Photovoltaic array multi-dimensional data merging acquisition and state evaluation edge intelligent terminal

Abstract

The invention provides a photovoltaic array multi-dimensional data merging collection and state evaluation edge intelligent terminal. The photovoltaic array multi-dimensional data merging collection and state evaluation edge intelligent terminal comprises a voltage / current collection unit, a solar irradiation unit, a wind speed collection unit, an environment temperature collection unit, a data merging unit, a state evaluation unit and a data transmission unit. The voltage / current acquisition unit is connected with a direct current confluence part of the photovoltaic array and is used for acquiring voltage and current of the direct current confluence part of the photovoltaic array; the voltage / current acquisition unit, the solar irradiation unit, the wind speed acquisition unit and the environment temperature acquisition unit are connected with the data merging unit, and are used for merging photovoltaic array high-dimensional data streams formed by acquired voltage and current information, current solar irradiation intensity information, current wind speed intensity information and environment temperature information; and two paths of parallel transmission are realized.

Description

Technical Field

[0001] The present invention belongs to the technical fields of photovoltaic systems, intelligent power equipment, etc., and specifically relates to an edge intelligent terminal for merging and collecting multi-dimensional data and evaluating the status of a photovoltaic array. Background Art

[0002] Traditional photovoltaic systems include a group of photovoltaic panels, an inverter, and additional equipment. Photovoltaic panels convert solar radiation into direct current, and then the inverter converts the direct current into alternating current for use by equipment or the power grid. However, there are some problems with this type of photovoltaic system. First, photovoltaic efficiency is affected by many factors, such as light intensity, temperature, panel direction, and angle. Second, when the system scale increases or the environment is complex and non-standardized, data collection, processing, and system optimization become extremely complex. Due to the complexity and large-scale application of photovoltaic arrays, how to effectively collect and process various multi-dimensional data, and how to provide in-depth and detailed status assessment, are key issues in the current photovoltaic field.

[0003] The current existing technology mainly processes data through central cluster nodes, but this method cannot process and feedback in real time when processing large and complex data, and may affect the accuracy of the final evaluation due to time delays and data loss during data transmission. In addition, with the continuous expansion of the scale of photovoltaic arrays and the increase in data dimensions, traditional data collection and processing methods can no longer meet the needs. Summary of the invention

[0004] In view of the defects and shortcomings of the prior art, the present invention proposes an edge intelligent terminal for merging and collecting multi-dimensional data and evaluating the state of a photovoltaic array. This solution can comprehensively collect and process the multi-dimensional data of the photovoltaic array, perform state evaluation in real time, and overcome many limitations of traditional methods. This is also an important improvement to the photovoltaic array technology, which can effectively promote further technological development in the photovoltaic field. Its main structure includes a photovoltaic array 1, a voltage / current acquisition unit 2, a solar irradiation unit 3, a wind speed acquisition unit 4, an ambient temperature acquisition unit 5, a data merging unit 6, a state evaluation unit 7 and a data transmission unit 8, wherein the voltage / current acquisition unit 2 is connected to the DC bus part of the photovoltaic array, the voltage and current acquisition unit 2, the solar irradiation unit 3, the wind speed acquisition unit 4 and the ambient temperature acquisition unit 5 are connected to the data merging unit 6, the data merging unit is connected to the state evaluation unit 7, and the state evaluation unit 7 is connected to the data transmission unit 8. Correspondingly, a photovoltaic multi-dimensional data merging collection and status evaluation process based on edge intelligence is published. First, the multi-dimensional data streams of the photovoltaic array are merged and collected through a data merging unit and transmitted in two parallel paths. One path is compressed by downsampling to generate a detection message, and the other path is embedded in the graph to form a feature vector; the generated feature vector enters the status evaluation unit to complete abnormal timing diagnosis, fault classification and positioning to generate a status message; the detection message generated by the merging collection unit and the status message generated by the status evaluation unit are merged and sent through the data transmission unit.

[0005] The technical solution specifically adopted by the present invention to solve the technical problem is: A photovoltaic array multi-dimensional data merging and acquisition and state evaluation edge intelligent terminal comprises: a voltage / current acquisition unit, a solar irradiation unit, a wind speed acquisition unit, an ambient temperature acquisition unit, a data merging unit, a state evaluation unit and a data transmission unit; the voltage / current acquisition unit is connected to the DC bus part of the photovoltaic array, and is used to collect the voltage and current of the DC bus part of the photovoltaic array; the voltage / current acquisition unit, the solar irradiation unit, the wind speed acquisition unit, and the ambient temperature acquisition unit are connected to the data merging unit, and are used to merge the photovoltaic array high-dimensional data stream formed by the collected voltage and current information, current solar irradiation intensity information, current wind speed intensity information and ambient temperature information, and are divided into two parallel transmissions: one is to generate a detection message through downsampling compression, and the other is to form a feature vector through graph embedding; the data merging unit is connected to the state evaluation unit, and is used to enter the generated feature vector into the state evaluation unit to complete abnormal timing diagnosis, so as to classify and locate the fault and generate a state message; the state evaluation unit is connected to the data transmission unit, and is used to merge the detection message generated by the acquisition unit and the state message generated by the state evaluation unit and send them through the data transmission unit.

[0006] Furthermore, in the first transmission, the data merging unit downsamples the multi-dimensional data stream, and the downsampled data is further compressed by a compression algorithm to generate a detection message, which contains detection information of anomalies, errors or faults in the photovoltaic array; in the second transmission, the data merging unit converts the multi-dimensional data stream into a graph embedding to form a feature vector, and uses a graph embedding algorithm to convert the multi-dimensional data into a high-dimensional feature vector to capture key features and patterns in the data.

[0007] Furthermore, in the state evaluation unit, the characteristic vector is first processed by abnormal timing diagnosis, and the fault classification and location are performed according to the results of the abnormal timing diagnosis, the specific fault type occurring in the photovoltaic array is identified, and the location of the fault is located, and finally a corresponding state message is generated according to the results of the diagnosis and location.

[0008] And, a photovoltaic array multi-dimensional data merging collection and status assessment method: The multi-dimensional data streams of the photovoltaic array are collected and transmitted in two parallel channels. One channel generates detection messages through downsampling compression, and the other channel forms feature vectors through graph embedding. Performing abnormal timing diagnosis on the generated feature vector to classify and locate the fault and generate a status message; The detection message and the status message are then combined and sent through a data transmission unit.

[0009] Furthermore, in the first transmission, the multi-dimensional data stream is downsampled, and the downsampled data is further compressed by a compression algorithm to generate a detection message, which contains detection information of anomalies, errors or faults in the photovoltaic array; in the second transmission, the multi-dimensional data stream is converted into a graph embedding to form a feature vector, and the graph embedding algorithm is used to convert the multi-dimensional data into a high-dimensional feature vector to capture key features and patterns in the data.

[0010] Furthermore, the characteristic vector is first processed by abnormal timing diagnosis, and according to the result of abnormal timing diagnosis, fault classification and location are performed to identify the specific fault type occurring in the photovoltaic array and locate the location of the fault, and finally a corresponding status message is generated according to the results of diagnosis and location.

[0011] Compared with the existing technology, the present invention and its preferred solution can fully collect and process the multi-dimensional data of photovoltaic arrays, conduct status assessment in real time, and overcome many limitations of traditional methods. This is also an important improvement in photovoltaic array technology, which can effectively promote further technological development in the photovoltaic field. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] The present invention is further described in detail below with reference to the accompanying drawings and specific embodiments: Figure 1 This is a flow chart of a photovoltaic array multi-dimensional data merging and collection and status assessment method according to an embodiment of the present invention; Figure 2 Schematic diagram of an edge intelligent terminal device for merging and collecting multi-dimensional data and evaluating status of a photovoltaic array according to an embodiment of the present invention; Figure 3 This is a schematic diagram of signal reception of a wind speed collection unit according to an embodiment of the present invention; Figure 4 This is a schematic diagram of receiving a temperature acquisition unit according to an embodiment of the present invention; Figure 5 This is a schematic diagram of receiving a solar radiation collection unit according to an embodiment of the present invention; Figure 6 This is a schematic diagram of data collection by a current and voltage acquisition unit according to an embodiment of the present invention; Figure 7 This is a structural diagram of a photovoltaic data merging and evaluation unit according to an embodiment of the present invention. DETAILED DESCRIPTION

[0013] In order to make the features and advantages of the present invention more clearly understood, the following embodiments are specifically described in detail as follows: It should be noted that the following detailed descriptions are illustrative and are intended to provide further explanation of the present application. Unless otherwise specified, all technical and scientific terms used in this specification have the same meanings as those commonly understood by those skilled in the art to which the present application belongs.

[0014] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit the exemplary embodiments according to the present application. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprise" and / or "include" are used in this specification, it indicates the presence of features, steps, operations, devices, components and / or combinations thereof.

[0015] The embodiment of the present invention provides a design of an edge intelligent terminal for merging and collecting multi-dimensional data of photovoltaic arrays and evaluating status. Figure 2As shown, it mainly includes a photovoltaic array 1, a voltage / current acquisition unit 2, a solar radiation unit 3, a wind speed acquisition unit 4, an ambient temperature acquisition unit 5, a data merging unit 6, a state evaluation unit 7 and a data transmission unit 8. Among them, the voltage / current acquisition unit 2 is connected to the DC bus part of the photovoltaic array, and is used to collect the voltage and current of the DC bus part of the photovoltaic array; the voltage and current acquisition unit 2, the solar radiation unit 3, the wind speed acquisition unit 4 and the ambient temperature acquisition unit 5 are connected to the data merging unit 6, which is used to merge and collect the high-dimensional data stream of the photovoltaic array formed by the voltage and current collected by the DC bus part of the photovoltaic array, the current solar radiation intensity information, the current wind speed intensity information and the ambient temperature information, and perform two-way parallel transmission, and one way generates a detection message through downsampling compression, and the other way forms a feature vector through graph embedding; the data merging unit 6 is connected to the state evaluation unit 7, and is used to enter the generated feature vector into the state evaluation unit to complete abnormal timing diagnosis, fault classification and positioning to generate a state message; the state evaluation unit 7 is connected to the data transmission unit 8, and is used to merge the detection message generated by the acquisition unit and the state message generated by the state evaluation unit and send them through the data transmission unit.

[0016] When working, the multi-dimensional data stream of the photovoltaic array is first merged and collected by the data merging unit and transmitted in two parallel paths. One path is compressed by downsampling to generate a detection message, and the other path is embedded in the graph to form a feature vector. Specifically, the various dimensional data of the photovoltaic array, including the voltage / current information of the photovoltaic bus, solar irradiation intensity, ambient wind speed and temperature information, will be collected and transmitted to a data merging unit, where the solar irradiation information, wind speed and temperature information are as follows: Figure 3 , Figure 4 , Figure 5 As shown, the current and voltage information is as follows Figure 6 As shown. The data merging unit integrates and merges the collected data. In the first transmission, the data merging unit downsamples the multi-dimensional data stream, and then the downsampled data is further compressed by the compression algorithm to generate a smaller detection message, which contains the detection information of abnormalities, errors or faults in the photovoltaic array. In the second transmission, the data merging unit converts the multi-dimensional data stream into a graph embedding to form a feature vector. This process uses a graph embedding algorithm to convert multi-dimensional data into a high-dimensional feature vector, capture the key features and patterns in the data, and generate a feature vector.

[0017] As a preferred solution of this embodiment, a data merging unit is connected to a state evaluation unit to input the generated feature vector into the state evaluation unit to complete abnormal timing diagnosis, fault classification and positioning to generate a state message. Specifically, in the state evaluation unit, the feature vector is first processed by abnormal timing diagnosis. According to the results of abnormal timing diagnosis, the state evaluation unit classifies and locates the fault, identifies the specific fault type in the photovoltaic array, and locates the location where the fault occurs. Finally, in the state evaluation unit, a corresponding state message is generated according to the results of diagnosis and positioning. The preferred structure of the data merging unit and the state evaluation unit is as follows: Figure 7 As shown: As a preferred design, the data merging unit may integrate a multi-channel photovoltaic data collection unit to perform at least data enhancement and data segmentation processing on the downsampled state detection message and various types of data directly collected.

[0018] The state evaluation unit preferably normalizes the time features and spatial features respectively, passes them through a neural network with a multi-channel attention mechanism, and after fusion, predicts the importance of each channel through gate control processing, performs feature allocation and state output, and obtains the judgment result.

[0019] As a preferred solution of this embodiment, the state evaluation unit is connected to the data transmission unit to merge the detection message generated by the acquisition unit and the state message generated by the state evaluation unit and send them together through the data transmission unit. Specifically, the data transmission unit merges the detection message and the state message, and the merged data is transmitted or stored in the form of network transmission, message queue, database, etc.

[0020] Compared with the above edge intelligent terminal design, the embodiment of the present invention also provides a process of photovoltaic array multi-dimensional data merging collection and status evaluation method as follows: Figure 1 As shown, the following steps are included: S01 first merges and collects the multi-dimensional data streams of the photovoltaic array through the data merging unit and transmits them in two parallel channels. One channel generates a detection message through downsampling compression, and the other channel forms a feature vector through graph embedding. Specifically, the various dimensional data of the photovoltaic array, including the voltage / current information of the photovoltaic confluence part, solar radiation intensity, ambient wind speed and temperature information, collect information such as Figure 3 , Figure 4 , Figure 5 , Figure 6As shown, the collected data is transmitted to a data merging unit. The data merging unit integrates and merges the collected data. In the first transmission, the data merging unit downsamples the multi-dimensional data stream, and then the downsampled data is further compressed by the compression algorithm to generate a smaller detection message, which contains the detection information of abnormalities, errors or faults in the photovoltaic array. In the second transmission, the data merging unit converts the multi-dimensional data stream into a graph embedding to form a feature vector. This process uses a graph embedding algorithm to convert multi-dimensional data into a high-dimensional feature vector, capture the key features and patterns in the data, and generate a feature vector.

[0021] S02 is connected to the state evaluation unit through the data merging unit, which is used to enter the generated feature vector into the state evaluation unit to complete abnormal timing diagnosis, fault classification and positioning to generate a state message. Specifically: in the state evaluation unit, the feature vector is first processed by abnormal timing diagnosis. According to the results of abnormal timing diagnosis, the state evaluation unit will classify and locate the fault, identify the specific fault type in the photovoltaic array, and locate the location where the fault occurs. Finally, in the state evaluation unit, the corresponding state message is generated according to the results of diagnosis and positioning. The structure of the data merging and evaluation unit is as follows: Figure 7 As shown; S03 is connected to the data transmission unit through the state evaluation unit, and is used to merge the detection message generated by the acquisition unit and the state message generated by the state evaluation unit and send them through the data transmission unit. Specifically, the data transmission unit merges the detection message and the state message, and the merged data is transmitted or stored through network transmission, message queue, database, etc.

[0022] The above method can be implemented through the edge intelligent terminal provided by the present invention, and can also be implemented through other similar or equivalent designs.

[0023] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the present invention should be understood by people with ordinary skills in the field to which the present invention belongs. The "first", "second" and similar words used in the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. "Include" or "comprise" and similar words mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0024] The above is only a preferred embodiment of the present invention, and does not limit the present invention in other forms. Any technician familiar with the profession may use the above disclosed technical content to change or modify it into an equivalent embodiment with equivalent changes. However, any simple modification, equivalent change and modification made to the above embodiment according to the technical essence of the present invention without departing from the technical solution of the present invention still belongs to the protection scope of the technical solution of the present invention.

[0025] The present invention is not limited to the above-mentioned optimal implementation mode. Anyone can derive other forms of a photovoltaic array multi-dimensional data merging collection and status assessment edge intelligent terminal under the inspiration of the present invention. All equal changes and modifications made within the scope of the invention application of the present invention should be covered by the scope of the present invention.

Claims

1. A photovoltaic array multi-dimensional data merging and state assessment edge intelligent terminal, characterized in that: include: A voltage / current acquisition unit, a solar radiation unit, a wind speed acquisition unit, an ambient temperature acquisition unit, a data merging unit, a state evaluation unit and a data transmission unit; the voltage / current acquisition unit is connected to the DC bus part of the photovoltaic array and is used to collect the voltage and current of the DC bus part of the photovoltaic array; the voltage / current acquisition unit, the solar radiation unit, the wind speed acquisition unit and the ambient temperature acquisition unit are connected to the data merging unit and are used to merge the photovoltaic array high-dimensional data stream formed by the collected voltage and current information, the current solar radiation intensity information, the current wind speed intensity information and the ambient temperature information, and are divided into two parallel transmissions: one is to generate a detection message through downsampling compression, and the other is to form a feature vector through graph embedding; the data merging unit is connected to the state evaluation unit and is used to enter the generated feature vector into the state evaluation unit to complete abnormal timing diagnosis, so as to classify and locate the fault and generate a state message; the state evaluation unit is connected to the data transmission unit and is used to merge the detection message generated by the acquisition unit and the state message generated by the state evaluation unit and send them through the data transmission unit.

2. According to claim 1, the edge intelligent terminal based on photovoltaic array multi-dimensional data merging collection and status assessment is characterized by: In the first transmission, the data merging unit downsamples the multi-dimensional data stream, and the downsampled data is further compressed by a compression algorithm to generate a detection message, which contains detection information of anomalies, errors or faults in the photovoltaic array; in the second transmission, the data merging unit converts the multi-dimensional data stream into a graph embedding to form a feature vector, and uses a graph embedding algorithm to convert the multi-dimensional data into a high-dimensional feature vector to capture key features and patterns in the data.

3. According to claim 1, a photovoltaic array multi-dimensional data merging collection and status assessment edge intelligent terminal is characterized by: In the state evaluation unit, the feature vector is first processed by abnormal timing diagnosis, and the fault classification and location are performed according to the results of the abnormal timing diagnosis, the specific fault type occurring in the photovoltaic array is identified, and the location of the fault is located, and finally the corresponding state message is generated according to the results of the diagnosis and location.

4. A photovoltaic array multi-dimensional data merging collection and status assessment method, characterized by: The multi-dimensional data streams of the photovoltaic array are combined and collected and transmitted in two parallel channels. One channel generates a detection message through downsampling compression, and the other channel forms a feature vector through graph embedding. Performing abnormal timing diagnosis on the generated feature vector to classify and locate the fault and generate a status message; The detection message and the status message are then combined and sent through a data transmission unit.

5. The photovoltaic array multi-dimensional data merging and state assessment edge intelligent terminal according to claim 4 is characterized by: In the first transmission, the multi-dimensional data stream is downsampled, and the downsampled data is further compressed by a compression algorithm to generate a detection message, which contains detection information of anomalies, errors or faults in the photovoltaic array; in the second transmission, the multi-dimensional data stream is converted into a graph embedding to form a feature vector, and the graph embedding algorithm is used to convert the multi-dimensional data into a high-dimensional feature vector to capture the key features and patterns in the data.

6. The photovoltaic array multi-dimensional data merging and state assessment edge intelligent terminal according to claim 4, characterized in that: The characteristic vector is first processed by abnormal timing diagnosis, and the fault classification and location are performed according to the results of the abnormal timing diagnosis, the specific fault type occurring in the photovoltaic array is identified, and the location of the fault is located, and finally the corresponding status message is generated according to the results of the diagnosis and location.

Images