CN117792279B - Distributed photovoltaic monitoring system based on neural network - Google Patents
Distributed photovoltaic monitoring system based on neural network Download PDFInfo
- Publication number
- CN117792279B CN117792279B CN202410211339.XA CN202410211339A CN117792279B CN 117792279 B CN117792279 B CN 117792279B CN 202410211339 A CN202410211339 A CN 202410211339A CN 117792279 B CN117792279 B CN 117792279B
- Authority
- CN
- China
- Prior art keywords
- module
- value
- adjustment
- fault
- condition
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 56
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 29
- 238000011156 evaluation Methods 0.000 claims abstract description 105
- 238000005457 optimization Methods 0.000 claims abstract description 56
- 238000000034 method Methods 0.000 claims abstract description 43
- 238000012423 maintenance Methods 0.000 claims abstract description 35
- 230000008569 process Effects 0.000 claims abstract description 32
- 238000003062 neural network model Methods 0.000 claims abstract description 26
- 238000012854 evaluation process Methods 0.000 claims abstract description 20
- 238000013135 deep learning Methods 0.000 claims description 5
- 230000000694 effects Effects 0.000 claims 2
- 238000012549 training Methods 0.000 description 9
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 238000010248 power generation Methods 0.000 description 3
- 238000000354 decomposition reaction Methods 0.000 description 2
- 230000001066 destructive effect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 230000001105 regulatory effect Effects 0.000 description 2
- 238000003860 storage Methods 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 239000000178 monomer Substances 0.000 description 1
Landscapes
- Photovoltaic Devices (AREA)
Abstract
The invention relates to the technical field of distributed photovoltaic monitoring, in particular to a distributed photovoltaic monitoring system based on a neural network, which comprises a monitoring module for monitoring operation data of photovoltaic equipment of each node; the neural network module is used for determining a standard data range value and a stable operation period when the photovoltaic equipment operates stably; the judging module is used for judging the running condition through the running data of the photovoltaic equipment of each node; the fault evaluation module is used for evaluating the fault condition of the photovoltaic equipment of each node in unstable operation; an adjustment module to determine an adjustment to the decision process based on the latent fault assessment values; the optimization module is used for determining optimization of the fault evaluation process according to the climate influence evaluation value, and the maintenance early warning module is used for determining to send fault maintenance early warning to the terminal according to the fault condition of the photovoltaic equipment of each node; the method and the device for monitoring the photovoltaic equipment through the neural network model determine the standard of the photovoltaic equipment in stable operation, and improve the accuracy and efficiency of photovoltaic monitoring.
Description
Technical Field
The invention relates to the technical field of distributed photovoltaic monitoring, in particular to a distributed photovoltaic monitoring system based on a neural network.
Background
Distributed photovoltaic starts rapid development in rural areas because of its advantages that have wide distribution area and monomer capacity are little, along with photovoltaic power generation user's increase, how to carry out accurate monitoring to distributed photovoltaic and become an important subject, and the prior art adopts the manpower to overhaul mostly, lacks the problem that the accuracy of monitoring leads to photovoltaic equipment to break down and causes economic loss.
Chinese patent publication No.: CN114070201a discloses a distributed photovoltaic monitoring control system. The system comprises: the system comprises a data acquisition and communication module, an information storage module, an information interaction module, a power prediction module and a power decomposition control module; the data acquisition and communication module is used for acquiring the power information of each distributed photovoltaic; the information storage module is used for storing the operation data of each distributed photovoltaic; the information interaction module is used for receiving an active output instruction sent by the power dispatching system; the power prediction module is used for predicting the output of each distributed photovoltaic to obtain predicted output; the power decomposition control module is used for determining an active adjustment instruction of each distributed photovoltaic in the target area at the preset moment according to the predicted output, the active output instruction and the operation data, and the active adjustment instruction is used for indicating each distributed photovoltaic to perform corresponding active output. The invention can realize the monitoring control of the distributed photovoltaic and can also combine factors such as deviation and the like to improve the practicability.
From this, it can be seen that the prior art has the problem that the accuracy and the inefficiency of monitoring distributed photovoltaic leads to photovoltaic damage to cause economic loss and potential safety hazard.
Disclosure of Invention
Therefore, the invention provides a distributed photovoltaic monitoring system based on a neural network, which is used for solving the problems of economic loss and potential safety hazard caused by photovoltaic damage due to the accuracy and low efficiency of distributed photovoltaic monitoring in the prior art.
To achieve the above object, the present invention provides a distributed photovoltaic monitoring system based on a neural network, including:
the monitoring module is used for monitoring the operation data of each node photovoltaic equipment when in operation;
The neural network module is connected with the monitoring module and is used for determining a standard data range value and a stable operation period when the operation of each node photovoltaic device is stable through a neural network model which carries out deep learning based on the historical operation data and the historical operation period data of each node photovoltaic device;
The judging module is connected with the neural network module and is used for determining the operation condition of each node photovoltaic device according to the operation data of each node photovoltaic device when in operation;
The fault evaluation module is connected with the judging module and used for calculating fault evaluation values of the photovoltaic equipment of each node in unstable operation;
the adjusting module is connected with the fault evaluation module and used for determining adjustment of the judging process according to the fault evaluation value;
the optimizing module is connected with the adjusting module and used for determining the optimization of the fault evaluation process according to the climate influence evaluation value;
The maintenance early warning module is connected with the adjusting module and the optimizing module and is used for determining to send out a fault maintenance early warning signal to the terminal according to the fault condition of the photovoltaic equipment of each node;
The judging module determines the operation condition of each node photovoltaic device according to the operation data of each node photovoltaic device monitored by the monitoring module, the standard data range value determined by the neural network model and the stable operation period; and the fault evaluation module determines a fault evaluation value of the photovoltaic equipment according to the difference value of the operation data among the photovoltaic equipment of each node and the time from the last maintenance.
Further, the judging module determines the running condition of each node photovoltaic device according to the comparison result of the stable condition evaluation value and the preset stable condition evaluation value, and determines that the running condition of each node photovoltaic device is unstable under the condition that the stable condition evaluation value is larger than the preset stable condition evaluation value.
Further, the fault evaluation module calculates a fault evaluation value of each node photovoltaic device under the condition that the running condition of each node photovoltaic device is unstable, and sets:
；
Wherein G represents a fault evaluation value, X represents a difference value of operation data among the photovoltaic devices of each node, and X0 represents a preset difference value; y represents the time from the last fault maintenance of the photovoltaic equipment of each node, and Y0 represents the preset time.
Further, the adjustment module determines adjustment of the judging process according to the comparison result of the fault evaluation value and the preset fault evaluation value, and the adjustment module determines adjustment of the judging process under the condition that the fault evaluation value is greater than or equal to the preset fault evaluation value.
Further, the adjustment module determines an adjustment mode according to a comparison result of a difference value between the fault evaluation value and a preset difference value under a condition that the adjustment is determined to adjust the judgment process, and determines to adjust the judgment process in a first adjustment mode under a condition that the difference value is smaller than a first preset difference value, wherein the first adjustment mode comprises that the adjustment module adjusts the maximum value of all the historical operation data and the average value of the historical operation stable time in a first adjustment coefficient and adjusts the minimum value of all the historical operation data in a second adjustment coefficient.
Further, the adjustment module determines an adjustment mode according to a comparison result of a difference value between the fault evaluation value and the preset fault evaluation value and a preset difference value under a condition that the adjustment is determined to adjust the judging process, and determines to adjust the judging process in a second adjustment mode under a condition that the difference value is greater than or equal to a first preset difference value and less than a second preset difference value, wherein the second adjustment mode comprises that the adjustment module adjusts the maximum value of all the historical operation data and the average value of the historical operation stable time in a second adjustment coefficient and adjusts the minimum value of all the historical operation data in a first adjustment coefficient.
Further, the adjustment module determines an adjustment mode according to a comparison result of a difference value between the fault evaluation value and a preset difference value under the condition that the adjustment module determines that the judgment process is adjusted, and determines that the photovoltaic equipment breaks down under the condition that the difference value is greater than or equal to a second preset difference value, and the maintenance early warning module sends a fault maintenance early warning signal to the terminal.
Further, the optimization module determines to optimize the fault evaluation process according to the comparison result of the climate influence evaluation value and the preset climate influence evaluation value, and determines to optimize the fault evaluation process under the condition that the climate influence evaluation value is greater than or equal to the preset climate influence evaluation value.
Further, the optimization module determines an optimization mode according to a comparison result of a difference value between the weather-related evaluation value and the preset weather-related evaluation value and a third preset difference value under the condition that the fault evaluation process is determined to be optimized, and optimizes the preset fault evaluation value in a first optimization mode under the condition that the difference value is smaller than or equal to the third preset difference value, wherein the first optimization mode comprises optimizing the preset fault evaluation value in an optimization coefficient.
Further, the optimization module determines an optimization mode according to a comparison result of a difference value between the weather influence evaluation value and the preset weather influence evaluation value and a third preset difference value under the condition that the fault evaluation process is determined to be optimized, and optimizes the fault evaluation process in a second optimization mode under the condition that the difference value is larger than the third preset difference value, wherein the second optimization mode comprises that the maintenance early warning module sends a fault maintenance early warning signal to a terminal.
Compared with the prior art, the method has the beneficial effects that the historical operation data of the photovoltaic equipment of each node to be monitored is evaluated by adopting the neural network model to obtain the standard data range value and the stable operation period of the operation data of the photovoltaic equipment of each node, and the stability of the operation condition is determined by using the neural network model of deep learning, so that not only is the consumption of a large amount of manpower resources saved, but also the efficiency and the accuracy of distributed photovoltaic monitoring are improved, and the normal operation of the distributed photovoltaic equipment is further ensured so as not to cause economic loss and potential safety hazard.
Further, the invention analyzes and calculates the operation data and the use time of each node photovoltaic device monitored by the monitoring module and the standard data range value and the stable operation period of the operation data determined by the neural network model through the judging module to determine the operation condition of each node photovoltaic device, and if the operation data of each node photovoltaic device is not in a plurality of types of standard data range values and has long use time, the operation condition of each node photovoltaic device is unstable; if the operation data of the photovoltaic equipment of each node is not in the standard data range, the types of the values are few, the service time is short, the operation condition of the photovoltaic equipment of each node is stable, and the accuracy and the efficiency of distributed photovoltaic monitoring are improved by the method, so that the economic loss and the potential safety hazard are reduced.
Further, the fault evaluation module is used for carrying out fault analysis on the photovoltaic equipment with unstable running conditions, the fault evaluation value is calculated according to the running data difference value of the photovoltaic equipment to be evaluated and other photovoltaic equipment and the maintenance time from last time, the adjustment module is used for determining whether to adjust the standard data range value and the stable running period of the running data determined by the neural network model according to the comparison result of the fault evaluation value and the preset fault evaluation value, the accuracy of distributed photovoltaic monitoring is improved through the method, and the phenomenon that the economic loss is caused by continuous use of the photovoltaic equipment due to unknowing condition of a user under the condition of unstable running is avoided.
Further, an adjustment mode is determined through an adjustment module according to the comparison result of the difference value of the fault evaluation value and the preset difference value, the adjustment module determines the fault occurrence probability of the photovoltaic equipment according to the difference value and the preset difference value, and if the fault occurrence probability is small, the adjustment module determines the standard data range value and the stable operation period of the reduced neural network model determination operation data; if the probability of occurrence of faults is high, the adjustment module determines the standard data range value and the stable operation period of the operation data determined by the increased neural network model; if the photovoltaic equipment is determined to have faults, the maintenance early warning module determines to send fault maintenance early warning signals to the terminal, and the accuracy of distributed photovoltaic monitoring is improved through the method, so that the parameters in the process of determining the distributed photovoltaic are flexibly regulated and controlled, and further economic loss and potential safety hazards are reduced.
Further, the optimization module is used for determining the optimization of the fault evaluation process according to the climate influence of the region where the photovoltaic equipment is located, and if the accuracy of the fault evaluation module is not high when the photovoltaic equipment is subjected to fault evaluation due to the fact that the climate of the region where the photovoltaic equipment is located is severe, the optimization module is used for determining parameters of the fault evaluation process to be improved by an optimization coefficient; if a major natural disaster occurs in the area where the photovoltaic equipment is located, the maintenance early warning module determines to send out a fault maintenance early warning signal to the terminal, and the accuracy of distributed photovoltaic monitoring is improved by the method, so that economic loss and potential safety hazards are reduced.
Drawings
FIG. 1 is a system architecture diagram of a distributed photovoltaic monitoring system based on a neural network in accordance with an embodiment of the present invention;
FIG. 2 is a flowchart of the operation of a distributed photovoltaic monitoring system adjustment module based on a neural network according to an embodiment of the present invention;
fig. 3 is a flowchart of the operation of the distributed photovoltaic monitoring system optimization module based on the neural network according to the embodiment of the present invention.
Detailed Description
In order that the objects and advantages of the invention will become more apparent, the invention will be further described with reference to the following examples; it should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
Preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are merely for explaining the technical principles of the present invention, and are not intended to limit the scope of the present invention.
It should be noted that, in the description of the present invention, terms such as "upper," "lower," "left," "right," "inner," "outer," and the like indicate directions or positional relationships based on the directions or positional relationships shown in the drawings, which are merely for convenience of description, and do not indicate or imply that the apparatus or elements must have a specific orientation, be constructed and operated in a specific orientation, and thus should not be construed as limiting the present invention.
Furthermore, it should be noted that, in the description of the present invention, unless explicitly specified and limited otherwise, the terms "mounted," "connected," and "connected" are to be construed broadly, and may be either fixedly connected, detachably connected, or integrally connected, for example; can be mechanically or electrically connected; can be directly connected or indirectly connected through an intermediate medium, and can be communication between two elements. The specific meaning of the above terms in the present invention can be understood by those skilled in the art according to the specific circumstances.
Referring to fig. 1-3, fig. 1 is a system configuration diagram of a distributed photovoltaic monitoring system based on a neural network according to an embodiment of the present invention; FIG. 2 is a flowchart of the operation of a distributed photovoltaic monitoring system adjustment module based on a neural network according to an embodiment of the present invention; fig. 3 is a flowchart of the operation of the distributed photovoltaic monitoring system optimization module based on the neural network according to the embodiment of the present invention.
The embodiment of the invention discloses a distributed photovoltaic monitoring system based on a neural network, which comprises the following components:
the monitoring module is used for monitoring the operation data of each node photovoltaic equipment when in operation;
The neural network module is connected with the monitoring module and is used for determining a standard data range value and a stable operation period when the operation of each node photovoltaic device is stable through a neural network model which carries out deep learning based on the historical operation data and the historical operation period data of each node photovoltaic device;
The judging module is connected with the neural network module and is used for determining the operation condition of each node photovoltaic device according to the operation data of each node photovoltaic device when in operation;
The fault evaluation module is connected with the judging module and used for calculating fault evaluation values of the photovoltaic equipment of each node in unstable operation;
the adjusting module is connected with the fault evaluation module and used for determining adjustment of the judging process according to the fault evaluation value;
the optimizing module is connected with the adjusting module and used for determining the optimization of the fault evaluation process according to the climate influence evaluation value;
and the maintenance early warning module is connected with the adjusting module and the optimizing module and is used for determining to send out a fault maintenance early warning signal to the terminal according to the fault condition of the photovoltaic equipment of each node.
The operation data in the embodiment of the invention comprises, but is not limited to, voltage when the photovoltaic equipment works, current when the photovoltaic equipment works, power when the photovoltaic equipment works and generating capacity when the photovoltaic equipment works.
The forming process of the neural network model comprises the steps of firstly selecting an original data set, including historical operation data and historical operation period data of each node photovoltaic device, then carrying out de-duplication and cleaning on the original data set by utilizing CCNet to obtain a plurality of training data samples, carrying out label classification on the training data samples according to rules to obtain a training data set, inputting the training data set into the neural network model, training the neural network model, obtaining an evaluation data set according to the training data set in the training process, judging operation data sets and stable operation period data sets of each node photovoltaic device for the neural network model, evaluating the neural network model after training by utilizing the evaluation data set, outputting an evaluation result, and determining whether the neural network model after training is qualified according to the evaluation result to obtain a qualified neural network model.
Specifically, the neural network module obtains a standard data range value and a stable operation period of operation data of each node photovoltaic device in stable operation through the neural network model.
The standard data range value of the operation data in the embodiment of the invention comprises a minimum value Djmin and a maximum value Djmax of all historical operation data when the operation of the photovoltaic equipment of each node is stable, and the stable operation period comprises an average value T0, j=1, 2,3 and 4 of the historical operation stable time of the photovoltaic equipment of each node; wherein D1min represents the minimum operating voltage of the photovoltaic equipment in stable operation, D2min represents the minimum operating current of the photovoltaic equipment in stable operation, D3min represents the minimum power of the photovoltaic equipment in stable operation, and D4min represents the minimum power generation amount of the photovoltaic equipment in stable operation; d1max represents the maximum operating voltage of the photovoltaic device during steady operation, D2max represents the maximum operating current of the photovoltaic device during steady operation, D3max represents the maximum power of the photovoltaic device during steady operation, and D4max represents the maximum power generation amount of the photovoltaic device during steady operation.
Specifically, the method and the system evaluate the historical operation data of the photovoltaic equipment of each node to be monitored by adopting the neural network model to obtain the standard data range value and the stable operation period of the operation data of the photovoltaic equipment of each node, and determine the stability of the operation condition by using the neural network model with deep learning, so that not only is a great deal of manpower resource consumption saved, but also the efficiency and the accuracy of distributed photovoltaic monitoring are improved, and the normal operation of the distributed photovoltaic equipment is further ensured so as not to cause economic loss and potential safety hazard.
Specifically, the determining module determining the operation condition of each node photovoltaic device includes determining the operation condition of each node photovoltaic device according to a comparison result of the stable condition evaluation value P and a preset stable condition evaluation value P0;
if P is less than or equal to P0, the judging module determines that the running condition of the photovoltaic equipment of each node is stable;
if P is more than P0, the judging module determines that the running condition of the photovoltaic equipment of each node is unstable;
However, the value of the preset stability condition evaluation value P0 is not limited to 0.4, and may be adjusted according to actual needs by those skilled in the art.
Specifically, the steady state evaluation value P is calculated by the following formula, and is set:
；
Wherein W (r) represents a data category in which the operation data is lower than the minimum value of the belonging-category history operation data, W (e) represents a data category in which the operation data is higher than the maximum value of the belonging-category history operation data, N0 represents a preset category number, and the value thereof is set to 2; t represents the time of stable operation of the photovoltaic equipment of each node, and T0 represents the average value of the historical operation stable time of the photovoltaic equipment of each node.
Specifically, the invention analyzes and calculates the operation data and the use time of each node photovoltaic device monitored by the monitoring module and the standard data range value and the stable operation period of the operation data determined by the neural network model through the judging module to determine the operation condition of each node photovoltaic device, and if the operation data of each node photovoltaic device is not in the plurality of types of the standard data range values and has long use time, the operation condition of each node photovoltaic device is unstable; if the operation data of the node photovoltaic devices are not in the standard data range, the types of the standard data range values are few, the service time is short, the operation condition of the node photovoltaic devices is stable, and the accuracy and the efficiency of distributed photovoltaic monitoring are improved by the method, so that the economic loss and the potential safety hazard are reduced.
Specifically, the fault evaluation module calculates a fault evaluation value G of each node photovoltaic device under the condition that the operation of each node photovoltaic device is determined to be unstable, and sets:
；
Wherein X represents the difference value of the operation data among the photovoltaic devices of each node, and X0 represents a preset difference value; y represents the time from the last fault maintenance of the photovoltaic equipment of each node, and Y0 represents the preset time.
In the embodiment of the invention, the value of the preset difference value X0 is the maximum difference value in the historical operation data of each node photovoltaic device in stable operation; the preset time is the historical average time of the faults of the photovoltaic equipment of each node.
Specifically, the adjustment module determining adjustment to the determination process includes determining adjustment to the determination process according to a comparison result of the failure evaluation value G and a preset failure evaluation value G0;
If G is more than or equal to G0, the adjustment module determines to adjust the judging process;
If G is less than G0, the adjustment module determines not to adjust the judging process;
however, the value of the predetermined failure evaluation value G0 is not limited to 0.5, and the value can be adjusted according to actual needs by those skilled in the art.
Specifically, the fault evaluation module is used for carrying out fault analysis on the photovoltaic equipment with unstable running conditions, the fault evaluation value is calculated according to the running data difference value of the photovoltaic equipment to be evaluated and other photovoltaic equipment and the maintenance time from last time, the adjustment module is used for determining whether to adjust the standard data range value and the stable running period of the running data determined by the neural network model according to the comparison result of the fault evaluation value and the preset fault evaluation value, the accuracy of distributed photovoltaic monitoring is improved through the method, and the phenomenon that the economic loss is caused by continuous use of the photovoltaic equipment due to unknowing condition of a user under the condition of unstable running is avoided.
Specifically, the adjustment module determines an adjustment mode according to a comparison result of a difference DeltaG between a fault evaluation value and a preset difference DeltaG 0i under the condition of determining to adjust the judging process;
If the delta G < [ delta ] G01, the adjustment module determines to adjust the judging process in a first adjustment mode;
If the delta G01 is less than or equal to delta G < [ delta ] G02, the adjustment module determines to adjust the judging process in a second adjustment mode;
if the delta G is not less than delta G02, the adjusting module determines that the photovoltaic equipment fails;
The first preset difference Δg01 is set to 0.7, the second preset difference Δg02 is set to 1.4, i=1, 2, but the above values are not limited thereto, and those skilled in the art can adjust the values according to actual needs.
Specifically, the adjustment module adjusts the maximum value of all the historical operation data and the average value of the historical operation stable time by a first adjustment coefficient K1 and adjusts the minimum value of the historical operation data by a second adjustment coefficient K2 under the condition that the adjustment of the judging process by the first adjustment mode is determined;
The adjustment module adjusts the maximum value of all the historical operation data and the average value of the historical operation stable time by a second adjustment coefficient K2 and adjusts the minimum value of all the historical operation data by a first adjustment coefficient K1 under the condition that the judgment process is determined to be adjusted by a second adjustment mode;
And the maintenance early warning module sends a fault maintenance early warning signal to the terminal under the condition that the photovoltaic equipment is determined to be in fault by the adjustment module.
Specifically, the first adjustment coefficient K1 is calculated by the following formula, and is set:
；
The second adjustment coefficient K2 is calculated by the following formula, set:
；
Setting the parameter of the determination process adjusted in the first adjustment manner to Djmax' =k1× Djmax; djmin '=k2× Djmin, T0' =k1×t0;
Setting the parameter of the determination process adjusted in the second adjustment manner to Djmax ″=k2× Djmax; djmin "=k1× Djmin, t0" =k2×t0.
The parameters of the judging process in the embodiment of the invention comprise the minimum value and the maximum value of all the historical operation data when the photovoltaic equipment of each node is stable in operation and the average value of the historical operation stability time of the photovoltaic equipment of each node.
Specifically, an adjustment mode is determined through an adjustment module according to the comparison result of the difference value of the fault evaluation value and the preset difference value, the adjustment module determines the fault occurrence probability of the photovoltaic equipment according to the difference value and the preset difference value, and if the fault occurrence probability is small, the adjustment module determines the standard data range value and the stable operation period of the operation data determined by the reduced neural network model; if the probability of occurrence of the fault is high, the adjustment module determines a standard data range value and a stable operation period of the operation data determined by the increased neural network model; if the photovoltaic equipment is determined to have faults, the maintenance early warning module determines to send fault maintenance early warning signals to the terminal, and the accuracy of distributed photovoltaic monitoring is improved through the method, so that the parameters of the photovoltaic equipment during judgment are flexibly regulated and controlled, and further economic loss and potential safety hazards are reduced.
Specifically, the optimization module determines that the fault evaluation process is optimized or not according to the comparison result of the climate influence evaluation value H and the preset climate influence evaluation value H0;
if H is more than or equal to H0, the optimization module determines to optimize the fault evaluation process;
If H is less than H0, the optimization module determines that the fault evaluation process is not optimized;
however, the above-mentioned value is not limited thereto, and the person skilled in the art may adjust the value according to actual needs.
Specifically, the climate influence evaluation value H is calculated by the following formula, and is set:
；
Wherein C represents the times of overcast days in the region where the photovoltaic equipment is located within a preset time, C0 represents the times of the preset overcast days, V represents the times of the region where the photovoltaic equipment is located at a temperature higher than 25 ℃, V0 represents the preset times, Represents a destructive natural disaster factor, which has a value of 0 or 2.
In the embodiment of the invention, the preset time is preferably 3 months, the value of the preset cloudy day number is an average value of historical cloudy day numbers in the preset time of the same time point in the region where the photovoltaic equipment is located, the value of the preset time number is the number that the historical temperature of the preset time of the same time point in the region where the photovoltaic equipment is located is higher than 25 ℃, the destructive natural disaster factor comprises that the value is 2 when the natural disaster including but not limited to hail, typhoon and earthquake occurs in the region where the photovoltaic equipment is located, and the value is 0 if the natural disaster does not occur.
Specifically, under the condition that the optimization module determines to optimize the fault evaluation process, the optimization module determines an optimization mode according to the comparison result of the difference value delta H of the weather influence evaluation value and the preset weather influence evaluation value and the third preset difference value delta H0;
if delta H is less than or equal to delta H0, the optimization module determines to optimize in a first optimization mode;
if delta H > -delta H0, the optimization module determines to optimize in a second optimization mode;
however, the value of the third preset difference Δh0 is not limited to 0.5, and may be adjusted according to actual needs by those skilled in the art.
Specifically, the optimization module determines to optimize a preset failure evaluation value by an optimization coefficient F under the condition of determining to optimize in a first optimization manner;
and the maintenance early warning module sends a fault maintenance early warning signal to the terminal under the condition of optimizing in a second optimization mode.
Specifically, the optimization coefficient F is calculated by the following formula, and is set:
；
the optimized preset failure evaluation value is set to g0' =f×g0.
Specifically, the optimization module determines the optimization of the fault evaluation process according to the climate influence of the region where the photovoltaic equipment is located, and if the accuracy of the fault evaluation module is not high when the photovoltaic equipment is subjected to fault evaluation due to the fact that the climate of the region where the photovoltaic equipment is located is severe, the optimization module determines parameters of the fault evaluation process to be improved by an optimization coefficient; if a major natural disaster occurs in the area where the photovoltaic equipment is located, the maintenance early warning module determines to send out a fault maintenance early warning signal to the terminal, and the accuracy of distributed photovoltaic monitoring is improved by the method, so that economic loss and potential safety hazards are reduced.
Thus far, the technical solution of the present invention has been described in connection with the preferred embodiments shown in the drawings, but it is easily understood by those skilled in the art that the scope of protection of the present invention is not limited to these specific embodiments. Equivalent modifications and substitutions for related technical features may be made by those skilled in the art without departing from the principles of the present invention, and such modifications and substitutions will be within the scope of the present invention.
The foregoing description is only of the preferred embodiments of the invention and is not intended to limit the invention; various modifications and variations of the present invention will be apparent to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (8)
1. A distributed photovoltaic monitoring system based on a neural network, comprising:
the monitoring module is used for monitoring the operation data of each node photovoltaic equipment when in operation;
The neural network module is connected with the monitoring module and is used for determining a standard data range value and a stable operation period when the operation of each node photovoltaic device is stable through a neural network model which carries out deep learning based on the historical operation data and the historical operation period data of each node photovoltaic device;
The judging module is connected with the neural network module and is used for determining the operation condition of each node photovoltaic device according to the operation data of each node photovoltaic device when in operation;
The fault evaluation module is connected with the judging module and used for calculating fault evaluation values of the photovoltaic equipment of each node in unstable operation;
the adjusting module is connected with the fault evaluation module and used for determining adjustment of the judging process according to the fault evaluation value;
the optimizing module is connected with the adjusting module and used for determining the optimization of the fault evaluation process according to the climate influence evaluation value;
The maintenance early warning module is connected with the adjusting module and the optimizing module and is used for determining to send out a fault maintenance early warning signal to the terminal according to the fault condition of the photovoltaic equipment of each node;
The judging module determines the operation condition of each node photovoltaic device according to the operation data of each node photovoltaic device monitored by the monitoring module, the standard data range value determined by the neural network model and the stable operation period; the fault evaluation module determines a fault evaluation value of the photovoltaic equipment according to the difference value of the operation data among the photovoltaic equipment of each node and the time from the last maintenance;
The judging module determines the running condition of each node photovoltaic device according to the comparison result of the stable condition evaluation value and the preset stable condition evaluation value, and determines that the running condition of each node photovoltaic device is unstable under the condition that the stable condition evaluation value is larger than the preset stable condition evaluation value;
The fault evaluation module calculates the fault evaluation value of each node photovoltaic device and sets the fault evaluation value under the condition that the running condition of each node photovoltaic device is unstable
，
Wherein G represents a fault evaluation value, X represents a difference value of operation data among the photovoltaic devices of each node, and X0 represents a preset difference value; y represents the time from the last fault maintenance of the photovoltaic equipment of each node, and Y0 represents the preset time.
2. The neural network-based distributed photovoltaic monitoring system according to claim 1, wherein the adjustment module determines adjustment of the determination process according to a comparison result of the failure evaluation value and a preset failure evaluation value, and the adjustment module determines adjustment of the determination process on the condition that the failure evaluation value is greater than or equal to the preset failure evaluation value.
3. The neural network-based distributed photovoltaic monitoring system according to claim 2, wherein the adjustment module determines an adjustment mode according to a comparison result of a difference value between a fault evaluation value and a preset difference value under a condition that the adjustment is determined to be performed on the determination process, and determines to perform adjustment on the determination process in a first adjustment mode under a condition that the difference value is smaller than a first preset difference value, the first adjustment mode including the adjustment module adjusting a maximum value of all historical operation data and an average value of historical operation stability time in a first adjustment coefficient and adjusting a minimum value of all historical operation data in a second adjustment coefficient.
4. The distributed photovoltaic monitoring system based on the neural network according to claim 3, wherein the adjustment module determines an adjustment mode according to a comparison result of a difference value between a fault evaluation value and a preset difference value under a condition that the adjustment is determined to be performed on the judging process, and determines to perform adjustment on the judging process in a second adjustment mode under a condition that the difference value is greater than or equal to a first preset difference value and less than a second preset difference value, the second adjustment mode includes the adjustment module adjusting a maximum value of all historical operation data and an average value of historical operation stable time in a second adjustment coefficient and adjusting a minimum value of all historical operation data in the first adjustment coefficient.
5. The distributed photovoltaic monitoring system based on the neural network according to claim 4, wherein the adjustment module determines an adjustment mode according to a comparison result of a difference value between a fault evaluation value and a preset difference value under a condition that the adjustment module determines that the photovoltaic device is faulty, and the maintenance early warning module sends a fault maintenance early warning signal to the terminal under a condition that the difference value is greater than or equal to a second preset difference value.
6. The neural network-based distributed photovoltaic monitoring system according to claim 5, wherein the optimization module determines to optimize the fault evaluation process according to a comparison result of the climate influence evaluation value and a preset climate influence evaluation value, and the optimization module determines to optimize the fault evaluation process under a condition that the climate influence evaluation value is greater than or equal to the preset climate influence evaluation value.
7. The neural network-based distributed photovoltaic monitoring system according to claim 6, wherein the optimization module determines an optimization mode according to a comparison result of a difference value between the climate influence evaluation value and the preset climate influence evaluation value and a third preset difference value under a condition that the difference value is less than or equal to the third preset difference value, and the optimization module performs optimization in a first optimization mode, wherein the first optimization mode includes optimizing the preset fault evaluation value with an optimization coefficient.
8. The distributed photovoltaic monitoring system based on the neural network according to claim 7, wherein the optimization module determines an optimization mode according to a comparison result of a difference value between the weather effect evaluation value and the preset weather effect evaluation value and a third preset difference value under the condition that the optimization module determines to optimize the fault evaluation process, and the optimization module performs optimization in a second optimization mode under the condition that the difference value is greater than the third preset difference value, wherein the second optimization mode comprises the maintenance early warning module sending a fault maintenance early warning signal to a terminal.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410211339.XA CN117792279B (en) | 2024-02-27 | 2024-02-27 | Distributed photovoltaic monitoring system based on neural network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410211339.XA CN117792279B (en) | 2024-02-27 | 2024-02-27 | Distributed photovoltaic monitoring system based on neural network |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117792279A CN117792279A (en) | 2024-03-29 |
| CN117792279B true CN117792279B (en) | 2024-05-17 |
Family
ID=90402180
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410211339.XA Active CN117792279B (en) | 2024-02-27 | 2024-02-27 | Distributed photovoltaic monitoring system based on neural network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117792279B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113283580A (en) * | 2021-04-30 | 2021-08-20 | 太原理工大学 | Automatic fault detection method for solar cell panel |
| CN115774951A (en) * | 2022-10-02 | 2023-03-10 | 中国三峡新能源(集团)股份有限公司陕西分公司 | Method for rapidly discriminating faults of photovoltaic power station array |
| CN116054740A (en) * | 2023-01-17 | 2023-05-02 | 阿里云计算有限公司 | Fault detection and fault detection model processing method and device for photovoltaic power generation equipment |
| CN117200693A (en) * | 2023-07-25 | 2023-12-08 | 国电环境保护研究院有限公司 | Photovoltaic module fault diagnosis method, device, equipment and storage medium |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117713221B (en) * | 2024-02-01 | 2024-04-16 | 深圳戴普森新能源技术有限公司 | Micro-inversion photovoltaic grid-connected optimization system |
-
2024
- 2024-02-27 CN CN202410211339.XA patent/CN117792279B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113283580A (en) * | 2021-04-30 | 2021-08-20 | 太原理工大学 | Automatic fault detection method for solar cell panel |
| CN115774951A (en) * | 2022-10-02 | 2023-03-10 | 中国三峡新能源(集团)股份有限公司陕西分公司 | Method for rapidly discriminating faults of photovoltaic power station array |
| CN116054740A (en) * | 2023-01-17 | 2023-05-02 | 阿里云计算有限公司 | Fault detection and fault detection model processing method and device for photovoltaic power generation equipment |
| CN117200693A (en) * | 2023-07-25 | 2023-12-08 | 国电环境保护研究院有限公司 | Photovoltaic module fault diagnosis method, device, equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117792279A (en) | 2024-03-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109146093B (en) | Power equipment field investigation method based on learning | |
| Chen et al. | A statistical risk assessment framework for distribution network resilience | |
| CN107390049A (en) | A kind of power cable fault monitoring method and device | |
| CN112611936A (en) | Distribution network transformer fault dynamic detection and classification system based on edge calculation | |
| CN113049142A (en) | Temperature sensor alarm method, device, equipment and storage medium | |
| Mitchell et al. | Using a neural network to predict the dynamic frequency response of a power system to an under-frequency load shedding scenario | |
| CN112886923B (en) | Photovoltaic power station operation and maintenance method and device in thunder and lightning weather | |
| CN117332215B (en) | High-low voltage power distribution cabinet abnormal fault information remote monitoring system | |
| US20220236451A1 (en) | Weather-related Overhead Distribution Line Failures Online Forecasting | |
| US11451053B2 (en) | Method and arrangement for estimating a grid state of a power distribution grid | |
| US11086278B2 (en) | Adaptive system monitoring using incremental regression model development | |
| CN116885766A (en) | Control method and system for grid-connected operation of distributed power supply | |
| CN115603459A (en) | Digital twin technology-based power distribution network key station monitoring method and system | |
| CN117792279B (en) | Distributed photovoltaic monitoring system based on neural network | |
| CN113379005A (en) | Intelligent energy management system and method for power grid power equipment | |
| JP2003090887A (en) | Predication system and prediction method of instantaneous voltage drop by thunderbolt | |
| CN115511156A (en) | Main transformer overload early warning method and system based on load prediction | |
| CN115619098A (en) | Intelligent electric power material data processing method based on grading monitoring and early warning | |
| CN111371484B (en) | Unmanned aerial vehicle base station control method, device and system and computer readable storage medium | |
| US20230012079A1 (en) | Renewable energy system stabilization system and system stabilization support method | |
| CN115224684A (en) | Intelligent power distribution network risk state identification method and system based on immune hazard theory | |
| CN113191535A (en) | Design wind speed correction method in gale disaster early warning | |
| CN111600392A (en) | Intelligent power grid equipment monitoring system | |
| Lair et al. | Windy Smart Grid: Forecasting the impact of storms on the power system | |
| CN116937631B (en) | Electric energy storage management system based on data processing |
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 |