Photovoltaic power station risk prediction method, device, equipment, medium and program product

Abstract

The invention discloses a photovoltaic power station risk prediction method, device and equipment, a medium and a program product, and the method comprises the steps: obtaining multi-dimensional data, collected by an information collection system, of a photovoltaic power station, processing the multi-dimensional data, obtaining event data, feature data and fault result data, and carrying out the processing of the event data, the feature data and the fault result data; constructing a mapping matrix based on a mapping relation among the event data, the feature data and the fault result data, analyzing a fault logic path of the photovoltaic power station according to the mapping matrix, constructing a risk prediction model based on an analysis result, and inputting real-time monitoring data of the photovoltaic power station into the risk prediction model. According to the method, the accuracy of risk prediction of the photovoltaic power station is effectively improved, accurate prediction of potential risks is realized, the timeliness of risk identification is ensured, and the safety of the photovoltaic power station is improved.

Description

Technical Field

[0001] The present invention relates to the field of electric power technology, and in particular to a photovoltaic power station risk prediction method, device, equipment, medium and program product. Background Art

[0002] With the development of science and technology, new energy systems represented by photovoltaics pay more attention to clean, low-carbon, safe and efficient energy consumption and power storage. With the continuous increase of global renewable energy, photovoltaic power generation, as a clean, environmentally friendly and sustainable energy form, has become an important part of the global energy supply.

[0003] During the long-term operation of photovoltaic power stations, due to equipment failures, changes in environmental factors, and challenges in maintenance and management, photovoltaic power stations face a variety of potential risks. Equipment failure risks mainly come from damage or aging of core components such as photovoltaic modules, inverters, battery energy storage systems, and transformers. These failures not only affect the power generation efficiency of the power station, but may also cause the system to shut down in serious cases. Therefore, risk prediction of photovoltaic power stations is particularly important. Current photovoltaic power station risk monitoring usually relies on a single or local data source, resulting in limited prediction accuracy and coverage, and unable to accurately detect potential risks of photovoltaic power stations. Summary of the invention

[0004] The main purpose of the present invention is to provide a method, device, equipment, medium and program product for risk prediction of photovoltaic power plants, aiming to solve the technical problem that the existing technology relies on a single data source in risk prediction of photovoltaic power plants, resulting in limited prediction accuracy and coverage, and cannot accurately detect the potential risks of photovoltaic power plants.

[0005] To achieve the above object, the present invention provides a photovoltaic power station risk prediction method, the method comprising the following steps:

[0006] Acquire multi-dimensional data of the photovoltaic power station collected by an information collection system, wherein the information collection system includes a space-based collection module, an air-based collection module, and a ground-based collection module, and the multi-dimensional data includes environmental data, equipment status data, and equipment operation data of the photovoltaic power station;

[0007] Processing the multidimensional data to obtain event data, feature data and fault result data, wherein the event data includes multiple fault events of the photovoltaic power station, the feature data includes feature data corresponding to each fault event, the feature data is composed of one or more faulty photovoltaic components corresponding to the fault event, and the fault result data includes fault event results corresponding to each fault event;

[0008] Constructing a mapping matrix based on the mapping relationship between the event data, the feature data and the fault result data;

[0009] Analyzing the fault logic path of the photovoltaic power station according to the mapping matrix, and building a risk prediction model based on the analysis results;

[0010] The real-time monitoring data of the photovoltaic power station collected by the information collection system is input into the risk prediction model to obtain the risk prediction result of the photovoltaic power station, and the risk prediction result includes the risk level of each area in the photovoltaic power station.

[0011] Optionally, analyzing the fault logic path of the photovoltaic power station according to the mapping matrix and constructing a risk prediction model based on the analysis result includes:

[0012] Analyzing the fault logic path of the photovoltaic power station according to the mapping matrix, and constructing a fault logic path model based on the analysis result, wherein the fault logic path model includes multiple fault logic paths;

[0013] Performing path significance analysis on each fault logic path in the fault logic path model;

[0014] Construct an initial path significance model based on the significance analysis results:

[0015]

[0016] Among them, p i is the reliability parameter of PV module i, Y i ={Pk:i∈Pk,1≤k≤u} represents the minimum path set containing PV module i, Y i Contains u paths, X=(X1,...,X n ) represents a binary random vector. If PV module i works, then X i is equal to 1, otherwise X i is equal to 0, N1 represents the fault logic path, and M(p) represents the reliability of the PV power station under the reliability vector p of PV module i;

[0017] The initial path significance model is optimized based on the logical relationship between each photovoltaic module and each fault event to obtain a risk prediction model.

[0018] Optionally, the optimizing the initial path significance model based on the logical relationship between each photovoltaic module and each fault event to obtain a risk prediction model includes:

[0019] Acquire a logical relationship between each photovoltaic component and each fault event based on the fault logic path;

[0020] Determining the relative position of each photovoltaic component and the logical connection relationship between each photovoltaic component and each fault event according to the logical relationship;

[0021] Constructing a reliability block diagram based on the relative positions and the logical connection relationships;

[0022] The initial path significance model is optimized according to the reliability block diagram to obtain a candidate significance model:

[0023]

[0024] Where M(p) represents the reliability of the photovoltaic power station under the reliability vector p of photovoltaic module i, p i is the reliability parameter of PV module i, represents a logic generation structure function constructed based on the logical connection relationship between the PV module and the fault event and the relative position of the PV module in the logical connection relationship, It represents the probability of normal operation of the PV power station under the action of PV module i;

[0025] A survival analysis is performed on the photovoltaic power station based on the photovoltaic components corresponding to each fault event, and the candidate significance model is optimized based on the survival analysis result to obtain a risk prediction model.

[0026] Optionally, performing survival analysis on the photovoltaic power station based on the photovoltaic components corresponding to each fault event, and optimizing the candidate significance model based on the survival analysis result to obtain a risk prediction model includes:

[0027] Based on the photovoltaic components corresponding to each fault event, the survival analysis of the photovoltaic power station is performed to construct a survival signature:

[0028]

[0029] The survival function of the photovoltaic power station is constructed according to the survival signature:

[0030]

[0031] The candidate significance model is optimized based on the survival function to obtain a risk prediction model; wherein, Indicates that it has l j PV panels and The state vector x n The number of j=1,...,n,{s(l1),s(l2),...,s(l n )} represents the set of all possible state vectors in the photovoltaic power station, W j (t) represents the number of working states of the j-th type of PV module at time t.

[0032] Optionally, the optimizing the candidate significance model based on the survival function to obtain a risk prediction model includes:

[0033] Obtain the failure time distribution information of each photovoltaic module;

[0034] Generate boundary conditions based on the failure time distribution information, wherein the boundary conditions include an upper limit condition and a lower limit condition:

[0035]

[0036] in, is the upper limit condition, S (t|T s ) is the lower limit condition, and An exponential decay function representing the change in the failure probability of a PV power plant or PV module over time;

[0037] The candidate significance model is optimized according to the boundary conditions to obtain a risk prediction model.

[0038] Optionally, optimizing the candidate significance model according to the boundary condition to obtain a risk prediction model includes:

[0039] Perform uncertainty analysis on each photovoltaic module to obtain the uncertainty impact information of each photovoltaic module:

[0040]

[0041] E k (t|P)=max{P(T s >t|T k >t)-P(T s >t|T k ≤t)}

[0042] The candidate significance model is optimized based on the uncertainty impact information and the boundary conditions to obtain a risk prediction model:

[0043]

[0044] Among them, G k (l|t) represents the relative uncertainty impact information of PV module k at a specific time t, E k (t|P) represents the relative interval parameter of the kth photovoltaic module, P(T s >t|T k >t) represents the possibility of a failure event in the photovoltaic system when the kth photovoltaic module appears, P(T s >t|T k≤t) represents the possibility of a failure event in the PV system when the kth PV module is not present, p i is the reliability parameter of PV module i, and M(p) represents the reliability of the PV power station under the reliability vector p of PV module i.

[0045] In addition, to achieve the above-mentioned purpose, the present invention also proposes a photovoltaic power station risk prediction device, the photovoltaic power station risk prediction device comprising:

[0046] A data acquisition module, used to acquire multi-dimensional data of the photovoltaic power station collected by an information acquisition system, wherein the information acquisition system includes a space-based acquisition module, an air-based acquisition module and a ground-based acquisition module, and the multi-dimensional data includes environmental data, equipment status data and equipment operation data of the photovoltaic power station;

[0047] A data processing module, used to process the multidimensional data to obtain event data, feature data and fault result data, wherein the event data includes multiple fault events of the photovoltaic power station, the feature data includes feature data corresponding to each fault event, the feature data is composed of one or more faulty photovoltaic components corresponding to the fault event, and the fault result data includes fault event results corresponding to each fault event;

[0048] A matrix construction module, used to construct a mapping matrix based on the mapping relationship between the event data and the feature data and the fault result data;

[0049] A model building module, used to analyze the fault logic path of the photovoltaic power station according to the mapping matrix, and build a risk prediction model based on the analysis results;

[0050] The risk prediction module is used to input the real-time monitoring data of the photovoltaic power station collected by the information collection system into the risk prediction model to obtain the risk prediction result of the photovoltaic power station, and the risk prediction result includes the risk level of each area in the photovoltaic power station.

[0051] In addition, to achieve the above-mentioned purpose, the present application also proposes a photovoltaic power station risk prediction device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, and the computer program is configured to implement the steps of the photovoltaic power station risk prediction method as described above.

[0052] In addition, to achieve the above-mentioned purpose, the present application also proposes a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the photovoltaic power station risk prediction method as described above are implemented.

[0053] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, the steps of the photovoltaic power station risk prediction method as described above are implemented.

[0054] The present invention acquires multi-dimensional data of a photovoltaic power station acquired by an information acquisition system, wherein the information acquisition system includes a space-based acquisition module, an air-based acquisition module and a ground-based acquisition module, and the multi-dimensional data includes environmental data, equipment status data and equipment operation data of the photovoltaic power station; processes the multi-dimensional data to acquire event data, feature data and fault result data, wherein the event data includes multiple fault events of the photovoltaic power station, the feature data includes feature data corresponding to each fault event, the feature data is composed of one or more faulty photovoltaic components corresponding to the fault event, and the fault result data includes fault event results corresponding to each fault event; constructs a mapping matrix based on the mapping relationship between the event data and the feature data and the fault result data; and constructs a mapping matrix based on the mapping relationship between the event data and the feature data and the fault result data. The mapping matrix analyzes the fault logic path of the photovoltaic power station and constructs a risk prediction model based on the analysis result; the real-time monitoring data of the photovoltaic power station collected by the information collection system is input into the risk prediction model to obtain the risk prediction result of the photovoltaic power station, and the risk prediction result includes the risk level of each area in the photovoltaic power station; because the present invention analyzes the mapping relationship and logical path between fault events and fault characteristics and fault results, thereby greatly improving the accuracy of risk prediction of photovoltaic power stations, and predicting risks for photovoltaic power stations through risk prediction models, thereby realizing risk prediction for remote areas, improving the risk prediction range, accurately detecting potential risks of photovoltaic power stations, ensuring the timeliness of risk identification, and improving the safety of photovoltaic power stations. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] The accompanying drawings herein are incorporated in and constitute a part of the specification, illustrate embodiments consistent with the present application, and together with the description, are used to explain the principles of the present application.

[0056] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0057] Figure 1 It is a schematic diagram of the structure of a photovoltaic power station risk prediction device in a hardware operating environment involved in an embodiment of the present invention;

[0058] Figure 2It is a schematic diagram of the flow chart of the first embodiment of the photovoltaic power station risk prediction method of the present invention;

[0059] Figure 3 A schematic diagram of the structure of a risk prediction and assessment system of an embodiment of a risk prediction method for a photovoltaic power station according to the present invention;

[0060] Figure 4 It is a schematic diagram of the flow chart of the second embodiment of the photovoltaic power station risk prediction method of the present invention;

[0061] Figure 5 It is a schematic diagram of the structure of a reliability block diagram in an embodiment of a photovoltaic power station risk prediction method of the present invention;

[0062] Figure 6 It is a schematic diagram of ROC curve test in an embodiment of a photovoltaic power station risk prediction method of the present invention;

[0063] Figure 7 It is a schematic diagram of PR curve inspection in an embodiment of a photovoltaic power station risk prediction method of the present invention;

[0064] Figure 8 This is a structural block diagram of the first embodiment of the photovoltaic power station risk prediction device of the present invention.

[0065] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0066] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0067] Reference Figure 1 , Figure 1 The schematic diagram of the structure of the risk prediction device for a photovoltaic power station in the hardware operating environment involved in the embodiment of the present invention is shown.

[0068] like Figure 1As shown, the photovoltaic power station risk prediction device may include: a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Among them, the communication bus 1002 is used to realize the connection and communication between these components. The user interface 1003 may include a display screen (Display), an input unit such as a keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface and a wireless interface. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a wireless fidelity (Wireless-Fidelity, WI-FI) interface). The memory 1005 may be a high-speed random access memory (Random Access Memory, RAM), or a stable non-volatile memory (Non-Volatile Memory, NVM), such as a disk storage. The memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0069] Those skilled in the art will understand that Figure 1 The structure shown in the figure does not constitute a limitation on the risk prediction device for a photovoltaic power station, and may include more or fewer components than shown in the figure, or a combination of certain components, or a different arrangement of components.

[0070] like Figure 1 As shown, the memory 1005 as a computer-readable storage medium may include an operating system, a network communication module, a user interface module, and a photovoltaic power plant risk prediction program.

[0071] exist Figure 1 In the photovoltaic power station risk prediction device shown, the network interface 1004 is mainly used for data communication with the network server; the user interface 1003 is mainly used for data interaction with the user; the processor 1001 and the memory 1005 in the photovoltaic power station risk prediction device of the present invention can be set in the photovoltaic power station risk prediction device, and the photovoltaic power station risk prediction device calls the photovoltaic power station risk prediction program stored in the memory 1005 through the processor 1001, and executes the photovoltaic power station risk prediction method provided by the embodiment of the present invention.

[0072] The embodiment of the present invention provides a photovoltaic power station risk prediction method, referring to Figure 2 , Figure 2 It is a flow chart of the first embodiment of the photovoltaic power station risk prediction method of the present invention.

[0073] In this embodiment, the photovoltaic power station risk prediction method includes the following steps:

[0074] Step S10: Acquire multi-dimensional data of the photovoltaic power station collected by the information collection system.

[0075] It should be understood that the execution subject of this embodiment can be a computing service device with data processing, network communication and program running functions, such as a computer, or a terminal electronic device capable of realizing the above functions. The following takes a photovoltaic power station risk prediction device (referred to as the prediction device) as an example to illustrate this embodiment and the following embodiments.

[0076] It should be noted that the information collection system includes a space-based collection module, an air-based collection module and a ground-based collection module, and the multi-dimensional data includes environmental data, equipment status data and equipment operation data of the photovoltaic power station. For example, the space-based collection module can be a satellite module, the air-based module can be a drone, etc., and the ground-based module can be a ground sensor, etc.

[0077] In some embodiments, the prediction device can rely on satellite remote sensing, drone inspections and ground monitoring equipment to fully obtain the environmental information, equipment status and real-time operation data of the photovoltaic power station. A multi-source heterogeneous data collection system is built to provide data support for the comprehensive risk assessment of photovoltaic power stations.

[0078] In some embodiments, the prediction device can obtain environmental information of the photovoltaic power station area through sensors carried by satellites. Satellite remote sensing data can provide macro-environmental monitoring for photovoltaic power stations and help identify potential external risks. By regularly obtaining this data, the external environment of the power station can be continuously monitored to provide data support for subsequent risk prediction and maintenance decisions.

[0079] In some embodiments, drone inspections and ground monitoring equipment are responsible for real-time monitoring of the internal equipment and site conditions of the photovoltaic power station. Drone inspections use high-altitude photography and thermal imaging technology to obtain high-definition images of photovoltaic panels, hot spot detection, and key issues such as surface cracks. Ground monitoring equipment directly collects the electrical parameters and environmental parameters of the power station, providing detailed data on the operating status of the photovoltaic power station.

[0080] In some embodiments, the prediction device can build a unified information processing center based on data collection of sky-ground collaboration, and form a comprehensive integrated risk prediction and assessment system through the integration of multi-source data, including sky-ground data collection module, information processing center and operation and maintenance module. Figure 3 As shown, Figure 3 This is a schematic diagram of the risk prediction and assessment system structure. The system combines multi-dimensional data obtained by multi-dimensional data sensing devices (including space-based sensing devices, air-based sensing devices and ground-based sensing devices) to provide comprehensive photovoltaic power station operation status monitoring and fault warning capabilities.

[0081] Step S20: Process the multi-dimensional data to obtain event data, feature data and fault result data.

[0082] It should be noted that the event data includes multiple fault events of the photovoltaic power station, the characteristic data includes characteristic data corresponding to each fault event, the characteristic data is composed of one or more faulty photovoltaic components corresponding to the fault event, and the fault result data includes fault event results corresponding to each fault event.

[0083] It should be noted that a fault event may include one or more features, for example, the features may include ambient temperature, radiation temperature, photovoltaic module power, etc. Each feature may be composed of one or more photovoltaic modules, for example, the radiation temperature feature may be the radiation temperature of one or more photovoltaic modules.

[0084] In some embodiments, the prediction device may pre-process the multidimensional data through data cleaning, abnormal data identification and elimination, missing data filling and other processing methods to improve data quality, reduce the interference of abnormal data and invalid data, and ensure the accuracy of feature analysis.

[0085] Step S30: constructing a mapping matrix based on the mapping relationship between the event data, the feature data and the fault result data.

[0086] It can be understood that the prediction device maps the event data, feature data and fault result data to a unified space for processing through mapping and feature processing.

[0087] In some embodiments, let T = {t1, t2, ..., t i ,……t m} is the fault event record set (i.e., event data) of the photovoltaic power station, where i=1,2,...,m represents an event in the entire m records. Each fault event t i Contains multiple features, such as ambient temperature, radiation temperature, photovoltaic module power, etc. For each fault event, a set of features F = {f1, f2, ..., f j ,…,f n ,f Y}, where j = 1, 2, ..., n represents one of the total n features, f j Represents the characteristics of fault events obtained by various sensors or remote sensing devices.

[0088] Each feature f j Composed of multiple photovoltaic modules j ={c j,1 ,c j,2 ,…,c j,k ,…,c j,l}, where k = 1, 2, ..., l represents f j To form the pattern X→Y, select a photovoltaic module c j,k As the condition variable x i,j , which belongs to the variable set X = {x i,1 ,x i,2 ,…,x i,j ,…,x i,n}, indicating a fault event t i One of all the relevant condition factors in the fault event t i The consequence is that the target PV module y is selected i , which is also included in the target set Y = {y1,y2,…,y i ,……y m}.

[0089] After the data mapping space is constructed, the collected raw data is processed for missing values, outlier detection and repair to ensure the integrity and reliability of the data. These inputs will be standardized into a unified mapping space. The implemented input mapping space can be represented by a matrix S, refer to the following mapping matrix:

[0090]

[0091] Among them, each row of the mapping matrix represents a fault event t i Record, each column x i,j Indicates the fault event t i A feature f j PV panels, but y i The consequences of the event. Through the construction of this matrix, the risks of the photovoltaic power station can be further analyzed and modeled.

[0092] Step S40: analyzing the fault logic path of the photovoltaic power station according to the mapping matrix, and constructing a risk prediction model based on the analysis result.

[0093] It should be noted that this embodiment introduces the concept of path and describes the photovoltaic power station fault with a logical path model. Each path represents a logical link that may cause a fault.

[0094] It can be understood that this embodiment analyzes the logical paths that cause photovoltaic power station failures according to the mapping matrix, determines the characteristics contained in each path that causes the failure, thereby determining the contribution of each characteristic to the failure event, and constructs a risk prediction model based on the analysis results.

[0095] In some embodiments, the risk prediction model may be an improved path-based significance metric impact weight assessment model (IPBS), and the prediction device achieves accurate risk prediction of various components and assemblies in a photovoltaic power station by improving the impact weight assessment model of the path-based significance metric.

[0096] Step S50: inputting the real-time monitoring data of the photovoltaic power station collected by the information collection system into the risk prediction model to obtain the risk prediction result of the photovoltaic power station.

[0097] It should be noted that the risk prediction result includes the risk level of each area in the photovoltaic power station.

[0098] In some embodiments, the prediction device can determine the risk level of each area in the photovoltaic power station based on the risk prediction results, and generate a risk heat map based on the risk level. The color depth of the risk heat map indicates the high and low risk level. The darker the color, the higher the safety risk, and the lighter the color, the lower the safety risk.

[0099] This embodiment acquires multi-dimensional data of the photovoltaic power station collected by an information collection system, the information collection system includes a space-based collection module, an air-based collection module and a ground-based collection module, the multi-dimensional data includes environmental data, equipment status data and equipment operation data of the photovoltaic power station; processes the multi-dimensional data to acquire event data, feature data and fault result data, the event data includes multiple fault events of the photovoltaic power station, the feature data includes feature data corresponding to each fault event, the feature data is composed of one or more faulty photovoltaic components corresponding to the fault event, and the fault result data includes fault event results corresponding to each fault event; constructs a mapping matrix based on the mapping relationship between the event data and the feature data and the fault result data; and The mapping matrix analyzes the fault logic path of the photovoltaic power station and constructs a risk prediction model based on the analysis result; the real-time monitoring data of the photovoltaic power station collected by the information collection system is input into the risk prediction model to obtain the risk prediction result of the photovoltaic power station, and the risk prediction result includes the risk level of each area in the photovoltaic power station; since this embodiment analyzes the mapping relationship and logical path between fault events and fault characteristics and fault results, the accuracy of risk prediction of photovoltaic power stations is greatly improved, and risk prediction of photovoltaic power stations is performed through risk prediction models, thereby realizing risk prediction of remote areas, improving the risk prediction range, accurately detecting potential risks of photovoltaic power stations, ensuring the timeliness of risk identification, and improving the safety of photovoltaic power stations.

[0100] refer to Figure 4 , Figure 4 It is a flow chart of the second embodiment of the photovoltaic power station risk prediction method of the present invention.

[0101] Based on the above first embodiment, in this embodiment, the step S40 further includes:

[0102] Step S41: analyzing the fault logic path of the photovoltaic power station according to the mapping matrix, and constructing a fault logic path model based on the analysis result.

[0103] It should be noted that the fault logic path model includes multiple fault logic paths, and each fault logic path represents a logic link that may cause a fault in a photovoltaic power station.

[0104] Step S42: performing path significance analysis on each fault logic path in the fault logic path model.

[0105] It can be understood that this embodiment calculates the failure probability contribution of the minimum path set containing a certain photovoltaic component by analyzing the path significance. The path significance model is used to analyze the direct impact of photovoltaic components on the reliability of photovoltaic power stations. Assuming that the photovoltaic power station can operate normally, at least one minimum logical path containing photovoltaic component i also operates normally.

[0106] Step S43: constructing an initial path significance model based on the significance analysis results.

[0107] It should be noted that the initial path significance model refers to the following formula:

[0108]

[0109] Among them, p i is the reliability parameter of PV module i, Y i ={Pk:i∈Pk,1≤k≤u} represents the minimum path set containing PV module i, Y i Contains u paths, X=(X1,...,X n ) represents a binary random vector. If PV module i works, then X i is equal to 1, otherwise X i is equal to 0, N1 represents the fault logic path, and M(p) represents the reliability of the PV power station under the reliability vector p of PV module i.

[0110] Step S44: Optimizing the initial path significance model based on the logical relationship between each photovoltaic module and each fault event to obtain a risk prediction model.

[0111] It can be understood that in this embodiment, by calculating the minimum path set p including the photovoltaic component i kThe contribution to the occurrence of photovoltaic power station failures quantifies the impact of abnormalities in each photovoltaic module on the function of the photovoltaic power station, thereby quantifying the contribution of photovoltaic module failures.

[0112] Furthermore, in order to improve the performance of the risk prediction model, the above step S44 may include:

[0113] Step S441: acquiring a logical relationship between each photovoltaic component and each fault event based on the fault logic path;

[0114] Step S442: determining the relative position of each photovoltaic component and the logical connection relationship between each photovoltaic component and each fault event according to the logical relationship;

[0115] Step S443: constructing a reliability block diagram based on the relative position and the logical connection relationship;

[0116] Step S444: optimizing the initial path significance model according to the reliability block diagram to obtain a candidate significance model;

[0117] Step S445: performing a survival analysis on the photovoltaic power station based on the photovoltaic components corresponding to each fault event, and optimizing the candidate significance model based on the survival analysis result to obtain a risk prediction model.

[0118] It should be noted that the candidate saliency model refers to the following formula:

[0119]

[0120] Where M(p) represents the reliability of the photovoltaic power station under the reliability vector p of photovoltaic module i, p i is the reliability parameter of PV module i, represents a logic generation structure function constructed based on the logical connection relationship between the PV module and the fault event and the relative position of the PV module in the logical connection relationship, It represents the probability of normal operation of the PV power station under the action of PV module i.

[0121] It should be noted that the significance of PV module i depends on its own reliability p i ,Whether the PV modules are proportional or inversely proportional depends on their series or parallel logic connection. In parallel connection, even the conduction of a minimum logic path can cause a fault event to occur, while in the logic path of series connection, all PV modules must be turned on to cause a fault event to occur.

[0122] It can be understood that, in this embodiment, by constructing a reliability block diagram, referring to Figure 5 , Figure 5Schematic diagram of the structure of a reliability block diagram in an embodiment, based on which the reliability block diagram can represent the logic generation structure function of the fault event of all features and their relative positions and logical connections of photovoltaic components

[0123] Furthermore, in order to improve the model performance and prediction accuracy, the above step S445 may include:

[0124] Step S4451: performing survival analysis on the photovoltaic power station based on the photovoltaic components corresponding to each fault event, and constructing a survival signature;

[0125] Step S4452: constructing a survival function of the photovoltaic power station according to the survival signature;

[0126] Step S4453: Optimize the candidate significance model based on the survival function to obtain a risk prediction model.

[0127] It should be noted that the survival function is used to quantify the survival or reliability probability of a PV power plant at a certain moment, while the survival signature is used to evaluate the survival probability of a PV power plant with multiple types and interchangeable PV modules. The survival signature describes the probability that a PV power plant can work normally under multiple PV module characteristics. The survival signature formula is as follows:

[0128]

[0129] Through the survival signature, the overall survival function of the photovoltaic power station can be expressed as:

[0130]

[0131] Among them, W j (t) represents the number of working states of the j-th type of PV module at time t, which can be calculated by the following formula:

[0132]

[0133] in, Indicates that it has l j PV panels and The state vector x n The number of j=1,...,n,{s(l1),s(l2),...,s(l n )} represents the set of all possible state vectors in the photovoltaic power station, W j (t) represents the number of working states of the j-th type of PV module at time t.

[0134] It should be noted that the survival signature provides an estimate of the survival probability of a PV power station as a whole by summing the states of all PV modules, and can efficiently evaluate the reliability of multi-type PV module systems.

[0135] Further, in order to solve the problem of insufficient samples and data volume and uncertainty in fault analysis, the above step S4453 may include:

[0136] Step S44531: Obtaining the failure time distribution information of each photovoltaic module;

[0137] Step S44532: generating boundary conditions based on the failure time distribution information;

[0138] Step S44533: Optimize the candidate significance model according to the boundary conditions to obtain a risk prediction model.

[0139] It should be noted that, assuming is a set of non-decreasing cumulative distribution functions (CDFs) that satisfy Then, will be a possibility box if they are used to describe the boundaries of a possibility distribution that is known to be imprecise. The lower and upper bounds of the failure time distribution of these PV modules in the jth feature can be expressed as F j (t) and And it can be determined by the numerical range of all distributions within the defined parameter interval. Its lower limit and upper limit are respectively expressed as: The boundary conditions include upper limit conditions and lower limit conditions:

[0140]

[0141] in, is the upper limit condition, S (t|T s ) is the lower limit condition, and The exponential decay function represents the change of the failure probability of a PV power station or PV module over time. The functions of the upper and lower limit conditions above represent the upper and lower limits of the survival function respectively. Through these functions, the impact of uncertainty on system reliability can be evaluated and boundary conditions can be provided for further risk assessment.

[0142] It should be noted that due to the insufficient amount of data, insufficient samples and incompleteness of input data, there is uncertainty in the probability of photovoltaic module failure. In order to solve this problem, this embodiment can introduce a possibility box model to handle these uncertainties.

[0143] Furthermore, in order to further consider the impact of the uncertainty of the photovoltaic module on the prediction of the fault event and improve the prediction performance, the above step S44533 may include:

[0144] Conduct uncertainty analysis on each photovoltaic module to obtain the uncertainty impact information of each photovoltaic module;

[0145] The candidate significance model is optimized based on the uncertainty impact information and the boundary conditions to obtain a risk prediction model.

[0146] It should be noted that the uncertainty impact information is obtained based on the following formula:

[0147]

[0148] E k (t|P)=max{P(T s >t|T k >t)-P(T s >t|T k ≤t)}

[0149] This embodiment further considers the impact of the uncertainty of photovoltaic modules on the prediction of fault events, combines the candidate significance model with the possibility framework to quantify the inaccuracy of photovoltaic modules, and finally obtains the contribution of photovoltaic modules to photovoltaic power station failures to obtain a risk prediction model. The risk prediction model refers to the following formula:

[0150]

[0151] Among them, G k (l|r) represents the relative uncertainty impact information of PV module k at a specific time t, E k (t|P) represents the relative interval parameter of the kth photovoltaic module, P(T s >t|T k >t) represents the possibility of a failure event in the photovoltaic system when the kth photovoltaic module appears, P(T s >t|T k ≤t) represents the possibility of a failure event in the PV system when the kth PV module is not present, p i is the reliability parameter of PV module i, and M(p) represents the reliability of the PV power station under the reliability vector p of PV module i.

[0152] In some embodiments, in order to verify the prediction accuracy of the model, the prediction device may use the ROC (Receiver Operating Characteristic Curve) curve and the PR (Precision-Recall Curve) curve to test the prediction effect. The ROC curve evaluates the performance of the classifier by showing the relationship between the false positive rate (False Positive Rate, FPR) and the true positive rate (True Positive Rate, TPR, or recall rate) of the model under different classification thresholds. The ideal model should be able to increase the true positive rate as much as possible while maintaining a low false positive rate, so that the ROC curve will be as close to the upper left corner as possible. AUC represents the area under the ROC curve, and the value range is from 0 to 1. The closer the AUC is to 1, the better the model performance. The PR curve focuses on the relationship between precision (Precision) and recall rate (Recall, or true positive rate), which is particularly suitable for processing data imbalance. In this case, the imbalance of class distribution may cause the ROC curve to produce more optimistic results. The ideal model should maintain a high precision while having a high recall rate, and the PR curve should be as close to the upper right corner as possible.

[0153] like Figure 6 , 7 As shown, Figure 6 This is a schematic diagram of the ROC curve test. Figure 7 It is a schematic diagram of the PR curve test. The larger the area under the ROC curve (AUC), the better the prediction accuracy of the risk prediction model. The risk prediction model is compared with the currently commonly used RNN and LSTM neural networks. Among them, the AUC of the risk prediction model is 0.9172, and the AUCs of the RNN and LSTM neural networks are 0.8846 and 0.8613 respectively. It can be seen that the risk prediction model has a high accuracy in predicting the risks of photovoltaic power stations under multi-source biased data environments. For the PR curve, the risk prediction model (IPBS) used in this embodiment is significantly better than the RNN and LSTM neural network models in performance.

[0154] This embodiment analyzes the fault logic path of the photovoltaic power station according to the mapping matrix, and constructs a fault logic path model based on the analysis result, performs path significance analysis on each fault logic path in the fault logic path model, constructs an initial path significance model based on the significance analysis result, optimizes the initial path significance model based on the logical relationship between each photovoltaic component and each fault event, and obtains a risk prediction model; because this embodiment performs logical path analysis on the fault of the photovoltaic power station, it realizes the quantification of the contribution of the features and components that cause the fault in each path, analyzes the influence of each element on the fault of the photovoltaic power station, and thus improves the accuracy of risk prediction.

[0155] In addition, an embodiment of the present invention also proposes a computer-readable storage medium, on which a photovoltaic power station risk prediction program is stored. When the photovoltaic power station risk prediction program is executed by a processor, the steps of the photovoltaic power station risk prediction method described above are implemented.

[0156] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination of the above.

[0157] The computer-readable storage medium may be included in the photovoltaic power station risk prediction device; or may exist independently without being assembled into the photovoltaic power station risk prediction device.

[0158] In addition, an embodiment of the present invention further provides a computer program product, including a photovoltaic power station risk prediction program, which implements the steps of the photovoltaic power station risk prediction method described above when executed by a processor.

[0159] The specific implementation methods of the computer program product of the present invention are basically the same as the above-mentioned embodiments of the photovoltaic power station risk prediction method, and will not be repeated here.

[0160] Reference Figure 8 , Figure 8 This is a structural block diagram of the first embodiment of the photovoltaic power station risk prediction device of the present invention.

[0161] like Figure 8 As shown, the photovoltaic power station risk prediction device proposed in the embodiment of the present invention includes:

[0162] The data acquisition module 10 is used to acquire multi-dimensional data of the photovoltaic power station collected by the information acquisition system, wherein the information acquisition system includes a space-based acquisition module, an air-based acquisition module and a ground-based acquisition module, and the multi-dimensional data includes environmental data, equipment status data and equipment operation data of the photovoltaic power station;

[0163] A data processing module 20 is used to process the multidimensional data to obtain event data, feature data and fault result data, wherein the event data includes multiple fault events of the photovoltaic power station, the feature data includes feature data corresponding to each fault event, the feature data is composed of one or more faulty photovoltaic components corresponding to the fault event, and the fault result data includes fault event results corresponding to each fault event;

[0164] A matrix construction module 30, configured to construct a mapping matrix based on a mapping relationship between the event data, the feature data, and the fault result data;

[0165] A model building module 40 is used to analyze the fault logic path of the photovoltaic power station according to the mapping matrix, and build a risk prediction model based on the analysis results;

[0166] The risk prediction module 50 is used to input the real-time monitoring data of the photovoltaic power station collected by the information collection system into the risk prediction model to obtain the risk prediction result of the photovoltaic power station, and the risk prediction result includes the risk level of each area in the photovoltaic power station.

[0167] Furthermore, the model building module 40 is further used to analyze the fault logic path of the photovoltaic power station according to the mapping matrix, and build a fault logic path model based on the analysis result, wherein the fault logic path model includes multiple fault logic paths;

[0168] Performing path significance analysis on each fault logic path in the fault logic path model;

[0169] Construct an initial path significance model based on the significance analysis results:

[0170]

[0171] Among them, p i is the reliability parameter of PV module i, Y i ={Pk:i∈Pk,1≤k≤u} represents the minimum path set containing PV module i, Y i Contains u paths, X=(X1,...,X n ) represents a binary random vector. If PV module i works, then X i is equal to 1, otherwise Xi is equal to 0, N1 represents the fault logic path, and M(p) represents the reliability of the PV power station under the reliability vector p of PV module i;

[0172] The initial path significance model is optimized based on the logical relationship between each photovoltaic module and each fault event to obtain a risk prediction model.

[0173] Furthermore, the model building module 40 is also used to optimize the initial path significance model based on the logical relationship between each photovoltaic module and each fault event to obtain a risk prediction model, including:

[0174] Acquire a logical relationship between each photovoltaic component and each fault event based on the fault logic path;

[0175] Determining the relative position of each photovoltaic component and the logical connection relationship between each photovoltaic component and each fault event according to the logical relationship;

[0176] Constructing a reliability block diagram based on the relative positions and the logical connection relationships;

[0177] The initial path significance model is optimized according to the reliability block diagram to obtain a candidate significance model:

[0178]

[0179] Where M(p) represents the reliability of the photovoltaic power station under the reliability vector p of photovoltaic module i, p i is the reliability parameter of PV module i, represents a logic generation structure function constructed based on the logical connection relationship between the PV module and the fault event and the relative position of the PV module in the logical connection relationship, It represents the probability of normal operation of the PV power station under the action of PV module i;

[0180] A survival analysis is performed on the photovoltaic power station based on the photovoltaic components corresponding to each fault event, and the candidate significance model is optimized based on the survival analysis result to obtain a risk prediction model.

[0181] Furthermore, the model building module 40 is also used to perform survival analysis on the photovoltaic power station based on the photovoltaic components corresponding to each fault event, and optimize the candidate significance model based on the survival analysis result to obtain a risk prediction model, including:

[0182] Based on the photovoltaic components corresponding to each fault event, the survival analysis of the photovoltaic power station is performed to construct a survival signature:

[0183]

[0184] The survival function of the photovoltaic power station is constructed according to the survival signature:

[0185]

[0186] The candidate significance model is optimized based on the survival function to obtain a risk prediction model; wherein, Indicates that it has l j PV panels and The state vector x n The number of j=1,...,n,{s(l1),s(l2),...,s(l n )} represents the set of all possible state vectors in the photovoltaic power station, W j (t) represents the number of working states of the j-th type of PV module at time t.

[0187] Furthermore, the model building module 40 is also used to optimize the candidate significance model based on the survival function to obtain a risk prediction model, including:

[0188] Obtain the failure time distribution information of each photovoltaic module;

[0189] Generate boundary conditions based on the failure time distribution information, wherein the boundary conditions include an upper limit condition and a lower limit condition:

[0190]

[0191] in, is the upper limit condition, S (t|T s ) is the lower limit condition, and An exponential decay function representing the change in the failure probability of a PV power plant or PV module over time;

[0192] The candidate significance model is optimized according to the boundary conditions to obtain a risk prediction model.

[0193] Furthermore, the model building module 40 is also used to optimize the candidate significance model according to the boundary conditions to obtain a risk prediction model, including:

[0194] Perform uncertainty analysis on each photovoltaic module to obtain the uncertainty impact information of each photovoltaic module:

[0195]

[0196] E k (t|P)=max{P(T s >t|Tk >t)-P(T s >t|T k ≤t)}

[0197] The candidate significance model is optimized based on the uncertainty impact information and the boundary conditions to obtain a risk prediction model:

[0198]

[0199] Among them, G k (l|t) represents the relative uncertainty impact information of PV module k at a specific time t, E k (t|P) represents the relative interval parameter of the kth photovoltaic module, P(T s >t|T k >t) represents the possibility of a failure event in the photovoltaic system when the kth photovoltaic module appears, P(T s >t|T k ≤t) represents the possibility of a failure event in the PV system when the kth PV module is not present, p i is the reliability parameter of PV module i, and M(p) represents the reliability of the PV power station under the reliability vector p of PV module i.

[0200] This embodiment acquires multi-dimensional data of the photovoltaic power station collected by an information collection system, the information collection system includes a space-based collection module, an air-based collection module and a ground-based collection module, the multi-dimensional data includes environmental data, equipment status data and equipment operation data of the photovoltaic power station; processes the multi-dimensional data to acquire event data, feature data and fault result data, the event data includes multiple fault events of the photovoltaic power station, the feature data includes feature data corresponding to each fault event, the feature data is composed of one or more faulty photovoltaic components corresponding to the fault event, and the fault result data includes fault event results corresponding to each fault event; constructs a mapping matrix based on the mapping relationship between the event data and the feature data and the fault result data; and The mapping matrix analyzes the fault logic path of the photovoltaic power station and constructs a risk prediction model based on the analysis result; the real-time monitoring data of the photovoltaic power station collected by the information collection system is input into the risk prediction model to obtain the risk prediction result of the photovoltaic power station, and the risk prediction result includes the risk level of each area in the photovoltaic power station; since this embodiment analyzes the mapping relationship and logical path between fault events and fault characteristics and fault results, the accuracy of risk prediction of photovoltaic power stations is greatly improved, and risk prediction of photovoltaic power stations is performed through risk prediction models, thereby realizing risk prediction of remote areas, improving the risk prediction range, accurately detecting potential risks of photovoltaic power stations, ensuring the timeliness of risk identification, and improving the safety of photovoltaic power stations.

[0201] The photovoltaic power station risk prediction device provided by the present application adopts the photovoltaic power station risk prediction method in the above embodiment, which can solve the technical problem of photovoltaic power station risk prediction. Compared with the prior art, the beneficial effects of the photovoltaic power station risk prediction device provided by the present application are the same as the beneficial effects of the photovoltaic power station risk prediction method provided by the above embodiment, and the other technical features in the photovoltaic power station risk prediction device are the same as the features disclosed in the above embodiment method, which will not be repeated here.

[0202] It should be understood that the above is only an example and does not constitute any limitation on the technical solution of the present invention. In specific applications, technicians in this field can make settings as needed, and the present invention does not limit this.

[0203] It should be noted that the workflow described above is merely illustrative and does not limit the scope of protection of the present invention. In practical applications, technicians in this field can select part or all of them according to actual needs to achieve the purpose of the present embodiment, and no limitation is made here.

[0204] In addition, for technical details not fully described in this embodiment, reference may be made to the photovoltaic power station risk prediction method provided in any embodiment of the present invention, and will not be repeated here.

[0205] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or system. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or system including the element.

[0206] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0207] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as a read-only memory / random access memory, a magnetic disk, or an optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to execute the methods described in each embodiment of the present invention.

[0208] The above are only preferred embodiments of the present invention, and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A photovoltaic power station risk prediction method, characterized in that: The photovoltaic power station risk prediction method comprises: Acquire multi-dimensional data of the photovoltaic power station collected by an information collection system, wherein the information collection system includes a space-based collection module, an air-based collection module, and a ground-based collection module, and the multi-dimensional data includes environmental data, equipment status data, and equipment operation data of the photovoltaic power station; Processing the multidimensional data to obtain event data, feature data and fault result data, wherein the event data includes multiple fault events of the photovoltaic power station, the feature data includes feature data corresponding to each fault event, the feature data is composed of one or more faulty photovoltaic components corresponding to the fault event, and the fault result data includes fault event results corresponding to each fault event; Constructing a mapping matrix based on the mapping relationship between the event data, the feature data and the fault result data; Analyzing the fault logic path of the photovoltaic power station according to the mapping matrix, and building a risk prediction model based on the analysis results; The real-time monitoring data of the photovoltaic power station collected by the information collection system is input into the risk prediction model to obtain the risk prediction result of the photovoltaic power station, and the risk prediction result includes the risk level of each area in the photovoltaic power station.

2. The photovoltaic power station risk prediction method according to claim 1, characterized in that: The step of analyzing the fault logic path of the photovoltaic power station according to the mapping matrix and constructing a risk prediction model based on the analysis result includes: Analyzing the fault logic path of the photovoltaic power station according to the mapping matrix, and constructing a fault logic path model based on the analysis result, wherein the fault logic path model includes multiple fault logic paths; Performing path significance analysis on each fault logic path in the fault logic path model; Construct an initial path significance model based on the significance analysis results: Among them, p i is the reliability parameter of PV module i, Y i ={Pk:i∈Pk,1≤k≤u} represents the minimum path set containing PV module i, Y i Contains u paths, X=(X1,...,X n ) represents a binary random vector. If PV module i works, then X i is equal to 1, otherwise X i is equal to 0, N1 represents the fault logic path, and M(p) represents the reliability of the PV power station under the reliability vector p of PV module i; The initial path significance model is optimized based on the logical relationship between each photovoltaic module and each fault event to obtain a risk prediction model.

3. The photovoltaic power station risk prediction method according to claim 2, characterized in that: The initial path significance model is optimized based on the logical relationship between each photovoltaic module and each fault event to obtain a risk prediction model, including: Acquire a logical relationship between each photovoltaic component and each fault event based on the fault logic path; Determining the relative position of each photovoltaic component and the logical connection relationship between each photovoltaic component and each fault event according to the logical relationship; Constructing a reliability block diagram based on the relative positions and the logical connection relationships; The initial path significance model is optimized according to the reliability block diagram to obtain a candidate significance model: Where M(p) represents the reliability of the photovoltaic power station under the reliability vector p of photovoltaic module i, p i is the reliability parameter of PV module i, represents a logic generation structure function constructed based on the logical connection relationship between the PV module and the fault event and the relative position of the PV module in the logical connection relationship, It represents the probability of normal operation of the PV power station under the action of PV module i; A survival analysis is performed on the photovoltaic power station based on the photovoltaic components corresponding to each fault event, and the candidate significance model is optimized based on the survival analysis result to obtain a risk prediction model.

4. The photovoltaic power station risk prediction method according to claim 3, characterized in that: The photovoltaic power station is subjected to survival analysis based on the photovoltaic components corresponding to each fault event, and the candidate significance model is optimized based on the survival analysis result to obtain a risk prediction model, including: Based on the photovoltaic components corresponding to each fault event, the survival analysis of the photovoltaic power station is performed to construct a survival signature: The survival function of the photovoltaic power station is constructed according to the survival signature: Optimizing the candidate significance model based on the survival function to obtain a risk prediction model; in, Indicates that it has l j PV panels and The state vector x n The number of represents the set of all possible state vectors in a photovoltaic power station, W j (t) represents the number of working states of the j-th type of PV module at time t.

5. The photovoltaic power station risk prediction method according to claim 4, characterized in that: The step of optimizing the candidate significance model based on the survival function to obtain a risk prediction model includes: Obtain the failure time distribution information of each photovoltaic module; Generate boundary conditions based on the failure time distribution information, wherein the boundary conditions include an upper limit condition and a lower limit condition: in, is the upper limit condition, S (t|T s ) is the lower limit condition, and An exponential decay function representing the change in the failure probability of a PV power plant or PV module over time; The candidate significance model is optimized according to the boundary conditions to obtain a risk prediction model.

6. The photovoltaic power station risk prediction method according to claim 5, characterized in that: The step of optimizing the candidate significance model according to the boundary condition to obtain a risk prediction model includes: Perform uncertainty analysis on each photovoltaic module to obtain the uncertainty impact information of each photovoltaic module: E k (t|P)=max{P(T s >t|T k >t)-P(T s >t|T k ≤t)} The candidate significance model is optimized based on the uncertainty impact information and the boundary conditions to obtain a risk prediction model: Among them, G k (l|t) represents the relative uncertainty impact information of PV module l at a specific time t, E k (t|P) represents the relative interval parameter of the lth photovoltaic module, P(T s >t|T k >t) represents the possibility of a failure event in the photovoltaic system when the kth photovoltaic module appears, P(T s >t|T k ≤t) represents the possibility of a failure event in the PV system when the kth PV module is not present, p i is the reliability parameter of PV module i, and M(p) represents the reliability of the PV power station under the reliability vector p of PV module i.

7. A photovoltaic power station risk prediction device, characterized in that: The photovoltaic power station risk prediction device comprises: A data acquisition module, used to acquire multi-dimensional data of the photovoltaic power station collected by an information acquisition system, wherein the information acquisition system includes a space-based acquisition module, an air-based acquisition module and a ground-based acquisition module, and the multi-dimensional data includes environmental data, equipment status data and equipment operation data of the photovoltaic power station; A data processing module, used to process the multidimensional data to obtain event data, feature data and fault result data, wherein the event data includes multiple fault events of the photovoltaic power station, the feature data includes feature data corresponding to each fault event, the feature data is composed of one or more faulty photovoltaic components corresponding to the fault event, and the fault result data includes fault event results corresponding to each fault event; A matrix construction module, used to construct a mapping matrix based on the mapping relationship between the event data and the feature data and the fault result data; A model building module, used to analyze the fault logic path of the photovoltaic power station according to the mapping matrix, and build a risk prediction model based on the analysis results; The risk prediction module is used to input the real-time monitoring data of the photovoltaic power station collected by the information collection system into the risk prediction model to obtain the risk prediction result of the photovoltaic power station, and the risk prediction result includes the risk level of each area in the photovoltaic power station.

8. A photovoltaic power station risk prediction device, characterized in that: The photovoltaic power station risk prediction device includes: a memory, a processor, and a photovoltaic power station risk prediction program stored in the memory and executable on the processor, wherein the photovoltaic power station risk prediction program is configured to implement the photovoltaic power station risk prediction method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a photovoltaic power station risk prediction program, and when the photovoltaic power station risk prediction program is executed by the processor, the photovoltaic power station risk prediction method according to any one of claims 1 to 6 is implemented.

10. A computer program product, characterized in that The computer program product comprises a photovoltaic power station risk prediction program, and when the photovoltaic power station risk prediction program is executed by a processor, the steps of the photovoltaic power station risk prediction method according to any one of claims 1 to 6 are implemented.

Images