CN115587642A - Photovoltaic system fault warning method based on BP neural network - Google Patents

Photovoltaic system fault warning method based on BP neural network Download PDF

Info

Publication number
CN115587642A
CN115587642A CN202210712863.6A CN202210712863A CN115587642A CN 115587642 A CN115587642 A CN 115587642A CN 202210712863 A CN202210712863 A CN 202210712863A CN 115587642 A CN115587642 A CN 115587642A
Authority
CN
China
Prior art keywords
neural network
photovoltaic system
network model
input
distributed photovoltaic
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
Application number
CN202210712863.6A
Other languages
Chinese (zh)
Other versions
CN115587642B (en
Inventor
贾炳军
刘彦鹏
程永卓
王永宏
唐宏芬
公冶令沛
李红涛
董颖华
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Datang Sanya Future Energy Research Institute Co ltd
New Energy Branch Of Datang Hainan Energy Development Co ltd
Datang Hainan Energy Development Co ltd
China Electric Power Research Institute Co Ltd CEPRI
Original Assignee
Datang Sanya Future Energy Research Institute Co ltd
New Energy Branch Of Datang Hainan Energy Development Co ltd
Datang Hainan Energy Development Co ltd
China Electric Power Research Institute Co Ltd CEPRI
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Datang Sanya Future Energy Research Institute Co ltd, New Energy Branch Of Datang Hainan Energy Development Co ltd, Datang Hainan Energy Development Co ltd, China Electric Power Research Institute Co Ltd CEPRI filed Critical Datang Sanya Future Energy Research Institute Co ltd
Priority to CN202210712863.6A priority Critical patent/CN115587642B/en
Publication of CN115587642A publication Critical patent/CN115587642A/en
Application granted granted Critical
Publication of CN115587642B publication Critical patent/CN115587642B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G06N3/084—Backpropagation, e.g. using gradient descent
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/20—Administration of product repair or maintenance
    • 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
    • G—PHYSICS
    • G08—SIGNALLING
    • G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
    • G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
    • G08B21/18—Status alarms
    • G08B21/185—Electrical failure alarms
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
    • Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
    • Y04S10/00—Systems supporting electrical power generation, transmission or distribution
    • Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Physics & Mathematics (AREA)
  • Human Resources & Organizations (AREA)
  • Theoretical Computer Science (AREA)
  • Economics (AREA)
  • General Physics & Mathematics (AREA)
  • Strategic Management (AREA)
  • Tourism & Hospitality (AREA)
  • Marketing (AREA)
  • General Business, Economics & Management (AREA)
  • Health & Medical Sciences (AREA)
  • Quality & Reliability (AREA)
  • Operations Research (AREA)
  • Entrepreneurship & Innovation (AREA)
  • General Health & Medical Sciences (AREA)
  • Data Mining & Analysis (AREA)
  • Computational Linguistics (AREA)
  • Mathematical Physics (AREA)
  • Development Economics (AREA)
  • General Engineering & Computer Science (AREA)
  • Game Theory and Decision Science (AREA)
  • Computing Systems (AREA)
  • Molecular Biology (AREA)
  • Evolutionary Computation (AREA)
  • Software Systems (AREA)
  • Biophysics (AREA)
  • Biomedical Technology (AREA)
  • Artificial Intelligence (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Public Health (AREA)
  • Water Supply & Treatment (AREA)
  • Primary Health Care (AREA)
  • Emergency Management (AREA)
  • Photovoltaic Devices (AREA)

Abstract

The invention discloses a photovoltaic system fault warning method based on a BP (back propagation) neural network, which screens out training data by establishing the BP neural network of a distributed photovoltaic system, and further warns output characteristic abnormity in the operation process of the distributed photovoltaic system in a region.

Description

Photovoltaic system fault warning method based on BP neural network
Technical Field
The invention relates to the field of distributed photovoltaic system fault diagnosis, in particular to a photovoltaic system fault warning method based on a BP neural network.
Background
The BP neural network has arbitrary complex pattern classification capability and excellent multidimensional function mapping capability, and solves Exclusive OR (XOR) and other problems which cannot be solved by a simple perceptron. Structurally, the BP network has an input layer, a hidden layer, and an output layer; in essence, the BP algorithm calculates the minimum value of an objective function by using a gradient descent method with the square of a network error as the objective function. In the prior art, a photovoltaic system fault warning method has single input data, high requirement on accuracy of early-stage data acquisition, and when running data is lacked, fault warning is easy to be reported or misreported, in the prior art, CN201510567882 discloses a distributed photovoltaic system fault diagnosis method based on a neural network, a power station is diagnosed only through historical input and output data of the diagnosed power station and meteorological data monitored by the power station, diagnosis precision is low, and meanwhile, in the prior art, a residual error between estimation output and system actual output is adopted for judgment, and an error is large.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and discloses a photovoltaic system fault warning method based on a BP (back propagation) neural network.
The technical scheme of the application specifically comprises:
a photovoltaic system fault warning method based on a BP neural network screens out training data by establishing the BP neural network of a distributed photovoltaic system, and then alarms output characteristic abnormity in the operation process of the distributed photovoltaic system in an area.
The invention discloses a photovoltaic system fault warning method based on a BP neural network, which comprises the following steps:
s1, acquiring output data of a distributed photovoltaic system in a regional photovoltaic system and meteorological data of the regional photovoltaic system;
s2, normalizing the output data and meteorological data of the distributed photovoltaic system;
s3, establishing a BP neural network model input matrix x of the distributed photovoltaic system based on the output data and meteorological data of the distributed photovoltaic system after normalization processing t-i * Inputting the BP neural network model into a matrix x t-i * Inputting the hidden layer activation function f (v) of the BP neural network model to obtain the BP neural network model of the photovoltaic system in the current area;
s4, normalizing the output data of the evaluated distributed photovoltaic system, and inputting the matrix x under the same timestamp t-i * And the output vector Y t * Performing correlation judgment to obtain filtered distributed photovoltaic system output data
Figure BDA0003707542650000011
And meteorological data
Figure BDA0003707542650000012
S5, filtered distributed photovoltaic system output data
Figure BDA0003707542650000013
And meteorological data
Figure BDA0003707542650000014
As an input training parameter of a BP neural network model of the photovoltaic system of the current region, training the BP neural network model of the photovoltaic system of the current region, and outputting the trained neural network system;
s6, applying the trained neural network system to regional photovoltaic system fault warning, monitoring all input parameter vectors of the BP neural network model, and obtaining output reference vectors
Figure BDA0003707542650000021
Computing an output reference vector
Figure BDA0003707542650000022
Actual output of photovoltaic power station to be evaluated under corresponding timestamp
Figure BDA0003707542650000023
And judging whether the evaluated distributed photovoltaic power station has suspicious faults or not according to the correlation.
A photovoltaic system fault warning method based on BP neural network is characterized in that,
step S1, specifically comprising the following steps:
101 Determining a distributed photovoltaic system which can be utilized in a regional environment range of a regional photovoltaic system, wherein the regional photovoltaic system comprises more than 1 other distributed photovoltaic systems besides an evaluated photovoltaic power generation system, and acquiring output data of the distributed photovoltaic system;
102 N) for the photovoltaic system being evaluated within the area and for other n distributed photovoltaic systems, n>=1, respectively obtaining the output data at time t, wherein the output data of the evaluated distributed photovoltaic system at time t is recorded as a vector Y t N distributed photovoltaic system output data form an output data matrix P t-i ，i＝1,2，…，n；P t-i Representing the output data of the ith distributed photovoltaic system at t moment;
103 Obtaining meteorological data of the regional photovoltaic system at the time t, wherein the meteorological data comprises data of 3 traditional parameters of irradiance, temperature and wind speed, and the meteorological data of the tropical region further comprises humidity data, and forming a meteorological data vector W at the time t t-j ，j＝1,2，3，4…，m，W t-j Represents the jth meteorological data vector at time t, and m =4 in the embodiment.
Preferably, the step S2 specifically includes the following steps:
201 Based on the installed capacity of the n distributed photovoltaic systems, normalizing the output data of the distributed photovoltaic systems, and taking the normalized parameters as input training parameters of the BP neural network model, wherein n input parameters of the BP neural network model are total, and the output data matrix after normalization at the time t is
Figure BDA0003707542650000024
202 When available meteorological data exist in the environmental range of the regional photovoltaic system, normalization processing is carried out on the meteorological data of the regional photovoltaic system on the basis of irradiance of 1000W/square meter, environmental temperature of 45 ℃, wind speed of 10m/s and humidity of 100% to form a normalized meteorological matrix W at the moment t t-j * The normalized output data is matrix of
Figure BDA0003707542650000025
And a meteorological matrix W t-j * As the input training parameters of the BP neural network model, all the input parameters of the BP neural network model are n + 4.
Preferably, step S3 specifically includes the following steps:
301 ) establishing an input matrix x of the BP neural network model of the regional photovoltaic system under the moment t t-i * Is represented by formula (1):
Figure BDA0003707542650000031
302 According to the input matrix x t-j * Determining the number of layers of a hidden layer of the BP neural network model according to the dimension of the BP neural network model and the requirement on the accuracy of a prediction result;
303 Adopting an M-layer unipolar Sigmoid function as a hidden layer activation function f (v) of the BP neural network model to obtain the BP neural network model of the photovoltaic system in the current area;
the hidden layer activation function f (v) of the BP neural network model is expressed as formula (2):
Figure BDA0003707542650000032
wherein v is an input parameter and is a multi-layer input of a hidden layer of the BP neural network model, and an initial value of the input parameter is an input matrix x t-i * The first layer is the input matrix x t-i * The input v to the second layer is the result after the computation of the first layer, v being defined in the field (— infinity, + ∞).
Preferably, step S4 specifically includes the following steps:
401 Normalizing the output data of the evaluated distributed photovoltaic system according to the installed capacity of the regional evaluated distributed photovoltaic system, wherein the output vector of the normalized output data of the evaluated distributed photovoltaic system is Y t * ；
402 For input matrix x at time t) t-i * And outputVector Y t * Screening, and judging the correlation of the input and output functions by utilizing a Pearson correlation coefficient;
Figure BDA0003707542650000033
in the formula: c is sample x t-i * And sample Y t * A correlation coefficient; cov (x) t-i * ,Y t * ) Is a sample x t-i * And sample Y t * Covariance of the correlation coefficient, var (x) t-i * )、Var(Y t * ) Fractional sample x t-i * And sample Y t * The variance of (a);
403 Setting a first correlation coefficient threshold value, filtering out the input matrix x with the correlation coefficient c smaller than the first correlation coefficient threshold value t-i * And the sum output vector is Y t * Obtaining filtered distributed photovoltaic system output data
Figure BDA0003707542650000034
And meteorological data
Figure BDA0003707542650000035
Preferably, step S5 specifically includes the following steps:
distributed photovoltaic system output data filtered at time t
Figure BDA0003707542650000036
And meteorological data
Figure BDA0003707542650000037
The method comprises the steps of taking the parameters as input training parameters of a BP neural network model of a photovoltaic system in a current region; hidden layer activation function f (v) based on BP neural network model * ) Training the neural network to optimize the neural network; using filtered input and output matrices and a 2-layer hidden layer activation function f (v) * ) To the neural networkPerforming training to form a multi-layer neural network to obtain a trained neural network system; (ii) a
Figure BDA0003707542650000041
v * Is the filtered input parameter of the BP neural network model, in this step, v * Is the filtered distributed photovoltaic system output data
Figure BDA0003707542650000042
And meteorological data
Figure BDA0003707542650000043
Preferably, step S6 specifically includes the following steps:
601 Applying the trained neural network system to the regional photovoltaic system fault alarm, monitoring all input parameter vectors of the BP neural network model in real time, and obtaining corresponding output reference vectors
Figure BDA0003707542650000044
Outputting a reference vector
Figure BDA0003707542650000045
Is obtained by inputting an input vector into a multilayer neural network composed of the formula (2).
602 Computing an output reference vector using Pearson's correlation coefficients
Figure BDA0003707542650000046
Actual output of photovoltaic power station to be evaluated under corresponding timestamp
Figure BDA0003707542650000047
Correlation, denoted c Y ：
Figure BDA0003707542650000048
603 Setting a second correlation coefficient threshold when c y And when the second correlation coefficient threshold value is less than 0.95, the suspicious fault of the evaluated distributed photovoltaic power station is considered to exist, and an alarm is given.
Preferably, the first correlation coefficient threshold is 0.95.
The second correlation coefficient threshold is 0.95.
Compared with the prior art, the invention has the following beneficial effects:
the invention discloses a photovoltaic system fault warning method based on a BP neural network, which is used for warning the fault condition of a distributed photovoltaic system in tropical regions, further improving the operation and maintenance level of the distributed photovoltaic system in the regions and improving the generated energy of the distributed photovoltaic system.
The method adopts a BP neural network method, theoretical output data of the photovoltaic power station to be evaluated is obtained through output data and meteorological data of all photovoltaic systems in the whole county, the theoretical output data and actual output data of the photovoltaic power station to be evaluated are judged by adopting Pearson correlation coefficients, and then fault alarm conditions of the photovoltaic power station to be evaluated are obtained, and fault alarm of the photovoltaic power station is achieved.
The input volume of this patent has not only contained by diagnostic power station self input and output data, meteorological data, has still included photovoltaic power plant's on every side electricity generation data, through more input data for when lacking certain operating data wherein, still can realize photovoltaic power plant fault diagnosis and report an emergency and ask for help or increased vigilance.
The Pearson correlation coefficient is adopted for fault judgment, and the judgment method is simple and high in precision.
Drawings
FIG. 1 is a flow chart of a photovoltaic system fault warning method based on a BP neural network according to the present application;
FIG. 2 is a diagram of a regional photovoltaic fault warning neural network;
fig. 3 shows the result of a regional photovoltaic system fault alarm.
Detailed Description
The technical solutions of the present invention will be described clearly and completely with reference to the accompanying drawings, and it is obvious that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
As shown in fig. 1, a photovoltaic system fault warning method based on a BP neural network screens out training data by establishing a BP neural network of a distributed photovoltaic system, and further warns of output characteristic abnormality in the operation process of the distributed photovoltaic system in a region (the region can refer to the whole county according to geographical division, and the patent is used for promoting photovoltaic in the whole county), so that the operation and maintenance capacity of the distributed photovoltaic system is improved.
A photovoltaic system fault warning method based on a BP neural network comprises the following steps:
s1, acquiring output data of a distributed photovoltaic system in a regional photovoltaic system and meteorological data of the regional photovoltaic system;
s2, normalizing the output data and meteorological data of the distributed photovoltaic system;
s3, establishing a BP neural network model input matrix x of the distributed photovoltaic system based on the output data and meteorological data of the distributed photovoltaic system after normalization processing t-i * Inputting the BP neural network model into a matrix x t-i * Inputting the BP neural network model hidden layer activation function f (v) to obtain a BP neural network model of the photovoltaic system in the current area;
f (v) is a common function of the neural network, and the function f (v) is trained by utilizing known input and output data through two steps S4 and S5, so that the special neural network for the power station fault alarm can be obtained
S4, normalizing the output data of the evaluated distributed photovoltaic system, and inputting the matrix x under the same timestamp t-i * And the output vector Y t * Performing relevance judgment to obtain filtered distributed photovoltaic system outputForce data
Figure BDA0003707542650000051
And meteorological data
Figure BDA0003707542650000052
S5, filtered distributed photovoltaic system output data
Figure BDA0003707542650000053
And meteorological data
Figure BDA0003707542650000054
As an input training parameter of a BP neural network model of the photovoltaic system in the current region, training the BP neural network model of the photovoltaic system in the current region and outputting the trained neural network model;
s6, applying the trained neural network system to regional photovoltaic system fault warning, monitoring all input parameter vectors of the BP neural network model, and obtaining output reference vectors
Figure BDA0003707542650000055
Computing an output reference vector
Figure BDA0003707542650000056
Actual output of photovoltaic power station to be evaluated under corresponding timestamp
Figure BDA0003707542650000057
And judging whether the evaluated distributed photovoltaic power station has suspicious faults or not according to the correlation.
Step S1, specifically comprising the following steps:
101 Determining a distributed photovoltaic system which can be used in a regional environment range of a regional photovoltaic system, wherein the regional photovoltaic system comprises more than 1 other distributed photovoltaic systems besides an evaluated photovoltaic power generation system, and acquiring output data of the distributed photovoltaic systems;
102 For photovoltaic systems being evaluated within a region and other n distributed lightsVolt system, n>=1, respectively obtaining the output data at the time t, wherein the output data of the evaluated distributed photovoltaic system at the time t is recorded as a vector Y t N distributed photovoltaic system output data form an output data matrix P t-i ，i＝1,2，…，n；P t-i Representing the output data of the ith distributed photovoltaic system at t time;
103 Obtaining meteorological data of a regional photovoltaic system at the time t, wherein the meteorological data comprises 3 traditional parameters of irradiance, temperature and wind speed, and the meteorological data of tropical regions also comprises humidity data to form a meteorological data vector W at the time t t-j ，j＝1,2，3，4…，m，W t-j Representing the jth meteorological data vector at time t.
The step S2 specifically includes the following steps:
201 Based on the installed capacity of the n distributed photovoltaic systems, normalizing the output data of the distributed photovoltaic systems, and taking the normalized parameters as input training parameters of the BP neural network model, wherein n input parameters of the BP neural network model are total, and the output data matrix after normalization at the time t is
Figure BDA0003707542650000061
202 When available meteorological data exist in the environmental range of the regional photovoltaic system, normalization processing is carried out on the meteorological data of the regional photovoltaic system on the basis of irradiance of 1000W/square meter, environment temperature of 45 ℃, wind speed of 10m/s and humidity of 100 percent to form a normalized meteorological matrix W at the moment t t-j * The normalized output data is matrix of
Figure BDA0003707542650000062
And a meteorological matrix W t-j * And as the input training parameters of the BP neural network model, all the input parameters of the BP neural network model are n + 4.
The step S3 specifically includes the following steps:
301 ) establishing an input matrix x of the BP neural network model of the regional photovoltaic system under the moment t t-i * Is represented by the formula (1):
Figure BDA0003707542650000063
302 According to the input matrix x t-j * Determining the number of layers of hidden layers of the BP neural network model according to the dimension of the BP neural network model and the requirement on the accuracy of a prediction result;
the hidden layer number is determined according to the empirical value, the more the layer number is, the more the calculation is complex, the less the layer number is, the calculation accuracy is insufficient, and the embodiment takes 2 layers.
303 Adopting an M-layer unipolar Sigmoid function as a hidden layer activation function f (v) of the BP neural network model to obtain the BP neural network model of the photovoltaic system in the current area; the BP neural network model of the photovoltaic system in the current region is shown in FIG. 2;
the hidden layer activation function f (v) of the BP neural network model is expressed as formula (2):
Figure BDA0003707542650000071
wherein v is an input parameter and is a multi-layer input of a hidden layer of the BP neural network model, and an initial value of the input parameter is an input matrix x t-i * The first layer is the input matrix x t-i * The input v to the second layer is the result after the computation of the first layer, v being defined in the field (— infinity, + ∞).
Step S4 specifically includes the following steps:
401 Normalizing the output data of the evaluated distributed photovoltaic system according to the installed capacity of the evaluated distributed photovoltaic system in the region, wherein the output vector of the normalized output data of the evaluated distributed photovoltaic system is Y t * ；
402 For input matrix x at time t t-i * And the output vector Y t * Screening, and judging the correlation of the input and output functions by using a Pearson correlation coefficient;
Figure BDA0003707542650000072
in the formula: c is sample x t-i * And sample Y t * A correlation coefficient; cov (x) t-i * ,Y t * ) Is a sample x t-i * And sample Y t * Covariance of the correlation coefficient, var (x) t-i * )、Var(Y t * ) Fractional sample x t-i * And sample Y t * The variance of (a);
403 Set the first correlation coefficient threshold value to 0.95, filter the input matrix x with correlation coefficient c less than the first correlation coefficient threshold value t-i * And the sum output vector is Y t * Obtaining filtered distributed photovoltaic system output data
Figure BDA0003707542650000073
And meteorological data
Figure BDA0003707542650000074
The step S5 specifically includes the following steps:
distributed photovoltaic system output data filtered at time t
Figure BDA0003707542650000075
And meteorological data
Figure BDA0003707542650000076
The BP neural network model is used as an input training parameter of the BP neural network model of the photovoltaic system in the current region; hidden layer activation function f (v) based on BP neural network model * ) Training the neural network to optimize the neural network; using filtered input and output matrices and a 2-layer hidden layer activation function f (v) * ) Training the neural network to form a multilayer neural network, and obtaining a trained neural network system; (ii) a
Figure BDA0003707542650000077
v * Is the filtered input parameter of the BP neural network model, in this step, v * Is the filtered distributed photovoltaic system output data
Figure BDA0003707542650000078
And meteorological data
Figure BDA0003707542650000079
Step S6 specifically includes the following steps:
601 Applying the trained neural network system to regional photovoltaic system fault alarm, monitoring all input parameter vectors of a BP neural network model in real time, and obtaining corresponding output reference vectors
Figure BDA0003707542650000081
Outputting a reference vector
Figure BDA0003707542650000082
Is obtained by inputting an input vector into a multilayer neural network composed of the formula (2).
602 Computing an output reference vector using Pearson's correlation coefficients
Figure BDA0003707542650000083
Actual output of photovoltaic power station to be evaluated under corresponding timestamp
Figure BDA0003707542650000084
Correlation, denoted c Y ：
Figure BDA0003707542650000085
603 Setting the second correlation coefficient threshold value to 0.95 when c is y When the correlation coefficient is less than the second correlation coefficient threshold value of 0.95, the evaluated distributed photovoltaic power station is considered to have suspicious faults and is informedAlarm, domain distributed photovoltaic fault alarm results are shown in fig. 3, and the prediction alarm is consistent with the actual results.
And S1-S4, establishing a neural network model, training the neural network model through known and definite input and output data, and enabling the trained model to have the capability of realizing the steps S5-S6. Namely, the model which is just built is a general model which cannot be identified, and the model can be pointed to the power station in the local area only through the training of S1-S4, so that the steps S5-S6 can be realized.
In the description provided herein, numerous specific details are set forth. It is understood, however, that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description.
Similarly, it should be appreciated that in the foregoing description of exemplary embodiments of the invention, various features of the invention are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure and aiding in the understanding of one or more of the various inventive aspects. However, the disclosed method should not be construed to reflect the intent: rather, the invention as claimed requires more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive aspects lie in less than all features of a single foregoing disclosed embodiment. Thus, the claims following the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate embodiment of this invention.
Those skilled in the art will appreciate that the modules or units or groups of devices in the examples disclosed herein may be arranged in a device as described in this embodiment, or alternatively may be located in one or more devices different from the devices in this example. The modules in the foregoing examples may be combined into one module or may be further divided into multiple sub-modules.
Those skilled in the art will appreciate that the modules in the devices in an embodiment may be adaptively changed and arranged in one or more devices different from the embodiment. Modules or units or groups in embodiments may be combined into one module or unit or group and may furthermore be divided into sub-modules or sub-units or sub-groups. All of the features disclosed in this specification (including any accompanying claims, abstract and drawings), and all of the processes or elements of any method or apparatus so disclosed, may be combined in any combination, except combinations where at least some of such features and/or processes or elements are mutually exclusive. Each feature disclosed in this specification (including any accompanying claims, abstract and drawings) may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise.
Furthermore, those skilled in the art will appreciate that while some embodiments described herein include some features included in other embodiments, rather than other features, combinations of features of different embodiments are meant to be within the scope of the invention and form different embodiments. For example, in the following claims, any of the claimed embodiments may be used in any combination.
Furthermore, some of the described embodiments are described herein as a method or combination of method elements that can be performed by a processor of a computer system or by other means of performing the described functions. A processor having the necessary instructions for carrying out the method or method elements thus forms a means for carrying out the method or method elements. Further, the elements of the apparatus embodiments described herein are examples of the following apparatus: the means for performing the functions performed by the elements for the purpose of carrying out the invention.
The various techniques described herein may be implemented in connection with hardware or software or, alternatively, with a combination of both. Thus, the methods and apparatus of the present invention, or certain aspects or portions thereof, may take the form of program code (i.e., instructions) embodied in tangible media, such as floppy diskettes, CD-ROMs, hard drives, or any other machine-readable storage medium, wherein, when the program is loaded into and executed by a machine, such as a computer, the machine becomes an apparatus for practicing the invention.
In the case of program code execution on programmable computers, the computing device will generally include a processor, a storage medium readable by the processor (including volatile and non-volatile memory and/or storage elements), at least one input device, and at least one output device. Wherein the memory is configured to store program code; the processor is configured to perform the method of the invention according to instructions in said program code stored in the memory.
By way of example, and not limitation, computer readable media may comprise computer storage media and communication media. Computer-readable media includes both computer storage media and communication media. Computer storage media store information such as computer readable instructions, data structures, program modules or other data. Communication media typically embodies computer readable instructions, data structures, program modules or other data in a modulated data signal such as a carrier wave or other transport mechanism and includes any information delivery media. Combinations of any of the above are also included within the scope of computer readable media.
As used herein, unless otherwise specified the use of the ordinal adjectives "first", "second", "third", etc., to describe a common object, merely indicate that different instances of like objects are being referred to, and are not intended to imply that the objects so described must be in a given sequence, either temporally, spatially, in ranking, or in any other manner.
While the invention has been described with respect to a limited number of embodiments, those skilled in the art, having benefit of this description, will appreciate that other embodiments can be devised which do not depart from the scope of the invention as disclosed herein. Moreover, it should be noted that the language used in the specification has been principally selected for readability and instructional purposes, and may not have been selected to delineate or circumscribe the inventive subject matter. Accordingly, many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the appended claims. The present invention has been disclosed in an illustrative rather than a restrictive sense, and the scope of the present invention is defined by the appended claims.

Claims (10)

1. A photovoltaic system fault warning method based on a BP neural network is characterized in that training data are screened out by establishing the BP neural network of a distributed photovoltaic system, and further, abnormal output characteristics in the operation process of the distributed photovoltaic system in an area are warned.
2. The photovoltaic system fault warning method based on the BP neural network as claimed in claim 1, wherein the invention comprises the following steps:
s1, acquiring output data of a distributed photovoltaic system in a regional photovoltaic system and meteorological data of the regional photovoltaic system;
s2, normalizing the output data and meteorological data of the distributed photovoltaic system;
s3, establishing a BP neural network model input matrix x of the distributed photovoltaic system based on the normalized distributed photovoltaic system output data and meteorological data t-i * Inputting the BP neural network model into a matrix x t-i * Inputting the BP neural network model hidden layer activation function f (v) to obtain a BP neural network model of the photovoltaic system in the current area;
s4, normalizing the output data of the evaluated distributed photovoltaic system, and inputting the matrix x under the same timestamp t-i * And the output vector Y t * Performing correlation judgment to obtain filtered distributed photovoltaic system output data
Figure FDA0003707542640000011
And meteorological data
Figure FDA0003707542640000012
S5, filtered distributed photovoltaic system output data
Figure FDA0003707542640000013
And meteorological data
Figure FDA0003707542640000014
As an input training parameter of a BP neural network model of the photovoltaic system of the current region, training the BP neural network model of the photovoltaic system of the current region, and outputting the trained neural network system;
s6, applying the trained neural network system to regional photovoltaic system fault warning, monitoring all input parameter vectors of the BP neural network model, and obtaining output reference vectors
Figure FDA0003707542640000015
Computing an output reference vector
Figure FDA0003707542640000016
Actual output of photovoltaic power station to be evaluated under corresponding timestamp
Figure FDA0003707542640000017
And judging whether the evaluated distributed photovoltaic power station has suspicious faults or not according to the correlation.
3. The photovoltaic system fault warning method based on the BP neural network as claimed in claim 1,
step S1, specifically comprising the following steps:
101 Determining a distributed photovoltaic system which can be used in a regional environment range of a regional photovoltaic system, wherein the regional photovoltaic system comprises more than 1 other distributed photovoltaic systems besides an evaluated photovoltaic power generation system, and acquiring output data of the distributed photovoltaic systems;
102 For an in-region rated photovoltaic system and other n distributed photovoltaic systems, n>=1, respectively acquiring time tThe output data of the distributed photovoltaic system evaluated at t time is recorded as a vector Y t N distributed photovoltaic system output data form an output data matrix P t-i ，i＝1,2，…，n；P t-i Representing the output data of the ith distributed photovoltaic system at t moment;
103 Obtaining meteorological data of the regional photovoltaic system at the time t) to form a meteorological data vector W at the time t t-j ，j＝1,2，3，4…，m，W t-j Represents the jth meteorological data vector at the time t.
4. The photovoltaic system fault warning method based on the BP neural network as claimed in claim 2, wherein the step S2 specifically comprises the following steps:
201 Based on the installed capacity of the n distributed photovoltaic systems, normalizing the output data of the distributed photovoltaic systems, and taking the normalized parameters as input training parameters of the BP neural network model, wherein n input parameters of the BP neural network model are total, and the output data matrix after normalization at the time t is
Figure FDA0003707542640000023
202 When available meteorological data exist in the environmental range of the regional photovoltaic system, the meteorological data of the regional photovoltaic system are normalized to form a normalized meteorological matrix W at the moment t t-j * The normalized output data is matrix of
Figure FDA0003707542640000024
And weather matrix
Figure FDA0003707542640000025
And as the input training parameters of the BP neural network model, all the input parameters of the BP neural network model are n + m.
5. The photovoltaic system fault warning method based on the BP neural network as claimed in claim 2, wherein the step S3 specifically comprises the following steps:
301 ) establishing an input matrix x of the BP neural network model of the regional photovoltaic system under the moment t t-i * Is represented by formula (1):
Figure FDA0003707542640000021
302 According to the input matrix x t-j * Determining the number of layers of hidden layers of the BP neural network model according to the dimension of the BP neural network model and the requirement on the accuracy of a prediction result;
303 Adopting an M-layer unipolar Sigmoid function as a hidden layer activation function f (v) of the BP neural network model to obtain the BP neural network model of the photovoltaic system in the current area;
the hidden layer activation function f (v) of the BP neural network model is expressed as formula (2):
Figure FDA0003707542640000022
wherein v is an input parameter and is a multi-layer input of a hidden layer of the BP neural network model, and an initial value of the input parameter is an input matrix x t-i * The first layer is the input matrix x t-i * The input v to the second layer is the result after the first layer computation, v being defined in the field (- ∞, + ∞).
6. The photovoltaic system fault warning method based on the BP neural network as claimed in claim 2, wherein the step S4 specifically comprises the following steps:
401 Normalizing the output data of the evaluated distributed photovoltaic system according to the installed capacity of the regional evaluated distributed photovoltaic system, wherein the output vector of the normalized output data of the evaluated distributed photovoltaic system is Y t * ；
402 For input matrix x at time t) t-i * And the output vector Y t * Screening with PeThe correlation of the input and output functions is judged by the arson correlation coefficient;
Figure FDA0003707542640000031
in the formula: c is sample x t-i * And sample Y t * A correlation coefficient; cov (x) t-i * ,Y t * ) Is a sample x t-i * And sample Y t * Covariance of the correlation coefficient, var (x) t-i * )、Var(Y t * ) Fractional sample x t-i * And sample Y t * The variance of (a);
403 Setting a first correlation coefficient threshold value, filtering out the input matrix x with the correlation coefficient c smaller than the first correlation coefficient threshold value t-i * And the sum output vector is Y t * Obtaining filtered distributed photovoltaic system output data
Figure FDA0003707542640000032
And meteorological data
Figure FDA0003707542640000033
7. The photovoltaic system fault warning method based on the BP neural network as claimed in claim 2, wherein the step S5 specifically comprises the following steps:
distributed photovoltaic system output data filtered at time t
Figure FDA0003707542640000034
And meteorological data
Figure FDA0003707542640000035
The method comprises the steps of taking the parameters as input training parameters of a BP neural network model of a photovoltaic system in a current region; hidden layer activation function f (v) based on BP neural network model * ) To neural networkTraining and optimizing a neural network; using the filtered input matrix, output matrix and hidden layer activation function f (v) * ) Training the neural network to form a multilayer neural network, and obtaining a trained neural network system; (ii) a
Figure FDA0003707542640000036
v * Is the filtered input parameter, v, of the BP neural network model * Is the filtered distributed photovoltaic system output data
Figure FDA0003707542640000037
And meteorological data
Figure FDA0003707542640000038
8. The photovoltaic system fault warning method based on the BP neural network as claimed in claim 2, wherein the step S6 specifically comprises the following steps:
601 Applying the trained neural network system to regional photovoltaic system fault alarm, monitoring all input parameter vectors of a BP neural network model in real time, and obtaining corresponding output reference vectors
Figure FDA0003707542640000039
602 Computing an output reference vector using Pearson's correlation coefficients
Figure FDA00037075426400000310
Actual output of photovoltaic power station to be evaluated under corresponding timestamp
Figure FDA00037075426400000311
Correlation, denoted c Y ：
Figure FDA00037075426400000312
603 Setting a second correlation coefficient threshold when c y And when the second correlation coefficient threshold value is less than 0.95, the suspicious fault of the evaluated distributed photovoltaic power station is considered to exist, and an alarm is given.
9. The photovoltaic system fault warning method based on the BP neural network as claimed in claim 6,
the first correlation coefficient threshold is 0.95.
10. The photovoltaic system fault warning method based on the BP neural network as claimed in claim 8,
the second correlation coefficient threshold is 0.95.
CN202210712863.6A 2022-06-22 2022-06-22 BP neural network-based photovoltaic system fault alarm method Active CN115587642B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210712863.6A CN115587642B (en) 2022-06-22 2022-06-22 BP neural network-based photovoltaic system fault alarm method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210712863.6A CN115587642B (en) 2022-06-22 2022-06-22 BP neural network-based photovoltaic system fault alarm method

Publications (2)

Publication Number Publication Date
CN115587642A true CN115587642A (en) 2023-01-10
CN115587642B CN115587642B (en) 2023-07-11

Family

ID=84771597

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210712863.6A Active CN115587642B (en) 2022-06-22 2022-06-22 BP neural network-based photovoltaic system fault alarm method

Country Status (1)

Country Link
CN (1) CN115587642B (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117670300A (en) * 2023-12-08 2024-03-08 西安中创新能网络科技有限责任公司 Distributed photovoltaic equipment detection operation and maintenance system and method

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106570593A (en) * 2016-11-10 2017-04-19 甘肃省电力公司风电技术中心 Photovoltaic power station output data repairing method based on weather information
CN109150100A (en) * 2018-09-13 2019-01-04 国网电子商务有限公司 Fault detection method, device, equipment and the storage medium of photovoltaic plant
CN110751326A (en) * 2019-10-17 2020-02-04 江苏远致能源科技有限公司 Photovoltaic day-ahead power prediction method and device and storage medium
CN111177127A (en) * 2019-12-09 2020-05-19 国网甘肃省电力公司电力科学研究院 Photovoltaic power station output data restoration method based on BP neural network
CN111680820A (en) * 2020-05-08 2020-09-18 国网河南省电力公司电力科学研究院 Distributed photovoltaic power station fault diagnosis method and device

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106570593A (en) * 2016-11-10 2017-04-19 甘肃省电力公司风电技术中心 Photovoltaic power station output data repairing method based on weather information
CN109150100A (en) * 2018-09-13 2019-01-04 国网电子商务有限公司 Fault detection method, device, equipment and the storage medium of photovoltaic plant
CN110751326A (en) * 2019-10-17 2020-02-04 江苏远致能源科技有限公司 Photovoltaic day-ahead power prediction method and device and storage medium
CN111177127A (en) * 2019-12-09 2020-05-19 国网甘肃省电力公司电力科学研究院 Photovoltaic power station output data restoration method based on BP neural network
CN111680820A (en) * 2020-05-08 2020-09-18 国网河南省电力公司电力科学研究院 Distributed photovoltaic power station fault diagnosis method and device

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
孙祥晟: "基于经验模态分解的神经网络光伏发电预测方法研究", pages 54 - 58 *
陈世群: "一种基于极限学习机和皮尔逊相关系数的光伏阵列故障快速诊断方法", pages 57 - 64 *

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117670300A (en) * 2023-12-08 2024-03-08 西安中创新能网络科技有限责任公司 Distributed photovoltaic equipment detection operation and maintenance system and method

Also Published As

Publication number Publication date
CN115587642B (en) 2023-07-11

Similar Documents

Publication Publication Date Title
US20200285900A1 (en) Power electronic circuit fault diagnosis method based on optimizing deep belief network
CN110766059A (en) Transformer fault prediction method, device and equipment
CN111539550B (en) Method, device, equipment and storage medium for determining working state of photovoltaic array
WO2019080367A1 (en) Method for evaluating health status of mechanical device
CN112433896B (en) Method, device, equipment and storage medium for predicting server disk faults
WO2022052510A1 (en) Anomaly detection system and method for sterile filling production line
Rao et al. Dropout and pruned neural networks for fault classification in photovoltaic arrays
CN114355240B (en) Power distribution network ground fault diagnosis method and device
CN113822421B (en) Neural network-based anomaly locating method, system, equipment and storage medium
CN110688617B (en) Fan vibration abnormity detection method and device
CN110829417A (en) Electric power system transient stability prediction method based on LSTM double-structure model
CN112132052A (en) Power transmission line short-circuit fault diagnosis method based on first-layer wide convolution kernel depth residual error network
Ramirez et al. Alarms management by supervisory control and data acquisition system for wind turbines
CN111060779B (en) Power grid partition fault diagnosis method and system based on probabilistic neural network
CN111260893A (en) Fault early warning method and device for ocean platform propeller
CN113405799A (en) Bearing early fault detection method based on health state index construction and fault early warning limit self-learning
CN111967620A (en) Photovoltaic module diagnosis method, device, equipment and readable storage medium
CN115587642A (en) Photovoltaic system fault warning method based on BP neural network
Vera-Tudela et al. On the selection of input variables for a wind turbine load monitoring system
CN115296933A (en) Industrial production data risk level assessment method and system
CN116070902A (en) Power transmission line state evaluation method, device, computer equipment, medium and product
CN113758652B (en) Oil leakage detection method and device for converter transformer, computer equipment and storage medium
US10915097B2 (en) Fault signal recovery system and method
CN116821730B (en) Fan fault detection method, control device and storage medium
CN112881518B (en) Method for predicting residual life of dynamic filter compensator

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