Photovoltaic array installation error detection and automatic correction system

Abstract

The invention provides a photovoltaic array installation error detection and automatic correction system, and relates to the field of photovoltaic technology. The photovoltaic array installation error detection and automatic correction system comprises a data acquisition layer, the data acquisition layer is connected with an edge processing layer, the edge processing layer is connected with a central processing layer, the central processing layer is connected with an execution layer, the execution layer is connected with a user interaction layer, and the user interaction layer is connected with a management and maintenance layer. Through dynamic reference generation and self-learning optimization, an optimal angle reference can be intelligently generated according to real-time environment change, an error detection and correction algorithm can be continuously optimized, prediction and advanced adjustment functions are combined, calculation is carried out in advance, a correction instruction is issued, it is ensured that the photovoltaic panel is always located at the optimal power generation position, and the power generation efficiency is improved. And meanwhile, an unattended automation technology is utilized, so that the maintenance cost and the manpower demand of the system are reduced, and the overall operation efficiency and reliability are improved.

Description

Technical Field

[0001] The invention relates to the field of photovoltaic technology, in particular to a photovoltaic array installation error detection and automatic correction system. Background Art

[0002] Photovoltaic arrays are systems composed of multiple photovoltaic modules (also known as solar panels) arranged in a certain way to convert sunlight directly into electrical energy. Each photovoltaic module contains multiple solar cells, which convert the absorbed solar energy into direct current. Depending on the needs of the actual application, photovoltaic arrays can consist of dozens or even thousands of photovoltaic modules, installed on roofs, ground or specially designed brackets. These arrays are connected in series or parallel to achieve the required voltage and current, and ultimately the generated electricity is transmitted to the grid or directly used for power supply. Photovoltaic arrays require error correction during installation, mainly because the ability to accurately align the direction of the sun can maximize the amount of sunlight received by the photovoltaic modules, thereby improving power generation efficiency. The position of the sun changes with time and season, and error correction can ensure that the array captures as much sunlight as possible. The correct installation angle and direction not only contributes to optimal performance, but also reduces additional stress caused by natural factors such as wind and snow, prevents premature damage to the components, and effectively extends the service life of the entire system. Through detailed analysis of the surrounding environment and appropriate error correction, possible obstructions such as trees and buildings can be avoided to reduce the impact of shadows on the photovoltaic array, because when a single cell or component is shaded, the output power of the entire array will drop significantly. Error correction during installation also involves ensuring that the electrical connections are correct and the structure is stable and safe to meet relevant technical and safety specifications, ensuring the long-term stable operation of the system and the safety of personnel.

[0003] In the prior art, the installation error detection and correction of photovoltaic arrays usually adopt the following methods: regular manual inspections, regular manual inspections of photovoltaic arrays, and the use of manual tools (such as angle meters, light meters) to check the angles and lighting conditions of photovoltaic panels. Once an error is found, manual adjustments are made. This method requires a lot of manpower and time, and the detection frequency is low, and the angle of the photovoltaic panel cannot be adjusted in real time. Another common method is to use a fixed reference angle and send correction instructions regularly through a central controller. Although this method of fixed reference angles reduces manual intervention, it cannot adapt to environmental changes, resulting in low power generation efficiency of photovoltaic panels in different environments. Summary of the invention

[0004] In view of the deficiencies in the prior art, the present invention provides a photovoltaic array installation error detection and automatic correction system, which solves the problem that the traditional correction method is insufficiently accurate and affects the power generation efficiency.

[0005] To achieve the above objectives, the present invention is implemented through the following technical solutions: a photovoltaic array installation error detection and automatic correction system, comprising a data acquisition layer, the data acquisition layer is connected to an edge processing layer, the edge processing layer is connected to a central processing layer, the central processing layer is connected to an execution layer, the execution layer is connected to a user interaction layer, and the user interaction layer is connected to a management and maintenance layer;

[0006] The data acquisition layer includes angle sensors, light intensity sensors, meteorological sensors, visual sensors, and drone inspections; the edge processing layer includes preliminary data processing, local error detection, and local adjustment; the central processing layer includes data fusion, environmental modeling, dynamic benchmark generation, self-learning models, and global decision-making; the user interaction layer includes mobile applications and a Web management platform.

[0007] Preferably, the angle sensor is used to collect the real-time inclination angle of the photovoltaic panel, the light intensity sensor is used to collect the real-time intensity of solar radiation, the meteorological sensor is used to collect wind speed, temperature, and humidity environmental parameters, the visual sensor is used to regularly capture images of the photovoltaic panel to assist in error detection, and the drone inspection is used to regularly inspect the photovoltaic array to collect high-resolution images and environmental data.

[0008] Preferably, the preliminary data processing is to remove noise in the data by filtering, calibrate the sensor data to a standard value, and then compress the data to reduce the transmission load, the local error detection is to calculate the error between the real-time angle of each photovoltaic panel and the preset reference angle, and the local adjustment is to use an adaptive control algorithm, adaptive PID or fuzzy control to perform local angle adjustment.

[0009] Preferably, the data fusion is to utilize the fusion algorithm Kalman filtering or data smoothing to merge the data of each node to generate global perception data, the environmental modeling is to establish an environmental model based on meteorological data and historical data to predict future environmental changes, the dynamic benchmark generation is to utilize the environmental model and astronomical algorithm to dynamically generate the optimal installation angle benchmark of the photovoltaic panel, the self-learning model is to utilize the deep learning model CNN or LSTM to continuously optimize the error detection and correction algorithm, and the global decision is to generate a global correction instruction based on the global perception data and the self-learning model.

[0010] Preferably, the execution layer uses a stepper motor to adjust the dual-axis angle of the photovoltaic panel according to the instructions of the central control unit, so as to achieve flexible adjustment of the photovoltaic panel in the horizontal and vertical directions.

[0011] Preferably, the mobile application displays the working status and performance indicators of the photovoltaic array, and the user remotely adjusts the system parameters. The Web management platform provides detailed historical data and analysis reports, and records the system's operation log to facilitate troubleshooting, and supports remote upgrades and maintenance of system software.

[0012] Preferably, the management and maintenance layer performs self-detection regularly, identifies potential faults, automatically repairs common faults or resets the system, and sends a notification to maintenance personnel when automatic repair is not possible.

[0013] The present invention provides a photovoltaic array installation error detection and automatic correction system. It has the following beneficial effects:

[0014] The present invention provides a photovoltaic array installation error detection and automatic correction system. The present invention adopts a distributed node architecture. The sensors and actuators installed on each photovoltaic panel can independently collect data and make local adjustments, thereby realizing high-precision real-time monitoring and rapid response, greatly improving the overall flexibility and robustness of the system. Through the dynamic reference generation technology, the system can intelligently generate the optimal angle reference according to the real-time sunlight, weather conditions and environmental changes, and no longer rely on a fixed installation angle, so that the photovoltaic panel is always in the best power generation position, significantly improving the power generation efficiency. At the same time, the self-learning optimization function enables the system to continuously accumulate operation data, optimize the error detection and correction algorithm, gradually improve the accuracy and speed of correction, and further improve the intelligence level of the system. The prediction and advance adjustment function calculates and issues correction instructions in advance through big data analysis and machine learning technology, and can make adjustments before the environment changes, avoiding the lag effect, and ensuring that the photovoltaic array can operate efficiently under various conditions. In addition, the unattended automation technology eliminates the need for manual inspections, reduces maintenance costs and manpower investment, improves the reliability and operation stability of the system, and makes the management of the photovoltaic array more convenient and efficient. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 It is a schematic diagram of the system framework flow of the present invention. DETAILED DESCRIPTION

[0016] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0017] like Figure 1 As shown, an embodiment of the present invention provides a photovoltaic array installation error detection and automatic correction system, including a data acquisition layer, the data acquisition layer is connected to an edge processing layer, the edge processing layer is connected to a central processing layer, the central processing layer is connected to an execution layer, the execution layer is connected to a user interaction layer, and the user interaction layer is connected to a management and maintenance layer;

[0018] The data collection layer includes angle sensors, light intensity sensors, meteorological sensors, visual sensors, and drone inspections. The edge processing layer includes preliminary data processing, local error detection, and local adjustment. The central processing layer includes data fusion, environmental modeling, dynamic benchmark generation, self-learning models, and global decision-making. The user interaction layer includes mobile applications and Web management platforms.

[0019] Angle sensors are used to collect the real-time inclination of photovoltaic panels, light intensity sensors are used to collect the real-time intensity of solar radiation, meteorological sensors are used to collect wind speed, temperature, and humidity environmental parameters, visual sensors are used to regularly capture images of photovoltaic panels to assist in error detection, and drone inspections are used to regularly inspect photovoltaic arrays to collect high-resolution images and environmental data.

[0020] Angle sensor An angle sensor is installed on each photovoltaic panel to monitor the inclination of the photovoltaic panel in real time. Light intensity sensor A light intensity sensor is installed at the center of each photovoltaic panel or multiple photovoltaic panels to monitor the intensity of solar radiation in real time. Meteorological sensor A meteorological sensor is installed around the photovoltaic array to monitor environmental parameters such as wind speed, temperature, and humidity. Visual sensor A visual sensor is installed at the center of each photovoltaic panel or multiple photovoltaic panels to capture images of the photovoltaic panels. Use drones equipped with high-resolution cameras and environmental sensors. Set up a regular inspection plan, such as once a day or once a week. The drone flies according to the plan, captures images of the photovoltaic array, and collects environmental data. After the drone inspection is completed, the collected data is transmitted to the central control unit via 4G / 5G or Wi-Fi wireless communication.

[0021] The preliminary data processing is to remove the noise in the data by filtering, calibrate the sensor data to the standard value, and then compress the data to reduce the transmission load. The local error detection is to calculate the error between the real-time angle of each photovoltaic panel and the preset reference angle. The local adjustment is to use the adaptive control algorithm adaptive PID or fuzzy control to adjust the local angle.

[0022] Use digital filters, low-pass filters or Kalman filters to remove noise from sensor data, calibrate sensor data according to known standard values, and use data compression algorithms LZ77 or JPEG to reduce the burden of data transmission. Generate local reference values ​​based on the dynamic reference angle issued by the central control unit. The node controller compares the actual angle of the local photovoltaic panel with the reference angle and calculates the error value. Use statistical methods or machine learning models to identify outliers in sensor data to ensure the reliability of error calculation. The node controller uses algorithms such as adaptive PID and fuzzy control to adjust the local angle according to the error value. The node controller feeds the adjusted angle and error data back to the central control unit for further optimization.

[0023] Data fusion is the use of fusion algorithm Kalman filtering or data smoothing to merge the data of each node to generate global perception data. Environmental modeling is the establishment of an environmental model based on meteorological data and historical data to predict future environmental changes. Dynamic benchmark generation is the use of environmental models and astronomical algorithms to dynamically generate the optimal installation angle benchmark for photovoltaic panels. The self-learning model is the use of deep learning models CNN or LSTM to continuously optimize the error detection and correction algorithm. Global decision-making is the generation of global correction instructions based on global perception data and self-learning models.

[0024] The central control unit receives the data uploaded by each node through the wireless communication module. The data fusion algorithm Kalman filter or data smoothing is used to merge the data of each node to generate global perception data. The fused data is stored in the central database for subsequent analysis and modeling. The time series of environmental parameters is generated based on the data collected by the meteorological sensor. Combined with historical data, the time series analysis method ARI MA or LSTM is used to predict future environmental changes. The deep learning model LSTM or GRU is used to train the environmental prediction model. The astronomical algorithm solar trajectory equation is used to predict the specific position of the sun in the future. According to the solar position prediction and environmental model, the optimal installation angle of each photovoltaic panel in the future is calculated. The calculated optimal angle benchmark is sent to each node controller. The central control unit collects the error data and adjustment results uploaded by each node. The deep learning model CNN or LSTM is used to train the error detection and correction algorithm to continuously optimize the performance of the model. The central control unit generates global correction instructions based on the global perception data and self-learning model. Combine the multiple objectives of power generation efficiency, energy consumption and equipment life to optimize the overall performance of the system. The correction instructions are sent to each node controller to guide the angle adjustment of the photovoltaic panel.

[0025] The execution layer uses stepper motors to adjust the dual-axis angles of the photovoltaic panels according to the instructions of the central control unit, thereby achieving flexible adjustment of the photovoltaic panels in the horizontal and vertical directions.

[0026] Each node controller controls the stepper motor through the motor driver to perform angle adjustment. The node controller makes further fine-tuning based on the error between the actual angle after adjustment and the reference angle to ensure that the photovoltaic panel is always in the optimal position.

[0027] The mobile application displays the working status and performance indicators of the photovoltaic array, and the user can adjust the system parameters remotely. The Web management platform provides detailed historical data and analysis reports, records the system operation log, facilitates troubleshooting, and supports remote upgrades and maintenance of system software. The management and maintenance layer performs regular self-tests, identifies potential faults, automatically repairs common faults or resets the system, and sends notifications to maintenance personnel when automatic repairs are not possible.

[0028] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. Photovoltaic array installation error detection and automatic correction system, including a data acquisition layer, characterized by: The data collection layer is connected to the edge processing layer, the edge processing layer is connected to the central processing layer, the central processing layer is connected to the execution layer, the execution layer is connected to the user interaction layer, and the user interaction layer is connected to the management and maintenance layer; The data acquisition layer includes angle sensors, light intensity sensors, meteorological sensors, visual sensors, and drone inspections; the edge processing layer includes preliminary data processing, local error detection, and local adjustment; the central processing layer includes data fusion, environmental modeling, dynamic benchmark generation, self-learning models, and global decision-making; the user interaction layer includes mobile applications and a Web management platform.

2. The photovoltaic array installation error detection and automatic correction system according to claim 1, characterized in that: The angle sensor is used to collect the real-time inclination of the photovoltaic panel, the light intensity sensor is used to collect the real-time intensity of solar radiation, the meteorological sensor is used to collect wind speed, temperature, and humidity environmental parameters, the visual sensor is used to regularly capture images of the photovoltaic panel to assist in error detection, and the drone inspection is used to regularly inspect the photovoltaic array to collect high-resolution images and environmental data.

3. The photovoltaic array installation error detection and automatic correction system according to claim 1, characterized in that: The preliminary data processing is to remove noise in the data by filtering, calibrate the sensor data to a standard value, and then compress the data to reduce the transmission load. The local error detection is to calculate the error between the real-time angle of each photovoltaic panel and the preset reference angle. The local adjustment is to use an adaptive control algorithm, adaptive PID or fuzzy control, to perform local angle adjustment.

4. The photovoltaic array installation error detection and automatic correction system according to claim 1, characterized in that: The data fusion is to use the fusion algorithm Kalman filtering or data smoothing to merge the data of each node to generate global perception data. The environmental modeling is to establish an environmental model based on meteorological data and historical data to predict future environmental changes. The dynamic benchmark generation is to use the environmental model and astronomical algorithm to dynamically generate the optimal installation angle benchmark of the photovoltaic panel. The self-learning model is to use the deep learning model CNN or LSTM to continuously optimize the error detection and correction algorithm. The global decision is to generate a global correction instruction based on the global perception data and the self-learning model.

5. The photovoltaic array installation error detection and automatic correction system according to claim 1, characterized in that: The execution layer uses a stepper motor to adjust the dual-axis angle of the photovoltaic panel according to the instructions of the central control unit, thereby realizing flexible adjustment of the photovoltaic panel in the horizontal and vertical directions.

6. The photovoltaic array installation error detection and automatic correction system according to claim 1, characterized in that: The mobile application displays the working status and performance indicators of the photovoltaic array, and the user remotely adjusts the system parameters. The Web management platform provides detailed historical data and analysis reports, records the system's operation log, facilitates troubleshooting, and supports remote upgrades and maintenance of system software.

7. The photovoltaic array installation error detection and automatic correction system according to claim 1, characterized in that: The management and maintenance layer performs self-detection regularly, identifies potential faults, automatically repairs common faults or resets the system, and sends a notification to maintenance personnel when automatic repair is not possible.

Images