CN117743958A - Photovoltaic array fault identification method and device and electronic equipment - Google Patents
Photovoltaic array fault identification method and device and electronic equipment Download PDFInfo
- Publication number
- CN117743958A CN117743958A CN202410184076.8A CN202410184076A CN117743958A CN 117743958 A CN117743958 A CN 117743958A CN 202410184076 A CN202410184076 A CN 202410184076A CN 117743958 A CN117743958 A CN 117743958A
- Authority
- CN
- China
- Prior art keywords
- photovoltaic array
- fault
- photovoltaic
- svm
- state
- 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
- 238000000034 method Methods 0.000 title claims abstract description 53
- 238000012706 support-vector machine Methods 0.000 claims abstract description 97
- 230000002159 abnormal effect Effects 0.000 claims abstract description 84
- 238000010248 power generation Methods 0.000 claims abstract description 31
- 230000032683 aging Effects 0.000 claims description 72
- 238000004088 simulation Methods 0.000 claims description 40
- 230000006870 function Effects 0.000 claims description 38
- 238000012549 training Methods 0.000 claims description 25
- 238000005457 optimization Methods 0.000 claims description 16
- 238000012360 testing method Methods 0.000 claims description 11
- 239000006185 dispersion Substances 0.000 claims description 10
- 238000010606 normalization Methods 0.000 claims description 9
- 238000012545 processing Methods 0.000 claims description 6
- 238000012795 verification Methods 0.000 claims description 3
- 230000008569 process Effects 0.000 description 19
- 238000004422 calculation algorithm Methods 0.000 description 12
- 238000010586 diagram Methods 0.000 description 7
- 235000005770 birds nest Nutrition 0.000 description 5
- 235000005765 wild carrot Nutrition 0.000 description 5
- 241000544061 Cuculus canorus Species 0.000 description 4
- 238000013528 artificial neural network Methods 0.000 description 4
- 238000003745 diagnosis Methods 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 238000013016 damping Methods 0.000 description 3
- 238000000605 extraction Methods 0.000 description 3
- 238000010801 machine learning Methods 0.000 description 3
- 238000013507 mapping Methods 0.000 description 3
- 238000010845 search algorithm Methods 0.000 description 3
- 230000006978 adaptation Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 238000003491 array Methods 0.000 description 2
- 239000003990 capacitor Substances 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 230000009977 dual effect Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000000926 separation method Methods 0.000 description 2
- NAWXUBYGYWOOIX-SFHVURJKSA-N (2s)-2-[[4-[2-(2,4-diaminoquinazolin-6-yl)ethyl]benzoyl]amino]-4-methylidenepentanedioic acid Chemical compound C1=CC2=NC(N)=NC(N)=C2C=C1CCC1=CC=C(C(=O)N[C@@H](CC(=C)C(O)=O)C(O)=O)C=C1 NAWXUBYGYWOOIX-SFHVURJKSA-N 0.000 description 1
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 229910052799 carbon Inorganic materials 0.000 description 1
- 238000013145 classification model Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000008571 general function Effects 0.000 description 1
- 230000006698 induction Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000017448 oviposition Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000011426 transformation method Methods 0.000 description 1
Landscapes
- Photovoltaic Devices (AREA)
Abstract
The invention relates to the technical field of photovoltaic power generation, and discloses a photovoltaic array fault identification method and device and electronic equipment, wherein the method comprises the following steps: establishing a topological structure of the grid-connected photovoltaic power generation system based on the power grid operation parameters; simulating the operation condition of the photovoltaic array under a preset abnormal condition based on the topological structure to obtain a first output characteristic of the photovoltaic array; comparing the first output characteristic with the second output characteristic of the photovoltaic array in a normal operation state to generate a three-dimensional fault characteristic quantity set; building a SVM support vector machine fault recognition model according to the three-dimensional fault feature quantity set, and optimizing penalty factors and kernel function parameters of the SVM fault recognition model to obtain a target SVM fault recognition model; and verifying the validity of the target three-dimensional fault characteristic quantity based on the target SVM fault identification model so as to identify faults of the photovoltaic array. The method and the device can improve the accuracy of identifying the faults of the photovoltaic array.
Description
Technical Field
The invention relates to the technical field of photovoltaic power generation, in particular to a photovoltaic array fault identification method and device and electronic equipment.
Background
Since the 'double carbon' target is proposed, suburban distributed photovoltaic is rapidly increased, and related photovoltaic industry is increasingly developed, but a photovoltaic array is easy to generate various faults due to complex working environment, so that the operation reliability and the energy conversion efficiency of a photovoltaic system are affected. How to introduce mature and efficient artificial intelligence algorithms into the field of photovoltaic array fault diagnosis is also gaining attention to students and researchers.
The photovoltaic system is used as an important component of new energy and runs in a complex and random environment for a long time. When the inside of the battery unit of the photovoltaic module is oxidized, the battery unit is not counted to run for a long time and the like to cause abnormal aging states with different degrees, the output voltage and current parameters of the array are reduced with different degrees. When the photovoltaic array is in a local shadow state with different degrees, the maximum power point voltage and the maximum power point current of the output characteristic of the array are influenced, so that the output power of the photovoltaic array is distorted, the output stability is influenced, and the power generation efficiency is reduced.
And the number of photovoltaic arrays of a power grid is large, and the whole photovoltaic system cannot safely and effectively operate due to faults of components or arrays, so that a person skilled in the art is urgent to provide a photovoltaic array fault identification method with simple process and high identification speed.
The machine learning method in the photovoltaic array intelligent detection method is mostly applied to the field of array fault recognition, the extracted fault characteristic data are input into a machine learning algorithm for model training, an intelligent fault recognition model is obtained, and quick and accurate intelligent learning classification of the photovoltaic array fault mode is realized.
The machine learning method commonly used at present is mainly a neural network and improved algorithms of various neural networks. However, the number of middle layer nodes of the neural network algorithm is difficult to determine, so that the neural network is easy to fall into a local optimum problem in learning and training, the calculation process is complex, and the accuracy of the photovoltaic array fault identification result is reduced.
Disclosure of Invention
The embodiment of the invention aims to provide a photovoltaic array fault identification method and device and electronic equipment, which can solve the problem of reduced accuracy of an identification result in the existing photovoltaic array fault identification scheme.
In order to solve the technical problems, the invention provides the following technical scheme:
the embodiment of the invention provides a photovoltaic array fault identification method, which comprises the following steps:
establishing a topological structure of the grid-connected photovoltaic power generation system based on the power grid operation parameters;
simulating the operation condition of the photovoltaic array under a preset abnormal condition based on the topological structure of the grid-connected photovoltaic power generation system to obtain a first output characteristic of the photovoltaic array;
Comparing the first output characteristic with a second output characteristic of the photovoltaic array in a normal operation state to generate a three-dimensional fault characteristic quantity set;
building an SVM fault recognition model according to the three-dimensional fault characteristic quantity set, and optimizing penalty factors and kernel function parameters of the SVM fault recognition model to obtain a target SVM fault recognition model;
and verifying the validity of the target three-dimensional fault characteristic quantity based on the target SVM fault identification model so as to identify faults of the photovoltaic array.
Optionally, the step of simulating the operation condition of the photovoltaic array under the preset abnormal condition based on the topological structure of the grid-connected photovoltaic power generation system to obtain the first output characteristic of the photovoltaic array includes:
establishing a simulation model based on the topological structure and a preset simulation platform;
performing photovoltaic array fault simulation under preset abnormal conditions on the simulation model, and acquiring first output characteristics of a corresponding photovoltaic array under each abnormal condition, wherein the preset abnormal conditions comprise: the photovoltaic array is in an abnormal aging state with different degrees and in a state with different degrees of local shadows.
Optionally, the photovoltaic array is subjected to different degrees of abnormal aging states including: a first group of strings in the photovoltaic array are aged to a first degree, and a second group of strings are normal; a first set of strings in the photovoltaic array are subject to a second degree of aging, the second set of strings being normal; the first set of strings and the second set of strings in the photovoltaic array are both aged;
The state in which the photovoltaic array has different degrees of local shadows includes: irradiance of a single group of string photovoltaic modules in the photovoltaic array is 0, and irradiance of a plurality of groups of string photovoltaic modules in the photovoltaic array is 0.
Optionally, the step of generating the three-dimensional fault feature set by comparing the first output characteristic with a second output characteristic of the photovoltaic array in a normal operation state includes:
aiming at the abnormal aging state of each degree, analyzing the output characteristics corresponding to the abnormal aging state, and determining the maximum power point voltage and the maximum power point current of the photovoltaic array;
comparing the maximum power point voltage and the maximum power point current corresponding to the abnormal aging state of each degree with the maximum power point voltage and the maximum power point current in the normal operation state of the photovoltaic array to obtain a second output characteristic in the abnormal aging state;
aiming at the state of the partial shadow of each degree, analyzing the output characteristic corresponding to the state of the partial shadow, and determining the number of step turns of the U-I curve of the photovoltaic array;
and taking the number of step turns of each U-I curve as a second output characteristic in a partial shadow state.
Optionally, building an SVM support vector machine fault recognition model according to the three-dimensional fault feature quantity set, and optimizing a penalty factor and a kernel function parameter of the SVM fault recognition model to obtain a target SVM fault recognition model, including:
performing dispersion normalization processing on the three-dimensional fault characteristic quantity set to obtain a target three-dimensional fault characteristic quantity set; the target three-dimensional fault characteristic quantity group comprises a plurality of groups of three-dimensional fault characteristic quantities formed by the number of U-I curve step turning points based on the maximum power point voltage and the maximum power point current of the photovoltaic array;
dividing fault characteristic quantities in the target three-dimensional fault characteristic quantity group into a training set and a testing set;
and constructing an initial SVM fault recognition model, and carrying out iterative optimization on the penalty factors and the kernel function parameters of the initial SVM fault recognition model according to the training set until the iterative optimization cut-off condition is met, so as to obtain a target SVM fault recognition model.
The embodiment of the invention also provides a photovoltaic array fault identification device, which comprises:
the building module is used for building a topological structure of the grid-connected photovoltaic power generation system based on the power grid operation parameters;
the simulation module is used for simulating the operation condition of the photovoltaic array under the preset abnormal condition based on the topological structure of the grid-connected photovoltaic power generation system to obtain a first output characteristic of the photovoltaic array;
The generating module is used for comparing the first output characteristic with the second output characteristic of the photovoltaic array in a normal operation state to generate a three-dimensional fault characteristic quantity set;
the model optimization module is used for building an SVM fault recognition model according to the three-dimensional fault characteristic quantity set, and optimizing penalty factors and kernel function parameters of the SVM fault recognition model to obtain a target SVM fault recognition model;
and the identification module is used for carrying out validity verification on the target three-dimensional fault characteristic quantity based on the target SVM fault identification model so as to carry out fault identification on the photovoltaic array.
Optionally, the simulation module includes:
the first sub-module is used for establishing a simulation model based on the topological structure of the grid-connected photovoltaic power generation system and a preset simulation platform;
the second sub-module is used for carrying out photovoltaic array fault simulation under preset abnormal conditions on the simulation model, and obtaining first output characteristics of the corresponding photovoltaic array under each abnormal condition, wherein the preset abnormal conditions comprise: the photovoltaic array is in an abnormal aging state with different degrees and in a state with different degrees of local shadows.
Optionally, the photovoltaic array is subjected to different degrees of abnormal aging states including: a first group of strings in the photovoltaic array are aged to a first degree, and a second group of strings are normal; a first set of strings in the photovoltaic array are subject to a second degree of aging, the second set of strings being normal; the first set of strings and the second set of strings in the photovoltaic array are both aged;
The state in which the photovoltaic array has different degrees of local shadows includes: irradiance of a single group of string photovoltaic modules in the photovoltaic array is 0, and irradiance of a plurality of groups of string photovoltaic modules in the photovoltaic array is 0.
Optionally, the generating module includes:
the third sub-module is used for analyzing the output characteristics corresponding to the abnormal aging state according to the abnormal aging state of each degree and determining the maximum power point voltage and the maximum power point current of the photovoltaic array;
the fourth sub-module is used for comparing the maximum power point voltage and the maximum power point current corresponding to the abnormal aging state of each degree with the maximum power point voltage and the maximum power point current in the normal operation state of the photovoltaic array to obtain a second output characteristic in the abnormal aging state;
a fifth sub-module, configured to analyze, for each degree of local shadow state, an output characteristic corresponding to the local shadow state, and determine a number of step turns of a U-I curve of the photovoltaic array;
and a sixth sub-module, configured to take the number of step turns of each U-I curve as a second output characteristic in a partial shadow state.
Optionally, the model optimization module includes:
A seventh sub-module, configured to perform dispersion normalization processing on the three-dimensional fault characteristic quantity set, to obtain a target three-dimensional fault characteristic quantity set; the target three-dimensional fault characteristic quantity group comprises a plurality of groups of three-dimensional fault characteristic quantities formed by the number of U-I curve step turning points based on the maximum power point voltage and the maximum power point current of the photovoltaic array;
an eighth sub-module, configured to divide the fault feature values in the target three-dimensional fault feature value set into a training set and a test set;
and the ninth sub-module is used for building an initial SVM fault recognition model, and carrying out iterative optimization on the penalty factors and the kernel function parameters of the initial SVM fault recognition model according to the training set until the iterative optimization cut-off condition is met, so as to obtain a target SVM fault recognition model.
The embodiment of the invention provides electronic equipment, which comprises a processor, a memory and a program or an instruction stored on the memory and capable of running on the processor, wherein the program or the instruction realizes the steps of any one of the photovoltaic array fault identification methods when being executed by the processor.
The embodiment of the invention provides a readable storage medium, wherein a program or an instruction is stored on the readable storage medium, and the program or the instruction realizes the steps of any one of the photovoltaic array fault identification methods when being executed by a processor.
According to the photovoltaic array fault identification scheme provided by the embodiment of the invention, a topological structure of a grid-connected photovoltaic power generation system is established based on power grid operation parameters; simulating the operation condition of the photovoltaic array under a preset abnormal condition based on the topological structure to obtain a first output characteristic of the photovoltaic array; comparing the first output characteristic with the second output characteristic of the photovoltaic array in a normal operation state to generate a three-dimensional fault characteristic quantity set; building an SVM fault recognition model according to the three-dimensional fault characteristic quantity set, and optimizing penalty factors and kernel function parameters of the SVM fault recognition model to obtain a target SVM fault recognition model; and verifying the validity of the target three-dimensional fault characteristic quantity based on the target SVM fault identification model so as to identify faults of the photovoltaic array. According to the photovoltaic array fault identification scheme, the SVM estimates expected risks based on a structural risk minimization principle, so that the problem of overfitting in the model training process can be solved, and the model based on SVM fault identification has good classification and discrimination capability; in addition, the SVM fault recognition model is trained through the three-dimensional fault feature quantity group, so that the accuracy of the SVM fault recognition model in recognizing the faults of the photovoltaic array can be improved.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the invention. In the drawings:
FIG. 1 is a flow chart illustrating a method for identifying faults in a photovoltaic array according to an embodiment of the present application;
FIG. 2 is a topology diagram illustrating a grid-tied photovoltaic power generation system according to an embodiment of the present application;
FIGS. 3 (a), (b) are graphs showing photovoltaic array output characteristics under three abnormal aging faults according to embodiments of the present application;
FIGS. 4 (a), (b) are graphs showing photovoltaic array output characteristics under two partial shadow faults according to embodiments of the present application;
FIG. 5 is a flow chart illustrating the failure recognition of a photovoltaic array based on an improved support vector failure recognition model in accordance with an embodiment of the present application;
FIG. 6 is a diagram showing a support vector machine classification according to an embodiment of the present application;
FIG. 7 is a search flow chart illustrating a cuckoo search algorithm according to an embodiment of the present application;
FIG. 8 is a graph showing fitness evolution according to an embodiment of the present application;
FIG. 9 is a graph showing the failure recognition accuracy of the improved SVM failure recognition model to the sample training set according to the embodiments of the present application;
FIG. 10 is a graph showing the failure recognition accuracy of the improved SVM failure recognition model to the sample test set according to the embodiments of the present application;
FIG. 11 is a block diagram illustrating a photovoltaic array fault identification device according to an embodiment of the present application;
fig. 12 is a block diagram showing a configuration of an electronic apparatus according to an embodiment of the present application.
Detailed Description
The invention will be described in detail below with reference to the drawings in connection with embodiments. It should be noted that, without conflict, the embodiments of the present invention and features of the embodiments may be combined with each other.
The following detailed description is exemplary and is intended to provide further details of the invention. Unless defined otherwise, all technical terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments in accordance with the invention.
In order to make the technical problems, technical solutions and advantages to be solved more apparent, the following detailed description will be given with reference to the accompanying drawings and specific embodiments.
The following describes in detail the photovoltaic array fault recognition scheme provided in the embodiment of the present application through specific embodiments and application scenarios thereof with reference to the accompanying drawings.
As shown in fig. 1, the method for identifying a photovoltaic array fault according to the embodiment of the present application includes the following steps:
step 101: and establishing a topological structure of the grid-connected photovoltaic power generation system based on the power grid operation parameters.
In the embodiment of the application, the topological structure of the grid-connected photovoltaic power generation system is established by considering the operation parameters of the power grid in combination with the actual working condition of the photovoltaic array in the complex environment.
Step 102: and simulating the operation condition of the photovoltaic array under the preset abnormal condition based on the topological structure of the grid-connected photovoltaic power generation system, and obtaining the first output characteristic of the photovoltaic array.
Optionally, the method for obtaining the first output characteristic of the photovoltaic array based on the operation condition of the photovoltaic array under the preset abnormal condition based on the topological structure of the grid-connected photovoltaic power generation system may be as follows:
firstly, establishing a simulation model based on a topological structure of a grid-connected photovoltaic power generation system and a preset simulation platform;
the preset simulation platform may include, but is not limited to: matlab/Simulink simulation platform.
And secondly, carrying out photovoltaic array fault simulation on the simulation model under the preset abnormal conditions, and acquiring first output characteristics of the corresponding photovoltaic array under each abnormal condition.
The preset abnormal conditions comprise: the photovoltaic array is in an abnormal aging state with different degrees and in a state with different degrees of local shadows.
In the actual implementation process, a simulation model is established to simulate the faults of the photovoltaic array under the complex working condition, and the first output characteristics of the photovoltaic array when different degrees of abnormal aging and different degrees of local shadow faults occur are obtained.
The occurrence of different degrees of abnormal aging states of the photovoltaic array comprises: a first group of strings in the photovoltaic array are aged to a first degree, and a second group of strings are normal; the first group of strings in the photovoltaic array are aged to a second degree, and the second group of strings are normal; the first group of strings and the second group of strings in the photovoltaic array are aged; the state in which the photovoltaic array has different degrees of local shadows includes: irradiance of a single group of string photovoltaic modules in the photovoltaic array is 0, and irradiance of a plurality of groups of string photovoltaic modules in the photovoltaic array is 0.
When an abnormal aging fault occurs in a component in the array, the internal resistance of the failed component becomes large, i.e., the series resistance increases in the equivalent circuit of the component. Thus, by varying the series resistance values of the strings in the array, aging faults of the array assembly can be simulated. The local shadow faults are achieved by setting irradiance of the photovoltaic module.
It should be noted that, the above-mentioned states are merely specific states including the normal aging state and the state of different degrees of local shadows, which are simulated by way of example, and in the actual implementation process, a person skilled in the art may flexibly set the specific states included in the above-mentioned two types of states according to actual requirements, which is not limited herein.
Step 103: and comparing the first output characteristic with the second output characteristic of the photovoltaic array in a normal operation state to generate a three-dimensional fault characteristic quantity set.
The method for generating the three-dimensional fault feature set may optionally compare the first output characteristic with the second output characteristic under the normal operation state of the photovoltaic array as follows:
aiming at the abnormal aging state of each degree, analyzing the output characteristics corresponding to the abnormal aging state, and determining the maximum power point voltage and the maximum power point current of the photovoltaic array; comparing the maximum power point voltage and the maximum power point current corresponding to the abnormal aging state of each degree with the maximum power point voltage and the maximum power point current in the normal operation state of the photovoltaic array to obtain a second output characteristic in the abnormal aging state; aiming at the state of the partial shadow of each degree, analyzing the output characteristic corresponding to the state of the partial shadow, and determining the number of U-I curve step turns of the photovoltaic array; the number of step turns of each U-I curve is taken as a second output characteristic in a partial shadow state.
In the actual implementation process, when the first output characteristic of the photovoltaic array is analyzed, aiming at abnormal aging faults with different degrees, the U of the array m (i.e., maximum power point voltage) and I m Since the maximum power point current becomes smaller as the degree of aging increases, um and Im are selected to identify abnormal aging failure. Aiming at partial shadow faults of slight and serious degrees, introducing the number of step turns of U-I curve of the photovoltaic array, and verifying U m 、I m The effectiveness of the two degrees of partial shading is discriminated as a feature quantity. The maximum power point voltage U of the photovoltaic array is proposed m Maximum power point current I m The U-I curve step inflection points are formed into the three-dimensional fault characteristic quantity.
Step 104: and building an SVM fault recognition model according to the three-dimensional fault characteristic quantity set, and optimizing penalty factors and kernel function parameters of the SVM fault recognition model to obtain a target SVM fault recognition model.
The support vector machine (support vector machines, SVM) is a two-class model whose basic model is a linear classifier defined at maximum separation in feature space, the maximum separation distinguishing it from the perceptron; the SVM also includes a kernel technique, which makes it a substantially nonlinear classifier.
Optionally, building an SVM fault recognition model according to the three-dimensional fault feature quantity set, and optimizing penalty factors and kernel function parameters of the SVM fault recognition model, wherein the mode of obtaining the target SVM fault recognition model can be as follows:
Performing dispersion normalization processing on the three-dimensional fault characteristic quantity set to obtain a target three-dimensional fault characteristic quantity set; the target three-dimensional fault characteristic quantity group comprises a plurality of three-dimensional fault characteristic quantities formed by the maximum power point voltage and the maximum power point current based on the photovoltaic array and the number of U-I curve step turns;
dividing fault characteristic quantities in the target three-dimensional fault characteristic quantity group into a training set and a testing set;
constructing an initial SVM fault recognition model, and according to a punishment factor and kernel function parameters of the training set to the initial SVM fault recognition modelγAnd performing iterative optimization, namely optimizing until the iterative optimization cut-off condition is met, and obtaining the target SVM fault recognition model.
Step 105: and verifying the validity of the target three-dimensional fault characteristic quantity based on the target SVM fault identification model so as to identify faults of the photovoltaic array.
The target three-dimensional fault feature may be one or more three-dimensional fault features selected from the set of three-dimensional fault features. One or more three-dimensional fault signatures in the test set may also be partitioned for the target three-dimensional fault signature set.
According to the photovoltaic array fault identification method, a grid-connected photovoltaic power generation system topological structure is established based on power grid operation parameters; simulating the operation condition of the photovoltaic array under a preset abnormal condition based on the topological structure to obtain a first output characteristic of the photovoltaic array; comparing the first output characteristic with the second output characteristic of the photovoltaic array in a normal operation state to generate a three-dimensional fault characteristic quantity set; building an SVM fault recognition model according to the three-dimensional fault characteristic quantity set, and optimizing penalty factors and kernel function parameters of the SVM fault recognition model to obtain a target SVM fault recognition model; and verifying the validity of the target three-dimensional fault characteristic quantity based on the SVM fault identification model so as to carry out fault identification on the photovoltaic array. According to the photovoltaic array fault identification method, the SVM estimates the expected risk based on the structural risk minimization principle, so that the problem of overfitting in the model training process can be overcome, and the model based on SVM fault identification has good classification and discrimination capability; in addition, the SVM fault recognition model is trained through the three-dimensional fault feature quantity group, so that the accuracy of the SVM fault recognition model in recognizing the faults of the photovoltaic array can be improved.
The following describes a method for identifying a photovoltaic array fault provided in an embodiment of the present application with a specific example.
In the specific example, the topological structure of the grid-connected photovoltaic power generation system is established by considering the operation parameters of the power grid in combination with the actual working condition of the photovoltaic array in the complex environment. Analyzing the output characteristics of the photovoltaic array, aiming at abnormal aging faults with different degrees, and U of the array m And I m As the aging degree increases and becomes smaller, U is selected m 、I m And identifying the abnormal aging fault. Aiming at partial shadow faults of slight and serious degrees, introducing the number of step turns of U-I curve of the photovoltaic array, and verifying U m 、I m The effectiveness of the two degrees of partial shading is discriminated as a feature quantity. The maximum power point voltage U of the photovoltaic array is proposed m Maximum power point current I m The U-I curve step inflection points are formed into the three-dimensional fault characteristic quantity.
Then, based on U m 、I m And constructing an SVM (support vector machine) fault recognition model, optimizing, namely optimizing, a penalty factor and a kernel function parameter gamma of the SVM fault recognition model, and verifying the validity of the selected three-dimensional fault feature based on the improved SVM fault recognition model, namely a target SVM fault recognition model, so as to accurately recognize the faults of the photovoltaic array.
This specific example includes the following processes S1-S3:
s1: and in combination with the actual working condition of the photovoltaic array in a complex environment, the grid operation parameters are considered, a Matlab/Simulink simulation platform is utilized to establish a topological structure of the grid-connected photovoltaic power generation system, and a topological structure diagram of the constructed grid-connected photovoltaic power generation system is shown in figure 2. L (L) 1 、L 2 For filtering inductance, C dc C is a filter capacitor, T 1 ~T 6 The switching tube is a switching tube of a photovoltaic grid-connected inverter circuit, and R is a passive damping resistor.
In order to meet the stability requirement of the grid-connected system, the grid-connected current harmonic wave is reduced, and the resonance problem is restrained by adopting a passive damping design. The selected filter circuit is determined to be an LCL type filter with a passive damping resistor R connected in series in a branch circuit of the filter capacitor C.
An exemplary photovoltaic array is composed of 9×8 photovoltaic modules connected in series-parallel (SP) mode, and key parameters of the simulation model of the photovoltaic system are shown in table 1:
table 1 photovoltaic system key parameter settings
S2: based on a simulation model, photovoltaic array fault simulation under different working states is carried out, the output characteristics of the photovoltaic array under the running conditions of abnormal aging, local shadow and the like, namely, the first output characteristics, are obtained, the output characteristics of the photovoltaic array are analyzed, and multidimensional fault feature extraction is carried out on different degrees of abnormal aging and different degrees of local shadow faults. The simulated photovoltaic array fault types in this particular example are shown in table 2.
Table 2 description of the operating states
1) An exemplary abnormal aging fault signature extraction method is as follows:
when an abnormal aging fault occurs in a component in the photovoltaic array, the internal resistance of the failed component becomes large, i.e., the series resistance increases in the equivalent circuit of the component. Thus by varying the series resistance of the strings in the arrayR s Aging faults of the array assembly can be simulated.
Simulating the abnormal aging fault conditions of the array strings, and respectively designing slight aging fault conditions: aging of the string 1 and normal of the string 2; general aging: the aging degree of the string 1 is deepened, and the string 2 is normal; severe aging: three different fault conditions of aging faults of different degrees occur in the group string 1 and the group string 2 respectively. The simulated aging resistance settings of the photovoltaic array at this time are shown in table 3:
TABLE 3 series resistance setting for array strings of abnormal burn-in faults
The output characteristics of the photovoltaic array under three abnormal aging faults obtained through simulation are shown in fig. 3 (a) and (b). When different degrees of abnormal ageing faults occur in group strings in a photovoltaic array, the arrayU oc AndI sc almost no change, but with increasing degree of aging, the arrayU m AndI m Gradually becoming smaller, the overall system power also decreases as the degree of aging increases.
2) An exemplary local shadow fault signature extraction method is as follows:
the local shadow faults are realized by setting irradiance of the photovoltaic module, and two different degrees of local shadow faults are considered in the specific example, namely slight shielding and serious shielding, as shown in table 4:
TABLE 4 degree of local shadow failure
The simulation results, namely the output characteristics of the photovoltaic array under the partial shadow faults are shown in fig. 4 (a) and (b), and the output characteristics of the photovoltaic array under the partial shadow faults and the normal state with different degrees are compared and analyzed. When the group strings are normal, the U-I curve output by the photovoltaic array is smoother, and when two partial shadow faults occur, the U-I curve of the photovoltaic array becomes stepped to generate inflection points, and the larger the shadow shielding area is, the steeper the steps are.
When the photovoltaic array has a local shadow fault, a step inflection point appears on the U-I curve, but the U-I curve is not normal, so the photovoltaic array is selectedU-IThe number of curve step turns is used as a characteristic quantity to distinguish local shadow faults and distinguish other states.
Considering that the number of step turns of the U-I curve cannot effectively distinguish local shadow faults of different degrees, the method is based on the condition of different shade numbersThe analysis of the change of the voltage and current parameters under the shadow shielding area can show that the photovoltaic array has different degrees of local shadow faults U m 、I m The variation is large, soU m 、I m As a feature quantity, two types of local shadow faults can be effectively distinguished.
S3: based onU m 、I m 、U-IAnd (3) improving an SVM fault recognition model according to the three-dimensional fault characteristic quantity formed by the curve ladder turning points, and carrying out fault recognition on the photovoltaic array based on the improved SVM fault recognition model.
The fault identification flow of the photovoltaic array based on the improved SVM fault identification model is shown in fig. 5.
1) Based on the built 9X 8 photovoltaic array simulation model, setting the irradiance change range to be 200-1200W/m 2 . The photovoltaic array obtains 90 groups of sample data under six working states of normal, three different degrees of abnormal aging and two different degrees of local shadows, and the total number of the sample data is 540. 360 sets of sample data under each running state are taken as training samples, and 180 sets of sample data are taken as test samples. The sample data is the first output characteristic.
2) The sample data is preprocessed to eliminate sample data distortion, noise, distortion, etc. caused during the acquisition phase. The data preprocessing adopts a dispersion normalization method.
Because the units of the collected sample data are not uniform, the numerical values of all parameters are greatly different, if the unprocessed sample data are directly input into an SVM fault recognition model, the convergence and the accuracy of classification can be affected, so that the efficiency of fault recognition is reduced, the classification is not facilitated, and therefore, the collected and obtained fault sample data must be subjected to normalization processing in units and numerical values, so that three parameters are agreed in order of magnitude and units.
The dispersion normalization adopts the difference value between the maximum value and the minimum value of a certain parameter in the sample data set as the dispersion value, and the ratio of the difference value between each parameter value and the minimum value in the sample to be processed and the dispersion value is used as the normalized result, so that a data set is formed and is divided into a training set and a testing set for input. The order of magnitude of the characteristic parameters can be unified through dispersion normalization, and the conversion formula is as follows:
(1)
in the method, in the process of the invention,X n for a certain parameter value of the sample to be processed,X min andX max for maximum and minimum values of a certain parameter in the sample dataset,Y min andY max the lower limit of the range and the upper limit of the range respectively,Y n is the normalized result.
3) And constructing an initial SVM fault recognition model, and determining the selection of the kernel function and the value range of algorithm parameters including the kernel function parameters and penalty factors. As shown in the support vector machine classification diagram of FIG. 6, the optimal classification hyperplane of the support vector machine can be represented as onemDimension hyperplane:
(2)
in the method, in the process of the invention,ωis a weight vector of the hyperplane,bis biased, R m Representing m dimensions is a set of real numbers, and R represents a set of real numbers.
Searching the optimal classification hyperplane of the support vector machine, i.e. the maximum classification interval, can be realized by converting into solving the following constraint problems:
(3)
From equation (3), it can be seen that solving the objective function of the support vector machine is a quadratic programming problem, thus converting the problem into another dual problem:
(4)
and then introducing a Lagrangian function for solving the corresponding dual problem:
(5)
wherein alpha is greater than or equal to 0 and is Lagrangian multiplier.
Will Lagrangian functionL(ω,b,α) Respectively toω,bDeriving and taking the derivative as 0 can obtain:
(6)
(7)
from equations (6) and (7), the expansion of the subset of the training sample set forms a normal vector of the optimal classification hyperplane, wherein the lagrangian multiplier forming the expanded sample is not 0, i.e., a support vector of the optimal classification hyperplane.
The classification discriminant function of the support vector machine is expressed as:
(8)
however, in practical problems, linear inseparability occurs, which may result in failure of classification of hard intervals, so that the training samples of the original space can be mapped non-linearly by using a mapping transformation methodφ(x) Transform to a linearly separable space of higher dimension. Due to finding non-linear mappings in an applicationφ(x) The problem of inner product operation is complex, and the basic concept based on the general function analysis in mathematics introduces a kernel functionK(x,x i )。
The common kernel functions in the support vector machine comprise radial basis functions, namely RBF functions, polynomial kernel functions, gaussian kernel functions, multi-layer perceptron functions and the like, and the RBF functions can reduce model complexity and have better performance when mapping is realized and parameters are fewer. Therefore, the RBF kernel function is selected as one of the SVM classification model parameters, and can be expressed as the following functional form:
(9)/>
Wherein,γis a kernel function parameter.
In order to obtain the optimal solution of the support vector machine parameter penalty factor and the kernel function parameter, a cuckoo search algorithm, namely a CS algorithm is introduced to improve the support vector machine to realize the search of each parameter, and the search flow of the cuckoo search algorithm is shown in figure 7.
The CS algorithm searches the habit of optimal nest egg laying based on cuckoo, sets an input parameter set as nest, optimizes the input parameter according to the Laiweider flight path principle, replaces the solution with poor output, and forms the solution with better result. The algorithm mainly comprises the following steps:
(I) Randomly generate m bird nests, set asX i =[X 1 0 ,X 2 0 ,…,X m 0 ]Calculating the position of the initial optimal bird nest by searchingX 0 ；
(II) calculating fitness values for each position, updating bird nest positions with better fitness by the lewy flight:
(10)
as shown in formula (10), each generation is compared with the previous generation, and after continuous replacement iteration, the optimal bird nest position is finally selected asX t =[X 1 t ,X 2 t ,…,X m t ]；
And (III) when the obtained optimal nest position reaches the accuracy requirement or the final iteration number, completing parameter optimizing search, and assigning values to the obtained result.
Setting the number of bird nests to 25, setting the upper limit of iteration times to 250, setting the lower limit of the fitness function to 0.05 and the upper limit to 0.1, and outputting the optimal solution of the parameters after the fitness evolution curve obtained after the circulation ending condition is met as shown in figure 8.
The search of each parameter of the support vector machine is carried out through CS algorithm, when RBF kernel function is used, penalty factors and kernel function parameters are obtainedγThe penalty factor = 10.0 respectively,kernel function parametersγModel classification accuracy is highest when =0.01 is nearby.
4) And constructing an improved SVM fault recognition model, namely a target SVM fault recognition model by using parameters obtained by an optimizing algorithm, inputting the preprocessed fault sample data into the constructed improved SVM fault recognition model for training and learning, and verifying that the fault diagnosis accuracy of a sample training set is 99.4444% by the model, wherein the fault recognition accuracy of the improved SVM fault recognition model to the sample training set is shown in figure 9. The fault diagnosis accuracy of the test set is 98.8889%, and the fault recognition accuracy of the improved SVM fault recognition model on the sample test set is shown in FIG. 10. Thus, byU m 、I m The three-dimensional fault characteristic quantity formed by the number of the U-I curve step turns can effectively represent different working states of abnormal aging, local shadow and the like of the photovoltaic array, and fault identification is completed.
The photovoltaic array fault identification method provided by the embodiment has wide application field in fault diagnosis, and the support vector machine algorithm is a small sample algorithm with a deeper theoretical basis, can rapidly predict sample data in the sample data training process, and avoids the steps from induction to deduction. The addition and removal of the non-support vector in the sample data has no influence on the model, so that the method has better robustness. The support vector machine estimates expected risks based on a structural risk minimization principle, so that the problem of overfitting in the model training process can be solved, and the support vector machine has strong popularization generalization capability in classification and discrimination. The introduction of the kernel function enables the support vector machine to perform dimension reduction operation on the sample space, greatly reduces the dimension of sample data, reduces the complexity of classification, and can solve the problem of non-linearity inseparability.
Not only the following is presented in this embodiment m 、I m The three-dimensional fault characteristic quantity group consisting of the number of U-I curve ladder turning points carries out punishment factor and kernel function parameter optimization on the SVM fault recognition model, the selected three-dimensional fault characteristic quantity is input into the improved SVM fault recognition model to verify the effectiveness of the SVM fault recognition model, and the SVM fault recognition model can be abnormally aged and not aged to different degrees of the photovoltaic arrayAccurate, convenient and efficient identification is carried out on the local shadow faults with the same degree.
Fig. 11 is a block diagram of a photovoltaic array fault recognition device according to an embodiment of the present application.
The photovoltaic array fault identification device provided by the embodiment of the application comprises the following functional modules:
the establishing module 801 is configured to establish a topology structure of the grid-connected photovoltaic power generation system based on the power grid operation parameters;
the simulation module 802 is configured to simulate an operation condition of the photovoltaic array under a preset abnormal condition based on the topology structure of the grid-connected photovoltaic power generation system, so as to obtain a first output characteristic of the photovoltaic array;
the generating module 803 is configured to compare the first output characteristic with a second output characteristic of the photovoltaic array in a normal running state, and generate a three-dimensional fault feature set;
the model optimization module 804 is configured to build an SVM fault recognition model according to the three-dimensional fault feature set, and optimize a penalty factor and a kernel function parameter of the SVM fault recognition model to obtain a target SVM fault recognition model;
And the identification module 805 is configured to perform validity verification on the target three-dimensional fault feature based on the target SVM fault identification model, so as to perform fault identification on the photovoltaic array.
Optionally, the simulation module includes:
the first sub-module is used for establishing a simulation model based on the topological structure of the grid-connected photovoltaic power generation system and a preset simulation platform;
the second sub-module is used for carrying out photovoltaic array fault simulation under preset abnormal conditions on the simulation model, and obtaining first output characteristics of the corresponding photovoltaic array under each abnormal condition, wherein the preset abnormal conditions comprise: the photovoltaic array is in an abnormal aging state with different degrees and in a state with different degrees of local shadows.
Optionally, the photovoltaic array is subjected to different degrees of abnormal aging states including: a first group of strings in the photovoltaic array are aged to a first degree, and a second group of strings are normal; a first set of strings in the photovoltaic array are subject to a second degree of aging, the second set of strings being normal; the first set of strings and the second set of strings in the photovoltaic array are both aged;
the state in which the photovoltaic array has different degrees of local shadows includes: irradiance of a single group of string photovoltaic modules in the photovoltaic array is 0, and irradiance of a plurality of groups of string photovoltaic modules in the photovoltaic array is 0.
Optionally, the generating module includes:
the third sub-module is used for analyzing the output characteristics corresponding to the abnormal aging state according to the abnormal aging state of each degree and determining the maximum power point voltage and the maximum power point current of the photovoltaic array;
the fourth sub-module is used for comparing the maximum power point voltage and the maximum power point current corresponding to the abnormal aging state of each degree with the maximum power point voltage and the maximum power point current in the normal operation state of the photovoltaic array to obtain a second output characteristic in the abnormal aging state;
a fifth sub-module, configured to analyze, for each degree of local shadow state, an output characteristic corresponding to the local shadow state, and determine a number of step turns of a U-I curve of the photovoltaic array;
and a sixth sub-module, configured to take the number of step turns of each U-I curve as a second output characteristic in a partial shadow state.
Optionally, the model optimization module includes:
a seventh sub-module, configured to perform dispersion normalization processing on the three-dimensional fault characteristic quantity set, to obtain a target three-dimensional fault characteristic quantity set; the target three-dimensional fault characteristic quantity group comprises a plurality of groups of three-dimensional fault characteristic quantities formed by the number of U-I curve step turning points based on the maximum power point voltage and the maximum power point current of the photovoltaic array;
An eighth sub-module, configured to divide the fault feature values in the target three-dimensional fault feature value set into a training set and a test set;
and the ninth sub-module is used for building an initial SVM fault recognition model, and carrying out iterative optimization on the penalty factors and the kernel function parameters of the initial SVM fault recognition model according to the training set until the iterative optimization cut-off condition is met, so as to obtain a target SVM fault recognition model.
According to the photovoltaic array fault recognition device provided by the embodiment of the application, the SVM estimates expected risks based on the structural risk minimization principle, so that the problem of overfitting in the model training process can be solved, and the SVM fault recognition model has good classification and discrimination capability; in addition, the SVM fault recognition model is trained through the three-dimensional fault feature quantity group, so that the accuracy of the SVM fault recognition model in recognizing the faults of the photovoltaic array can be improved.
The photovoltaic array fault recognition device shown in fig. 11 in the embodiment of the present application may be disposed in a mobile device or may be disposed in a server. The mobile device or server provided with the apparatus may be an apparatus having an operating system. The operating system may be an Android operating system, an iOS operating system, or other possible operating systems, which are not specifically limited in the embodiments of the present application.
The photovoltaic array fault recognition device shown in fig. 11 provided in this embodiment of the present application can implement each process implemented by the method embodiment of fig. 1, and in order to avoid repetition, a description is omitted here.
Optionally, referring to fig. 12, the embodiment of the present application further provides an electronic device 900, which includes a processor 901, a memory 902, and a program or an instruction stored in the memory and capable of being executed by the processor, where the program or the instruction is executed by the processor to implement each process executed by the above-mentioned photovoltaic array fault identification device, and the process may achieve the same technical effect, and for avoiding repetition, a description is omitted herein.
It should be noted that the electronic device in the embodiment of the present application includes the server described above.
Wherein the processor is a processor in the electronic device described in the above embodiment. The readable storage medium includes a computer readable storage medium such as a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), a magnetic disk or an optical disk, and the like.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
While the foregoing is directed to the preferred embodiments of the present invention, it will be appreciated by those skilled in the art that various modifications and adaptations can be made without departing from the principles of the present invention, and such modifications and adaptations are intended to be comprehended within the scope of the present invention.
Claims (10)
1. A method for identifying faults in a photovoltaic array, comprising:
establishing a topological structure of the grid-connected photovoltaic power generation system based on the power grid operation parameters;
simulating the operation condition of the photovoltaic array under a preset abnormal condition based on the topological structure of the grid-connected photovoltaic power generation system to obtain a first output characteristic of the photovoltaic array;
comparing the first output characteristic with a second output characteristic of the photovoltaic array in a normal operation state to generate a three-dimensional fault characteristic quantity set;
building an SVM fault recognition model according to the three-dimensional fault characteristic quantity set, and optimizing penalty factors and kernel function parameters of the SVM fault recognition model to obtain a target SVM fault recognition model;
and verifying the validity of the target three-dimensional fault characteristic quantity based on the target SVM fault identification model so as to identify faults of the photovoltaic array.
2. The method according to claim 1, wherein the step of simulating the operation condition of the photovoltaic array under the preset abnormal condition based on the topology of the grid-connected photovoltaic power generation system to obtain the first output characteristic of the photovoltaic array comprises:
Establishing a simulation model based on the topological structure of the grid-connected photovoltaic power generation system and a preset simulation platform;
performing photovoltaic array fault simulation under preset abnormal conditions on the simulation model, and acquiring first output characteristics of a corresponding photovoltaic array under each abnormal condition, wherein the preset abnormal conditions comprise: the photovoltaic array is in an abnormal aging state with different degrees and in a state with different degrees of local shadows.
3. The method according to claim 2, characterized in that:
the photovoltaic array is subjected to different degrees of abnormal aging states, including: a first group of strings in the photovoltaic array are aged to a first degree, and a second group of strings are normal; a first set of strings in the photovoltaic array are subject to a second degree of aging, the second set of strings being normal; the first set of strings and the second set of strings in the photovoltaic array are both aged;
the state in which the photovoltaic array has different degrees of local shadows includes: irradiance of a single group of string photovoltaic modules in the photovoltaic array is 0, and irradiance of a plurality of groups of string photovoltaic modules in the photovoltaic array is 0.
4. The method of claim 2, wherein the step of generating a three-dimensional set of fault signatures by comparing the first output characteristic to a second output characteristic of the photovoltaic array during normal operation comprises:
Aiming at the abnormal aging state of each degree, analyzing the output characteristics corresponding to the abnormal aging state, and determining the maximum power point voltage and the maximum power point current of the photovoltaic array;
comparing the maximum power point voltage and the maximum power point current corresponding to the abnormal aging state of each degree with the maximum power point voltage and the maximum power point current in the normal operation state of the photovoltaic array to obtain a second output characteristic in the abnormal aging state;
aiming at the state of the partial shadow of each degree, analyzing the output characteristic corresponding to the state of the partial shadow, and determining the number of step turns of the U-I curve of the photovoltaic array;
and taking the number of step turns of each U-I curve as a second output characteristic in a partial shadow state.
5. The method of claim 4, wherein the step of constructing an SVM support vector machine fault recognition model according to the three-dimensional fault feature set, and optimizing a penalty factor and a kernel function parameter of the SVM fault recognition model to obtain a target SVM fault recognition model comprises:
performing dispersion normalization processing on the three-dimensional fault characteristic quantity set to obtain a target three-dimensional fault characteristic quantity set; the target three-dimensional fault characteristic quantity group comprises a plurality of groups of three-dimensional fault characteristic quantities formed by the number of U-I curve step turning points based on the maximum power point voltage and the maximum power point current of the photovoltaic array;
Dividing fault characteristic quantities in the target three-dimensional fault characteristic quantity group into a training set and a testing set;
and constructing an initial SVM fault recognition model, and carrying out iterative optimization on the penalty factors and the kernel function parameters of the initial SVM fault recognition model according to the training set until the iterative optimization cut-off condition is met, so as to obtain a target SVM fault recognition model.
6. A photovoltaic array fault identification device, comprising:
the building module is used for building a topological structure of the grid-connected photovoltaic power generation system based on the power grid operation parameters;
the simulation module is used for simulating the operation condition of the photovoltaic array under the preset abnormal condition based on the topological structure of the grid-connected photovoltaic power generation system to obtain a first output characteristic of the photovoltaic array;
the generating module is used for comparing the first output characteristic with the second output characteristic of the photovoltaic array in a normal operation state to generate a three-dimensional fault characteristic quantity set;
the model optimization module is used for building an SVM fault recognition model according to the three-dimensional fault characteristic quantity set, and optimizing penalty factors and kernel function parameters of the SVM fault recognition model to obtain a target SVM fault recognition model;
and the identification module is used for carrying out validity verification on the target three-dimensional fault characteristic quantity based on the target SVM fault identification model so as to carry out fault identification on the photovoltaic array.
7. The apparatus of claim 6, wherein the simulation module comprises:
the first sub-module is used for establishing a simulation model based on the topological structure of the grid-connected photovoltaic power generation system and a preset simulation platform;
the second sub-module is used for carrying out photovoltaic array fault simulation under preset abnormal conditions on the simulation model, and obtaining first output characteristics of the corresponding photovoltaic array under each abnormal condition, wherein the preset abnormal conditions comprise: the photovoltaic array is in an abnormal aging state with different degrees and in a state with different degrees of local shadows.
8. The apparatus according to claim 7, wherein:
the photovoltaic array is subjected to different degrees of abnormal aging states, including: a first group of strings in the photovoltaic array are aged to a first degree, and a second group of strings are normal; a first set of strings in the photovoltaic array are subject to a second degree of aging, the second set of strings being normal; the first set of strings and the second set of strings in the photovoltaic array are both aged;
the state in which the photovoltaic array has different degrees of local shadows includes: irradiance of a single group of string photovoltaic modules in the photovoltaic array is 0, and irradiance of a plurality of groups of string photovoltaic modules in the photovoltaic array is 0.
9. The apparatus of claim 7, wherein the generating module comprises:
the third sub-module is used for analyzing the output characteristics corresponding to the abnormal aging state according to the abnormal aging state of each degree and determining the maximum power point voltage and the maximum power point current of the photovoltaic array;
the fourth sub-module is used for comparing the maximum power point voltage and the maximum power point current corresponding to the abnormal aging state of each degree with the maximum power point voltage and the maximum power point current in the normal operation state of the photovoltaic array to obtain a second output characteristic in the abnormal aging state;
a fifth sub-module, configured to analyze, for each degree of local shadow state, an output characteristic corresponding to the local shadow state, and determine a number of step turns of a U-I curve of the photovoltaic array;
and a sixth sub-module, configured to take the number of step turns of each U-I curve as a second output characteristic in a partial shadow state.
10. An electronic device comprising a processor, a memory and a program or instruction stored on the memory and executable on the processor, the program or instruction being executable by the processor to perform the steps of the method for identifying a photovoltaic array fault of any of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410184076.8A CN117743958A (en) | 2024-02-19 | 2024-02-19 | Photovoltaic array fault identification method and device and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410184076.8A CN117743958A (en) | 2024-02-19 | 2024-02-19 | Photovoltaic array fault identification method and device and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117743958A true CN117743958A (en) | 2024-03-22 |
Family
ID=90281678
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410184076.8A Pending CN117743958A (en) | 2024-02-19 | 2024-02-19 | Photovoltaic array fault identification method and device and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117743958A (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112949198A (en) * | 2021-03-10 | 2021-06-11 | 阳光电源股份有限公司 | Fault detection method and device for photovoltaic string and computer storage medium |
| CN114117921A (en) * | 2021-11-29 | 2022-03-01 | 青海大学 | Intelligent diagnosis method for faults of photovoltaic array |
| CN114881143A (en) * | 2022-05-07 | 2022-08-09 | 河北工业大学 | Photovoltaic array fault characteristic determination method |
-
2024
- 2024-02-19 CN CN202410184076.8A patent/CN117743958A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112949198A (en) * | 2021-03-10 | 2021-06-11 | 阳光电源股份有限公司 | Fault detection method and device for photovoltaic string and computer storage medium |
| CN114117921A (en) * | 2021-11-29 | 2022-03-01 | 青海大学 | Intelligent diagnosis method for faults of photovoltaic array |
| CN114881143A (en) * | 2022-05-07 | 2022-08-09 | 河北工业大学 | Photovoltaic array fault characteristic determination method |
Non-Patent Citations (2)
| Title |
|---|
| 孙培胜等: "基于 SOA-SVM 模型的光伏阵列故障诊断研究", 《电源学报》, 23 August 2022 (2022-08-23), pages 1 - 8 * |
| 薛浩然等: "基于布谷鸟算法和支持向量机的变压器故障诊断", 《电力系统保护与控制》, vol. 43, no. 8, 16 April 2015 (2015-04-16) * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109873610B (en) | Photovoltaic array fault diagnosis method based on IV characteristic and depth residual error network | |
| US11544917B2 (en) | Power electronic circuit fault diagnosis method based on optimizing deep belief network | |
| Deka et al. | Estimating distribution grid topologies: A graphical learning based approach | |
| CN109842373B (en) | Photovoltaic array fault diagnosis method and device based on space-time distribution characteristics | |
| CN110008628B (en) | Photovoltaic array fault parameter identification method | |
| CN109635928A (en) | A kind of voltage sag reason recognition methods based on deep learning Model Fusion | |
| CN112787591B (en) | Photovoltaic array fault diagnosis method based on fine-tuning dense connection convolutional neural network | |
| CN110728195B (en) | Power quality disturbance detection method based on YOLO algorithm | |
| CN113259388B (en) | Network flow abnormity detection method, electronic equipment and readable storage medium | |
| CN114640304B (en) | Photovoltaic module current mismatch fault diagnosis method based on I-V curve | |
| CN115618249A (en) | Low-voltage power distribution station area phase identification method based on LargeVis dimension reduction and DBSCAN clustering | |
| Jia et al. | Validity evaluation of transformer DGA online monitoring data in grid edge systems | |
| CN114528883A (en) | Wind power converter IGBT fault identification method | |
| CN114881143B (en) | Photovoltaic array fault feature determination method | |
| CN115469184A (en) | New energy transmission line fault identification method based on convolutional network | |
| Ye et al. | Single pole‐to‐ground fault location method for mmc‐hvdc system using wavelet decomposition and dbn | |
| CN118427720A (en) | Power system transient stability judging method and system based on interpretable graph neural tree | |
| CN117972419A (en) | Anomaly-transporter photovoltaic power generation abnormality detection method | |
| CN117743958A (en) | Photovoltaic array fault identification method and device and electronic equipment | |
| CN116318925A (en) | Multi-CNN fusion intrusion detection method, system, medium, equipment and terminal | |
| CN115936926A (en) | SMOTE-GBDT-based unbalanced electricity stealing data classification method and device, computer equipment and storage medium | |
| CN116010831A (en) | Combined clustering scene reduction method and system based on potential decision result | |
| Dehghani et al. | Distribution feeder classification based on self organized maps (case study: Lorestan province, Iran) | |
| CN115208309A (en) | Photovoltaic module current mismatch fault diagnosis method based on I-V characteristic curve | |
| CN114881176A (en) | Non-invasive load identification method based on self-adaptive optimization random forest |
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 |