CN117273489A - Photovoltaic state evaluation method and device - Google Patents
Photovoltaic state evaluation method and device Download PDFInfo
- Publication number
- CN117273489A CN117273489A CN202311267431.XA CN202311267431A CN117273489A CN 117273489 A CN117273489 A CN 117273489A CN 202311267431 A CN202311267431 A CN 202311267431A CN 117273489 A CN117273489 A CN 117273489A
- Authority
- CN
- China
- Prior art keywords
- matrix
- data
- photovoltaic
- determining
- principal component
- 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.)
- Pending
Links
- 238000011156 evaluation Methods 0.000 title claims abstract description 59
- 239000011159 matrix material Substances 0.000 claims abstract description 120
- 238000000034 method Methods 0.000 claims abstract description 48
- 238000012544 monitoring process Methods 0.000 claims abstract description 28
- 230000009467 reduction Effects 0.000 claims abstract description 19
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 16
- 238000000513 principal component analysis Methods 0.000 claims abstract description 15
- 238000007417 hierarchical cluster analysis Methods 0.000 claims abstract description 10
- 238000012847 principal component analysis method Methods 0.000 claims abstract description 8
- 238000012545 processing Methods 0.000 claims description 22
- 238000004458 analytical method Methods 0.000 claims description 11
- 238000010606 normalization Methods 0.000 claims description 11
- 230000032683 aging Effects 0.000 claims description 8
- 230000036541 health Effects 0.000 abstract description 8
- 238000007781 pre-processing Methods 0.000 abstract description 3
- 230000006870 function Effects 0.000 description 20
- 238000003860 storage Methods 0.000 description 9
- 230000008569 process Effects 0.000 description 7
- 230000003287 optical effect Effects 0.000 description 6
- 238000003745 diagnosis Methods 0.000 description 5
- 238000009826 distribution Methods 0.000 description 5
- 238000004590 computer program Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 238000007619 statistical method Methods 0.000 description 4
- 230000002159 abnormal effect Effects 0.000 description 3
- 238000003491 array Methods 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 230000002093 peripheral effect Effects 0.000 description 3
- 238000010248 power generation Methods 0.000 description 3
- 238000004445 quantitative analysis Methods 0.000 description 3
- 239000013598 vector Substances 0.000 description 3
- 230000002776 aggregation Effects 0.000 description 2
- 238000004220 aggregation Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000007621 cluster analysis Methods 0.000 description 2
- 230000008878 coupling Effects 0.000 description 2
- 238000010168 coupling process Methods 0.000 description 2
- 238000005859 coupling reaction Methods 0.000 description 2
- 230000001186 cumulative effect Effects 0.000 description 2
- 238000007405 data analysis Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 238000013210 evaluation model Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000004451 qualitative analysis Methods 0.000 description 2
- 208000032953 Device battery issue Diseases 0.000 description 1
- 230000000903 blocking effect Effects 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000013144 data compression Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 238000013079 data visualisation Methods 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000003862 health status Effects 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 230000007257 malfunction Effects 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0637—Strategic management or analysis, e.g. setting a goal or target of an organisation; Planning actions based on goals; Analysis or evaluation of effectiveness of goals
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
- G06F18/2135—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods based on approximation criteria, e.g. principal component analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/231—Hierarchical techniques, i.e. dividing or merging pattern sets so as to obtain a dendrogram
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Educational Administration (AREA)
- Entrepreneurship & Innovation (AREA)
- Development Economics (AREA)
- Marketing (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- General Health & Medical Sciences (AREA)
- Water Supply & Treatment (AREA)
- Public Health (AREA)
- Photovoltaic Devices (AREA)
Abstract
The disclosure provides a photovoltaic state evaluation method and device, and relates to the technical field of photovoltaic state evaluation. Comprising the following steps: acquiring multidimensional monitoring data of a photovoltaic power station under various working conditions; based on a principal component analysis method, dimension reduction is carried out on the multi-dimensional monitoring data to obtain a target matrix; performing hierarchical clustering analysis on the target matrix, and selecting the clustering number with the maximum CH function value as the optimal clustering number; and evaluating the operation state of the photovoltaic power station based on the target matrix, the optimal cluster number and a component state evaluation algorithm model. The method comprises the steps of preprocessing original multidimensional input variables by adopting principal component analysis, performing principal component analysis dimension reduction on multidimensional monitoring data generated in different working environments, then evaluating the running state of a photovoltaic power station by using hierarchical clustering analysis, establishing a thought of health evaluation of a photovoltaic module, and finally giving out health evaluation results and conclusions.
Description
Technical Field
The disclosure relates to the technical field of photovoltaic state evaluation, in particular to a photovoltaic state evaluation method and device.
Background
Along with the increasing development scale of new energy in China, the requirements for evaluating the condition of photovoltaic power generation equipment are also increased, so that comprehensive analysis of equipment monitoring data is needed, and the data analysis collected by the equipment operation recording device is used for state evaluation. The state-assessment problem is predictive in nature, and is typically performed by qualitative and quantitative analysis. Qualitative analysis creates an evaluation model according to the operation data and expert experience, while quantitative analysis creates an evaluation model by adopting data analysis and data mining methods. The quantitative analysis method can realize evaluation more objectively and conveniently under the condition of sufficient data objects. Meanwhile, the state evaluation is beneficial to early determination of the fault type of the equipment, measures are quickly taken, the maintenance efficiency is improved, and meanwhile, the possible faults of the power distribution equipment can be predicted through the evaluated fault data searching characteristics.
In the operation process of the photovoltaic power station, a large number of faults are easy to generate due to the change of environment and external factors, and the system evaluation and intelligent diagnosis of the photovoltaic power station are very important.
Disclosure of Invention
The present disclosure aims to solve, at least to some extent, one of the technical problems in the related art.
An embodiment of a first aspect of the present disclosure provides a photovoltaic state evaluation method, including:
acquiring multidimensional monitoring data of a photovoltaic power station under various working conditions;
based on a principal component analysis method, dimension reduction is carried out on the multi-dimensional monitoring data to obtain a target matrix;
performing hierarchical clustering analysis on the target matrix, and selecting the clustering number with the maximum CH function value as the optimal clustering number;
and evaluating the operation state of the photovoltaic power station based on the target matrix, the optimal cluster number and a component state evaluation algorithm model.
Embodiments of a second aspect of the present disclosure provide a photovoltaic state evaluation apparatus, including:
the acquisition module is used for acquiring multidimensional monitoring data of the photovoltaic power station under various working conditions;
the dimension reduction module is used for reducing dimensions of the multi-dimensional monitoring data based on a principal component analysis method so as to obtain a target matrix;
the first analysis module is used for carrying out hierarchical clustering analysis on the target matrix and selecting the clustering number when the CH function value is the maximum as the optimal clustering number;
and the evaluation module is used for evaluating the operation state of the photovoltaic power station based on the target matrix, the optimal cluster number and a component state evaluation algorithm model.
An embodiment of a third aspect of the present disclosure provides an electronic device, including: the photovoltaic state evaluation system comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor realizes the photovoltaic state evaluation method according to the embodiment of the first aspect of the present disclosure when the processor executes the program.
An embodiment of a fourth aspect of the present disclosure proposes a computer readable storage medium storing a computer program which, when executed by a processor, implements a photovoltaic state evaluation method as proposed by an embodiment of the first aspect of the present disclosure.
The photovoltaic state evaluation method and device provided by the disclosure have the following beneficial effects:
in the embodiment of the disclosure, firstly, multi-dimensional monitoring data of a photovoltaic power station under various working conditions are obtained, then, based on a principal component analysis method, the multi-dimensional monitoring data are subjected to dimension reduction to obtain a target matrix, then, hierarchical clustering analysis is performed on the target matrix, the clustering number when the CH function value is the largest is selected as the optimal cluster number, and finally, based on the target matrix, the optimal cluster number and a component state evaluation algorithm model, the operation state of the photovoltaic power station is evaluated. The method can effectively solve the problem of operation state evaluation of the photovoltaic power station under the condition of lack of prior knowledge, has important theoretical and application values, has better adaptability under the condition of larger data volume and lack of prior knowledge because of the method for evaluating the state of the photovoltaic power station based on unsupervised learning, and does not need to calibrate a large amount of experimental set labels compared with a fault diagnosis method represented by a neural network. Because the number of data dimensions is large, and the accuracy of the clustering result is related to the data with proper attribute selection, the method firstly reduces the dimension of the data, removes some unimportant features and noise, and facilitates the clustering analysis of the subsequent data. The data characteristics after PCA dimension reduction are more obvious, and the process of selecting proper data attributes through rich experience is effectively replaced. The method combines the PCA feature dimension reduction and hierarchical clustering methods, and has certain theoretical and experimental significance for the state evaluation of the photovoltaic power station. The method for determining the clustering number based on the CH function adopts a dividing principle that the distance between groups is large enough and the distance between elements in the groups is small enough, so that the optimal judgment effect can be obtained, and the clustering quality is greatly improved.
Additional aspects and advantages of the disclosure will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the disclosure.
Drawings
The foregoing and/or additional aspects and advantages of the present disclosure will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings, in which:
fig. 1 is a schematic flow chart of a photovoltaic state evaluation method according to an embodiment of the disclosure;
FIG. 2 is a flow chart of a hierarchical clustering optimal cluster number determination method;
FIG. 3 is a flowchart of a PCA-hierarchical clustering algorithm;
FIG. 4 is a flow chart of a photovoltaic state evaluation;
fig. 5 is a schematic structural diagram of a photovoltaic state evaluation device according to another embodiment of the present disclosure;
fig. 6 illustrates a block diagram of an exemplary electronic device suitable for use in implementing embodiments of the present disclosure.
Detailed Description
Embodiments of the present disclosure are described in detail below, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to like or similar elements or elements having like or similar functions throughout. The embodiments described below by referring to the drawings are exemplary and intended for the purpose of explaining the present disclosure and are not to be construed as limiting the present disclosure.
The following describes a photovoltaic state evaluation method and a device according to embodiments of the present disclosure with reference to the accompanying drawings.
In the operation process of the photovoltaic power station, a large number of faults are easy to generate due to the change of environment and external factors, and the system evaluation and intelligent diagnosis of the photovoltaic power station are very important, so that the multi-dimensional data are required to be subjected to characteristic dimension reduction, hierarchical clustering analysis is carried out on the dimension reduced data, and the operation state of the photovoltaic power station is evaluated. The data acquisition stage is a link for acquiring data required in the subsequent stage, and ensuring the accuracy of data acquisition is a precondition for realizing accurate evaluation results. The feature extraction stage is a data preprocessing stage, and the data preprocessing method influences the evaluation result to a great extent. Methods that can be used include principal component analysis, fisher's criteria, wavelet decomposition, and the like.
Fig. 1 is a flow chart of a photovoltaic state evaluation method according to an embodiment of the disclosure.
As shown in fig. 1, the photovoltaic state evaluation method may include the steps of:
and step 101, acquiring multidimensional monitoring data of the photovoltaic power station under various working conditions.
The characteristic parameters related to the operation state of the photovoltaic system comprise environmental parameters and electrical parameters, and the number of the parameters is large. The characteristic parameters may include temperatures T1 and T2 … of different photovoltaic strings, voltages V1 and V2 … of different photovoltaic strings, currents I1 and I2 … of different photovoltaic strings, ambient temperature, irradiance, and power.
It should be noted that, the selection of the characteristic parameters of the health state of the photovoltaic system should consider that the characteristic parameters have direct or indirect influence on the system performance and have a coupling relationship with each other. The following are descriptions of some photovoltaic system health status feature parameters that may be selected in embodiments of the present disclosure:
component temperature: the temperature of the photovoltaic module is an important parameter, and high temperatures lead to reduced efficiency and increased risk of damage.
Component voltage and current: the voltage and current of the photovoltaic module reflect the power output of the system, and abnormal voltage or current may mean malfunction or damage.
Efficiency index: including efficiency, conversion efficiency, etc. of the photovoltaic module for evaluating the performance of photoelectric conversion.
Generating capacity: the actual power generation amount of the photovoltaic system is recorded and compared with the theoretical value, so that the running condition of the system can be estimated.
Environmental factors: including ambient temperature, irradiance, and other weather conditions, which directly affect the performance of the photovoltaic system.
Power curve: the power output curves of the photovoltaic system under different illumination conditions are recorded, and whether the working state of the system is normal can be judged.
The reasonable selection of the characteristic parameters of the health state of the photovoltaic system is a precondition for realizing the evaluation of the health state of the photovoltaic system. The selected characteristic parameters should have a direct or indirect influence on the performance state of the photovoltaic system and have a coupling relationship with each other. Raw data collected from the photovoltaic power plant is processed. And carrying out statistical analysis on the collected original data, and combining a data distribution histogram and a normal distribution probability map of the data to obtain the data space distribution condition after PCA dimension reduction.
Specifically, various types of sensors, such as temperature sensors, voltage sensors, current sensors, irradiance sensors, etc., can be installed in the photovoltaic power station to monitor key parameters under different working conditions in real time. These sensors collect and transmit raw data to a data collection system or monitoring platform. A data acquisition system is built for collecting and storing data from the various sensors. The data acquisition system may be a dedicated hardware device or a software-based solution, responsible for acquiring, processing and storing the monitoring data in real time. The operation working conditions of the photovoltaic power station are adjusted and controlled, such as component inclination angles are changed, components are oriented in different directions, cleaning degree is adjusted, fault states are simulated, and the like, so that data under different working conditions are obtained. The monitoring under normal operation, partial fault or abnormal working condition is ensured, so that a more comprehensive data set is obtained. And recording and storing the collected monitoring data, including information such as time stamps, measured values of all sensors and the like. Data integrity and accessibility may be ensured using a database or cloud storage, etc. Analyzing and mining the obtained multidimensional monitoring data, extracting characteristic parameters, finding abnormal conditions, predicting performance changes and the like through methods of statistical analysis, data visualization, mode identification and the like, and providing support for health state assessment and maintenance of the photovoltaic power station.
And 102, performing dimension reduction on the multi-dimensional monitoring data based on a principal component analysis method to obtain a target matrix.
Principal Component Analysis (PCA) is a multivariate statistical analysis technique for data compression and feature extraction that converts a plurality of related variables into a few uncorrelated integrated variables that contain a large portion of the information contained in the original variables. As a multivariate statistical analysis method, principal component analysis transforms a set of variables that are originally interrelated into a series of linearly independent principal components based on correlations between the variables.
Optionally, the multi-dimensional monitoring data may be first divided to obtain M groups of samples, where each group of samples includes N feature parameters, then a first matrix, a mean value, and a variance corresponding to the M groups of samples may be determined, and then the first matrix is converted into a second matrix based on the mean value and the variance, then a data unit corresponding to the second matrix is determined, then a contribution rate of the accumulated variance is determined based on the data unit, if the contribution rate is greater than a preset threshold, the first p components corresponding to the first p components may be used as main components, then a third matrix corresponding to the main components is determined, and finally the target matrix is determined based on a deviation between the third matrix and the first matrix.
Optionally, determining the data unit corresponding to the second matrix includes:
wherein the second matrix is a matrix of M rows and N columns
Data elements X of said second matrix ij Expressed as:
wherein i=1, 2, …, M; j=1, 2, …, N, x j For the j-th characteristic parameter, x ij Is the ith row and the jth characteristic parameter.
Normalization of raw data. In order to eliminate the influence caused by the difference of the original variable dimensions and the overlarge numerical value difference, the original data is subjected to standardization processing. Assuming that the original variable has M sets of samples, each set of samples contains N feature parameters, the original variable can be expressed as:
converting the matrix into matrix X through center normalization * 。
Delta is the mean and variance of the sample variables, respectively. Matrix->Can be expressed as:
wherein: i=1, 2, …, M; j=1, 2, …, N; x is X ij Is a matrixIs a data unit of (1); x is x j Is the j-th characteristic parameter.
S2: and determining the number of main components. The number of principal components selected depends on the contribution rate of the cumulative variance. When the contribution rate of the accumulated variance is generally greater than 85%, the first p corresponding principal components contain most of information which can be provided by the original variable, and the number of the principal components is p.
S3: a feature vector matrix is calculated. The eigenvector matrix corresponding to the p principal components is U NP = (u 1, u2, …, up), then the matrix of p principal components of the M samples of the photovoltaic system is
S4: and calculating the deviation of the original variable and the principal component. Assuming that the health data has M samples in total, each sample containing p feature parameters, the health data can be represented by a matrix pm×p, the center of which is normalized to a matrixThe data elements of the matrix are:
wherein: p (P) ij For matrix P Mp Is a data unit of (1);is the average value of the characteristic parameter j. Sj is the variance of the characteristic parameter j; i=1, 2, …, M; j=1, 2, …, P.
Matrix arrayCovariance matrix of (2) is
Wherein:for matrix->Center normalized row i.
S5: sample data matrixIs>The data units are:
wherein i=1, 2, …, M; j=1, 2, …, P.
Optionally, the determining the target matrix based on the deviation between the third matrix and the first matrix includes:
performing normalization processing on the first matrix, and determining a fourth matrix based on the deviation between each group of samples after the normalization processing and each principal component in the third matrix;
and carrying out standardization processing on the fourth matrix to obtain a fifth matrix.
Specifically, the principal component analysis steps are as follows:
firstly, normalizing the original data, and carrying out normalization processing on the original data to eliminate dimension differences and numerical differences among variables. The raw data is converted into a central normalized form by calculating the mean and variance of each characteristic parameter. The number of principal components can then be determined: and determining the selected number of the main components according to the contribution rate of the accumulated variance. Typically, when the contribution rate of the cumulative variance is greater than 85%, the first p principal components are selected, which contain most of the information that the original variables can provide. The eigenvector matrix may then be calculated: the feature vectors corresponding to the p principal components are selected to form a feature vector matrix. Finally, the deviation between the original variable and the principal component can be calculated: after the original data is subjected to center standardization, calculating the deviation between each sample data and the principal component to obtain a new data matrix taking the principal component as a dimension. The new data matrix may then be normalized: and (3) carrying out standardization processing on the new data matrix to obtain a matrix with unified dimension and numerical range.
Through the steps, the original characteristic parameters can be converted into a plurality of comprehensive indexes, wherein the indexes are main components, and have lower dimensionality and smaller correlation. The main components can be used for comprehensive evaluation or comparison and sequencing, so that a comprehensive evaluation result of the operation state of the photovoltaic system is obtained. The dimensions are reduced and the redundancy of information is reduced, thereby better describing and analyzing the operating state of the photovoltaic system.
And 103, performing hierarchical clustering analysis on the target matrix, and selecting the clustering number with the maximum CH function value as the optimal clustering number.
The hierarchical clustering algorithm is also called a tree clustering algorithm, and uses a data connection rule to repeatedly split or aggregate data in a hierarchical architecture mode so as to form a hierarchical sequence clustering problem solution.
Firstly, determining the hierarchical clustering number and the inter-cluster distance aggregation mode:
when a clustering algorithm is applied, the defect that a k value needs to be set in advance exists, and when clustering operation of a large number of data sets is performed or priori knowledge is insufficient, the determination of the proper k value is not easy. Comparing various functions for judging the clustering quality according to an optimal clustering quality judging principle based on the fact that the distance between elements in a group is minimum and the distance between the groups is maximum: DB function, DI function and Calinski-Harabasz function, select CH to define the distance between clusters. The CH function is the ratio of the distance between groups and the distance between elements in the groups, and in order to improve the clustering quality, the distance between the groups needs to be large enough, and the distance between the elements in the groups is small enough, so that the larger the CH value is, the better the clustering quality is, and the clustering number when the CH value is the largest can be selected as the optimal k value. And judging the optimal k value by adopting CH, obtaining different clustering results after multiple tests, wherein each group is a CH value corresponding to the different k values one by one, namely an effectiveness CH value, judging the effectiveness of a plurality of groups of clustering results, and selecting the k value corresponding to the largest CH value as the highest effectiveness of the clustering result.
For inter-cluster distance selection, the introduced commonality classification correlation coefficient is used for selection.
The hierarchical clustering flow is as follows: a. dividing all objects into a single cluster; b. merging two clusters closest to each other into one cluster according to an aggregation rule; c. updating clusters and updating inter-cluster distances; d. returning to step b until all objects are in the same object. As shown in fig. 2, the hierarchical clustering optimal cluster number determining method is provided.
As shown in fig. 3, a PCA-hierarchical clustering algorithm flow is shown.
And step 104, evaluating the operation state of the photovoltaic power station based on the target matrix, the optimal cluster number and the component state evaluation algorithm model.
Specifically, an experimental scene with clear weather can be selected first, four operation states including normal operation, open-circuit fault, equipment aging and shadow shielding can be set, and then feature data set analysis can be performed based on a target matrix and the optimal cluster number so as to analyze and obtain the operation state corresponding to each feature data set.
The experimental scene may be clear weather, cloudy weather, etc., which is not limited herein.
The operation states comprise a normal operation state, an open circuit fault, equipment aging and shadow shielding.
Open circuit fault condition: certain battery cells or connectors fail causing circuit interruption, thereby affecting power output.
Device aging state: due to factors such as component aging, battery failure or connector loosening, the efficiency of the photovoltaic system is reduced, and the output performance of the photovoltaic system is affected.
Shadow blocking state: due to shielding of buildings or trees and the like, part of photovoltaic modules cannot receive enough sunlight, and the power generation capacity of the photovoltaic system is reduced.
Specifically, after the optimal cluster number K is determined, the running state corresponding to each cluster can be determined by observing the data distribution and the characteristic value in the cluster.
Wherein the component state evaluation algorithm model may consider using an unsupervised learning algorithm for component state evaluation. Common unsupervised learning algorithms include cluster analysis and anomaly detection. Cluster analysis may separate components into different clusters to discover potential state differences present therein. Anomaly detection can identify those components that deviate greatly from normal, thereby identifying components that may have a fault or problem. Hierarchical clustering is divided into four types according to the degree of correlation of data points, and data characteristics are analyzed: normal operation and shadow occlusion are only irradiance changes, data features are relatively similar, and data sets which are far apart are available, so that the data sets which are far apart can be determined to be equipment aging and open circuit faults. Further analysis of the dataset characteristics may determine the status of the device characterized by the different datasets.
As shown in fig. 4, fig. 4 is a flowchart of overall photovoltaic state evaluation.
It should be noted that, the embodiment of the disclosure can effectively solve the problem of operation state evaluation of the photovoltaic power station under the condition of lack of prior knowledge, has important theoretical and application values, and has better adaptability under the condition of large data quantity and lack of prior knowledge because of the non-supervision learning-based photovoltaic power station state evaluation method, compared with a fault diagnosis method represented by a neural network, the method does not need to calibrate a large amount of experimental set labels. Because the number of data dimensions is large, and the accuracy of the clustering result is related to the data with proper attribute selection, the method firstly reduces the dimension of the data, removes some unimportant features and noise, and facilitates the clustering analysis of the subsequent data. The data characteristics after PCA dimension reduction are more obvious, and the process of selecting proper data attributes through rich experience is effectively replaced. The method combines the PCA feature dimension reduction and hierarchical clustering methods, and has certain theoretical and experimental significance for the state evaluation of the photovoltaic power station. The method for determining the clustering number based on the CH function adopts a dividing principle that the distance between groups is large enough and the distance between elements in the groups is small enough, so that the optimal judgment effect can be obtained, and the clustering quality is greatly improved.
In order to implement the above embodiment, the present disclosure further proposes a photovoltaic state evaluation system.
Fig. 5 is a schematic structural diagram of a photovoltaic state evaluation system according to an embodiment of the disclosure.
As shown in fig. 5, the photovoltaic state evaluation system 500 may include:
the acquisition module 510 is configured to acquire multidimensional monitoring data of the photovoltaic power station under multiple working conditions;
the dimension reduction module 520 is configured to reduce dimensions of the multi-dimensional monitoring data based on a principal component analysis method, so as to obtain a target matrix;
the first analysis module 530 is configured to perform hierarchical cluster analysis on the target matrix, and select the number of clusters when the CH function value is the maximum as the optimal number of clusters;
and the evaluation module 540 is configured to evaluate an operation state of the photovoltaic power station based on the target matrix, the optimal cluster number, and a component state evaluation algorithm model.
Optionally, the dimension reduction module includes:
the dividing unit is used for dividing the multidimensional monitoring data to obtain M groups of samples, and each group of samples contains N characteristic parameters;
a first determining unit, configured to determine a first matrix, a mean value, and a variance corresponding to the M groups of samples, and further convert the first matrix into a second matrix based on the mean value and the variance;
a second determining unit, configured to determine a data unit corresponding to the second matrix;
a third determining unit, configured to determine a contribution rate of the accumulated variance based on the data unit, and if the contribution rate is greater than a preset threshold, may use the first p components as main components;
a fourth determination unit configured to determine a third matrix corresponding to the principal component;
and a fifth determining unit configured to determine the target matrix based on a deviation between the third matrix and the first matrix.
Optionally, the fifth determining unit is specifically configured to:
performing normalization processing on the first matrix, and determining a fourth matrix based on the deviation between each group of samples after the normalization processing and each principal component in the third matrix;
and carrying out standardization processing on the fourth matrix to obtain a fifth matrix.
Optionally, the second determining unit is specifically configured to:
wherein the second matrix is a matrix of M rows and N columns
Data elements X of said second matrix ij Expressed as:
wherein i=1, 2, …, M; j=1, 2, …, N, x j For the j-th characteristic parameter, x ij Is the ith row and the jth characteristic parameter.
Optionally, the device further includes:
the setting module is used for selecting an experimental scene with clear weather and setting four running states of normal running, open-circuit fault, equipment aging and shadow shielding;
and the second analysis module is used for analyzing the characteristic data sets based on the target matrix and the optimal cluster number so as to obtain the running state corresponding to each characteristic data set.
It should be noted that, the embodiment of the disclosure can effectively solve the problem of operation state evaluation of the photovoltaic power station under the condition of lack of prior knowledge, has important theoretical and application values, and has better adaptability under the condition of large data quantity and lack of prior knowledge because of the non-supervision learning-based photovoltaic power station state evaluation method, compared with a fault diagnosis method represented by a neural network, the method does not need to calibrate a large amount of experimental set labels. Because the number of data dimensions is large, and the accuracy of the clustering result is related to the data with proper attribute selection, the method firstly reduces the dimension of the data, removes some unimportant features and noise, and facilitates the clustering analysis of the subsequent data. The data characteristics after PCA dimension reduction are more obvious, and the process of selecting proper data attributes through rich experience is effectively replaced. The method combines the PCA feature dimension reduction and hierarchical clustering methods, and has certain theoretical and experimental significance for the state evaluation of the photovoltaic power station. The method for determining the clustering number based on the CH function adopts a dividing principle that the distance between groups is large enough and the distance between elements in the groups is small enough, so that the optimal judgment effect can be obtained, and the clustering quality is greatly improved.
In order to achieve the above embodiments, the present disclosure further proposes an electronic device including: the photovoltaic state evaluation method comprises a memory, a processor and a computer program stored in the memory and capable of running on the processor, wherein the processor realizes the photovoltaic state evaluation method according to the previous embodiment of the disclosure when executing the program.
In order to implement the above-mentioned embodiments, the present disclosure also proposes a computer-readable storage medium storing a computer program which, when executed by a processor, implements a photovoltaic state evaluation method as proposed in the foregoing embodiments of the present disclosure.
Fig. 6 illustrates a block diagram of an exemplary electronic device suitable for use in implementing embodiments of the present disclosure. The electronic device 12 shown in fig. 6 is merely an example and should not be construed as limiting the functionality and scope of use of the disclosed embodiments.
As shown in fig. 6, the electronic device 12 is in the form of a general purpose computing device. Components of the electronic device 12 may include, but are not limited to: one or more processors or processing units 16, a system memory 28, a bus 18 that connects the various system components, including the system memory 28 and the processing units 16.
Bus 18 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor, and a local bus using any of a variety of bus architectures. By way of example, and not limitation, such architectures include industry Standard architecture (Industry Standard Architecture; hereinafter ISA) bus, micro channel architecture (Micro Channel Architecture; hereinafter MAC) bus, enhanced ISA bus, video electronics standards Association (Video Electronics Standards Association; hereinafter VESA) local bus, and peripheral component interconnect (Peripheral Component Interconnection; hereinafter PCI) bus.
Electronic device 12 typically includes a variety of computer system readable media. Such media can be any available media that is accessible by electronic device 12 and includes both volatile and nonvolatile media, removable and non-removable media.
Memory 28 may include computer system readable media in the form of volatile memory, such as random access memory (Random Access Memory; hereinafter: RAM) 30 and/or cache memory 32. The electronic device 12 may further include other removable/non-removable, volatile/nonvolatile computer system storage media. By way of example only, storage system 34 may be used to read from or write to non-removable, nonvolatile magnetic media (not shown in FIG. 6, commonly referred to as a "hard disk drive"). Although not shown in fig. 6, a magnetic disk drive for reading from and writing to a removable non-volatile magnetic disk (e.g., a "floppy disk"), and an optical disk drive for reading from or writing to a removable non-volatile optical disk (e.g., a compact disk read only memory (Compact Disc Read Only Memory; hereinafter CD-ROM), digital versatile read only optical disk (Digital Video Disc Read Only Memory; hereinafter DVD-ROM), or other optical media) may be provided. In such cases, each drive may be coupled to bus 18 through one or more data medium interfaces. Memory 28 may include at least one program product having a set (e.g., at least one) of program modules configured to carry out the functions of the various embodiments of the disclosure.
A program/utility 40 having a set (at least one) of program modules 42 may be stored in, for example, memory 28, such program modules 42 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each or some combination of which may include an implementation of a network environment. Program modules 42 generally perform the functions and/or methods in the embodiments described in this disclosure.
The electronic device 12 may also communicate with one or more external devices 14 (e.g., keyboard, pointing device, display 24, etc.), one or more devices that enable a user to interact with the electronic device 12, and/or any devices (e.g., network card, modem, etc.) that enable the electronic device 12 to communicate with one or more other computing devices. Such communication may occur through an input/output (I/O) interface 22. Also, the electronic device 12 may communicate with one or more networks, such as a local area network (Local Area Network; hereinafter: LAN), a wide area network (Wide Area Network; hereinafter: WAN) and/or a public network, such as the Internet, via the network adapter 20. As shown, the network adapter 20 communicates with other modules of the electronic device 12 over the bus 18. It should be appreciated that although not shown, other hardware and/or software modules may be used in connection with electronic device 12, including, but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, data backup storage systems, and the like.
The processing unit 16 executes various functional applications and data processing by running programs stored in the system memory 28, for example, implementing the methods mentioned in the foregoing embodiments.
In the description of the present specification, a description referring to terms "one embodiment," "some embodiments," "examples," "specific examples," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present disclosure. In this specification, schematic representations of the above terms are not necessarily directed to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, the different embodiments or examples described in this specification and the features of the different embodiments or examples may be combined and combined by those skilled in the art without contradiction.
Furthermore, the terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include at least one such feature. In the description of the present disclosure, the meaning of "a plurality" is at least two, such as two, three, etc., unless explicitly specified otherwise.
Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing specific logical functions or steps of the process, and additional implementations are included within the scope of the preferred embodiment of the present disclosure in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the embodiments of the present disclosure.
Logic and/or steps represented in the flowcharts or otherwise described herein, e.g., a ordered listing of executable instructions for implementing logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). In addition, the computer readable medium may even be paper or other suitable medium on which the program is printed, as the program may be electronically captured, via, for instance, optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner, if necessary, and then stored in a computer memory.
It should be understood that portions of the present disclosure may be implemented in hardware, software, firmware, or a combination thereof. In the above-described embodiments, the various steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. As with the other embodiments, if implemented in hardware, may be implemented using any one or combination of the following techniques, as is well known in the art: discrete logic circuits having logic gates for implementing logic functions on data signals, application specific integrated circuits having suitable combinational logic gates, programmable Gate Arrays (PGAs), field Programmable Gate Arrays (FPGAs), and the like.
Those of ordinary skill in the art will appreciate that all or a portion of the steps carried out in the method of the above-described embodiments may be implemented by a program to instruct related hardware, where the program may be stored in a computer readable storage medium, and where the program, when executed, includes one or a combination of the steps of the method embodiments.
Furthermore, each functional unit in the embodiments of the present disclosure may be integrated in one processing module, or each unit may exist alone physically, or two or more units may be integrated in one module. The integrated modules may be implemented in hardware or in software functional modules. The integrated modules may also be stored in a computer readable storage medium if implemented in the form of software functional modules and sold or used as a stand-alone product.
The above-mentioned storage medium may be a read-only memory, a magnetic disk or an optical disk, or the like. Although embodiments of the present disclosure have been shown and described above, it will be understood that the above embodiments are illustrative and not to be construed as limiting the present disclosure, and that variations, modifications, alternatives, and variations may be made to the above embodiments by one of ordinary skill in the art within the scope of the present disclosure.
Claims (10)
1. A method of photovoltaic state assessment, comprising:
acquiring multidimensional monitoring data of a photovoltaic power station under various working conditions;
based on a principal component analysis method, dimension reduction is carried out on the multi-dimensional monitoring data to obtain a target matrix;
performing hierarchical clustering analysis on the target matrix, and selecting the clustering number with the maximum CH function value as the optimal clustering number;
and evaluating the operation state of the photovoltaic power station based on the target matrix, the optimal cluster number and a component state evaluation algorithm model.
2. The method of claim 1, wherein the dimension reducing the multi-dimensional monitoring data based on principal component analysis to obtain a target matrix comprises:
dividing the multidimensional monitoring data to obtain M groups of samples, wherein each group of samples contains N characteristic parameters;
determining a first matrix, a mean value and a variance corresponding to the M groups of samples, and further converting the first matrix into a second matrix based on the mean value and the variance;
determining a data unit corresponding to the second matrix;
determining a contribution rate of the accumulated variance based on the data unit, and if the contribution rate is greater than a preset threshold, taking the corresponding first p components as main components;
determining a third matrix corresponding to the principal component;
the target matrix is determined based on a deviation between the third matrix and the first matrix.
3. The method of claim 2, wherein the determining the target matrix based on the deviation between the third matrix and the first matrix comprises:
performing normalization processing on the first matrix, and determining a fourth matrix based on the deviation between each group of samples after the normalization processing and each principal component in the third matrix;
and carrying out standardization processing on the fourth matrix to obtain a fifth matrix.
4. The method of claim 2, wherein the determining the data unit corresponding to the second matrix comprises:
wherein the second matrix is a matrix of M rows and N columns
Data elements X of said second matrix ij Expressed as:
wherein i=1, 2, …, M; j=1, 2, …, N, x j For the j-th characteristic parameter, x ij Is the ith row and the jth characteristic parameter.
5. The method as recited in claim 1, further comprising:
selecting an experimental scene with clear weather, and setting four operation states of normal operation, open-circuit fault, equipment aging and shadow shielding;
and analyzing the characteristic data sets based on the target matrix and the optimal cluster number so as to obtain the running state corresponding to each characteristic data set.
6. A photovoltaic state evaluation apparatus, characterized by comprising:
the acquisition module is used for acquiring multidimensional monitoring data of the photovoltaic power station under various working conditions;
the dimension reduction module is used for reducing dimensions of the multi-dimensional monitoring data based on a principal component analysis method so as to obtain a target matrix;
the first analysis module is used for carrying out hierarchical clustering analysis on the target matrix and selecting the clustering number when the CH function value is the maximum as the optimal clustering number;
and the evaluation module is used for evaluating the operation state of the photovoltaic power station based on the target matrix, the optimal cluster number and a component state evaluation algorithm model.
7. The apparatus of claim 6, wherein the dimension reduction module comprises:
the dividing unit is used for dividing the multidimensional monitoring data to obtain M groups of samples, and each group of samples contains N characteristic parameters;
a first determining unit, configured to determine a first matrix, a mean value, and a variance corresponding to the M groups of samples, and further convert the first matrix into a second matrix based on the mean value and the variance;
a second determining unit, configured to determine a data unit corresponding to the second matrix;
a third determining unit, configured to determine a contribution rate of the accumulated variance based on the data unit, and if the contribution rate is greater than a preset threshold, may use the first p components as main components;
a fourth determination unit configured to determine a third matrix corresponding to the principal component;
and a fifth determining unit configured to determine the target matrix based on a deviation between the third matrix and the first matrix.
8. The apparatus according to claim 7, wherein the fifth determining unit is specifically configured to:
performing normalization processing on the first matrix, and determining a fourth matrix based on the deviation between each group of samples after the normalization processing and each principal component in the third matrix;
and carrying out standardization processing on the fourth matrix to obtain a fifth matrix.
9. The apparatus according to claim 7, wherein the second determining unit is specifically configured to:
wherein the second matrix is a matrix of M rows and N columns
Data elements X of said second matrix ij Expressed as:
wherein i=1, 2, …, M; j=1, 2, …, N, x j For the j-th characteristic parameter, x ij Is the ith row and the jth characteristic parameter.
10. The apparatus as recited in claim 6, further comprising:
the setting module is used for selecting an experimental scene with clear weather and setting four running states of normal running, open-circuit fault, equipment aging and shadow shielding;
and the second analysis module is used for analyzing the characteristic data sets based on the target matrix and the optimal cluster number so as to obtain the running state corresponding to each characteristic data set.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311267431.XA CN117273489A (en) | 2023-09-27 | 2023-09-27 | Photovoltaic state evaluation method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311267431.XA CN117273489A (en) | 2023-09-27 | 2023-09-27 | Photovoltaic state evaluation method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117273489A true CN117273489A (en) | 2023-12-22 |
Family
ID=89215723
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311267431.XA Pending CN117273489A (en) | 2023-09-27 | 2023-09-27 | Photovoltaic state evaluation method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117273489A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117574303A (en) * | 2024-01-16 | 2024-02-20 | 深圳市九象数字科技有限公司 | Construction condition monitoring and early warning method, device, equipment and storage medium |
| CN117591814A (en) * | 2024-01-19 | 2024-02-23 | 北京志翔科技股份有限公司 | Data restoration method, device and equipment based on photovoltaic envelope |
| CN117977717A (en) * | 2024-04-01 | 2024-05-03 | 国网黑龙江省电力有限公司佳木斯供电公司 | Cold region wind-solar-thermal energy storage comprehensive energy collaborative management method and system |
-
2023
- 2023-09-27 CN CN202311267431.XA patent/CN117273489A/en active Pending
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117574303A (en) * | 2024-01-16 | 2024-02-20 | 深圳市九象数字科技有限公司 | Construction condition monitoring and early warning method, device, equipment and storage medium |
| CN117574303B (en) * | 2024-01-16 | 2024-05-07 | 深圳市九象数字科技有限公司 | Construction condition monitoring and early warning method, device, equipment and storage medium |
| CN117591814A (en) * | 2024-01-19 | 2024-02-23 | 北京志翔科技股份有限公司 | Data restoration method, device and equipment based on photovoltaic envelope |
| CN117591814B (en) * | 2024-01-19 | 2024-06-07 | 北京志翔科技股份有限公司 | Data restoration method, device and equipment based on photovoltaic envelope |
| CN117977717A (en) * | 2024-04-01 | 2024-05-03 | 国网黑龙江省电力有限公司佳木斯供电公司 | Cold region wind-solar-thermal energy storage comprehensive energy collaborative management method and system |
| CN117977717B (en) * | 2024-04-01 | 2024-06-11 | 国网黑龙江省电力有限公司佳木斯供电公司 | Cold region wind-solar-thermal energy storage comprehensive energy collaborative management method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112699913B (en) | Method and device for diagnosing abnormal relationship of household transformer in transformer area | |
| CN117273489A (en) | Photovoltaic state evaluation method and device | |
| CN111382542B (en) | Highway electromechanical device life prediction system facing full life cycle | |
| CN111459700B (en) | Equipment fault diagnosis method, diagnosis device, diagnosis equipment and storage medium | |
| CN110543903B (en) | Data cleaning method and system for GIS partial discharge big data system | |
| CN113884961B (en) | SOC calibration method, modeling device, computer equipment and medium | |
| CN105653427A (en) | Log monitoring method based on abnormal behavior detection | |
| CN112461537B (en) | Wind power gear box state monitoring method based on long-time and short-time neural network and automatic coding machine | |
| CN114861788A (en) | Load abnormity detection method and system based on DBSCAN clustering | |
| CN116361679A (en) | Intelligent cable life prediction method and system based on data driving | |
| CN113408548A (en) | Transformer abnormal data detection method and device, computer equipment and storage medium | |
| CN112132210A (en) | Electricity stealing probability early warning analysis method based on customer electricity consumption behavior | |
| CN112101471A (en) | Electricity stealing probability early warning analysis method | |
| CN114118219A (en) | Data-driven real-time abnormal detection method for health state of long-term power-on equipment | |
| CN116578436A (en) | Real-time online detection method based on asynchronous multielement time sequence data | |
| CN115659271A (en) | Sensor abnormality detection method, model training method, system, device, and medium | |
| CN114638039B (en) | Structural health monitoring characteristic data interpretation method based on low-rank matrix recovery | |
| CN115269319A (en) | CEPH distributed computer fault diagnosis method | |
| CN116956089A (en) | Training method and detection method for temperature anomaly detection model of electrical equipment | |
| KR20230075150A (en) | Method for managing system health | |
| CN112307671A (en) | Method for self-adapting to different large-scale equipment instrument state threshold values | |
| CN112001530A (en) | Predictive maintenance method and system for transformer oil chromatography online monitoring device | |
| Ma et al. | Visualization methodology of the health state for wind turbines based on dimensionality reduction techniques | |
| CN112541554B (en) | Multi-mode process monitoring method and system based on time constraint and nuclear sparse representation | |
| CN112884167B (en) | Multi-index anomaly detection method based on machine learning and application system thereof |
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 |