BIPV management method and system based on photovoltaic modules

Abstract

The present invention discloses a BIPV management method and system based on photovoltaic components, and relates to the field related to building photovoltaic integrated management. The method includes: configuring multiple edge fault monitoring nodes for multiple BIPV components of a target building; using component position identification as a constraint, building a communication link between the edge fault monitoring node and the BIPV monitoring cloud; after receiving a photovoltaic fault warning, identifying adjacent components, performing fault warning verification according to the identification result, and outputting real-time fault component information; generating a fault monitoring window and M fault monitoring components; locating M edge fault monitoring nodes according to the M fault monitoring components, running the M edge fault monitoring nodes with the fault monitoring window as a constraint to perform dynamic cross-verification of faults, and outputting real-time photovoltaic component faults. The technical problem of inaccurate fault monitoring in existing BIPV management is solved, and the technical effect of improving the accuracy of fault monitoring is achieved.

Description

Technical Field

[0001] The present application relates to the field related to building photovoltaic integrated management, and in particular to a BIPV management method and system based on photovoltaic modules. Background Art

[0002] As a clean and renewable energy source, the development and utilization of solar energy is increasingly valued. Building Integrated Photovoltaics (BIPV), as a technology that uses photovoltaic modules as building components or building materials and integrates them with buildings to achieve integrated design and installation, is gradually becoming an important development direction in the field of green buildings. BIPV can not only generate electricity, but also replace traditional building materials to achieve the dual effects of energy conservation and emission reduction and beautification of building appearance. In the management and maintenance of BIPV systems, it mainly relies on sensors installed on photovoltaic modules. These sensors are responsible for collecting the operating data of photovoltaic modules and judging whether there is a fault based on the preset threshold. However, due to the complex and changeable actual operating conditions of photovoltaic modules, the preset threshold cannot accurately reflect the actual status of the module, resulting in false alarms or missed faults.

[0003] Among the current related technologies, BIPV management based on photovoltaic modules has the technical problem of inaccurate fault monitoring. Summary of the invention

[0004] The present application provides a BIPV management method and system based on photovoltaic components, configures multiple edge fault monitoring nodes, and builds a communication link with component location identification as a constraint. After receiving the photovoltaic fault warning, the BIPV monitoring cloud identifies adjacent components and verifies the fault warning, outputs real-time fault component information, generates a fault monitoring window and fault monitoring components based on the real-time fault component information, and uses edge fault monitoring nodes to perform dynamic cross-validation of faults and other technical means to achieve the technical effect of improving the accuracy of fault monitoring.

[0005] The present application provides a BIPV management method based on photovoltaic components, including: configuring multiple edge fault monitoring nodes for multiple BIPV components of a target building, wherein the multiple edge fault monitoring nodes have multiple component location identifiers; using the multiple component location identifiers as constraints, building a communication link between the multiple edge fault monitoring nodes and a BIPV monitoring cloud; after receiving a photovoltaic fault warning, the BIPV monitoring cloud identifies adjacent components according to the photovoltaic fault warning, performs fault warning verification according to the identification result, and outputs real-time fault component information; generates a fault monitoring window and M fault monitoring components according to the real-time fault component information; after locating M edge fault monitoring nodes at the multiple edge fault monitoring nodes according to the M fault monitoring components, runs the M edge fault monitoring nodes with the fault monitoring window as a constraint to perform dynamic fault cross-validation, and outputs real-time photovoltaic component faults.

[0006] In a possible implementation, multiple edge fault monitoring nodes are configured for multiple BIPV components of a target building, and the following processing is performed: multiple environmental information perception units are configured for the multiple BIPV components, wherein the environmental information perception units are integrated with an irradiance sensor, an ambient temperature sensor, a backplane temperature sensor, a wind speed-direction sensor, a humidity sensor, and a sun tracking sensor; multiple electrical parameter monitoring units are configured for the multiple BIPV components, wherein the electrical parameter monitoring units are integrated with a current sensor, a voltage sensor, and a power sensor; progressive parameter optimization of the electrical prediction model is performed according to the component adjacency relationship of the multiple BIPV components to obtain multiple electrical prediction models of the multiple BIPV components; a first deviation evaluation model of the first BIPV component is pre-constructed; the first electrical prediction model of the first BIPV component is called from the multiple electrical prediction models; the first environmental information perception unit is connected to the first input end of the first electrical prediction model, the output end of the first electrical prediction model is connected to the second input end of the first deviation evaluation model, and the first electrical parameter monitoring unit is connected to the third input end of the first deviation evaluation model to complete the construction of the first edge fault monitoring node; and so on, the multiple edge fault monitoring nodes are configured for the multiple BIPV components.

[0007] In a possible implementation, the electrical prediction model is progressively optimized according to the component adjacency relationship of the multiple BIPV components to obtain multiple electrical prediction models of the multiple BIPV components, and the following processing is performed: a first historical environmental information set and a first historical electrical parameter set of the first BIPV component are interactively obtained; after a standard electrical prediction model is constructed based on a CNN network, the first historical environmental information set and the first historical electrical parameter set are used as training data to optimize the standard electrical prediction model, and the first electrical prediction model is output; an adjacency relationship analysis is performed according to the first component position of the first BIPV component to locate K second BIPV components; K second historical environmental information sets and K second historical electrical parameter sets of the K second BIPV components are interactively obtained; the first electrical prediction model is used as an optimization starting point, and the first electrical prediction model is optimized according to the K second historical environmental information sets and the K second historical electrical parameter sets, and K second electrical prediction models are output; and so on, the electrical prediction model is progressively optimized according to the component adjacency relationship of the multiple BIPV components until the multiple electrical prediction models are obtained.

[0008] In a possible implementation, after receiving a photovoltaic fault warning, the BIPV monitoring cloud identifies adjacent components according to the photovoltaic fault warning, performs fault warning verification according to the identification result, outputs real-time fault component information, and performs the following processing: obtains second real-time environmental information of the second BIPV component through the second environmental information perception unit; obtains second real-time electrical parameters of the second BIPV component through the second electrical parameter monitoring unit; after synchronizing the second real-time environmental information to the second electrical prediction model of the second edge fault monitoring node to obtain the second predicted electrical parameters, the second predicted electrical parameters and the second real-time electrical parameters are input into the second deviation evaluation model to obtain the second deviation scale parameter; if the second deviation scale parameter meets the preset deviation scale threshold, the second component position of the second BIPV component is obtained interactively; the second component position, the second real-time electrical parameters and the second deviation scale parameters are packaged to generate the photovoltaic fault warning, and the photovoltaic fault warning is sent to the BIPV monitoring cloud; the BIPV monitoring cloud identifies adjacent components according to the photovoltaic fault warning, performs fault warning verification according to the identification result, and outputs the real-time fault component information.

[0009] In a possible implementation, the BIPV monitoring cloud identifies adjacent components according to the photovoltaic fault warning, performs fault warning verification based on the identification result, outputs the real-time fault component information, and performs the following processing: extracts the second component position from the photovoltaic fault warning, and performs adjacent component identification based on the second component position to obtain M adjacent components; generates M feedback instructions based on the M component positions of the M adjacent components; locates M adjacent fault monitoring nodes at the multiple edge fault monitoring nodes based on the M adjacent components and multiple component position identifiers; the BIPV monitoring cloud sends the M feedback instructions to the M adjacent fault monitoring nodes to obtain M adjacent electrical parameters returned by the M adjacent fault monitoring nodes; interactively obtains M electrical ratio parameters of the second BIPV component and the M adjacent components; performs fault warning verification on the photovoltaic fault warning based on the M electrical ratio parameters and the M adjacent electrical parameters, and outputs the real-time fault component information.

[0010] In a possible implementation, the photovoltaic fault warning is verified according to the M electrical proportion parameters and the M adjacent electrical parameters, the real-time fault component information is output, and the following processing is performed: the second real-time electrical parameter and the second deviation scale parameter are extracted from the photovoltaic fault warning; the M real-time proportion parameters of the M adjacent electrical parameters and the second real-time electrical parameters are calculated; the deviation mean is calculated for the M real-time proportion parameters and the M electrical proportion parameters to obtain a third deviation scale; the proportion deviation weight and the prediction deviation weight are predefined; the third deviation scale and the second deviation scale are weightedly solved using the proportion deviation weight and the prediction deviation weight, and the verification deviation scale is output; if the verification deviation scale meets the preset verification deviation threshold, the second deviation scale parameter, the second component position and the M adjacent components are output as the real-time fault component information.

[0011] In a possible implementation, after locating M edge fault monitoring nodes among the multiple edge fault monitoring nodes according to the M fault monitoring components, the M edge fault monitoring nodes are run with the fault monitoring window as a constraint to perform dynamic cross-validation of faults, and real-time photovoltaic component faults are output, and the following processing is performed: monitoring window matching is performed according to the second deviation scale parameter in the real-time fault component information to obtain the fault monitoring window; the M adjacent components in the real-time fault component information are used as the M fault monitoring components; M edge fault monitoring nodes are located among the multiple edge fault monitoring nodes according to the M fault monitoring components; the M edge fault monitoring nodes are run with the fault monitoring window as a constraint to perform dynamic cross-validation of faults, and the real-time photovoltaic component faults are output.

[0012] The present application also provides a BIPV management system based on photovoltaic components, including: an edge fault monitoring node configuration module, which is used to configure multiple edge fault monitoring nodes for multiple BIPV components of a target building, wherein the multiple edge fault monitoring nodes have multiple component location identifiers; a communication link construction module, which is used to construct a communication link between the multiple edge fault monitoring nodes and a BIPV monitoring cloud with the multiple component location identifiers as constraints; a fault warning verification module, which is used for the BIPV monitoring cloud to identify adjacent components according to the photovoltaic fault warning after receiving the photovoltaic fault warning, and to perform fault warning verification based on the identification result, and output real-time fault component information; a fault monitoring window generation module, which is used to generate a fault monitoring window and M fault monitoring components according to the real-time fault component information; a fault dynamic cross-validation module, which is used to run the M edge fault monitoring nodes with the fault monitoring window as a constraint to perform fault dynamic cross-validation after locating the M edge fault monitoring nodes in the multiple edge fault monitoring nodes according to the M fault monitoring components, and output real-time photovoltaic component faults.

[0013] The BIPV management method and system based on photovoltaic components proposed in this application first configure multiple edge fault monitoring nodes for multiple BIPV components of the target building, wherein the multiple edge fault monitoring nodes have multiple component location identifiers, and then use the multiple component location identifiers as constraints to build communication links between the multiple edge fault monitoring nodes and the BIPV monitoring cloud. After receiving the photovoltaic fault warning, the BIPV monitoring cloud identifies adjacent components based on the photovoltaic fault warning, performs fault warning verification based on the identification results, outputs real-time fault component information, and then generates a fault monitoring window and M fault monitoring components based on the real-time fault component information. Finally, after locating M edge fault monitoring nodes at multiple edge fault monitoring nodes based on the M fault monitoring components, the M edge fault monitoring nodes are run with the fault monitoring window as a constraint to perform dynamic fault cross-validation, and output real-time photovoltaic component faults, thereby achieving the technical effect of improving the accuracy of fault monitoring. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to more clearly illustrate the technical solution of the embodiment of the present invention, the accompanying drawings of the embodiment of the present invention will be briefly introduced below. A flow chart is used in the present application to illustrate the operations performed by the system according to the embodiment of the present application. It should be understood that the preceding or following operations are not necessarily performed accurately in order. On the contrary, various steps can be processed in reverse order or simultaneously as needed. At the same time, other operations can also be added to these processes, or one or more operations can be removed from these processes.

[0015] Figure 1 A schematic flow chart of a BIPV management method based on photovoltaic modules provided in an embodiment of the present application.

[0016] Figure 2 A schematic diagram of the structure of a BIPV management system based on photovoltaic components provided in an embodiment of the present application.

[0017] Explanation of the accompanying drawings: edge fault monitoring node configuration module 10, communication link construction module 20, fault warning verification module 30, fault monitoring window generation module 40, fault dynamic cross-validation module 50. DETAILED DESCRIPTION

[0018] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below.

[0019] In order to make the objectives, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. The described embodiments should not be regarded as limiting the present application. All other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of this application.

[0020] In the following description, reference is made to "some embodiments", which describe a subset of all possible embodiments, but it is understood that "some embodiments" may be the same subset or different subsets of all possible embodiments, and may be combined with each other without conflict, and the terms "first\second" involved are merely to distinguish similar objects and do not represent a specific ordering of objects. The terms "including" and "having" and any variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products, or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those generally understood by technicians in the technical field of this application. The terms used herein are for the purpose of describing the embodiments of the present application only.

[0021] The present application embodiment provides a BIPV management method based on photovoltaic modules, such as Figure 1 As shown, the method includes:

[0022] Step S100, configuring multiple edge fault monitoring nodes for multiple BIPV components of a target building, wherein the multiple edge fault monitoring nodes have multiple component location identifiers.

[0023] Specifically, the BIPV components refer to building materials that integrate photovoltaic power generation functions, such as photovoltaic tiles, photovoltaic curtain walls, etc. Smart sensors or monitoring devices are installed near each BIPV component. These devices serve as edge fault monitoring nodes to collect real-time operating data of photovoltaic components. Based on the physical location (such as longitude and latitude), component number or coordinates in the grid layout, a unique location identifier is assigned to each edge fault monitoring node for data management and fault location.

[0024] In a possible implementation, multiple edge fault monitoring nodes are configured for multiple BIPV components of the target building, and step S100 further includes step S110, configuring multiple environmental information sensing units for the multiple BIPV components, wherein the environmental information sensing unit integrates an irradiance sensor, an ambient temperature sensor, a backplane temperature sensor, a wind speed-wind direction sensor, a humidity sensor, and a solar tracking sensor. Specifically, an environmental information sensing unit is configured for each BIPV component or its vicinity. This unit integrates a variety of sensors, including an irradiance sensor (for measuring the intensity of solar radiation), an ambient temperature sensor (for measuring the ambient temperature around the component), a backplane temperature sensor (directly measuring the temperature of the backplane of the photovoltaic component), a wind speed-wind direction sensor (for measuring wind speed and wind direction), a humidity sensor (for measuring humidity in the air), and a solar tracking sensor (including a solar radiation tracker and an inclination sensor for tracking solar radiation and radiation angle). These sensors can collect environmental parameters in real time and provide basic data for fault monitoring and early warning.

[0025] Step S120, multiple electrical parameter monitoring units are configured for the multiple BIPV components, wherein the electrical parameter monitoring units are integrated with current sensors, voltage sensors, and power sensors. Specifically, an electrical parameter monitoring unit is configured for each BIPV component. This unit integrates current sensors, voltage sensors, and power sensors, and is used to monitor the electrical performance parameters of the BIPV components in real time, such as current, voltage, and power.

[0026] Step S130, based on the adjacent relationship of the multiple BIPV components, the electrical prediction model is progressively optimized to obtain multiple electrical prediction models of the multiple BIPV components. Specifically, the adjacent relationship between the BIPV components is used to perform progressive parameter optimization on the electrical prediction model (a model built based on historical data and a machine learning algorithm), including collecting historical data, building an initial model, and verifying and adjusting the model through data from adjacent components. Finally, an optimized electrical prediction model is obtained for each BIPV component to predict the electrical performance parameters of the BIPV component.

[0027] Step S140, pre-constructing a first deviation evaluation model for a first BIPV component. Specifically, pre-constructing a deviation evaluation model for a first BIPV component (any one of a plurality of BIPV components). This model is used to evaluate the difference between actual electrical parameters and predicted electrical parameters to identify potential faults or anomalies.

[0028] Step S150, calling the first electrical prediction model of the first BIPV component from the multiple electrical prediction models; Step S160, connecting the first environmental information perception unit to the first input end of the first electrical prediction model, connecting the output end of the first electrical prediction model to the second input end of the first deviation evaluation model, connecting the first electrical parameter monitoring unit to the third input end of the first deviation evaluation model, and completing the construction of the first edge fault monitoring node.

[0029] Specifically, the output of the first environmental information perception unit is connected to the first input end of the first electrical prediction model, the output of the first electrical prediction model is connected to the second input end of the first deviation evaluation model, and the output of the first electrical parameter monitoring unit is connected to the third input end of the first deviation evaluation model to complete the construction of the first edge fault monitoring node. That is, the edge fault monitoring node is a device that integrates the environmental information perception unit, the electrical prediction model and the deviation evaluation model. This node can receive environmental information and predict electrical parameters in real time, and evaluate the difference between the actual electrical parameters and the predicted values, thereby identifying potential faults.

[0030] Step S170, and so on, configure the multiple edge fault monitoring nodes for the multiple BIPV components. Specifically, repeat the above steps S110 to S160 to configure edge fault monitoring nodes for the remaining BIPV components. Thus, each BIPV component is configured with an edge fault monitoring node that can monitor and evaluate its health status in real time. This implementation method realizes comprehensive monitoring and evaluation of the environmental information and electrical performance of BIPV components by integrating multiple sensors and constructing electrical prediction models and deviation evaluation models, so that potential faults or abnormalities can be discovered in a timely manner, thereby improving the reliability and safety of the BIPV system.

[0031] In one possible implementation, the electrical prediction model is progressively optimized according to the component adjacency relationship of the multiple BIPV components to obtain multiple electrical prediction models of the multiple BIPV components, and step S130 further includes step S131, interactively obtaining the first historical environmental information set and the first historical electrical parameter set of the first BIPV component. Specifically, by interacting with the data acquisition system or sensor network related to the BIPV component, the environmental information (such as irradiance, ambient temperature, backplane temperature, wind speed, wind direction, humidity, solar radiation and radiation angle, etc.) and electrical parameters (such as current, voltage, power, etc.) of the first BIPV component in the past period of time are collected. These data are organized into historical environmental information sets and historical electrical parameter sets for model training.

[0032] Step S132, after building a standard electrical prediction model based on the CNN network, use the first historical environmental information set and the first historical electrical parameter set as training data to optimize the parameters of the standard electrical prediction model, and output the first electrical prediction model. Specifically, a standard electrical prediction model is constructed using a convolutional neural network (CNN). CNN is a deep learning model used to learn the complex relationship between environmental information and electrical parameters. Using the first historical environmental information set and the first historical electrical parameter set obtained in step S131 as training data, the CNN model is trained (i.e., parameter optimization) to minimize the prediction error. After the training is completed, the first electrical prediction model for the first BIPV component is obtained.

[0033] Step S133, performing an adjacent relationship analysis based on the first component position of the first BIPV component, and locating K second BIPV components. Specifically, based on the location information of the first BIPV component, the K second BIPV components adjacent to the first BIPV component are determined through spatial analysis or geographic information system (GIS) technology.

[0034] Step S134, interactively obtain K second historical environmental information sets and K second historical electrical parameter sets of the K second BIPV components. Specifically, similar to step S131, by interacting with the data acquisition system or sensor network, the historical environmental information sets and historical electrical parameter sets of the K second BIPV components are collected for model optimization.

[0035] Step S135, taking the first electrical prediction model as the optimization starting point, adjusting and optimizing the first electrical prediction model according to the K second historical environmental information sets and the K second historical electrical parameter sets, and outputting K second electrical prediction models. Specifically, taking the first electrical prediction model as the optimization starting point, further adjusting and optimizing the model using the historical environmental information sets and historical electrical parameter sets of the K second BIPV components, respectively, to obtain K second electrical prediction models.

[0036] Step S136, and so on, perform progressive parameter optimization of the electrical prediction model according to the component adjacent relationship of the multiple BIPV components until the multiple electrical prediction models are obtained. Specifically, the process of steps S133 to S135 is repeated. This process is progressive, that is, the model of the component closest to the first BIPV component is first optimized, and then gradually expanded to components farther away. In this way, the similarity between adjacent components can be used to improve the prediction accuracy of the model, and finally an optimized electrical prediction model is constructed for each BIPV component. Adjacent BIPV components are often in similar environmental conditions and exhibit similar electrical performance. This implementation method improves the prediction accuracy of the model by utilizing this similarity through progressive parameter optimization.

[0037] Step S200, using the multiple component location identifiers as constraints, constructing communication links between the multiple edge fault monitoring nodes and the BIPV monitoring cloud.

[0038] Specifically, wireless communication technologies (such as LoRa, Zigbee, NB-IoT, etc.) or wired networks are used to connect edge fault monitoring nodes to the BIPV monitoring cloud to form a data transmission channel, that is, the path for data to be transmitted from edge fault monitoring nodes to the BIPV monitoring cloud. When building a communication link, the component location identifier is used as a constraint to ensure that data can be accurately and efficiently transmitted to the cloud, and to facilitate the cloud to manage and analyze monitoring data based on location information. Among them, the BIPV monitoring cloud is a central server or cloud platform used to receive, process and analyze data from edge fault monitoring nodes and provide remote monitoring and management functions.

[0039] Step S300: After receiving the photovoltaic fault warning, the BIPV monitoring cloud identifies adjacent components according to the photovoltaic fault warning, performs fault warning verification according to the identification result, and outputs real-time fault component information.

[0040] Specifically, when the edge fault monitoring node detects abnormal data (such as power drop, temperature abnormality, etc.), it sends a fault warning signal to the BIPV monitoring cloud. The cloud identifies other components adjacent to the faulty component based on the component location identifier, and verifies the fault warning by comparing historical data, operating parameters and the status of adjacent components to reduce false alarms and missed alarms.

[0041] In a possible implementation, after receiving the photovoltaic fault warning, the BIPV monitoring cloud identifies adjacent components according to the photovoltaic fault warning, performs fault warning verification according to the identification result, and outputs real-time fault component information. Step S300 further includes step S310, in which the second real-time environmental information of the second BIPV component is sensed by the second environmental information sensing unit. Specifically, the environmental information sensing unit integrated in the BIPV component is used to collect the environmental conditions of the component in real time to obtain environmental parameters such as irradiance, temperature, and humidity.

[0042] Step S320, collect and obtain the second real-time electrical parameters of the second BIPV component through the second electrical parameter monitoring unit. Specifically, the electrical parameter monitoring unit is used to measure the electrical output of the BIPV component in real time to obtain the electrical parameters of the component such as current, voltage, power, etc., which reflect the current working status of the component.

[0043] Step S330, after synchronizing the second real-time environmental information to the second electrical prediction model of the second edge fault monitoring node and obtaining the second predicted electrical parameters, the second predicted electrical parameters and the second real-time electrical parameters are input into the second deviation evaluation model to obtain the second deviation scale parameters. Specifically, the real-time environmental information is input into the electrical prediction model of the edge fault monitoring node, and the model predicts the expected electrical parameters (such as predicted current, predicted voltage) based on this information. Then, these predicted electrical parameters and the electrical parameters collected in real time are input into the deviation evaluation model, and the model calculates the deviation scale parameters between the two, that is, the numerical value representing the deviation between the predicted electrical parameters and the real-time electrical parameters.

[0044] Step S340, if the second deviation scale parameter meets the preset deviation scale threshold, the second component position of the second BIPV component is interactively obtained. Specifically, if the calculated deviation scale parameter exceeds the preset deviation scale threshold (a numerical limit for determining whether the deviation is sufficient to trigger a fault warning), it indicates that the second BIPV component (any one of the multiple BIPV components) may be faulty, and the position information of the component is interactively obtained.

[0045] Step S350, pack the second component position, the second real-time electrical parameter and the second deviation scale parameter, generate the photovoltaic fault warning, and send the photovoltaic fault warning to the BIPV monitoring cloud. Specifically, the component position, real-time electrical parameter and deviation scale parameter and other information are packed into a complete photovoltaic fault warning information package, and sent to the BIPV monitoring cloud through a communication link.

[0046] In step S360, the BIPV monitoring cloud identifies adjacent components according to the photovoltaic fault warning, performs fault warning verification according to the identification results, and outputs the real-time fault component information. Specifically, after receiving the fault warning, the BIPV monitoring cloud identifies adjacent components according to the component location information provided in the warning, and uses the historical data and real-time data of these components to perform further fault verification. If a fault is confirmed, detailed real-time fault component information is output. This implementation method can detect potential fault signs at an early stage by collecting environmental information and electrical parameters in real time, and using electrical prediction models and deviation evaluation models to predict and evaluate component status. At the same time, through the use of cloud processing capabilities and adjacent component information, fault warnings can be further verified and refined, thereby avoiding false alarms and missed alarms, and improving the timeliness and effectiveness of fault handling.

[0047] In one possible implementation, the BIPV monitoring cloud identifies adjacent components based on the photovoltaic fault warning, performs fault warning verification based on the identification result, and outputs the real-time fault component information. Step S360 further includes step S361, extracting the second component position from the photovoltaic fault warning, and identifying adjacent components based on the second component position to obtain M adjacent components. Specifically, when the BIPV monitoring cloud receives a photovoltaic fault warning, it first parses the component position (i.e., the second component position) in the warning information. Then, based on the component layout information of the BIPV system, identify other components adjacent to the faulty component, including but not limited to directly adjacent components in the four directions of up, down, left, and right, and finally determine the positions and identifications of M adjacent components, where M is a specific value.

[0048] Step S362, generating M feedback instructions according to the M component positions of the M adjacent components. Specifically, for each identified adjacent component, the BIPV monitoring cloud generates a feedback instruction, which includes the identification of the component and information requesting its electrical parameters. These instructions are then sent to the corresponding edge fault monitoring node.

[0049] Step S363, based on the M adjacent components and multiple component location identifiers, locate the M adjacent fault monitoring nodes in the multiple edge fault monitoring nodes. Specifically, the BIPV monitoring cloud determines which edge fault monitoring nodes are responsible for monitoring these adjacent components based on the location information of the adjacent components and the location information of the previously configured edge fault monitoring nodes. The identifiers of these nodes are recorded for sending feedback instructions.

[0050] Step S364, the BIPV monitoring cloud sends the M feedback instructions to the M adjacent fault monitoring nodes to obtain the M adjacent electrical parameters transmitted by the M adjacent fault monitoring nodes. Specifically, the BIPV monitoring cloud sends the M feedback instructions to the M adjacent fault monitoring nodes through the established communication link. After receiving the instructions, these nodes collect real-time electrical parameters from the adjacent components they monitor and transmit them back to the BIPV monitoring cloud through the communication link.

[0051] Step S365, interactively obtain M electrical ratio parameters of the second BIPV component and M adjacent components. Specifically, the BIPV monitoring cloud uses historical data (such as electrical parameter ratios during normal operation) or preset electrical ratio rules to calculate the electrical ratio parameters between the faulty component (the second BIPV component) and its adjacent components. These parameters reflect the relative relationship between the electrical performance of the components.

[0052] Step S366, perform fault warning verification on the photovoltaic fault warning according to the M electrical proportion parameters and the M adjacent electrical parameters, and output the real-time fault component information. Specifically, the BIPV monitoring cloud compares and analyzes the M electrical proportion parameters with the M adjacent electrical parameters. If the proportional relationship between the electrical parameters of the adjacent components and the electrical parameters of the faulty components does not match the preset electrical proportion parameters, or exceeds the normal fluctuation range, the validity of the fault warning is further confirmed, and detailed real-time fault component information is output, including the specific location of the faulty component, the type of fault, the degree of fault, etc. This implementation method further verifies and refines the fault warning by using the electrical parameters and electrical proportional relationship of the adjacent components, thereby reducing false alarms and missed alarms.

[0053] In one possible implementation, the photovoltaic fault warning is verified according to the M electrical ratio parameters and the M adjacent electrical parameters, and the real-time fault component information is output. Step S366 further includes step S3661, extracting the second real-time electrical parameter and the second deviation scale parameter from the photovoltaic fault warning. Specifically, the BIPV monitoring cloud automatically parses the warning information package through its internal data processing system, and extracts the key fault component data, including the second real-time electrical parameter and the second deviation scale parameter, according to the preset data format and structure. The second real-time electrical parameter is the electrical parameter such as real-time current, voltage or power of the fault component when a fault occurs. The second deviation scale parameter is the degree of deviation between the real-time electrical parameter of the fault component and the predicted electrical parameter.

[0054] Step S3662, calculate M real-time proportional parameters of the M adjacent electrical parameters and the second real-time electrical parameters. Specifically, the BIPV monitoring cloud performs a division operation on the real-time electrical parameters of each adjacent component and the real-time electrical parameters of the faulty component through a built-in calculation module to obtain M real-time proportional parameters. These proportional parameters reflect the relative relationship between the electrical performance of the adjacent component and the faulty component.

[0055] Step S3663, calculate the mean deviation of the M real-time proportion parameters and the M electrical proportion parameters to obtain a third deviation scale. Specifically, the BIPV monitoring cloud uses its data processing system to compare the M real-time proportion parameters with the M electrical proportion parameters one by one, calculate the deviation value of each proportion, and then calculate the mean of these deviation values ​​to obtain the third deviation scale. This scale reflects the overall deviation degree of the electrical proportion relationship between the faulty component and the adjacent components.

[0056] Step S3664, predefine proportional deviation weights and predicted deviation weights. Specifically, proportional deviation weights and predicted deviation weights are set in the system configuration according to the system's operating experience and actual needs. These weights reflect the importance of different types of deviations in fault judgment. Among them, the proportional deviation weight is a weight value used to measure the importance of electrical proportional deviation in fault judgment. The predicted deviation weight is a weight value used to measure the importance of the deviation between the predicted electrical parameters and the real-time electrical parameters in fault judgment.

[0057] Step S3665, use the proportional deviation weight and the predicted deviation weight to weight the third deviation scale and the second deviation scale to solve, and output the verification deviation scale. Specifically, the BIPV monitoring cloud uses its data processing system to weight the third deviation scale and the second deviation scale according to the predefined proportional deviation weight and predicted deviation weight, and calculates the verification deviation scale. This scale comprehensively reflects the overall situation of the faulty component in terms of electrical proportional relationship and predicted deviation.

[0058] Step S3666, if the verification deviation scale meets the preset verification deviation threshold, the second deviation scale parameter, the second component position and M adjacent components are output as the real-time faulty component information. Specifically, the BIPV monitoring cloud automatically compares the verification deviation scale with the preset verification deviation threshold (the deviation threshold used to determine whether a faulty component exists) through its data processing system. If the verification deviation scale is greater than or equal to the threshold, the faulty component is confirmed, and the second deviation scale parameter, the second component position and the information of the M adjacent components are output as real-time faulty component information to relevant personnel or systems for processing. This implementation method can more accurately determine the existence and severity of faulty components by comprehensively considering the overall situation of the electrical proportional relationship and predicted deviation between the faulty component and the adjacent components, thereby improving the accuracy and reliability of fault detection in the BIPV system.

[0059] Step S400: generating a fault monitoring window and M fault monitoring components according to the real-time fault component information.

[0060] Specifically, according to the fault severity of the faulty component, a fault monitoring window is determined. The fault monitoring window is the time period or data range for continuous monitoring of the faulty component and its adjacent components. Within the fault monitoring window, M key components are selected as key monitoring objects. These components are directly related to the faulty component or have potential failure risks.

[0061] Step S500, after locating M edge fault monitoring nodes according to the M fault monitoring components in the multiple edge fault monitoring nodes, the M edge fault monitoring nodes are operated with the fault monitoring window as a constraint to perform fault dynamic cross-validation and output real-time photovoltaic component faults.

[0062] Specifically, according to the location identification of M fault monitoring components, the corresponding edge fault monitoring node is found. Within the fault monitoring window, the data of the M edge fault monitoring nodes are used to dynamically cross-validate the fault components to improve the accuracy and reliability of fault identification. The verified fault information is fed back to the management personnel in real time or the fault handling process is automatically triggered. The embodiment of the present application adopts the configuration of multiple edge fault monitoring nodes, and builds a communication link with the component location identification as a constraint. After receiving the photovoltaic fault warning, the BIPV monitoring cloud performs adjacent component identification and fault warning verification, outputs real-time fault component information, generates a fault monitoring window and a fault monitoring component according to the real-time fault component information, and uses edge fault monitoring nodes to perform dynamic cross-validation of faults and other technical means to achieve the technical effect of improving the accuracy of fault monitoring.

[0063] In a possible implementation, after locating M edge fault monitoring nodes at the multiple edge fault monitoring nodes according to the M fault monitoring components, the M edge fault monitoring nodes are run with the fault monitoring window as a constraint to perform dynamic cross-validation of faults, and real-time photovoltaic component faults are output. Step S500 further includes step S510, matching the monitoring window according to the second deviation scale parameter in the real-time fault component information to obtain the fault monitoring window. Specifically, after receiving the real-time fault component information, the BIPV monitoring cloud extracts the second deviation scale parameter therein. According to a preset matching rule or algorithm, the second deviation scale parameter is compared with a plurality of preset monitoring window sizes. The monitoring window size that best matches the second deviation scale parameter is selected as the fault monitoring window.

[0064] Step S520: The M adjacent components in the real-time fault component information are used as the M fault monitoring components. Specifically, the information of the M adjacent components is extracted from the real-time fault component information. The M adjacent components are directly used as the fault monitoring components that need to be further monitored and verified.

[0065] Step S530, locate M edge fault monitoring nodes in the multiple edge fault monitoring nodes according to the M fault monitoring components. Specifically, extract the location identifier of the fault monitoring component from the information of the fault monitoring component, search and match in the multiple edge fault monitoring nodes according to the location identifier, and find the edge fault monitoring node corresponding to each fault monitoring component.

[0066] Step S540, run the M edge fault monitoring nodes to perform dynamic cross-validation of faults with the fault monitoring window as a constraint, and output the real-time photovoltaic component fault. Specifically, start the data collection process of the M edge fault monitoring nodes with the fault monitoring window as the time range or data collection condition. The collected data include the actual electrical parameters of the fault monitoring component, the predicted electrical parameters, and the electrical parameters of M adjacent components. The same fault warning verification method as steps S3661-S3666 is used to process and analyze these data, and calculate the verification deviation scale. According to the results of cross-validation, it is determined whether the electrical parameters of the faulty component have returned to normal. If the verification deviation scale meets the preset verification deviation threshold, it indicates that the fault persists, and the relevant information is output as a real-time photovoltaic component fault. This implementation method further confirms the authenticity of the fault through the dynamic cross-validation process of the fault, and improves the accuracy of fault detection.

[0067] In the above, refer to Figure 1 The BIPV management method based on photovoltaic modules according to an embodiment of the present invention is described in detail. Figure 2A BIPV management system based on photovoltaic components according to an embodiment of the present invention is described.

[0068] The BIPV management system based on photovoltaic modules according to the embodiment of the present invention is used to solve the technical problem of inaccurate fault monitoring in the existing BIPV management, and achieve the technical effect of improving the accuracy of fault monitoring. The BIPV management system based on photovoltaic modules includes: an edge fault monitoring node configuration module 10, a communication link construction module 20, a fault warning verification module 30, a fault monitoring window generation module 40, and a fault dynamic cross-validation module 50.

[0069] An edge fault monitoring node configuration module 10 is used to configure multiple edge fault monitoring nodes for multiple BIPV components of a target building, wherein the multiple edge fault monitoring nodes have multiple component location identifiers; a communication link construction module 20 is used to construct a communication link between the multiple edge fault monitoring nodes and a BIPV monitoring cloud using the multiple component location identifiers as constraints; a fault warning verification module 30 is used for the BIPV monitoring cloud to identify adjacent components according to the photovoltaic fault warning after receiving a photovoltaic fault warning, and to perform fault warning verification based on the identification result, and output real-time fault component information; a fault monitoring window generation module 40 is used to generate a fault monitoring window and M fault monitoring components according to the real-time fault component information; a fault dynamic cross-validation module 50 is used to operate the M edge fault monitoring nodes with the fault monitoring window as a constraint to perform fault dynamic cross-validation after locating M edge fault monitoring nodes at the multiple edge fault monitoring nodes according to the M fault monitoring components, and output real-time photovoltaic component faults.

[0070] Below, the specific configuration of the edge fault monitoring node configuration module 10 will be described in detail. As described above, multiple edge fault monitoring nodes are configured for multiple BIPV components of the target building, and the edge fault monitoring node configuration module 10 may further include: an environmental information perception unit is used to configure multiple environmental information perception units for the multiple BIPV components, wherein the environmental information perception unit is integrated with an irradiance sensor, an ambient temperature sensor, a backplane temperature sensor, a wind speed-direction sensor, a humidity sensor, and a solar tracking sensor; an electrical parameter monitoring unit is used to configure multiple electrical parameter monitoring units for the multiple BIPV components, wherein the electrical parameter monitoring unit is integrated with a current sensor, a voltage sensor, and a power sensor; an electrical prediction model acquisition unit is used to perform progressive parameter optimization of the electrical prediction model according to the component adjacency relationship of the multiple BIPV components to obtain the Multiple electrical prediction models for multiple BIPV components; a first deviation evaluation model pre-construction unit is used to pre-construct a first deviation evaluation model for a first BIPV component; a first electrical prediction model calling unit is used to call the first electrical prediction model of the first BIPV component from the multiple electrical prediction models; a first edge fault monitoring node construction unit is used to connect the first environmental information perception unit to the first input end of the first electrical prediction model, connect the output end of the first electrical prediction model to the second input end of the first deviation evaluation model, and connect the first electrical parameter monitoring unit to the third input end of the first deviation evaluation model to complete the construction of the first edge fault monitoring node; multiple edge fault monitoring node configuration units are used to configure the multiple edge fault monitoring nodes for the multiple BIPV components by analogy.

[0071] Among them, the electrical prediction model is progressively optimized according to the component adjacency relationship of the multiple BIPV components to obtain multiple electrical prediction models of the multiple BIPV components. The electrical prediction model acquisition unit may further include: a first historical information acquisition subunit is used to interactively obtain a first historical environmental information set and a first historical electrical parameter set of the first BIPV component; a first electrical prediction model output subunit is used to build a standard electrical prediction model based on the CNN network, and then use the first historical environmental information set and the first historical electrical parameter set as training data to optimize the parameters of the standard electrical prediction model and output the first electrical prediction model; the adjacent relationship analysis subunit is used to analyze the adjacent relationship of the first BIPV component according to the adjacent relationship of the first BIPV component. The first component position is subjected to adjacent relationship analysis to locate K second BIPV components; the second historical information acquisition subunit is used to interactively obtain K second historical environmental information sets and K second historical electrical parameter sets of the K second BIPV components; the second electrical prediction model output subunit is used to use the first electrical prediction model as an optimization starting point, perform parameter adjustment and optimization on the first electrical prediction model according to the K second historical environmental information sets and the K second historical electrical parameter sets, and output K second electrical prediction models; multiple electrical prediction model acquisition subunits are used to perform progressive parameter adjustment and optimization of the electrical prediction model according to the adjacent relationship of the multiple BIPV components, and so on, until the multiple electrical prediction models are obtained.

[0072] The specific configuration of the fault warning verification module 30 will be described in detail below. As described above, after receiving the photovoltaic fault warning, the BIPV monitoring cloud identifies adjacent components according to the photovoltaic fault warning, performs fault warning verification according to the identification result, and outputs real-time fault component information. The fault warning verification module 30 may further include: a second real-time environmental information acquisition unit for obtaining second real-time environmental information of the second BIPV component through a second environmental information perception unit; a second real-time electrical parameter acquisition unit for obtaining second real-time electrical parameters of the second BIPV component through a second electrical parameter monitoring unit; a deviation evaluation unit for synchronizing the second real-time environmental information to the second electrical prediction model of the second edge fault monitoring node, and obtaining the second predicted electrical parameters. , input the second predicted electrical parameter and the second real-time electrical parameter into the second deviation evaluation model to obtain the second deviation scale parameter; the second component position acquisition unit is used to interactively obtain the second component position of the second BIPV component if the second deviation scale parameter meets the preset deviation scale threshold; the photovoltaic fault warning generation unit is used to package the second component position, the second real-time electrical parameter and the second deviation scale parameter, generate the photovoltaic fault warning, and send the photovoltaic fault warning to the BIPV monitoring cloud; the fault warning verification unit is used in the BIPV monitoring cloud to identify adjacent components according to the photovoltaic fault warning, and perform fault warning verification according to the identification result, and output the real-time fault component information.

[0073] Among them, the BIPV monitoring cloud identifies adjacent components according to the photovoltaic fault warning, performs fault warning verification according to the identification result, and outputs the real-time fault component information. The fault warning verification unit may further include: an adjacent component identification subunit is used to extract the second component position from the photovoltaic fault warning, and perform adjacent component identification according to the second component position to obtain M adjacent components; a feedback instruction generation subunit is used to generate M feedback instructions according to the M component positions of the M adjacent components; an adjacent fault monitoring node positioning subunit is used to locate M adjacent fault monitoring nodes at the multiple edge fault monitoring nodes according to the M adjacent components and multiple component position identifiers; an adjacent electrical parameter acquisition subunit is used for the BIPV monitoring cloud to send the M feedback instructions to the M adjacent fault monitoring nodes to obtain the M adjacent electrical parameters returned by the M adjacent fault monitoring nodes; the electrical ratio parameter acquisition subunit is used to interactively obtain the M electrical ratio parameters of the second BIPV component and the M adjacent components; the fault warning verification subunit is used to perform fault warning verification on the photovoltaic fault warning according to the M electrical ratio parameters and M adjacent electrical parameters, and output the real-time fault component information.

[0074] Among them, the photovoltaic fault warning is verified according to the M electrical proportion parameters and M adjacent electrical parameters, and the real-time fault component information is output. The fault warning verification subunit may further include: a parameter extraction component is used to extract the second real-time electrical parameter and the second deviation scale parameter from the photovoltaic fault warning; a real-time proportion parameter calculation component is used to calculate the M real-time proportion parameters of the M adjacent electrical parameters and the second real-time electrical parameters; a deviation mean calculation component is used to perform deviation mean calculation on the M real-time proportion parameters and the M electrical proportion parameters to obtain a third deviation scale; a deviation weight predefinition component is used to predefine a proportion deviation weight and a prediction deviation weight; a verification deviation scale output component is used to use the proportion deviation weight and the prediction deviation weight to perform a weighted solution on the third deviation scale and the second deviation scale, and output a verification deviation scale; a real-time fault component information output component is used to output the second deviation scale parameter, the second component position and M adjacent components as the real-time fault component information if the verification deviation scale meets a preset verification deviation threshold.

[0075] The specific configuration of the fault dynamic cross-validation module 50 will be described in detail below. As described above, after locating the M edge fault monitoring nodes according to the M fault monitoring components at the multiple edge fault monitoring nodes, the M edge fault monitoring nodes are run with the fault monitoring window as a constraint to perform fault dynamic cross-validation, and the real-time photovoltaic component fault is output. The fault dynamic cross-validation module 50 may further include: a monitoring window matching unit is used to perform monitoring window matching according to the second deviation scale parameter in the real-time fault component information to obtain the fault monitoring window; a fault monitoring component determination unit is used to use the M adjacent components in the real-time fault component information as the M fault monitoring components; an edge fault monitoring node positioning unit is used to locate the M edge fault monitoring nodes at the multiple edge fault monitoring nodes according to the M fault monitoring components; a fault dynamic cross-validation unit is used to run the M edge fault monitoring nodes with the fault monitoring window as a constraint to perform fault dynamic cross-validation, and output the real-time photovoltaic component fault.

[0076] The photovoltaic component-based BIPV management system provided in the embodiment of the present invention can execute the photovoltaic component-based BIPV management method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0077] Although the present application makes various references to certain modules in the system according to the embodiments of the present application, any number of different modules may be used and run on the user terminal and / or server, and the various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention.

[0078] The above specific implementation manner does not constitute a limitation to the protection scope of the present application. It should be understood by those skilled in the art that various modifications, combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present application should be included in the protection scope of the present application. In some cases, the actions or steps recorded in the present application can be performed in an order different from that in the embodiment and can still achieve the desired results. In addition, the process depicted in the accompanying drawings does not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

Claims

1. A BIPV management method based on photovoltaic modules, characterized in that: The method comprises: Configuring a plurality of edge fault monitoring nodes for a plurality of BIPV components of a target building, wherein the plurality of edge fault monitoring nodes have a plurality of component location identifiers; Using the multiple component location identifiers as constraints, constructing communication links between the multiple edge fault monitoring nodes and the BIPV monitoring cloud; After receiving the photovoltaic fault warning, the BIPV monitoring cloud identifies adjacent components according to the photovoltaic fault warning, performs fault warning verification according to the identification result, and outputs real-time fault component information; Generate a fault monitoring window and M fault monitoring components according to the real-time fault component information; The M fault monitoring components refer to M adjacent components of the real-time fault component; After locating M edge fault monitoring nodes according to the M fault monitoring components, the M edge fault monitoring nodes are operated with the fault monitoring window as a constraint to perform dynamic cross-validation of faults and output real-time photovoltaic component faults.

2. The BIPV management method based on photovoltaic modules according to claim 1, characterized in that: A plurality of edge fault monitoring nodes are configured for a plurality of BIPV components of a target building, the method comprising: A plurality of environmental information sensing units are configured for the plurality of BIPV components, wherein the environmental information sensing units are integrated with an irradiance sensor, an ambient temperature sensor, a backplane temperature sensor, a wind speed-direction sensor, a humidity sensor, and a sun tracking sensor; Configuring multiple electrical parameter monitoring units for the multiple BIPV components, wherein the electrical parameter monitoring units integrate current sensors, voltage sensors, and power sensors; Performing progressive parameter optimization of an electrical prediction model according to the component adjacency relationship of the plurality of BIPV components to obtain a plurality of electrical prediction models of the plurality of BIPV components; pre-constructing a first deviation evaluation model for a first BIPV component; calling a first electrical prediction model of the first BIPV component from the plurality of electrical prediction models; Connecting the first environmental information sensing unit to the first input end of the first electrical prediction model, connecting the output end of the first electrical prediction model to the second input end of the first deviation evaluation model, and connecting the first electrical parameter monitoring unit to the third input end of the first deviation evaluation model to complete the construction of the first edge fault monitoring node; By analogy, the multiple edge fault monitoring nodes are configured for the multiple BIPV components.

3. The BIPV management method based on photovoltaic modules according to claim 2, characterized in that: According to the component adjacency relationship of the plurality of BIPV components, a progressive parameter adjustment optimization of the electrical prediction model is performed to obtain a plurality of electrical prediction models of the plurality of BIPV components, the method comprising: Interactively obtaining a first historical environmental information set and a first historical electrical parameter set of the first BIPV component; After a standard electrical prediction model is constructed based on the CNN network, the first historical environmental information set and the first historical electrical parameter set are used as training data to adjust and optimize the standard electrical prediction model, and the first electrical prediction model is output; Performing an adjacent relationship analysis based on the first component position of the first BIPV component to locate K second BIPV components; Interactively obtaining K second historical environmental information sets and K second historical electrical parameter sets of the K second BIPV components; Taking the first electrical prediction model as an optimization starting point, optimizing the first electrical prediction model according to the K second historical environment information sets and the K second historical electrical parameter sets, and outputting K second electrical prediction models; By analogy, the electrical prediction model is progressively optimized according to the component adjacency relationship of the multiple BIPV components until the multiple electrical prediction models are obtained.

4. The BIPV management method based on photovoltaic modules according to claim 2, characterized in that: After receiving the photovoltaic fault warning, the BIPV monitoring cloud identifies adjacent components according to the photovoltaic fault warning, performs fault warning verification according to the identification result, and outputs real-time fault component information. The method includes: Acquiring second real-time environmental information of the second BIPV component through the second environmental information sensing unit; Acquire a second real-time electrical parameter of the second BIPV component by means of a second electrical parameter monitoring unit; After synchronizing the second real-time environmental information to a second electrical prediction model of a second edge fault monitoring node to obtain a second predicted electrical parameter, the second predicted electrical parameter and the second real-time electrical parameter are input into a second deviation evaluation model to obtain a second deviation scale parameter; If the second deviation scale parameter satisfies a preset deviation scale threshold, interactively obtaining a second component position of the second BIPV component; Packing the second component position, the second real-time electrical parameter, and the second deviation scale parameter, generating the photovoltaic fault warning, and sending the photovoltaic fault warning to the BIPV monitoring cloud; The BIPV monitoring cloud identifies adjacent components based on the photovoltaic fault warning, performs fault warning verification based on the identification results, and outputs the real-time fault component information.

5. The BIPV management method based on photovoltaic modules according to claim 4, characterized in that: The BIPV monitoring cloud identifies adjacent components according to the photovoltaic fault warning, performs fault warning verification according to the identification result, and outputs the real-time fault component information. The method includes: Extracting the second component position from the photovoltaic fault warning, and identifying adjacent components according to the second component position to obtain M adjacent components; Generate M return instructions according to the M component positions of the M adjacent components; Locating M adjacent fault monitoring nodes at the plurality of edge fault monitoring nodes according to the M adjacent components and the plurality of component position identifiers; The BIPV monitoring cloud sends the M feedback instructions to M adjacent fault monitoring nodes to obtain M adjacent electrical parameters transmitted back by the M adjacent fault monitoring nodes; Interactively obtaining M electrical ratio parameters of the second BIPV component and M adjacent components; The photovoltaic fault warning is verified according to the M electrical proportion parameters and the M adjacent electrical parameters, and the real-time fault component information is output.

6. The BIPV management method based on photovoltaic modules according to claim 5, characterized in that: Performing fault warning verification on the photovoltaic fault warning according to the M electrical proportion parameters and the M adjacent electrical parameters, and outputting the real-time fault component information, the method includes: extracting the second real-time electrical parameter and the second deviation scale parameter from the photovoltaic fault warning; Calculate M real-time proportional parameters of the M adjacent electrical parameters and the second real-time electrical parameter; Calculating the mean deviation of the M real-time proportional parameters and the M electrical proportional parameters to obtain a third deviation scale; Predefined proportional bias weights and forecast bias weights; The third deviation scale and the second deviation scale are weightedly solved by using the proportional deviation weight and the prediction deviation weight, and the verification deviation scale is output; If the verification deviation scale satisfies a preset verification deviation threshold, the second deviation scale parameter, the second component position and M adjacent components are output as the real-time fault component information.

7. The BIPV management method based on photovoltaic modules according to claim 6, characterized in that: After locating M edge fault monitoring nodes according to the M fault monitoring components at the plurality of edge fault monitoring nodes, operating the M edge fault monitoring nodes with the fault monitoring window as a constraint to perform fault dynamic cross-validation, and outputting real-time photovoltaic component faults, the method includes: Performing monitoring window matching according to the second deviation scale parameter in the real-time fault component information to obtain the fault monitoring window; Using the M adjacent components in the real-time fault component information as the M fault monitoring components; Locating M edge fault monitoring nodes at the plurality of edge fault monitoring nodes according to the M fault monitoring components; The M edge fault monitoring nodes are operated with the fault monitoring window as a constraint to perform fault dynamic cross-validation, and the real-time photovoltaic component fault is output.

8. BIPV management system based on photovoltaic modules, characterized in that: The system is used to implement the BIPV management method based on photovoltaic components according to any one of claims 1 to 7, and the system comprises: An edge fault monitoring node configuration module, used to configure multiple edge fault monitoring nodes for multiple BIPV components of a target building, wherein the multiple edge fault monitoring nodes have multiple component location identifiers; A communication link construction module, used to construct a communication link between the plurality of edge fault monitoring nodes and the BIPV monitoring cloud using the plurality of component location identifiers as constraints; A fault warning verification module is used for the BIPV monitoring cloud to identify adjacent components according to the photovoltaic fault warning after receiving the photovoltaic fault warning, and to perform fault warning verification according to the identification result, and output real-time fault component information; A fault monitoring window generating module, used to generate a fault monitoring window and M fault monitoring components according to the real-time fault component information; The fault dynamic cross-validation module is used to locate M edge fault monitoring nodes according to the M fault monitoring components at the multiple edge fault monitoring nodes, run the M edge fault monitoring nodes for fault dynamic cross-validation with the fault monitoring window as a constraint, and output real-time photovoltaic component faults.

Images