CN111008584B - Power quality measurement missing repair method for fuzzy self-organizing neural network - Google Patents
Power quality measurement missing repair method for fuzzy self-organizing neural network Download PDFInfo
- Publication number
- CN111008584B CN111008584B CN201911197788.9A CN201911197788A CN111008584B CN 111008584 B CN111008584 B CN 111008584B CN 201911197788 A CN201911197788 A CN 201911197788A CN 111008584 B CN111008584 B CN 111008584B
- Authority
- CN
- China
- Prior art keywords
- data
- dimensional
- missing
- repairing
- neural network
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/043—Architecture, e.g. interconnection topology based on fuzzy logic, fuzzy membership or fuzzy inference, e.g. adaptive neuro-fuzzy inference systems [ANFIS]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/08—Feature extraction
- G06F2218/10—Feature extraction by analysing the shape of a waveform, e.g. extracting parameters relating to peaks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/12—Classification; Matching
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Software Systems (AREA)
- General Physics & Mathematics (AREA)
- Computing Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Biomedical Technology (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Mathematical Physics (AREA)
- Biophysics (AREA)
- Health & Medical Sciences (AREA)
- Automation & Control Theory (AREA)
- Computational Mathematics (AREA)
- Fuzzy Systems (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Remote Monitoring And Control Of Power-Distribution Networks (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The application discloses a method for repairing the loss of electric energy quality measurement data based on a fuzzy self-organizing neural network, which is implemented by a computer program: the method comprises the following steps: 1) Inputting a one-dimensional measurement data set containing the missing electric energy quality; 2) Sectionally intercepting the sampled one-dimensional waveform data according to N power quality sampling periods; 3) Converting the matrix x into an image by adopting a graying method; 4) Extracting the characteristic value of the two-dimensional harmonic gray scale map, and carrying out normalization processing; 5) Determining the optimal clustering number of the harmonic data of the power grid; 6) Constructing an objective function by taking the weighted square sum of the distances from each sample to all cluster centers as a target; 7) Repairing the two-dimensional gray scale map is completed; 8) The data of each layer of repaired data are fused, and experimental data analysis is carried out, so that the method provided by the application has lower repair error and higher signal to noise ratio under the conditions of low data loss rate and high data loss rate compared with the existing algorithm under the conditions of random loss or continuous loss.
Description
Technical Field
The application relates to a method for repairing missing measured data, in particular to a method for repairing missing measured data of electric energy quality of a fuzzy self-organizing neural network.
Background
The ubiquitous power internet of things (Ubiquitous Electric Internet of Things, UEIoT) realizes comprehensive perception and intelligent measurement of a power system, and provides a strong information support for safe, stable and economic operation of a power grid. The ubiquitous awareness big data of the UEiot bottom layer is the basis of overall system situation awareness and state recognition. The power grid harmonic monitoring data are key to mastering harmonic rules, realizing harmonic treatment and improving the power quality. However, whether the classical Nyquist sampling or the compressed sensing sampling mode is adopted, the problem that part of collected harmonic signals are lost due to faults of sensors, transmission equipment, conversion equipment and the like is often caused; or the phenomenon of data loss caused by channel interference in the propagation process of a communication channel, such as a power line carrier. Due to the unrepeatability of the power grid data acquisition, under the condition of insufficient redundancy, missing harmonic data is used for analysis, and the clear conclusion has larger deviation from the correct rule; in the case of compressed sampling to reconstruct a signal, since a large amount of information is contained in each sampling point, the loss of each sampling value has a great influence on the reconstruction of the signal. Therefore, how to accurately and effectively repair the missing data and restore the original appearance of the collected data is an important point for managing the harmonic waveform data.
The repair strategy provided by the application not only is to perform missing data repair according to the obvious measurement time sequence characteristics of the power quality data of the power grid, but also is to perform missing data repair according to the data autocorrelation and harmonic variation regularity and through the similarity relationship among different data, so that the repair error is greatly reduced.
Disclosure of Invention
The application aims to solve the technical problem of providing a method for repairing the loss of the power quality measurement data of a fuzzy self-organizing neural network, which has lower repairing error and higher signal-to-noise ratio under the conditions of low loss rate and high loss rate of the data under the condition of random loss or continuous loss.
The technical scheme adopted by the application is as follows: a repair method suitable for power quality measurement data loss comprises the following steps:
1) Inputting a one-dimensional measurement data set containing the missing electric energy quality;
2) The sampled one-dimensional waveform data is sectioned according to N power quality sampling periods (20 is suitable through experimental analysis N), and the mapping rule x (i, j) =x (N) |n= (i-1) N of the two-dimensional matrix x is adopted l +j j≤n l Mapping the signals into rows or columns in a two-dimensional matrix x, and carrying out two-dimensional truncation recombination on one-dimensional signals;
3) Calculating a space gray value P (i, j) = [ (255- (254 x (m-x (i, j)/(m-n)) ], and converting the matrix x into an image by using a gray method;
4) Extracting characteristic value X of two-dimensional harmonic gray scale image j ＝[X 1,j ,X 2,j ,…,X m+l,j ]And carrying out normalization treatment;
5) Determining an optimal cluster number of the grid harmonic data, comprising:
(1) Calculating coefficients of degree of aggregationAnd a coefficient characterizing the degree of dispersion from class to class ∈>
(2) Calculating the index λ=α of the overall clustering effect max +(1-β min )；
(3) When I lambda (k) -lambda (k-1) I < epsilon, judging that the total number of clustering iterations before convergence is the optimal classification number k of the clusters; otherwise, returning to (1);
6) Constructing an objective function by taking the weighted square sum of the distances from each sample to all cluster centers as a target:and constructing a membership matrix U= [ U ] ij ]To->And training an optimal clustering mode for constraint conditions. The updating of the parameters in the objective function comprises the following steps:
(1) Updating membershipAnd ambiguity index->
(2) Updating learning efficiency
(3) Updating neuron node weights
(4) Updating weight vectorsIf Deltaw is | 2 ＝||w(t+1)-w(t)|| 2 >Epsilon, returning to (1); otherwise, the cycle is ended.
7) The method for repairing the two-dimensional gray scale map comprises the following steps:
(1) Traversing all data, searching and recording the position sequence and the layering sequence of each missing point;
(2) Searching the same missing value in all layers, finding out the maximum value of the number of available information around the missing value, and extracting the position information and the layer information of the missing point;
(3) Repairing the defect point with the highest number of surrounding available information in the layer firstly;
(4) Deleting the position information and the layer information of the repaired points, and if the position information and the layer information of the repaired points have missing data, entering the step (2) to search again; otherwise enter 8).
8) And fusing the repaired data of each layer, and restoring the image information into waveform signals.
Advantageous effects
The application relates to a repair method suitable for power quality measurement data loss, which has the following characteristics:
the electrical measurement data borne by the ubiquitous electric power Internet of things are interfered in various links such as acquisition, transmission, conversion and the like, so that the data are lost, and the state estimation accuracy and the stable operation of the system are affected. Aiming at the defect that the data repair accuracy is low due to the fact that only one-dimensional measurement data transverse distribution rules are considered in the traditional repair strategy, the application provides a power quality measurement data missing repair method based on a fuzzy self-organizing neural network by fully considering the neighborhood data of measurement data missing points of a power system and the periodic change rules of the measurement data. In the application, the time-space correlation analysis between the data is improved by mapping the one-dimensional measurement data of the electric energy quality into the two-dimensional gray level image in the early stage. And clustering the original data by adopting an artificial intelligent FSOM neural network algorithm in the later stage, analyzing out a multi-layer characteristic value of the data, and carrying out layered restoration on the clustered data. Through experimental data analysis, the FSOM repair algorithm provided by the application has lower repair error and higher signal-to-noise ratio under the conditions of low data loss rate and high data loss rate compared with the existing algorithm under the condition of random loss or continuous loss.
Drawings
The accompanying drawings, which are included to provide a further understanding of embodiments of the application and are incorporated in and constitute a part of this specification, illustrate embodiments of the application and together with the description serve to explain the principles of the application. In the drawings:
FIG. 1 is a two-dimensional truncated reorganization of one-dimensional data;
FIG. 2 is a FSOM neural network map;
FIG. 3 is an algorithm implementation flow;
FIG. 4 is a comparison of the effects of voltage sag loss measurement repair;
FIG. 5 is a comparison of the voltage harmonic loss measurement data restoration effect.
Detailed Description
The following describes in further detail the embodiments of the present application with reference to the drawings and examples. The following examples are illustrative of the application and are not intended to limit the scope of the application.
The repair method for the electric energy quality measurement data deficiency is suitable for mapping the electric energy quality one-dimensional measurement data into a two-dimensional gray scale image in the early stage, and improves time-space correlation analysis between the data. And then clustering the original data by adopting an artificial intelligence FSOM neural network algorithm, analyzing out a plurality of layers of characteristic values of the data, and finally carrying out layered restoration on the clustered data.
Step one: inputting a one-dimensional measurement data set of power quality containing a deficiency
Step two: two-dimensional truncated reorganization of waveform data
And carrying out high-frequency sampling on the voltage or current waveform of the monitoring point to obtain a one-dimensional signal. The method shown in fig. 1 is utilized to intercept and reorganize sampled one-dimensional waveform data in sections according to N power quality sampling periods (20 is suitable through experimental analysis), and the acquired one-dimensional waveform data are mapped into rows or columns in a two-dimensional matrix, so that two-dimensional interception and reorganization of signals are realized. The mapping rule is as follows:
x(i,j)＝x(n)|n＝(i-1)n l +j j≤n l (1)
step three: two-dimensional matrix spatial graying
Converting the matrix into an image by adopting a graying method, and mapping the original two-dimensional matrix value of the power quality signal into a space gray value. The mapping rule is as follows:
step four: extracting characteristic values of two-dimensional harmonic gray level diagram
And extracting time domain characteristic values of waveforms from each sampling period, and establishing a characteristic matrix according to the statistical characteristics. The eigenvalue matrix can be expressed as:
the time domain characteristic value indexes selected are as follows:
TABLE 1 time domain eigenvalue index
Calculating time domain eigenvalue T in each harmonic signal period 1 ～T 6 And normalized.
Step five: clustering waveform data by adopting an FSOM neural network, and gathering all samples into k layers, wherein a data set P can be expressed as: p=p 1 ∪P 2 ∪...∪P k ,i≠j。
1) Initializing clustering parameters of the harmonic missing data set, including: output layer node number, fuzzy index d t Initializing the iteration number t=1, and the maximum iteration number T max Initial neuron node weight v t 。
2) Clustering the harmonic missing data sets, and constructing an objective function by taking the weighted square sum of distances from each sample to all clustering centers as a target:
3) Building membership matrix U= [ U ] ij ]To represent the relation between each power quality cycle data and the clustering waveform data, wherein the membership degree matrix needs to satisfy
4) Determining an optimal cluster number of the harmonic data of the power grid, comprising:
(1) Calculating coefficients of aggregation degree of power grid harmonic data setsAnd a coefficient characterizing the degree of dispersion from class to class ∈>
(2) Index lambda=alpha for calculating overall clustering effect of power grid harmonic data set max +(1-β min )。
(3) When I lambda (k) -lambda (k-1) I < epsilon, judging that the total number of clustering iterations before convergence is the optimal classification number k of the clusters; otherwise, return to (1).
5) Optimizing objective functions using Lagrangian multiplier methodIs a constraint conditionThe updating of the parameters in the objective function comprises the following steps:
(1) Updating membership matrixAnd ambiguity index->
(2) Updating learning efficiency
(3) Updating neuron node weights
(4) Updating weight vectorsIf Deltaw is | 2 ＝||w(t+1)-w(t)|| 2 >Epsilon, returning to (1); otherwise, the cycle is ended.
Step six: the method for repairing the two-dimensional gray scale map comprises the following steps:
(1) Traversing all data, searching for the position sequence x (i, j) and hierarchical sequence q of the missing points r (r is the number of clustering layers).
(2) Searching the same missing value in all layers to find the maximum S of the number of available information around the missing value max Extracting the position information x ' (i, j) and the layer information q ' of the defect point ' r 。
(3) The disadvantage of the most amount of information available to the surroundings is first as per equation (3) in this layerAnd repairing.
(4) Deleting the position information x ' (i, j) and the layer information q ' of the repaired point ' r If the missing data exists, the step (2) is entered for searching again; otherwise, the step (5) is carried out.
(5) The repaired data of each layer is pressed again (4)Fusion is performed.
In order to verify the effectiveness of the electric energy quality measurement data missing repair method based on the fuzzy self-organizing neural network, the method is applied to the original harmonic missing measurement data to analyze the data repair effect.
The grid harmonic data sets are clustered according to the characteristic values of the waveforms by using the FSOM neural network mapping method shown in fig. 2. The algorithm flow chart is shown in fig. 4.
The raw data set is built using the power quality standard signal and perturbation signal models in table 2 below. And in the experiment, the abnormal power quality data defect comprising the voltage sag is repaired, and the original signal to noise ratio after Gaussian white noise is mixed is 17db. The second data is the harmonic voltage loss. The maximum sampling frequency is 20kHZ, and the deletion modes of each group of experimental data are divided into two modes, namely continuous loss and random loss.
Meter 2 model of electric energy quality standard signal and disturbance signal
The application selects a plurality of evaluation indexes to evaluate the quality of the data restoration effect, and comprises the following steps: average absolute error (mean absolute deviation, MAD), the index can avoid the problem that errors cancel each other, and the actual situation of repairing errors can be reflected better; signal-to-noise ratio (SNR) reflecting the accuracy of restoration of the noisy signal waveform; root Mean Square Error (RMSE) can reflect the degree of dispersion of the repair results. The calculation formula is as follows:
by using the method for repairing the missing of the power quality measurement data based on the fuzzy self-organizing neural network, the missing measurement data is repaired respectively, the voltage sag and dip missing measurement repair effect is shown in a graph like that shown in fig. 4, and the voltage harmonic missing measurement data repair effect is shown in a graph like that shown in fig. 5.
The abscissa in fig. 4 and 5 is the data deletion ratio. Under the condition of 30% data loss rate of the continuous loss mode, the average absolute error of the algorithm provided by the application is reduced by 60.71% compared with the MARS algorithm; the signal to noise ratio is improved by 47.3%; the root mean square error is reduced by 56.76%. The FSOM repair algorithm provided by the application has lower repair errors and higher signal-to-noise ratio than a time dynamic matrix decomposition method, a multi-element self-adaptive regression spline method and a KNN repair method under the condition of random deletion or continuous deletion.
Claims (4)
1. A method for repairing missing power quality measurement data of a fuzzy self-organizing neural network, the method being executed by a computer program: the method comprises the following steps:
step 1), inputting a one-dimensional measurement data set containing the missing electric energy quality;
step 2) carrying out segmentation interception on the sampled one-dimensional waveform data according to N power quality sampling periods and carrying out mapping rules of x (i, j) =x (N) |n= (i-1) N through a two-dimensional matrix x l +j j≤n l Mapping the signals into rows or columns in a two-dimensional matrix x, and carrying out two-dimensional truncation recombination on one-dimensional signals;
step 3) calculating a space gray value P (i, j) = [ (255- (254 (m-x (i, j)/(m-n)) ], and converting the matrix x into an image by using a gray method;
step 4) extracting characteristic value X of two-dimensional harmonic gray scale j ＝[X 1,j ,X 2,j ,…,X m+l,j ]And normalized；
Step 5) determining the optimal clustering number of the harmonic data of the power grid; the step 5) is used for determining the optimal clustering number of the harmonic data of the power grid, and comprises the following steps:
(1) Calculating coefficients of degree of aggregationAnd a coefficient characterizing the degree of dispersion from class to class ∈>
(2) Calculating the index λ=α of the overall clustering effect max +(1-β min )；
(3) When I lambda (k) -lambda (k-1) I < epsilon, judging that the total number of clustering iterations before convergence is the optimal classification number k of the clusters; otherwise, returning to the step 5) (1);
step 6) taking the weighted square sum of the distances from each sample to all cluster centers as a target to construct an objective function:and constructing a membership matrix U= [ U ] ij ]To->Training an optimal clustering mode for constraint conditions;
step 7) repairing the two-dimensional gray scale map; and 7) finishing the repair of the two-dimensional gray scale map, which comprises the following steps:
(1) Traversing all data, searching and recording the position sequence x (i, j) and the layering sequence q of each missing point r ；
(2) Searching the same missing point in all layers, finding out the maximum value of the number of available information around the missing point, and extracting the position information and the layer information of the missing point;
(3) Repairing the defect point with the highest number of surrounding available information in the layer firstly;
(4) Deleting the position information and the layer information of the repaired points, and if the position information and the layer information of the repaired points have missing data, entering the step 7), and searching again in the step (2); otherwise enter 8);
and 8) fusing the repaired data of each layer, and restoring the image information into waveform signals.
2. The method for repairing the loss of power quality measurement data of the fuzzy self-organizing neural network according to claim 1, wherein the method comprises the following steps: the updating of the parameters in the objective function in the step 6) comprises the following steps:
(1) Updating membershipAnd ambiguity index->
(2) Updating learning efficiency
(3) Updating neuron node weights
(4) Updating weight vectorsIf Deltaw is | 2 ＝||w(t+1)-w(t)|| 2 >Epsilon, returning to (1); otherwise, the cycle is ended.
3. The method for repairing missing power quality measurement data of a fuzzy self-organizing neural network according to claim 1, wherein when repairing the two-dimensional gray scale map in step 7), if the corresponding data is not missing, the data is not processed.
4. The method for repairing missing power quality measurement data of a fuzzy self-organizing neural network according to claim 1, wherein the final clustering number k determined in the step 5) is substituted into the step 6) to perform similarity clustering.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911197788.9A CN111008584B (en) | 2019-11-29 | 2019-11-29 | Power quality measurement missing repair method for fuzzy self-organizing neural network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911197788.9A CN111008584B (en) | 2019-11-29 | 2019-11-29 | Power quality measurement missing repair method for fuzzy self-organizing neural network |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111008584A CN111008584A (en) | 2020-04-14 |
| CN111008584B true CN111008584B (en) | 2023-09-08 |
Family
ID=70112527
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911197788.9A Active CN111008584B (en) | 2019-11-29 | 2019-11-29 | Power quality measurement missing repair method for fuzzy self-organizing neural network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111008584B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111597925A (en) * | 2020-04-29 | 2020-08-28 | 山东卓文信息科技有限公司 | Power system transient signal analysis method based on DCNN |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107291765A (en) * | 2016-04-05 | 2017-10-24 | 南京航空航天大学 | The clustering method of processing missing data is planned based on DC |
| CN109584260A (en) * | 2018-11-27 | 2019-04-05 | 烟台中科网络技术研究所 | A kind of liver imaging dividing method and system |
| WO2019218263A1 (en) * | 2018-05-16 | 2019-11-21 | 深圳大学 | Extreme learning machine-based extreme ts fuzzy inference method and system |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8385676B2 (en) * | 2009-07-30 | 2013-02-26 | Hewlett-Packard Development Company, L.P. | Context-cluster-level control of filtering iterations in an iterative discrete universal denoiser |
-
2019
- 2019-11-29 CN CN201911197788.9A patent/CN111008584B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107291765A (en) * | 2016-04-05 | 2017-10-24 | 南京航空航天大学 | The clustering method of processing missing data is planned based on DC |
| WO2019218263A1 (en) * | 2018-05-16 | 2019-11-21 | 深圳大学 | Extreme learning machine-based extreme ts fuzzy inference method and system |
| CN109584260A (en) * | 2018-11-27 | 2019-04-05 | 烟台中科网络技术研究所 | A kind of liver imaging dividing method and system |
Non-Patent Citations (1)
| Title |
|---|
| 陈阳.拓扑梯度耦合FCMC的全自动图像修复优化算法.包装工程.2014,第35卷(第21期),96-103. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111008584A (en) | 2020-04-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106055918B (en) | Method for identifying and correcting load data of power system | |
| CN110929847A (en) | Converter transformer fault diagnosis method based on deep convolutional neural network | |
| CN106656357B (en) | Power frequency communication channel state evaluation system and method | |
| CN110443724B (en) | Electric power system rapid state estimation method based on deep learning | |
| CN110087207A (en) | Wireless sensor network missing data method for reconstructing | |
| CN111008726A (en) | Class image conversion method in power load prediction | |
| CN112596016A (en) | Transformer fault diagnosis method based on integration of multiple one-dimensional convolutional neural networks | |
| CN114997506B (en) | Atmospheric pollution propagation path prediction method based on link prediction | |
| CN116937559A (en) | Power system load prediction system and method based on cyclic neural network and tensor decomposition | |
| CN117370766A (en) | Satellite mission planning scheme evaluation method based on deep learning | |
| CN114970946A (en) | PM2.5 pollution concentration long-term space prediction method based on deep learning model and empirical mode decomposition coupling | |
| CN115994605A (en) | Multi-data fusion photovoltaic power prediction algorithm for comprehensive meteorological factor data | |
| CN115342814A (en) | Unmanned ship positioning method based on multi-sensor data fusion | |
| CN114048819A (en) | Power distribution network topology identification method based on attention mechanism and convolutional neural network | |
| CN113065223A (en) | Multi-level probability correction method for digital twin model of tower mast cluster | |
| CN117371207A (en) | Extra-high voltage converter valve state evaluation method, medium and system | |
| CN111008584B (en) | Power quality measurement missing repair method for fuzzy self-organizing neural network | |
| CN117473430A (en) | Non-invasive load classification method and device | |
| CN117520809A (en) | Transformer fault diagnosis method based on EEMD-KPCA-CNN-BiLSTM | |
| JP6950647B2 (en) | Data determination device, method, and program | |
| CN116167465A (en) | Solar irradiance prediction method based on multivariate time series ensemble learning | |
| CN115081551A (en) | RVM line loss model building method and system based on K-Means clustering and optimization | |
| CN115049136A (en) | Transformer load prediction method | |
| CN118565537B (en) | Shield tunnel monitoring method and system based on distributed long-gauge fiber bragg grating | |
| CN118378178B (en) | Transformer fault identification method and system based on residual map convolution neural network |
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 |