CN111612074B - Identification method and device of non-invasive load monitoring electric equipment and related equipment - Google Patents
Identification method and device of non-invasive load monitoring electric equipment and related equipment Download PDFInfo
- Publication number
- CN111612074B CN111612074B CN202010443916.XA CN202010443916A CN111612074B CN 111612074 B CN111612074 B CN 111612074B CN 202010443916 A CN202010443916 A CN 202010443916A CN 111612074 B CN111612074 B CN 111612074B
- Authority
- CN
- China
- Prior art keywords
- imf
- current
- matrix
- decomposition
- data
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 36
- 238000012544 monitoring process Methods 0.000 title claims abstract description 22
- 239000011159 matrix material Substances 0.000 claims abstract description 46
- 238000000354 decomposition reaction Methods 0.000 claims abstract description 40
- 238000004458 analytical method Methods 0.000 claims abstract description 11
- 238000007621 cluster analysis Methods 0.000 claims abstract description 10
- 238000012545 processing Methods 0.000 claims abstract description 8
- 239000013598 vector Substances 0.000 claims description 20
- 238000005070 sampling Methods 0.000 claims description 19
- 238000005192 partition Methods 0.000 claims description 12
- 238000003064 k means clustering Methods 0.000 claims description 9
- 238000012216 screening Methods 0.000 claims description 7
- 238000010276 construction Methods 0.000 claims description 6
- 230000006870 function Effects 0.000 claims description 4
- 238000000926 separation method Methods 0.000 claims description 3
- 238000012360 testing method Methods 0.000 claims description 3
- 230000005611 electricity Effects 0.000 abstract description 5
- 238000004088 simulation Methods 0.000 abstract description 2
- 238000005516 engineering process Methods 0.000 description 6
- 230000006872 improvement Effects 0.000 description 4
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000004807 localization Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/16—Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Mathematical Physics (AREA)
- General Engineering & Computer Science (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Optimization (AREA)
- Mathematical Analysis (AREA)
- Computational Mathematics (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computing Systems (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Probability & Statistics with Applications (AREA)
- Bioinformatics & Computational Biology (AREA)
- Algebra (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- Remote Monitoring And Control Of Power-Distribution Networks (AREA)
Abstract
The invention discloses a method, a device and related equipment for identifying non-invasive load monitoring electric equipment, wherein the method comprises the following steps: s101, collecting the instantaneous current of a single electric device, and extracting a current value; s102, EMD decomposition is carried out on the collected current value data, and IMF components are screened out; s103, performing singular value decomposition on the obtained IMF component based on an EMD-SVD mode, and constructing a standard eigenvalue matrix; s104, processing the actually measured current data of the user incoming line by adopting the steps of S101-S103 to obtain an actual operation characteristic value matrix; s105, carrying out cluster analysis on the actual operation characteristic value matrix and the standard characteristic value matrix, and outputting an analysis result. Under the condition of limited equipment types, the method acquires user electricity data in a non-invasive mode, and identifies a plurality of electric equipment types through EMD decomposition and cluster analysis; through simulation analysis, the method has high identification accuracy.
Description
Technical Field
The invention belongs to the field of non-invasive identification, and is suitable for identifying the class of electric equipment. In particular to a method, a device and related equipment for identifying non-invasive load monitoring electric equipment.
Background
The non-invasive load identification technology has good development prospect in the power industry, the technology has less electric quantity to be detected, and the type of the electric equipment of the user can be accurately identified only by the total current and the total voltage of the measured object, so that the technology is convenient for the user to use and convenient for the management and the power operation of the power company.
In large and medium-sized cities with front development level at present, the non-invasive load identification technology has been put into households, the non-invasive installation form is well-received, the daily electricity utilization behavior of users is facilitated, and the management of power supply companies is facilitated to a certain extent. For users with relatively small total load, single variety and high unified management degree, the non-invasive load identification technology is suitable for popularization.
Disclosure of Invention
The invention aims to overcome the defects in the prior art and provides a method, a device and related equipment for identifying non-invasive load monitoring electric equipment. Under the condition of limited equipment types, user electricity data is obtained in a non-invasive mode, and a plurality of electric equipment types are identified through EMD decomposition and cluster analysis; through simulation analysis, the method has high identification accuracy.
In order to solve the technical problems, the invention is realized by the following technical scheme:
a non-invasive load monitoring electric equipment identification method comprises the following steps:
s101, collecting the instantaneous current of a single electric device, and extracting a current value;
s102, EMD decomposition is carried out on the collected current value data, and IMF components are screened out;
s103, performing singular value decomposition on the obtained IMF component based on an EMD-SVD mode, and constructing a standard eigenvalue matrix;
s104, processing the actually measured current data of the user incoming line by adopting the steps of S101-S103 to obtain an actual operation characteristic value matrix;
s105, carrying out cluster analysis on the actual operation characteristic value matrix and the standard characteristic value matrix, and outputting an analysis result.
As a further improvement of the present invention, in S101, a current high frequency sampling device is used to collect the instantaneous current.
As a further improvement of the present invention, in S102, the specific steps of EMD decomposition of the collected current value data are as follows:
calculating all extreme points of the acquired original current signal X (t), fitting by using a cubic spline curve, connecting local maximum points into an upper envelope, and connecting local minimum points into a lower envelope, so that the upper and lower envelopes contain all data points; from the average N of the upper envelope and the lower envelope 1 (t) obtaining:
M 1 (t)＝X(t)-N 1 (t)
m1 may be considered a first IMF component if the IMF condition is satisfied;
if the IMF condition is not satisfied, M is 1 Processing as target signal, repeating the above steps to obtain upper and lower envelope mean N 11 (t) calculating M 11 (t)＝M 1 (t)-N 11 (t) test M 11 (t) whether the conditions of IMF are met;
if not, repeating the steps K times until the steps are met; at this time, the first IMF component is calculated as:
A 1 (t)＝M 1 K(t)
separation of A from raw current signal 1 (t) obtaining P 1 (t)＝X(t)-A 1 (t) at this time, P 1 (t) repeating the above steps as a new original signal, and repeating r times until an nth IMF component is obtained;
after the original current signal becomes a monotonic function, the residual component composition is utilized:
wherein X (t) represents an original current signal, N 1 (t) is the average of the upper and lower envelopes of X (t), ai (t) represents the ith IMF component, and Pn (t) represents the IMF remainder of the original signal.
As a further improvement of the present invention, in S103, the specific steps of performing singular value decomposition on the obtained IMF component based on the EMD-SVD mode are as follows:
raw current signal from EMD decompositionN IMF components to form an initial eigenvector matrix Q; singular value decomposition of matrix Q using
Q＝UΣV*
Constructing a characteristic value matrix, wherein the columns of U form a pair of Q orthogonal input basis vectors, and the vectors are QQ characteristic vectors; the columns of V form a set of basis vectors for the quadrature output of Q, the vectors being characteristic vectors of Q x Q.
As a further improvement of the present invention, in S105, the specific steps of outputting the analysis result are:
substituting n IMF components Ai (t) obtained by the original current signal into a data set X= { X of d-dimension data points respectively 1 ,x 2 ,...,x i ,...,x n X, where x i ∈R d Because the number of data subsets to be generated is K, the K-means clustering algorithm organizes the data object into K partitions c= { C k I=1, 2,..k }; each partition represents a class c k Each class c k With a class centre mu i The method comprises the steps of carrying out a first treatment on the surface of the The Euclidean distance is selected as a similarity and distance judgment criterion, and the distance between each point in the class and the clustering center mu is calculated i Sum of distance squares of (2)The clustering target is to square sum of total distances of various types +.>Minimum;
wherein,
the total distance square sum in the K-means clustering algorithm tends to decrease along with the increase of the number K of the categories, and the total distance square sum can only obtain the minimum value under a certain determined number K of the categories; after the minimum value is obtained, a clustering result is output, namely the load type is identified;
where xi represents the ith dimension component, c, of the original dataset X k Represents the kth partition, μ of the data i Representing the cluster center of the ith partition.
An identification device of non-invasive load monitoring electric equipment, comprising:
the acquisition module is used for acquiring the instantaneous current of the single electric equipment by using the current high-frequency sampling device and extracting a current value;
the decomposition module is used for carrying out EMD decomposition on the collected current value data and screening out IMF components;
the construction module is used for carrying out singular value decomposition on the obtained IMF component based on an EMD-SVD mode and constructing a standard eigenvalue matrix;
the updating module is used for feeding the instantaneous current of the user through the acquisition module, extracting a current value, screening IMF components through the decomposition module, and obtaining an actual operation characteristic value matrix through the construction module;
and the judging module is used for carrying out cluster analysis on the actual operation characteristic value matrix and the standard characteristic value matrix and outputting an analysis result.
An identification device for non-invasive load monitoring consumer, 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 used for executing the identification method of the non-invasive load monitoring electric equipment according to the instructions in the program codes.
A computer readable storage medium for storing program code for performing the method of identifying a non-invasive load monitoring consumer.
Compared with the prior art, the invention has the beneficial effects that:
firstly, carrying out high-frequency sampling by using a non-invasive load acquisition technology to obtain a plurality of user unit instantaneous current sampling points; then, through EMD decomposition, proper IMF components are reserved, and an initial feature vector matrix is formed; extracting features through singular value decomposition, and perfecting a vector matrix; and finally, obtaining a clustering center by k-means clustering, and comparing cluster names to obtain the class of the electric equipment. Compared with the Fourier transform and wavelet noise reduction algorithm, the EMD-SVD algorithm has good localization characteristics in time frequency and self-adaptive characteristics; the method has strong adaptability in analyzing non-stationary and nonlinear vibration signals. Under the condition that the types of the electric equipment are single, the method has good identification accuracy and stability and high operation speed.
Drawings
The conception, specific structure, and technical effects of the present invention will be further described with reference to the accompanying drawings to fully understand the objects, features, and effects of the present invention.
FIG. 1 is a flow chart of an identification method of the present invention.
FIG. 2 is a diagram of the clustering result of raw data according to an embodiment of the present invention.
FIG. 3 is a final clustering result of unknown devices according to an embodiment of the present invention.
Fig. 4 is a schematic diagram of an embodiment of an identification device of a non-invasive load monitoring consumer according to the present invention.
Detailed Description
In order to make the technical solution of the present invention better understood by those skilled in the art, the technical solution of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, shall fall within the scope of the invention.
As shown in FIG. 1, the identification method of the non-invasive load monitoring electric equipment comprises the following steps:
and step 1, collecting the instantaneous current of a single electric device by using a current high-frequency sampling device, and extracting the current from the instantaneous current.
And step 2, performing EMD decomposition on the acquired data, and screening out IMF components.
Further, all extreme points of the acquired original current signal X (t) are solved, a cubic spline curve is used for fitting, local maximum points are connected into an upper envelope line, local minimum points are connected into a lower envelope line, and the fact that the upper envelope line and the lower envelope line contain all data points is met. From the average N of the upper envelope and the lower envelope 1 (t) obtaining:
M 1 (t)＝X(t)-N 1 (t)
m1 may be considered to be the first IMF component if the IMF condition is satisfied.
If the IMF condition is not satisfied, M is 1 Processing as target signal, repeating the above steps to obtain upper and lower envelope mean N 11 (t) calculating M 11 (t)＝M 1 (t)-N 11 (t) test M 11 (t) whether the conditions of IMF are met. If not, repeating the above steps K times until the steps are satisfied. At this time, the first IMF component is calculated as:
A 1 (t)＝M 1 K(t)
separation of A from raw current signal 1 (t) obtaining P 1 (t)＝X(t)-A 1 (t) at this time, P 1 (t) repeating the above steps as a new original signal, and repeating r times until the nth IMF component is obtained.
After the original signal becomes a monotonic function, the residual component composition is utilized:
wherein X (t) represents the original signal, N 1 (t) is the average of the upper and lower envelopes of X (t), ai (t) represents the ith IMF component, and Pn (t) represents the IMF remainder of the original signal.
And 3, carrying out singular value decomposition on IMF components obtained through the original sampling current signals based on an EMD-SVD mode, and constructing a standard eigenvalue matrix.
Further, the current signal obtained by EMD decomposition in step 3N IMF components to form an initial eigenvector matrix Q; singular value decomposition is performed on matrix Q, q=uΣv, where the columns of U constitute a pair of Q's orthogonal "input" basis vectors, which are characteristic vectors of QQ. The columns of V form a set of basis vectors for the quadrature "outputs" of Q. These vectors are Q x Q eigenvectors.
The actual measured current data is processed.
And 4, acquiring the actual total instantaneous current of the user incoming line by using a current sampling device.
And 5, processing the data by using the processing method in the step 2.
And 6, forming an actual operation characteristic value matrix by the IMF components obtained in the step 5.
And 7, carrying out cluster analysis on the actual operation characteristic value matrix and the standard characteristic value matrix, and outputting an analysis result.
Further, in step 7, for each IMF component Ai (t) of the original current signal, the IMF component Ai (t) is substituted into the data set x= { X of d-dimension data points, respectively 1 ,x 2 ,...,x i ,...,x n X, where x i ∈R d And the number of data subsets to be generated, K-means clustering algorithm organizes the data object into K partitions c= { C k I=1, 2,..k }. Each partition represents a class c k Each class c k With a class centre mu i . The Euclidean distance is selected as a similarity and distance judgment criterion, and the distance between each point in the class and the clustering center mu is calculated i Sum of distance squares of (2)Clustering aims at summing the squares of the total distances of various typesMinimum.
Wherein,
because the sum of squares of total distances in the K-means clustering algorithm tends to decrease as the number of categories K increases (J (C) =0 when k=n). Therefore, the sum of the squares of the total distances can only be minimized for a certain number K of categories. And after the minimum value is obtained, outputting a clustering result, namely identifying the load type.
Where xi represents the ith dimension component, c, of the original dataset X k Represents the kth partition, μ of the data i Representing the cluster center of the ith partition. The present invention will be described in detail with reference to specific embodiments and drawings.
Examples
Taking a certain resident household electricity environment as an example, acquiring the instantaneous current of a single electric device by adopting 12kHz high-frequency current sampling equipment to obtain 30 sampling current samples containing 7 different electricity loads of a microwave oven, a bedroom lamp, a bathroom lamp, a refrigerator, an air conditioner, a backyard lamp and a blower, wherein each sample contains 400 continuous sampling points.
And 2, respectively carrying out EMD decomposition on the 30 specific sampling current samples, reserving the first 5 IMF components of each sampling current sample, and sequentially arranging the obtained 5 IMF components into a matrix.
And 3, respectively carrying out singular value decomposition on a matrix formed by 5 IMF components corresponding to each sampling current sample, and forming a matrix X by the singular value decomposition results of 30 samples.
Performing cluster analysis on the X matrix by using a k-means clustering algorithm to obtain vectors composed of 7 cluster centers:
the clustering results are shown in fig. 2.
By comparing the clustering result with the names of the clustering devices, the devices corresponding to the clustering centers are respectively: refrigerators, air compressors, bathroom ceiling lights, bedroom lights, backyard lights, kitchen choppers, and blowers.
When an unknown device is newly put into operation,
and 4, acquiring actual total instantaneous current of the incoming line of the user room by using a 12kHz high-frequency current sampling device, and obtaining 400 continuous sampling points corresponding to the steady-state process of the unknown equipment.
And 5, performing EMD (empirical mode decomposition) on the sampling signals, and sequentially forming a matrix form by taking the first five IMF components.
Step 6, singular value decomposition is carried out on the obtained matrix, vectors obtained by singular value decomposition are added into the matrix X, and a new singular value feature matrix X 'is obtained'
And 7, clustering the X' by using a k-means clustering algorithm, wherein the clustering result is shown in figure 3.
It can be seen that the unknown device is assigned to the bedroom lamp cluster, and the invention successfully identifies the new device type.
Referring to fig. 4, a second aspect of the present application provides an identification device for a non-invasive load monitoring electric device.
The identification device of non-invasive load monitoring electric equipment provided by the embodiment of the application comprises:
the acquisition module is used for acquiring the instantaneous current of the single electric equipment by using the current high-frequency sampling device and extracting a current value;
the decomposition module is used for carrying out EMD decomposition on the collected current value data and screening out IMF components;
the construction module is used for carrying out singular value decomposition on the obtained IMF component based on an EMD-SVD mode and constructing a standard eigenvalue matrix;
the updating module is used for feeding the instantaneous current of the user through the acquisition module, extracting a current value, screening IMF components through the decomposition module, and obtaining an actual operation characteristic value matrix through the construction module;
and the judging module is used for carrying out cluster analysis on the actual operation characteristic value matrix and the standard characteristic value matrix and outputting an analysis result.
A third aspect of the present application provides an apparatus for non-intrusive load monitoring of an identification of a powered device, the apparatus 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 steps of the method for identifying a non-invasive load monitoring consumer according to the first aspect according to the instructions in the program code.
A fourth aspect of the present application provides a computer readable storage medium for storing program code for executing the identification method of the non-invasive load monitoring consumer according to the first aspect.
It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, which are not repeated herein.
The terms "first," "second," "third," "fourth," and the like in the description of the present application and in the above-described figures, if any, are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that embodiments of the present application described herein may be capable of operation in sequences other than those illustrated or described herein, for example. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
It should be understood that in this application, "at least one" means one or more, and "a plurality" means two or more. "and/or" for describing the association relationship of the association object, the representation may have three relationships, for example, "a and/or B" may represent: only a, only B and both a and B are present, wherein a, B may be singular or plural. The character "/" generally indicates that the context-dependent object is an "or" relationship. "at least one of" or the like means any combination of these items, including any combination of single item(s) or plural items(s). For example, at least one (one) of a, B or C may represent: a, B, C, "A and B", "A and C", "B and C", or "A and B and C", wherein A, B, C may be single or plural.
In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods may be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative, e.g., the division of the units is merely a logical function division, and there may be additional divisions when actually implemented, e.g., multiple units or components may be combined or integrated into another system, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical or other form.
The units described as separate units may or may not be physically separate, and units shown 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 may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in each embodiment of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.
The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application may be embodied in essence or a part contributing to the prior art or all or part of the technical solution in the form of a software product stored in a storage medium, including several instructions to cause a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in the embodiments of the present application. And the aforementioned storage medium includes: u disk, mobile hard disk, READ-only memory (ROM), random access memory (RANDOMACCESS MEMORY, RAM), magnetic disk or optical disk, etc. various media capable of storing program codes.
The above embodiments are merely for illustrating the technical solution 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 scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the corresponding technical solutions.
Claims (5)
1. A non-invasive load monitoring electric equipment identification method is characterized in that: the method comprises the following steps:
s101, collecting the instantaneous current of a single electric device, and extracting a current value;
s102, EMD decomposition is carried out on the collected current value data, and IMF components are screened out;
s103, performing singular value decomposition on the obtained IMF component based on an EMD-SVD mode, and constructing a standard eigenvalue matrix;
s104, processing the actually measured current data of the user incoming line by adopting the steps of S101-S103 to obtain an actual operation characteristic value matrix;
s105, carrying out cluster analysis on the actual operation characteristic value matrix and the standard characteristic value matrix, and outputting an analysis result;
in S102, the specific steps of EMD decomposition on the collected current value data are as follows:
calculating all extreme points of the acquired original current signal X (t), fitting by using a cubic spline curve, connecting local maximum points into an upper envelope, and connecting local minimum points into a lower envelope, so that the upper and lower envelopes contain all data points; from the average N of the upper envelope and the lower envelope 1 (t) obtaining:
M 1 (t)＝X(t)-N 1 (t)
M 1 (t) if the IMF condition is satisfied, then it is considered to be the first IMF component;
if the IMF condition is not satisfied, M is 1 (t) processing as target signal, repeating the above steps to obtain upper and lower envelope mean values N 11 (t) calculating M 11 (t)＝M 1 (t)-N 11 (t) test M 11 (t) whether the conditions of IMF are met;
if not, repeating the steps K times until the steps are met; at this time, the first IMF component is calculated as:
A 1 (t)＝M 1 K(t)
separation of A from raw current signal 1 (t) obtaining P 1 (t)＝X(t)-A 1 (t) at this time, P 1 (t) repeating the above steps as a new original signal, and repeating the above steps r timesUntil the nth IMF component is derived;
after the original current signal becomes a monotonic function, the residual component composition is utilized:
wherein X (t) represents an original current signal, N 1 (t) is the average of the upper and lower envelopes of X (t), ai (t) represents the ith IMF component, pn (t) represents the IMF remainder of the original signal;
in S103, the specific steps of singular value decomposition of the obtained IMF component based on the EMD-SVD mode are as follows:
raw current signal from EMD decompositionN IMF components to form an initial eigenvector matrix Q; singular value decomposition of matrix Q using
Q＝UΣV*
Constructing a characteristic value matrix, wherein the columns of U form a pair of Q orthogonal input basis vectors, and the basis vectors are QQ characteristic vectors; v columns form a set of base vectors of quadrature output of Q, and the base vectors are characteristic vectors of Q;
in S105, the specific steps of outputting the analysis result are:
substituting n IMF components Ai (t) obtained by the original current signal into a data set X= { X of d-dimension data points respectively 1 ,x 2 ,...,x i ,...,x n X, where x i ∈R d Because the number of data subsets to be generated is K, the K-means clustering algorithm organizes the data object into K partitions c= { C k K=1, 2,..k }; each partition represents a class c k Each class c k With a class centre mu k The method comprises the steps of carrying out a first treatment on the surface of the The Euclidean distance is selected as a similarity and distance judgment criterion, and the distance between each point in the class and the clustering center mu is calculated k Sum of distance squares of (2)The clustering target is to square sum of total distances of various types +.>Minimum;
wherein,
the total distance square sum in the K-means clustering algorithm tends to decrease along with the increase of the number K of the categories, and the total distance square sum can only obtain the minimum value under a certain determined number K of the categories; after the minimum value is obtained, a clustering result is output, namely the load type is identified;
wherein x is i Representing the ith dimension component, c, of the original dataset X k Represents the kth partition, μ of the data k Representing the cluster center of the kth partition.
2. The identification method according to claim 1, wherein: in S101, an instantaneous current is acquired using a current high-frequency sampling device.
3. An identification device for non-invasive load monitoring electric equipment based on the identification method as claimed in claim 1 or 2, comprising:
the acquisition module is used for acquiring the instantaneous current of the single electric equipment by using the current high-frequency sampling device and extracting a current value;
the decomposition module is used for carrying out EMD decomposition on the collected current value data and screening out IMF components;
the construction module is used for carrying out singular value decomposition on the obtained IMF component based on an EMD-SVD mode and constructing a standard eigenvalue matrix;
the updating module is used for feeding the instantaneous current of the user through the acquisition module, extracting a current value, screening IMF components through the decomposition module, and obtaining an actual operation characteristic value matrix through the construction module;
and the judging module is used for carrying out cluster analysis on the actual operation characteristic value matrix and the standard characteristic value matrix and outputting an analysis result.
4. An identification device for non-invasive load monitoring consumer, 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 identification method of the non-invasive load monitoring electric equipment according to the instructions in the program code.
5. A computer readable storage medium storing program code for performing the identification method of a non-invasive load monitoring consumer according to claim 1 or 2.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010443916.XA CN111612074B (en) | 2020-05-22 | 2020-05-22 | Identification method and device of non-invasive load monitoring electric equipment and related equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010443916.XA CN111612074B (en) | 2020-05-22 | 2020-05-22 | Identification method and device of non-invasive load monitoring electric equipment and related equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111612074A CN111612074A (en) | 2020-09-01 |
| CN111612074B true CN111612074B (en) | 2024-02-02 |
Family
ID=72196396
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010443916.XA Active CN111612074B (en) | 2020-05-22 | 2020-05-22 | Identification method and device of non-invasive load monitoring electric equipment and related equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111612074B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113158134B (en) * | 2021-04-07 | 2024-02-27 | 国网江苏省电力有限公司信息通信分公司 | Method, device and storage medium for constructing non-invasive load identification model |
| CN113255724A (en) * | 2021-04-15 | 2021-08-13 | 国家计算机网络与信息安全管理中心 | Method and device for identifying node type, computer storage medium and terminal |
| CN113408622A (en) * | 2021-06-21 | 2021-09-17 | 国网山东省电力公司泰安供电公司 | Non-invasive load identification method and system considering characteristic quantity information expression difference |
| CN115051363B (en) * | 2022-08-17 | 2023-01-13 | 广东电网有限责任公司佛山供电局 | Distribution network area user change relation identification method and device and computer storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103674511A (en) * | 2013-03-18 | 2014-03-26 | 北京航空航天大学 | Mechanical wearing part performance assessment and prediction method based on EMD (empirical mode decomposition)-SVD (singular value decomposition) and MTS (Mahalanobis-Taguchi system) |
| CN103839197A (en) * | 2014-03-19 | 2014-06-04 | 国家电网公司 | Method for judging abnormal electricity consumption behaviors of users based on EEMD method |
| CN106096562A (en) * | 2016-06-15 | 2016-11-09 | 浙江大学 | Separate based on vibration signal blind sources and the gearbox of wind turbine method for diagnosing faults of sparse component analysis |
| CN109708875A (en) * | 2019-01-24 | 2019-05-03 | 北华大学 | A kind of Fault Diagnosis of Rotor based on variation mode decomposition Volterra model singular value entropy |
| CN110687393A (en) * | 2019-09-03 | 2020-01-14 | 南京理工大学 | Valve short-circuit protection fault positioning method based on VMD-SVD-FCM |
-
2020
- 2020-05-22 CN CN202010443916.XA patent/CN111612074B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103674511A (en) * | 2013-03-18 | 2014-03-26 | 北京航空航天大学 | Mechanical wearing part performance assessment and prediction method based on EMD (empirical mode decomposition)-SVD (singular value decomposition) and MTS (Mahalanobis-Taguchi system) |
| CN103839197A (en) * | 2014-03-19 | 2014-06-04 | 国家电网公司 | Method for judging abnormal electricity consumption behaviors of users based on EEMD method |
| CN106096562A (en) * | 2016-06-15 | 2016-11-09 | 浙江大学 | Separate based on vibration signal blind sources and the gearbox of wind turbine method for diagnosing faults of sparse component analysis |
| CN109708875A (en) * | 2019-01-24 | 2019-05-03 | 北华大学 | A kind of Fault Diagnosis of Rotor based on variation mode decomposition Volterra model singular value entropy |
| CN110687393A (en) * | 2019-09-03 | 2020-01-14 | 南京理工大学 | Valve short-circuit protection fault positioning method based on VMD-SVD-FCM |
Non-Patent Citations (1)
| Title |
|---|
| 徐锋等."基于EMD-SVD的声发射信号特征提取及分类方法".《应用基础与工程科学学报》.2014,第1238-1247页. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111612074A (en) | 2020-09-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111612074B (en) | Identification method and device of non-invasive load monitoring electric equipment and related equipment | |
| CN110826648B (en) | Method for realizing fault detection by utilizing time sequence clustering algorithm | |
| CN110533089B (en) | Self-adaptive non-invasive load identification method based on random forest | |
| CN110443302B (en) | Load identification method based on feature fusion and deep learning and application thereof | |
| Lin et al. | Non-intrusive load monitoring by novel neuro-fuzzy classification considering uncertainties | |
| CN110954744A (en) | Non-invasive load monitoring method based on event detection | |
| US8156055B2 (en) | System and method for utility usage, monitoring and management | |
| CN111564842B (en) | Method for statistical estimation of medium-and-long-term energy consumption in non-invasive electric load monitoring | |
| CN110381126A (en) | Electrical equipment recognition methods, system, equipment and medium based on edge calculations | |
| CN111553444A (en) | Load identification method based on non-invasive load terminal data | |
| CN113673480A (en) | Non-intrusive load identification method and device | |
| CN112819649A (en) | Method and device for determining station area subscriber change relationship | |
| CN113886587A (en) | Data classification method based on deep learning and map building method | |
| CN106680621A (en) | Method for identifying residential load electricity utilization based on current signal separation | |
| CN117436006B (en) | Intelligent ring main unit fault real-time monitoring method and system | |
| CN116861316B (en) | Electrical appliance monitoring method and device | |
| CN113098912B (en) | User account abnormity identification method and device, electronic equipment and storage medium | |
| WO2021171303A1 (en) | A system and method for energy management of identical appliances using non-intrusive load monitoring technique | |
| CN113094448A (en) | Method and device for analyzing vacant state of house and electronic equipment | |
| GB2563860A (en) | A system and method for identifying appliances under recall | |
| CN116881752A (en) | Data clustering method and device, storage medium and electronic equipment | |
| CN110009231A (en) | A kind of power load recognition methods and device based on repeatability and entropy weight distinction | |
| CN112487991B (en) | High-precision load identification method and system based on characteristic self-learning | |
| Moore et al. | Pico-grid smart home energy management system using Mel frequency cepstral coefficients | |
| Yan et al. | A clustering method for power time series curves based on improved self-organizing mapping algorithm |
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 |