CN114139614A - Fisher photovoltaic module hot spot diagnosis method and system based on typical correlation analysis feature extraction - Google Patents
Fisher photovoltaic module hot spot diagnosis method and system based on typical correlation analysis feature extraction Download PDFInfo
- Publication number
- CN114139614A CN114139614A CN202111374913.6A CN202111374913A CN114139614A CN 114139614 A CN114139614 A CN 114139614A CN 202111374913 A CN202111374913 A CN 202111374913A CN 114139614 A CN114139614 A CN 114139614A
- Authority
- CN
- China
- Prior art keywords
- hot spot
- fisher
- data
- photovoltaic module
- correlation analysis
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000010219 correlation analysis Methods 0.000 title claims abstract description 25
- 238000000605 extraction Methods 0.000 title claims abstract description 21
- 238000000034 method Methods 0.000 title claims abstract description 21
- 238000003745 diagnosis Methods 0.000 title claims abstract description 19
- 238000012360 testing method Methods 0.000 claims abstract description 20
- 238000012549 training Methods 0.000 claims abstract description 15
- 238000004458 analytical method Methods 0.000 claims abstract description 8
- 238000012545 processing Methods 0.000 claims abstract description 8
- 238000007781 pre-processing Methods 0.000 claims abstract description 4
- 239000011159 matrix material Substances 0.000 claims description 13
- 239000013598 vector Substances 0.000 claims description 8
- 238000010606 normalization Methods 0.000 claims description 3
- 239000000126 substance Substances 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 claims description 2
- 238000002405 diagnostic procedure Methods 0.000 claims 7
- 238000003672 processing method Methods 0.000 claims 1
- 238000001514 detection method Methods 0.000 abstract description 5
- 238000010248 power generation Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 3
- 238000005286 illumination Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 230000032683 aging Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 210000003608 fece Anatomy 0.000 description 1
- 238000007667 floating Methods 0.000 description 1
- 238000013467 fragmentation Methods 0.000 description 1
- 238000006062 fragmentation reaction Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000002689 soil Substances 0.000 description 1
Images
Classifications
-
- 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
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- 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
-
- 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
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E10/00—Energy generation through renewable energy sources
- Y02E10/50—Photovoltaic [PV] energy
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Economics (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Biology (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Photovoltaic Devices (AREA)
Abstract
The invention provides a Fisher photovoltaic module hot spot diagnosis method based on typical correlation analysis feature extraction, which comprises the following steps of: s01, collecting photovoltaic data; s02, preprocessing data; s03, canonical correlation analysis; s04, constructing a training set and a testing set; s05, Fisher discriminant analysis; and S06, fault diagnosis. The invention also provides a Fisher photovoltaic module hot spot diagnosis system based on typical correlation analysis feature extraction. The method can obtain the conclusion whether the photovoltaic module has faults or not only through data processing and analysis, has low detection cost, solves the problems that the prior art depends on auxiliary equipment and the hot spot fault detection cost is high, has real and reliable output results, and is suitable for wide popularization and application.
Description
Technical Field
The invention belongs to the technical field of photovoltaic power generation, and particularly relates to a Fisher photovoltaic module hot spot diagnosis method and system based on typical correlation analysis feature extraction.
Background
Solar energy is widely applied to a photovoltaic power generation system as a clean and sustainable energy source, the related scientific research technical level of the solar energy is rapidly improved since 2013 countries greatly support the solar energy industry, the enterprise competitiveness is continuously enhanced, the market share is continuously expanded, and the quantity of new added devices is the first global.
Since the solar panels for photovoltaic power generation need to be erected in the outdoor natural environment, a plurality of failure problems are inevitably generated in part of the photovoltaic modules. The main faults of the photovoltaic module include open-circuit faults, short-circuit faults, module fragmentation, bypass diode failure, performance aging and the like. The hot spot phenomenon generated by the photovoltaic module due to shielding of objects such as floating soil, bird droppings, leaves and the like is one of the most common faults.
Because most of photovoltaic power generation systems are located on a roof with sufficient sunlight or in remote areas with severe environments, the automation degree of the manual inspection technology is low, the cost is huge, certain danger also exists, faults are difficult to find, maintenance and treatment cannot be performed in time, and economic loss is caused.
With the development of digital information technology, the fault research of photovoltaic components has also made a long-standing progress, and the existing intelligent detection technology mainly collects infrared information with the help of external equipment, such as an unmanned aerial vehicle. This approach increases the economic cost of photovoltaic power generation and the complexity of the system, and is not widely used.
Disclosure of Invention
In order to solve the technical problems, the invention aims to provide a Fisher photovoltaic module hot spot diagnosis method and system based on typical correlation analysis feature extraction, so as to solve the problems that the prior art depends on auxiliary equipment and is high in cost.
In order to solve the technical problems, the technical scheme adopted by the invention is as follows:
a Fisher photovoltaic module hot spot diagnosis method based on typical correlation analysis feature extraction comprises the following steps:
s01, collecting photovoltaic data;
s02, preprocessing data;
s03, canonical correlation analysis;
s04, constructing a training set and a testing set;
s05, Fisher discriminant analysis;
and S06, fault diagnosis.
S01 includes the following: and acquiring data X of a plurality of characteristic variables of the photovoltaic module in a normal state and a hot spot fault state to obtain a data set X.
S02 includes the following: for data set X is belonged to Rn×mCarrying out standardization processing, and then arbitrarily dividing the data set X into two subdata sets X according to the characteristic variables of the data set X1And X2；
Wherein, R represents a real number set, data X in the data set X are all real numbers, and n rows and m columns exist in the real number set R.
S03 includes the following: computing two subdata sets X1And X2The individual covariance and cross covariance of (a) are as follows:
wherein the content of the first and second substances,
is X1The covariance of (a) of (b),
is X2The covariance of (a) of (b),
is X1And X2Cross covariance of (2);
constructing a matrix gamma, and decomposing the singular value of the matrix gamma, wherein a formula adopted by the matrix gamma is expressed as:
wherein k represents the number of non-zero singular values, and k is less than or equal to min (N)1,N2) I.e. k and N1,N2Medium and small are consistent; lambdak＝diag(λ1…λk)；λ1≥λ2≥…≥λkIs a singular value; zetai，i＝1,…,N1And xij，j＝1,…,N2Is the corresponding singular vector; n is a radical of1Representing a subdata set X1The number of data of all the characteristic variables in the database; n is a radical of2Representing a subdata set X2The number of data of all the characteristic variables in the database;
calculating to obtain projection vectors a and b, wherein the adopted formula is as follows:
calculating to obtain a projection sample X1 ’And X2', the formula used is:
s04 includes the following: combine to new data set X '═ X'1 X′2]T∈R2×mAnd is divided into training sets X 'after normalizing the new data set X'tr∈R2×dAnd test set X't∈R2×(m-d)。
S05 includes the following: calculating an intra-class divergence matrix S of a training setwThe formula adopted is as follows:
wherein, XiRepresenting an ith sample, wherein the values of i are 0 and 1, when i is 0, the ith sample is a normal sample, and when i is 1, the ith sample is a fault sample; the normal sample is photovoltaic data collected in a normal state, and the fault sample is photovoltaic data collected in a hot spot fault state;
μirepresents the mean of the class i samples;
wherein m isiRepresenting the total number of the ith sample;
and introducing a Lagrange multiplier method to obtain the optimal discrimination direction:
wherein, mu0Represents the mean of normal samples; mu.s1Represents the mean of the fault samples.
S06 includes the following: classifying the test set based on the projection of a discrimination axis w, wherein the adopted formula is as follows:
y＝wTX′t (15)
identifying whether a fault occurs, if different types of points after projection can be distinguished, indicating that a hot spot fault occurs; if the points of different types are mixed together, the hot spot fault does not occur.
The characteristic variables include open circuit voltage, short circuit current, maximum power point voltage, maximum power point current, maximum power, fill factor, temperature, and illumination amplitude.
The method for the standardization treatment comprises the following steps: processing data x to between-1 and 1; adopts the formula of
Wherein mu represents mean value, sigma represents variance, i.e. n rows of data, each row is processed once, mean value is calculated, variance is calculated, and then each data x of the row is calculated by formula
The calculation yields results lying between-1 and 1.
The system of the Fisher photovoltaic module hot spot diagnosis method based on typical correlation analysis feature extraction is adopted.
The invention has the beneficial effects that: the method can obtain the conclusion whether the photovoltaic module has faults or not only through data processing and analysis, has low detection cost, solves the problems that the prior art depends on auxiliary equipment and the hot spot fault detection cost is high, has real and reliable output results, and is suitable for wide popularization and application.
In addition, the traditional Fisher discriminant analysis belongs to a linear analysis method, but the photovoltaic system belongs to a typical nonlinear system.
Drawings
FIG. 1 is a flow chart of hot spot fault diagnosis of the present invention.
Detailed Description
The Fisher photovoltaic module hot spot diagnosis method and system based on the typical correlation analysis feature extraction are further described in detail below with reference to the accompanying drawings and a specific implementation method.
As shown in fig. 1, a Fisher photovoltaic module hot spot diagnosis method based on typical correlation analysis feature extraction includes the following steps:
step 1: photovoltaic data is collected. The method comprises the following steps of collecting photovoltaic data in a normal state and various hot spot fault states, wherein main measurement parameters are as follows: open circuit voltage, short circuit current, maximum power point voltage, maximum power point current, maximum power, fill factor, temperature, illumination amplitude.
Step 2: and (4) preprocessing data. For data set X is belonged to Rn×mAnd carrying out standardization processing, and dividing into two subdata sets according to the characteristic variable parameters. The manner in which the two sub data sets are partitioned is arbitrary, such as 4 characteristic variables (X)1) And 4 characteristic variables (X)2) A set of, or 3, characteristic variables (X)1) And 5 characteristic variables (X)2) One group, and so on.
Normalization is the processing of data between-1 and 1. Adopts the formula of
Where μ represents the mean and σ represents the variance. For the n-line data set, each line is processed once, for example, the first line, the mean is calculated, the variance is calculated, and then each data of the line is formulated to obtain the result. And after changing a line, calculating the mean value and the variance, and obtaining a result by using a formula.
And step 3: typical correlation analysis. Calculating the individual covariance and cross covariance of the two subdata sets using the formula:
wherein, X1And X2For the two sub-data sets,
is X1The covariance of (a) of (b),
is X2The covariance of (a) of (b),
is X1And X2Cross covariance of (2);
constructing a matrix gamma, and decomposing the singular value of the matrix gamma, wherein a formula adopted by the matrix gamma is expressed as:
wherein k represents the number of non-zero singular values, and k is less than or equal to min (N)1,N2)。Λk＝diag(λ1…λk),λ1≥λ2≥…≥λkAre singular values. Zetai，i＝1,…,N1And xij，j＝1,…,N2Is the corresponding singular vector; n is a radical of1And N2Respectively represent two subdata sets X1And X2The number of data in the sequence. Singular values are k, the size of k and N1、N2Medium, and smaller. Each singular value has two singular vectors, left and right.
Calculating to obtain projection vectors a and b, wherein the adopted formula is as follows:
calculating to obtain a projection sample X1' and X2', the formula used is:
and 4, step 4: and constructing a training set and a testing set. Combine to new data set X '═ X'1 X′2]T∈R2×mAnd dividing the new data set X ' into a training set X ' after normalization 'tr∈R2×dAnd test set X't∈R2×(m-d)。
d is divided according to actual requirements. The original data set X is 2 rows and m columns, 2 rows and d columns are divided into a training set in the embodiment, and the remaining 2 rows and m-d columns are a testing set.
And 5: fisher discriminant analysis. Calculating an inter-class divergence matrix S of a training setbAnd an intra-class divergence matrix SwThe formula adopted is as follows:
Sb＝(μ1-μ0)(μ1-μ0)T
wherein the content of the first and second substances,
the mean value of the ith sample is obtained; m isiRepresenting the total number of class i samples, the values are 300 and 700, for example, below.
XiAnd representing the ith sample, wherein the value of i is 0 and 1, which indicates that the samples are two types in total, one type is a normal sample, and the other type is a fault sample.
In step 4, the present embodiment divides the training set and the test set, and both data sets include normal samples and fault samples. For example, 1000 samples are initially taken, 300 normal samples are obtained, and 700 hot spot failure samples are obtained. The ratio of the total weight of the components can be 1: 4, dividing the training set into a training set and a testing set, wherein the training set comprises 200 samples, 60 normal samples and 140 hot spot fault samples; there were 800 test sets with 240 normal samples and 560 hot spot samples.
And introducing a Lagrange multiplier method to obtain the optimal discrimination direction:
step 6: and (5) fault diagnosis. Classifying the test set based on the projection of a discrimination axis w, wherein the adopted formula is that y is equal to wTX′tAnd identifying whether a fault occurs. If the different types of points after projection can be distinguished, hot spot faults are shown; if the points of different types are mixed together, the hot spot fault does not occur.
w is the discrimination direction (i.e., discrimination axis), X'tAnd (4) obtaining a projection result y which is a two-dimensional vector for testing the set, and finally drawing a coordinate graph, wherein the result is the condition of looking at different types of points in the coordinate graph.
The points in different categories are two categories, namely a normal sample and a test sample, if the test sample is distinguished from the normal sample, the test sample is a fault, and if the test sample is mixed with the normal sample and is not distinguished, the test sample is normal and no fault occurs.
Meanwhile, the embodiment provides a system adopting the Fisher photovoltaic module hot spot diagnosis method based on the typical correlation analysis feature extraction.
The above description is only of the preferred embodiments of the present invention, and it should be noted that: it will be apparent to those skilled in the art that various modifications and adaptations can be made without departing from the principles of the invention and these are intended to be within the scope of the invention.
Claims (10)
1. A Fisher photovoltaic module hot spot diagnosis method based on typical correlation analysis feature extraction is characterized by comprising the following steps:
s01, collecting photovoltaic data;
s02, preprocessing data;
s03, canonical correlation analysis;
s04, constructing a training set and a testing set;
s05, Fisher discriminant analysis;
and S06, fault diagnosis.
2. The Fisher photovoltaic module hot spot diagnostic method based on canonical correlation analysis feature extraction of claim 1, wherein S01 comprises the following contents: and acquiring data X of a plurality of characteristic variables of the photovoltaic module in a normal state and a hot spot fault state to obtain a data set X.
3. The Fisher photovoltaic module hot spot diagnostic method based on canonical correlation analysis feature extraction of claim 2, wherein S02 comprises the following contents: for data set X is belonged to Rn×mCarrying out standardization processing, and then arbitrarily dividing the data set X into two subdata sets X according to the characteristic variables of the data set X1And X2；
Wherein, R represents a real number set, data X in the data set X are all real numbers, and n rows and m columns exist in the real number set R.
4. The Fisher photovoltaic module hot spot diagnostic method based on canonical correlation analysis feature extraction according to claim 3, wherein S03 includes the following contents: computing two subdata sets X1And X2The individual covariance and cross covariance of (a) are as follows:
wherein the content of the first and second substances,
is X1The covariance of (a) of (b),
is X2The covariance of (a) of (b),
is X1And X2Cross covariance of (2);
constructing a matrix gamma, and decomposing the singular value of the matrix gamma, wherein a formula adopted by the matrix gamma is expressed as:
wherein k represents the number of non-zero singular values, and k is less than or equal to min (N)1,N2) I.e. k and N1,N2Medium and small are consistent; lambdak＝diag(λ1…λk)；λ1≥λ2≥…≥λkIs a singular value; zetai，i＝1,…,N1And xij，j＝1,…,N2Is the corresponding singular vector; n is a radical of1Representing a subdata set X1The number of data of all the characteristic variables in the database; n is a radical of2Representing a subdata set X2The number of data of all the characteristic variables in the database;
calculating to obtain projection vectors a and b, wherein the adopted formula is as follows:
calculating to obtain a projection sample X1' and X2', the formula used is:
5. the Fisher photovoltaic module hot spot diagnostic method based on canonical correlation analysis feature extraction according to claim 4, wherein S04 includes the following contents: combine to new data set X '═ X'1 X′2]T∈R2×mAnd is divided into training sets X 'after normalizing the new data set X'tr∈R2×dAnd test set X't∈R2×(m-d)。
6. The Fisher photovoltaic module hot spot diagnostic method based on canonical correlation analysis feature extraction according to claim 5, wherein S05 includes the following contents: calculating an intra-class divergence matrix S of a training setwThe formula adopted is as follows:
wherein, XiRepresentsThe value of the ith sample is 0 and 1, when i is 0, the ith sample is a normal sample, and when i is 1, the ith sample is a fault sample; the normal sample is photovoltaic data collected in a normal state, and the fault sample is photovoltaic data collected in a hot spot fault state;
μirepresents the mean of the class i samples;
wherein m isiRepresenting the total number of the ith sample;
and introducing a Lagrange multiplier method to obtain the optimal discrimination direction:
wherein, mu0Represents the mean of normal samples; mu.s1Represents the mean of the fault samples.
7. The Fisher photovoltaic module hot spot diagnostic method based on canonical correlation analysis feature extraction according to claim 6, wherein S06 includes the following contents: classifying the test set based on the projection of a discrimination axis w, wherein the adopted formula is as follows:
y＝wTX′t (15)
identifying whether a fault occurs, if different types of points after projection can be distinguished, indicating that a hot spot fault occurs; if the points of different types are mixed together, the hot spot fault does not occur.
8. The Fisher photovoltaic module hot spot diagnostic method based on canonical correlation analysis feature extraction according to claim 2, wherein the feature variables include open circuit voltage, short circuit current, maximum power point voltage, maximum power point current, maximum power, fill factor, temperature, and light amplitude.
9. The Fisher photovoltaic module hot spot diagnosis method based on canonical correlation analysis feature extraction according to claim 3, wherein the normalization processing method is as follows: processing data x to between-1 and 1; adopts the formula of
Wherein mu represents mean value, sigma represents variance, i.e. n rows of data, each row is processed once, mean value is calculated, variance is calculated, and then each data x of the row is calculated by formula
The calculation yields results lying between-1 and 1.
10. The system adopting the Fisher photovoltaic module hot spot diagnosis method based on the canonical correlation analysis feature extraction as claimed in any one of claims 1 to 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111374913.6A CN114139614B (en) | 2021-11-18 | 2021-11-18 | Fisher photovoltaic module hot spot diagnosis method and system based on typical correlation analysis feature extraction |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111374913.6A CN114139614B (en) | 2021-11-18 | 2021-11-18 | Fisher photovoltaic module hot spot diagnosis method and system based on typical correlation analysis feature extraction |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114139614A true CN114139614A (en) | 2022-03-04 |
| CN114139614B CN114139614B (en) | 2022-09-23 |
Family
ID=80390152
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111374913.6A Active CN114139614B (en) | 2021-11-18 | 2021-11-18 | Fisher photovoltaic module hot spot diagnosis method and system based on typical correlation analysis feature extraction |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114139614B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115455730A (en) * | 2022-09-30 | 2022-12-09 | 南京工业大学 | Photovoltaic module hot spot fault diagnosis method based on complete neighborhood preserving embedding |
| CN115758284A (en) * | 2022-11-14 | 2023-03-07 | 南京工业大学 | Photovoltaic hot spot fault detection method and system based on fusion of nuclear entropy and information gain |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103971123A (en) * | 2014-05-04 | 2014-08-06 | 南京师范大学 | Hyperspectral image classification method based on linear regression Fisher discrimination dictionary learning (LRFDDL) |
| CN107103125A (en) * | 2017-04-01 | 2017-08-29 | 宁波大学 | A kind of method for diagnosing faults based on two classification Fisher discriminant analyses |
| WO2020023989A1 (en) * | 2018-08-03 | 2020-02-06 | Rehabswift Pty Ltd | Stroke rehabilitation method and system using a brain-computer interface (bci) |
| CN110874576A (en) * | 2019-11-14 | 2020-03-10 | 西安工程大学 | Pedestrian re-identification method based on canonical correlation analysis fusion features |
-
2021
- 2021-11-18 CN CN202111374913.6A patent/CN114139614B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103971123A (en) * | 2014-05-04 | 2014-08-06 | 南京师范大学 | Hyperspectral image classification method based on linear regression Fisher discrimination dictionary learning (LRFDDL) |
| CN107103125A (en) * | 2017-04-01 | 2017-08-29 | 宁波大学 | A kind of method for diagnosing faults based on two classification Fisher discriminant analyses |
| WO2020023989A1 (en) * | 2018-08-03 | 2020-02-06 | Rehabswift Pty Ltd | Stroke rehabilitation method and system using a brain-computer interface (bci) |
| CN110874576A (en) * | 2019-11-14 | 2020-03-10 | 西安工程大学 | Pedestrian re-identification method based on canonical correlation analysis fusion features |
Non-Patent Citations (4)
| Title |
|---|
| 张伟 等: "基于分维LLE和Fisher判别的故障诊断方法", 《仪器仪表学报》 * |
| 曹文谊: "人脸识别的一种神经网络方法研究", 《中国优秀博硕士学位论文全文数据库(硕士) 信息科技辑》 * |
| 杨斌 等: "基于独立特征选择核Fishier判别分析的电机轴承故障诊断", 《电子测量与仪器学报》 * |
| 魏赟: "兰州市农村居民人均可支配收入的典型相关分析", 《湖北农业科学》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115455730A (en) * | 2022-09-30 | 2022-12-09 | 南京工业大学 | Photovoltaic module hot spot fault diagnosis method based on complete neighborhood preserving embedding |
| CN115758284A (en) * | 2022-11-14 | 2023-03-07 | 南京工业大学 | Photovoltaic hot spot fault detection method and system based on fusion of nuclear entropy and information gain |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114139614B (en) | 2022-09-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Zhu et al. | Fault diagnosis approach for photovoltaic arrays based on unsupervised sample clustering and probabilistic neural network model | |
| Pierdicca et al. | Deep convolutional neural network for automatic detection of damaged photovoltaic cells | |
| Mehta et al. | Deepsolareye: Power loss prediction and weakly supervised soiling localization via fully convolutional networks for solar panels | |
| CN109660206B (en) | Wasserstein GAN-based photovoltaic array fault diagnosis method | |
| CN109873610B (en) | Photovoltaic array fault diagnosis method based on IV characteristic and depth residual error network | |
| CN109842373B (en) | Photovoltaic array fault diagnosis method and device based on space-time distribution characteristics | |
| CN114139614B (en) | Fisher photovoltaic module hot spot diagnosis method and system based on typical correlation analysis feature extraction | |
| CN109086793B (en) | Abnormity identification method for wind driven generator | |
| Liu et al. | Fault diagnosis approach for photovoltaic array based on the stacked auto-encoder and clustering with IV curves | |
| CN108009730B (en) | Photovoltaic power station system health state analysis method | |
| CN109766952B (en) | Photovoltaic array fault detection method based on partial least square method and extreme learning machine | |
| CN109670553B (en) | Photovoltaic array fault diagnosis method based on adaptive neural fuzzy inference system | |
| CN109672406B (en) | Photovoltaic power generation array fault diagnosis and classification method based on sparse representation and SVM | |
| Zaki et al. | Deep‐learning–based method for faults classification of PV system | |
| CN105141255A (en) | Fault diagnosis method of photovoltaic array | |
| Kuo et al. | Automatic detection, classification and localization of defects in large photovoltaic plants using unmanned aerial vehicles (UAV) based infrared (IR) and RGB imaging | |
| Liu et al. | Intelligent fault diagnosis of photovoltaic array based on variable predictive models and I–V curves | |
| CN109039280A (en) | Diagnosing failure of photovoltaic array method based on non-primary component data characteristics | |
| Yu et al. | Convolutional neural network with feature reconstruction for monitoring mismatched photovoltaic systems | |
| He et al. | Compound fault diagnosis for photovoltaic arrays based on multi-label learning considering multiple faults coupling | |
| CN116738355A (en) | Electric power multi-mode feature level fusion method considering data difference | |
| Tang et al. | Automatic defect identification of PV panels with IR images through unmanned aircraft | |
| Klobučar et al. | Detecting forest damage in CIR aerial photographs using a neural network | |
| Attouri et al. | Fault detection in photovoltaic systems using machine learning technique | |
| Naveen Venkatesh et al. | Photovoltaic Module Fault Detection Based on Deep Learning Using Cloud Computing |
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 |