values being constrained by a detection window length of the preset load event, further comprises:
initializing parameters for pre-load event detection, the parameters comprising: a detection time period and a detection window length.
3. The method according to claim 1, wherein the calculating a plurality of first direction sub-features corresponding to each effective current value in the detection window specifically comprises:
and solving a plurality of first direction sub-features corresponding to each current effective value through a first direction sub-feature formula, wherein the first direction sub-feature formula is as follows:
wherein A is the effective value of the current in the window, SwFor the length of the detection window, i and j represent the index numbers of different current effective values in the detection window.
4. The method for detecting the load recognition event according to claim 1, wherein the step of calculating the confidence of the effective current value corresponding to the direction feature which is the largest in the step S4, and outputting the payload event when the confidence is smaller than a threshold value comprises:
the confidence of the current effective value corresponding to the largest direction feature is obtained through a confidence formula, wherein the confidence formula is as follows:
N＝max(S(x))
C＝X×exp(Y×N2/Sw 3+Sw 2)
P＝e-C
wherein, P is the confidence index, S(x)For the directional feature, x represents the index of the detection window, N is the largest directional feature, X, Y is the preset confidence parameter, SwC is the intermediate quantity of the confidence for the detection window length.
5. A load recognition event detection device, comprising:
the system comprises an acquisition module, a detection module and a control module, wherein the acquisition module is used for acquiring a plurality of current effective values meeting the detection time period of a preset load event, and the number of the current effective values is constrained by the length of a detection window of the preset load event;
the calculation module is used for calculating a plurality of first direction sub-features corresponding to each current effective value in the detection window;
the first accumulation module is used for accumulating the plurality of first direction sub-characteristics corresponding to each current effective value to obtain a second direction sub-characteristic of each current effective value;
the second accumulation module is used for accumulating all the second direction sub-characteristics of the current effective value to obtain the direction characteristics of the current effective value in the detection window;
the updating module is used for sliding the detection window based on a preset sliding step length, updating the effective current value in the detection window, and triggering the calculating module to obtain the direction characteristic of the effective current value in the sliding detection window;
and the judging module is used for calculating the confidence coefficient of the current effective value corresponding to the maximum direction feature in the second accumulation module or the updating module, and outputting an effective load event when the confidence coefficient is smaller than a threshold value.
6. The load recognition event detection device of claim 5, further comprising:
an initialization module configured to initialize parameters for preset load event detection, the parameters including: the detection time period and the length of the detection window.
7. The load recognition event detection device of claim 5, wherein the calculation module comprises:
the first calculation sub-module is configured to obtain, through a first direction sub-feature formula, a plurality of first direction sub-features corresponding to each of the current effective values, where the first direction sub-feature formula is as follows:
wherein A is the effective value of the current in the window, SwFor the length of the detection window, i and j represent the index numbers of different current effective values in the detection window.
8. The load recognition event detecting device of claim 5, wherein the determining module comprises:
a second calculation submodule, configured to solve the confidence of the current effective value corresponding to the largest directional feature through a confidence formula, where the confidence formula is as follows:
N＝max(S(x))
C＝X×exp(Y×N2/Sw 3+Sw 2)
P＝e-C
wherein, P is the confidence index, S(x)For the directional feature, x represents the index of the detection window, N is the largest directional feature, X, Y is the preset confidence parameter, SwC is the intermediate quantity of the confidence for the detection window length.
9. A load-discriminating event detection device, comprising: a processor and a memory;
the memory is used for storing program codes and transmitting the program codes to the processor;
the processor is configured to execute the load recognition event detection method of any one of claims 1-4 according to instructions in the program code.
10. A computer-readable storage medium for storing program code for performing the load recognition event detection method of any one of claims 1-4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911368330.5A CN111103490B (en) | 2019-12-26 | 2019-12-26 | Load identification event detection method, device and equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911368330.5A CN111103490B (en) | 2019-12-26 | 2019-12-26 | Load identification event detection method, device and equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111103490A true CN111103490A (en) | 2020-05-05 |
| CN111103490B CN111103490B (en) | 2021-08-27 |
Family
ID=70424965
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911368330.5A Active CN111103490B (en) | 2019-12-26 | 2019-12-26 | Load identification event detection method, device and equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111103490B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113176451A (en) * | 2021-04-22 | 2021-07-27 | 浙江威星智能仪表股份有限公司 | Pulse signal detection method based on table look-up method |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130132423A1 (en) * | 2011-11-21 | 2013-05-23 | Shiao-Li Tsao | Method and system for detecting an applicance based on users' feedback information |
| CN105823948A (en) * | 2016-05-18 | 2016-08-03 | 国网上海市电力公司 | Non-invasive resident load identification method |
| CN105972761A (en) * | 2016-05-25 | 2016-09-28 | 华北电力大学（保定） | Non-invasive air conditioner load monitoring method |
| CN106483370A (en) * | 2016-10-21 | 2017-03-08 | 威胜集团有限公司 | Non-intrusion type household loads real-time identification method based on multi-feature fusion and device |
| KR20180042496A (en) * | 2016-10-17 | 2018-04-26 | 고려대학교 산학협력단 | Load disaggergation system in home using voltage signal and the controlling method thereof |
| CN108021736A (en) * | 2017-11-08 | 2018-05-11 | 天津大学 | A kind of load switching action monitoring method based on sliding window Remanent Model |
| CN109461095A (en) * | 2018-10-18 | 2019-03-12 | 深圳供电局有限公司 | Data processing method and equipment for load event detection for non-invasive load identification |
| CN110426554A (en) * | 2019-08-09 | 2019-11-08 | 威胜集团有限公司 | Household loads electric characteristic extracting method, device and computer readable storage medium |
| CN110488112A (en) * | 2019-05-23 | 2019-11-22 | 杭州海兴电力科技股份有限公司 | Classification metering method non-intrusion type load identification and its realized based on recognition result |
-
2019
- 2019-12-26 CN CN201911368330.5A patent/CN111103490B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130132423A1 (en) * | 2011-11-21 | 2013-05-23 | Shiao-Li Tsao | Method and system for detecting an applicance based on users' feedback information |
| CN105823948A (en) * | 2016-05-18 | 2016-08-03 | 国网上海市电力公司 | Non-invasive resident load identification method |
| CN105972761A (en) * | 2016-05-25 | 2016-09-28 | 华北电力大学（保定） | Non-invasive air conditioner load monitoring method |
| KR20180042496A (en) * | 2016-10-17 | 2018-04-26 | 고려대학교 산학협력단 | Load disaggergation system in home using voltage signal and the controlling method thereof |
| CN106483370A (en) * | 2016-10-21 | 2017-03-08 | 威胜集团有限公司 | Non-intrusion type household loads real-time identification method based on multi-feature fusion and device |
| CN108021736A (en) * | 2017-11-08 | 2018-05-11 | 天津大学 | A kind of load switching action monitoring method based on sliding window Remanent Model |
| CN109461095A (en) * | 2018-10-18 | 2019-03-12 | 深圳供电局有限公司 | Data processing method and equipment for load event detection for non-invasive load identification |
| CN110488112A (en) * | 2019-05-23 | 2019-11-22 | 杭州海兴电力科技股份有限公司 | Classification metering method non-intrusion type load identification and its realized based on recognition result |
| CN110426554A (en) * | 2019-08-09 | 2019-11-08 | 威胜集团有限公司 | Household loads electric characteristic extracting method, device and computer readable storage medium |
Non-Patent Citations (3)
| Title |
|---|
| 曹美晗: "几种典型负荷建模及其非侵入式监测研究", 《中国优秀硕士论文全文数据库》 * |
| 牛卢璐: "基于暂态过程的非侵入式负荷监测", 《中国优秀硕士论文全文数据库》 * |
| 牛卢璐等: "一种适用于非侵入式负荷监测的暂态事件检测算法", 《电力系统自动化》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113176451A (en) * | 2021-04-22 | 2021-07-27 | 浙江威星智能仪表股份有限公司 | Pulse signal detection method based on table look-up method |
| CN113176451B (en) * | 2021-04-22 | 2023-08-15 | 浙江威星智能仪表股份有限公司 | Pulse signal detection method based on table look-up method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111103490B (en) | 2021-08-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111244954B (en) | Non-invasive load identification method and device | |
| Cho et al. | Multiple-change-point detection for high dimensional time series via sparsified binary segmentation | |
| CN104483562B (en) | Power equipment method for early warning and device | |
| CN113376551B (en) | Method, system, device and storage medium for detecting series fault arc | |
| CN109164327A (en) | Electricity system electric appliance behavior discrimination method and device based on combined type criterion | |
| CN107918688B (en) | Scene model dynamic estimation method, data analysis method and device and electronic equipment | |
| CN107292512B (en) | Power equipment space-time multi-dimensional safety assessment method based on symbolic dynamics and hidden Markov model | |
| CN111103490B (en) | Load identification event detection method, device and equipment | |
| CN111291328B (en) | Transient event identification method, system and equipment based on fine slope | |
| CN109587145B (en) | False data intrusion detection method, device and equipment in power network | |
| CN109409165A (en) | A kind of video content recognition method, apparatus and electronic equipment | |
| CN117147958B (en) | Method and device for discriminating electricity larceny based on real-time electricity utilization monitoring | |
| CN117233645B (en) | Energy storage inverter battery abnormality judging method, system and medium | |
| CN117909818A (en) | Arc fault identification method and system based on multicycle features and multiscale convolution | |
| CN117093943A (en) | Power consumption monitoring and early warning method and device | |
| Bariya et al. | Data-driven topology estimation with limited sensors in radial distribution feeders | |
| CN114818907A (en) | State monitoring method, device and equipment of power transmission line and storage medium | |
| CN110020223B (en) | Behavior data analysis method and device | |
| CN108038451A (en) | Anomaly detection method and device | |
| CN115902557A (en) | Switch cabinet fault diagnosis processing method and device and nonvolatile storage medium | |
| CN115564324A (en) | Electric power fingerprint identification method, device and equipment based on event detection | |
| CN110647858B (en) | Video occlusion judgment method and device and computer storage medium | |
| CN111126785B (en) | Electricity stealing behavior identification method and device | |
| CN114595746A (en) | Method, device, equipment and storage medium for classifying power distribution network fault reasons | |
| CN110245617A (en) | Artificial intelligence analysis's method based on transient state recording waveform |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |