Thermal power plant photovoltaic array dynamic light following system based on multi-dimensional modeling and intelligent control

Abstract

The invention relates to the technical field of photovoltaic power generation, and particularly provides a thermal power plant photovoltaic array dynamic light following system based on multi-dimensional modeling and intelligent control. The system comprises a multi-dimensional dynamic modeling module, a regional adaptive light following control module, a hot spot intelligent prediction and protection module and a digital twinning and intelligent operation and maintenance module. The multi-dimensional dynamic modeling module is fused with laser radar, oblique photography and remote sensing images to construct a three-dimensional model of the plant area of the thermal power plant; a dynamic shielding source identification mechanism is introduced, and a shielding model is dynamically updated in combination with factory operation data; based on a sun trajectory algorithm, generating an annual dynamic shadow thermodynamic diagram, and guiding the initial layout of the photovoltaic module; the grid irradiation analysis is adopted to divide illumination level areas, a factory area is divided into a plurality of illumination level areas, the areas with the annual sunshine duration larger than 1200 hours are preferentially selected for plate distribution, and efficient, safe and intelligent operation of a photovoltaic system is achieved through the system.

Description

Dynamic tracking system for photovoltaic arrays in thermal power plants based on multidimensional modeling and intelligent control Technical Field

[0001] This invention relates to the field of photovoltaic power generation technology, and in particular to a dynamic light tracking system for photovoltaic arrays in thermal power plants based on multi-dimensional modeling and intelligent control. Background Technology

[0002] As thermal power plants accelerate their transformation towards green and low-carbon practices, utilizing idle space within the plant area to construct photovoltaic power stations has become an important approach. However, the presence of numerous tall and large structures (such as chimneys, cooling towers, and transmission towers) in the thermal power plant environment causes severe shading of photovoltaic modules, leading to a significant decrease in power generation efficiency and even triggering hot spot effects, thus impacting system safety.

[0003] In existing technologies, some studies use software such as PVsyst for shadow analysis or mitigate the effects of shading through component-level optimizers, but the following shortcomings still exist: shading modeling is mostly static and does not consider dynamic operating factors (such as chimney emission cycles); tracking systems are mostly uniformly controlled and do not consider regionally differentiated lighting conditions; hot spot protection is mostly a passive response and lacks prediction and active intervention; and there is a lack of system integration and intelligent operation and maintenance capabilities, making it difficult to achieve long-term optimized operation. Summary of the Invention

[0004] In view of this, the present invention provides a dynamic light tracking system for photovoltaic arrays in thermal power plants based on multi-dimensional modeling and intelligent control, so as to achieve efficient, safe and intelligent operation of photovoltaic systems.

[0005] In a first aspect, the present invention provides a dynamic solar tracking system for photovoltaic arrays in thermal power plants based on multidimensional modeling and intelligent control. The system includes: a multidimensional dynamic modeling module, a regional adaptive solar tracking control module, a hot spot intelligent prediction and protection module, and a digital twin and intelligent operation and maintenance module. The multidimensional dynamic modeling module integrates lidar, oblique photography, and remote sensing images to construct a three-dimensional model of the thermal power plant area; it introduces a dynamic shading source identification mechanism and dynamically updates the shading model based on plant operation data; it generates a dynamic annual shadow heat map based on a solar trajectory algorithm to guide the initial layout of photovoltaic modules; and it uses gridded irradiance analysis to divide the irradiance level areas, dividing the plant area into multiple irradiance level areas, and prioritizing the placement of modules in areas with an annual sunshine duration greater than 1200 hours.

[0006] Optionally, the 3D model of the thermal power plant area acquires point cloud data through lidar, captures texture information through oblique photography, and provides geographical reference through remote sensing imagery.

[0007] Optionally, the regional adaptive tracking control module divides the photovoltaic array into multiple regions according to shading characteristics, with each group configured with an independent dual-axis tracker, integrating a photosensitive sensor, a solar trajectory prediction algorithm, and an edge computing controller to achieve a regionally differentiated tracking strategy; a multi-objective optimization algorithm is introduced to dynamically adjust the regionally differentiated tracking strategy, comprehensively considering factors such as light intensity, component temperature, wind speed, and grid load, to dynamically adjust the tracking strategy.

[0008] Optionally, the regional differentiated tracking strategy includes: physical tracking is used in unobstructed areas, and mechanical tracking is stopped in obstructed areas during the shadow period, switching to virtual tracking mode, and power optimization is achieved through string reconstruction; in virtual tracking mode, based on the power electronic switch matrix, the obstructed components are isolated from the string, and the remaining components are recombined into the optimal string.

[0009] Optionally, the photosensitive sensor is used to sense light intensity in real time, the solar trajectory prediction algorithm is used to plan the light-tracking path in advance, and the edge computing controller is used to achieve local rapid decision-making.

[0010] Optionally, the hot spot intelligent prediction and protection module integrates an intelligent bypass module in each combiner box to monitor the component voltage, current and temperature in real time, construct a hot spot prediction model based on the Long Short-Term Memory (LSTM) network, and combine infrared image recognition technology to realize automatic hot spot identification and location. When a hot spot risk is detected, the current component is automatically bypassed and the fault information is reported.

[0011] Optionally, in the hot spot intelligent prediction and protection module, the input parameters of the hot spot prediction model include historical shading data, component operating temperature, current fluctuations, and meteorological data, and the output is the trend of hot spot occurrence in the next 2 hours.

[0012] Optionally, the digital twin and intelligent operation and maintenance module constructs a photovoltaic system digital twin platform to realize functions such as remote monitoring, fault prediction, power generation prediction, and operation and maintenance scheduling; it introduces edge computing and 5G communication to support drone inspection and AI image recognition, so as to provide an operation and maintenance decision support system.

[0013] Optionally, the photovoltaic system digital twin platform in the digital twin and intelligent operation and maintenance module collects real-time operation data and meteorological data of the photovoltaic system and integrates them with the three-dimensional model to achieve real-time mapping between the physical system and the virtual system.

[0014] Optionally, the multi-objective optimization algorithm in the regional adaptive light tracking control module is the NSGA-II algorithm, which comprehensively considers factors such as light intensity, component temperature, wind speed, and grid load.

[0015] The technical solution provided by this invention includes a multi-dimensional dynamic modeling module, a regional adaptive light-tracking control module, a hot spot intelligent prediction and protection module, and a digital twin and intelligent operation and maintenance module. The multi-dimensional dynamic modeling module integrates lidar, oblique photography, and remote sensing images to construct a three-dimensional model of the thermal power plant area. A dynamic shading source identification mechanism is introduced, and the shading model is dynamically updated in combination with the plant's operating data. Based on the solar trajectory algorithm, a dynamic annual shadow heat map is generated to guide the initial layout of photovoltaic modules. A gridded irradiance analysis is used to divide the irradiance level areas, dividing the plant area into multiple irradiance level areas, and prioritizing the area with an annual sunshine duration of more than 1200 hours for panel placement. This system achieves efficient, safe, and intelligent operation of the photovoltaic system. Attached Figure Description

[0016] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1 is a schematic diagram of a dynamic light-tracking system for photovoltaic arrays in thermal power plants based on multidimensional modeling and intelligent control, provided in an embodiment of the present invention; Figure 2 is a schematic diagram of a multidimensional dynamic modeling module provided in an embodiment of the present invention; Figure 3 is a schematic diagram of a regional adaptive light-tracking control module provided in an embodiment of the present invention; Figure 4 is a circuit diagram of a hot spot intelligent prediction and protection module provided in an embodiment of the present invention; Figure 5 is an interface diagram of a digital twin platform provided in an embodiment of the present invention. Detailed Implementation

[0018] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0019] It should be understood that the described embodiments are merely some, not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without inventive effort are within the scope of protection of the present invention.

[0020] The terminology used in the embodiments of this invention is for the purpose of describing particular embodiments only and is not intended to limit the invention. The singular forms “a,” “the,” and “the” used in the embodiments of this invention are also intended to include the plural forms unless the context clearly indicates otherwise.

[0021] It should be understood that the term "and / or" used in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this article generally indicates that the preceding and following related objects have an "or" relationship.

[0022] Depending on the context, the word "if" as used here can be interpreted as "when," "when," "in response to determination," or "in response to detection." Similarly, depending on the context, the phrase "if determination" or "if detection (of the stated condition or event)" can be interpreted as "when determination," "in response to determination," "when detection (of the stated condition or event)," or "in response to detection (of the stated condition or event)."

[0023] Figure 1 is a schematic diagram of a dynamic light-tracking system for photovoltaic arrays in thermal power plants based on multidimensional modeling and intelligent control, provided in an embodiment of the present invention. As shown in Figure 1, the system includes: a multidimensional dynamic modeling module, a regional adaptive light-tracking control module, a hot spot intelligent prediction and protection module, and a digital twin and intelligent operation and maintenance module. In this embodiment of the present invention, as shown in Figure 2, the multidimensional dynamic modeling module integrates lidar, oblique photography, and remote sensing images to construct a three-dimensional model of the thermal power plant area; a dynamic shading source identification mechanism is introduced, and the shading model is dynamically updated in combination with plant operation data (such as chimney emission cycle and cooling tower operation status). For example, when the chimney enters its ash removal cycle (once every 3 months, lasting 24 hours), the model can update the shadow range 12 hours in advance; based on the solar trajectory algorithm (considering geographical latitude, season, and time), a dynamic shadow heat map for the whole year is generated to guide the initial layout of photovoltaic modules. Through the dynamic shadow heat map for the whole year, the shadow distribution of each area of ​​the factory can be clearly understood at different times; gridded irradiance analysis is used to divide the irradiance level areas, dividing the factory area into multiple irradiance level areas, and prioritizing the placement of panels in areas with an annual sunshine duration of more than 1200 hours to improve the power generation efficiency of photovoltaic modules.

[0024] In this embodiment of the invention, the three-dimensional model of the thermal power plant area acquires point cloud data through lidar, captures texture information through oblique photography, and provides geographical reference through remote sensing imagery. The three are fused and processed to make the three-dimensional model more accurately reflect the topography and structure of the plant area.

[0025] In this embodiment of the invention, as shown in Figure 3, the regional adaptive tracking control module divides the photovoltaic array into multiple regions according to shading characteristics (e.g., region A is an unshaded region, region B is a region partially shaded by chimneys in the afternoon, and region C is a shaded region). Each group is equipped with an independent dual-axis tracker, integrating a photosensor, a solar trajectory prediction algorithm, and an edge computing controller to achieve a regionally differentiated tracking strategy. A multi-objective optimization algorithm is introduced to dynamically adjust the regionally differentiated tracking strategy, comprehensively considering factors such as light intensity, module temperature, wind speed, and grid load, and dynamically adjusting the tracking strategy.

[0026] In this embodiment of the invention, the regional differentiated tracking strategy includes: physical tracking is used in unobstructed areas (area A), mechanical tracking is stopped (standby) in obstructed areas (area C) during shadow periods, and partially obstructed areas (area B) are switched to virtual tracking mode, achieving power optimization through string reconstruction; in virtual tracking mode, based on the power electronic switch matrix, the obstructed components are isolated from the string, and the remaining components are recombined into the optimal string, avoiding the drop in overall string power caused by the weakest link effect.

[0027] In this embodiment of the invention, a photosensitive sensor is used to sense light intensity in real time, a solar trajectory prediction algorithm is used to plan the light-tracking path in advance, and an edge computing controller is used to achieve rapid local decision-making.

[0028] In this embodiment of the invention, as shown in Figure 4, the intelligent hot spot prediction and protection module integrates an intelligent bypass module (intelligent bypass switch IGBT / SiC, voltage / current sensor) in each combiner box. This module monitors the component voltage, current, and temperature in real time, constructs a hot spot prediction model (LSTM prediction unit) based on a Long Short-Term Memory (LSTM) network, and combines it with infrared image recognition technology (infrared camera) to achieve automatic hot spot identification and location. The infrared image clearly displays the temperature distribution of the component, facilitating rapid hot spot location. When a hot spot risk is detected, the current component is automatically bypassed, and fault information is reported to the digital twin platform.

[0029] In this embodiment of the invention, when the intelligent bypass module detects a hot spot risk, it can complete the bypass operation of the component within less than 50ms, effectively avoiding overheating damage to the component.

[0030] In this embodiment of the invention, the hot spot intelligent prediction and protection module uses an LSTM-based hot spot prediction model to predict the hot spot occurrence trend and intervene in advance. The input parameters of the hot spot prediction model include historical shading data, component operating temperature, current fluctuations, and meteorological data. The output is the trend of hot spot occurrence in the next 2 hours (accuracy ≥ 90%).

[0031] In this embodiment of the invention, as shown in Figure 5, the digital twin and intelligent operation and maintenance module constructs a digital twin platform for the photovoltaic system, which is used to realize the functions of remote monitoring, fault prediction, power generation prediction, and operation and maintenance scheduling. Edge computing and 5G communication are introduced to realize local rapid response and remote collaborative control. Edge computing reduces data transmission latency, and 5G communication ensures the stability and high speed of data transmission. It supports drone inspection and AI image recognition, which can automatically identify problems such as shading, hot spots, and component damage to provide an operation and maintenance decision support system. Drone inspection improves inspection efficiency, and AI image recognition makes problem detection more accurate.

[0032] In this embodiment of the invention, the operation and maintenance decision support system optimizes cleaning, maintenance, and component replacement strategies based on historical data and the LSTM hot spot prediction model, reducing operation and maintenance workload by 60% and shortening fault handling time by 50%.

[0033] In this embodiment of the invention, the photovoltaic system digital twin platform in the digital twin and intelligent operation and maintenance module collects real-time operating data and meteorological data of the photovoltaic system and integrates them with a three-dimensional model to achieve real-time mapping between the physical system and the virtual system, with a deviation rate of less than 3%. The digital twin platform enables remote monitoring, fault prediction, power generation prediction, and operation and maintenance scheduling. Through remote monitoring, staff can understand the operating status of the photovoltaic system at any time. The fault prediction function, based on historical data and real-time monitoring data, can detect potential faults in advance. Power generation prediction provides a reference for grid dispatch. Operation and maintenance scheduling allows for the rational arrangement of operation and maintenance work.

[0034] In this embodiment of the invention, the multi-objective optimization algorithm in the regional adaptive tracking control module is the NSGA-II algorithm, which comprehensively considers factors such as light intensity, component temperature, wind speed, and grid load, so that the photovoltaic array can maintain high power generation efficiency under various conditions.

[0035] This invention relates to a system applicable to the design and operation optimization of photovoltaic systems in complex environments with high shading, such as thermal power plants. The system integrates 3D modeling, zoned tracking, hot spot prediction, and digital twin technologies. A multi-dimensional dynamic modeling module constructs a high-precision 3D model of the plant area and a dynamic shadow heat map. A regional adaptive tracking control module implements differentiated tracking strategies. A hot spot intelligent prediction and protection module provides early intervention. A digital twin and intelligent operation and maintenance module enables full lifecycle management. This system solves problems such as low power generation efficiency, high hot spot risk, inaccurate tracking control, and insufficient intelligent operation and maintenance in complex shading environments of thermal power plants, thereby improving the high efficiency, safety, and intelligent operation level of photovoltaic systems.

[0036] Compared with the prior art, the present invention has the following beneficial effects: I. More accurate dynamic shading modeling: For the first time, the dynamic operating parameters of thermal power plants are incorporated into the shading model, which solves the problem that traditional static modeling cannot cope with temporary shading. The shadow prediction error is less than 5%, which is 10% higher than PVsyst software, providing a more reliable basis for the layout of photovoltaic modules and the adjustment of the tracking strategy.

[0037] II. More Efficient Light Tracking Control: The combination of regionally differentiated light tracking strategies and virtual light tracking modes enables photovoltaic arrays to maintain high power generation efficiency under various shading conditions. Compared with traditional fixed string modes, power output is increased by 15%-20%, regional light tracking angle accuracy reaches ±0.5°, and dual-mode switching response time is less than 1 second.

[0038] III. More Proactive Hot Spot Protection: The intelligent hot spot prediction and protection module realizes the transformation from passive detection to proactive prediction and early intervention. The hot spot identification accuracy rate is greater than or equal to 98%, the annual reduction of power generation loss caused by hot spots is greater than or equal to 5%, and the component damage rate caused by hot spots is reduced to below 0.1% (the industry average is about 1%).

[0039] IV. Smarter Operation and Maintenance Management: The digital twin and intelligent operation and maintenance module enables full lifecycle management of the photovoltaic system, with a fault prediction accuracy rate of greater than or equal to 85%, significantly improving operation and maintenance efficiency. Compared with traditional manual inspections, it reduces workload by 60% and shortens fault handling time by 50%. At the same time, this module can also coordinate with the decommissioning plan of thermal power units, planning photovoltaic replacement schemes 3 years in advance, and improving asset utilization.

[0040] The technical solution provided by this invention includes a multi-dimensional dynamic modeling module, a regional adaptive light-tracking control module, a hot spot intelligent prediction and protection module, and a digital twin and intelligent operation and maintenance module. The multi-dimensional dynamic modeling module integrates lidar, oblique photography, and remote sensing images to construct a three-dimensional model of the thermal power plant area. A dynamic shading source identification mechanism is introduced, and the shading model is dynamically updated in combination with the plant's operating data. Based on the solar trajectory algorithm, a dynamic annual shadow heat map is generated to guide the initial layout of photovoltaic modules. A gridded irradiance analysis is used to divide the irradiance level areas, dividing the plant area into multiple irradiance level areas, and prioritizing the area with an annual sunshine duration of more than 1200 hours for panel placement. This system achieves efficient, safe, and intelligent operation of the photovoltaic system.

[0041] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A dynamic light-tracking system for photovoltaic arrays in thermal power plants based on multi-dimensional modeling and intelligent control, characterized in that, The system includes: a multi-dimensional dynamic modeling module, a regional adaptive light-tracking control module, a hot spot intelligent prediction and protection module, and a digital twin and intelligent operation and maintenance module. The multi-dimensional dynamic modeling module integrates lidar, oblique photography, and remote sensing images to construct a three-dimensional model of the power plant area; it introduces a dynamic shading source identification mechanism and dynamically updates the shading model based on the plant's operational data; it generates a dynamic annual shadow heat map based on a solar trajectory algorithm to guide the initial layout of photovoltaic modules; and it uses gridded irradiance analysis to divide the plant area into multiple irradiance level zones, prioritizing the placement of modules in areas with an annual sunshine duration greater than 1200 hours.

2. The system according to claim 1, characterized in that, The 3D model of the thermal power plant area uses LiDAR to acquire point cloud data, oblique photography to capture texture information, and remote sensing imagery to provide geographic reference.

3. The system according to claim 1, characterized in that, The regional adaptive tracking control module divides the photovoltaic array into multiple regions according to shading characteristics. Each group is equipped with an independent dual-axis tracker and integrates a photosensitive sensor, a solar trajectory prediction algorithm, and an edge computing controller to realize a regional differentiated tracking strategy. A multi-objective optimization algorithm is introduced to dynamically adjust the regional differentiated tracking strategy, taking into account factors such as light intensity, module temperature, wind speed, and grid load.

4. The system according to claim 3, characterized in that, The regional differentiated tracking strategy includes: physical tracking is used in unobstructed areas, while mechanical tracking is stopped in obstructed areas during shadow periods and switched to virtual tracking mode, achieving power optimization through string reconstruction; in virtual tracking mode, based on the power electronic switch matrix, the obstructed components are isolated from the string, and the remaining components are recombined into the optimal string.

5. The system according to claim 3, characterized in that, The photosensitive sensor is used to sense light intensity in real time, the solar trajectory prediction algorithm is used to plan the light-tracking path in advance, and the edge computing controller is used to realize local rapid decision-making.

6. The system according to claim 3, characterized in that, The hot spot intelligent prediction and protection module integrates an intelligent bypass module in each combiner box, which monitors the component voltage, current and temperature in real time, constructs a hot spot prediction model based on the Long Short-Term Memory (LSTM) network, and combines infrared image recognition technology to realize automatic hot spot identification and location. When a hot spot risk is detected, the current component is automatically bypassed and the fault information is reported.

7. The system according to claim 6, characterized in that, In the hot spot intelligent prediction and protection module, the input parameters of the hot spot prediction model include historical shadow data, component operating temperature, current fluctuation, and meteorological data, and the output is the trend of hot spot occurrence in the next 2 hours.

8. The system according to claim 6, characterized in that, The digital twin and intelligent operation and maintenance module constructs a digital twin platform for the photovoltaic system, which is used to realize the functions of remote monitoring, fault prediction, power generation prediction, and operation and maintenance scheduling; it introduces edge computing and 5G communication to support drone inspection and AI image recognition, so as to provide an operation and maintenance decision support system.

9. The system according to claim 8, characterized in that, The photovoltaic system digital twin platform in the digital twin and intelligent operation and maintenance module collects real-time operation data and meteorological data of the photovoltaic system and integrates them with a three-dimensional model to achieve real-time mapping between the physical system and the virtual system.

10. The system according to claim 8, characterized in that, The multi-objective optimization algorithm in the regional adaptive light tracking control module is the NSGA-II algorithm, which comprehensively considers factors such as light intensity, component temperature, wind speed, and grid load.

Images