Photovoltaic ventilation integrated curtain wall building design system with fused AI prediction model

Abstract

The application discloses a photovoltaic ventilation integrated curtain wall building design system fusing an AI prediction model, which comprises an AI prediction model module, a photovoltaic management module, a building design circuit management module, a current regulation module, a photovoltaic power supply and a power grid power supply, the AI prediction model module is based on machine learning and deep learning algorithms, and a prediction model of photovoltaic power generation, ventilation efficiency and indoor environmental quality is established, and the photovoltaic management module is used for monitoring the operation state of photovoltaic components in real time, and the key parameters of the photovoltaic components include power generation, efficiency, temperature and irradiance; the application classifies power consumption circuits, so that, after power failure, the photovoltaic power generation system can supply power according to the importance level of electrical appliances and the power consumption degree, the AI prediction module analyzes historical data and real-time environmental factors, the AI model can accurately predict photovoltaic power generation and building ventilation demand, so as to optimize system performance, and the photovoltaic management module is responsible for real-time monitoring of the working state and power generation efficiency of photovoltaic panels.

Description

Technical Field

[0001] This invention relates to the field of curtain wall building design technology, and in particular to a photovoltaic ventilation integrated curtain wall building design system that integrates AI prediction models. Background Technology

[0002] With the increasing awareness of energy utilization and environmental protection, photovoltaic integrated technology has emerged and developed rapidly. Photovoltaic integration perfectly combines solar photovoltaic power generation with buildings, which not only meets the functional needs of buildings, but also makes full use of solar energy resources for power generation, reducing dependence on traditional energy. Solar energy is an abundant, clean, and renewable energy source, and buildings, with their large external surface area, are the main carriers for solar energy utilization. Combining photovoltaic power generation technology with building envelopes is an effective way to achieve energy conservation and emission reduction in the building sector. With the continuous promotion of photovoltaic building integration applications, photovoltaic curtain wall technology has developed rapidly and is gradually becoming one of the key transformation directions for curtain walls.

[0003] In Chinese patent CN119743077A, traditional photovoltaic systems operate in isolation and cannot regulate their interaction with the power grid. The system cannot efficiently schedule energy usage within a reasonable timeframe, which leads to significant energy waste. Therefore, this invention proposes a photovoltaic ventilation integrated curtain wall building design system that incorporates an AI prediction model to address the problems existing in the prior art. Summary of the Invention

[0004] To address the aforementioned issues, the present invention aims to propose a photovoltaic-ventilation integrated curtain wall building design system that integrates an AI prediction model. This system categorizes power lines, allowing the photovoltaic power generation system to differentiate power supply based on the importance and power consumption of electrical appliances during power outages. The AI ​​prediction module analyzes historical data and real-time environmental factors, enabling the AI ​​model to accurately predict photovoltaic power generation and building ventilation needs, thereby optimizing system performance. The photovoltaic management module is responsible for real-time monitoring of the photovoltaic panel's operating status and power generation efficiency.

[0005] To achieve the objectives of this invention, the invention is implemented through the following technical solution: a photovoltaic ventilation integrated curtain wall building design system that integrates AI prediction models, including an AI prediction model module, a photovoltaic management module, a building design circuit management module, a current regulation module, a photovoltaic power supply, and a grid power supply;

[0006] The AI ​​prediction model module, based on machine learning and deep learning algorithms, establishes predictive models for photovoltaic power generation, ventilation efficiency, and indoor environmental quality.

[0007] The photovoltaic management module monitors the operating status of photovoltaic modules in real time, including key parameters such as power generation, efficiency, temperature, and irradiance.

[0008] The building design circuit management module divides the circuit into low-power charging circuits, high-power electrical appliance circuits, low-power electrical circuits, and necessary electrical appliance circuits.

[0009] The current regulation module monitors the current values ​​of the photovoltaic system and ventilation equipment in real time, including the output current of the photovoltaic modules and the input current of the load.

[0010] The building energy consumption analysis module assesses the building's energy consumption needs and uses AI models to predict energy consumption performance under different design schemes.

[0011] Photovoltaic power supply, which is a photovoltaic circuit board, uses solar energy to convert it into electrical energy;

[0012] Grid power, through its collaboration with photovoltaic systems, helps achieve dynamic energy balance.

[0013] A further improvement is that the AI ​​prediction model module inputs the environmental data collected in real time into the trained AI prediction model to make real-time predictions. The prediction results of the model are then applied to system control to predict the photovoltaic power generation and building ventilation demand in the future for current regulation and load management.

[0014] A further improvement is made in that: the photovoltaic management module acquires current regulation and load information. When the current regulation information is a power grid outage signal, the server sends a verification request to the photovoltaic management module and receives the verification information transmitted from the photovoltaic management module. When the verification information indicates that power generation is not possible, the server sends a medium-level danger signal to the building design line management module. When the verification information indicates that power generation is possible, the server sends a low-level danger signal to the building design line management module.

[0015] A further improvement is that the building design line management module receives signals transmitted from the AI ​​prediction model module and the photovoltaic management module to control the opening and closing of the lines.

[0016] A further improvement is that the current regulation module is used to connect the photovoltaic power supply and the grid power supply; when the internal battery power supply is low on power, the current regulation module connects to the grid power supply to charge the battery power supply.

[0017] Further improvements are made in that the building energy consumption analysis module integrates multi-dimensional data such as building orientation, thermal performance of the building envelope, indoor occupancy density, and equipment operation patterns to construct an energy consumption simulation model. During the design phase, the design parameters of the photovoltaic curtain wall area ratio, ventilation layout, and material selection are iteratively optimized to predict its cooling load, heating load, and lighting energy consumption in different seasons and at different times.

[0018] A further improvement is that when the photovoltaic power generation is 20% of the rated power generation, the photovoltaic management module sends a message to the photovoltaic management module indicating that power generation is not possible.

[0019] Further improvements include: the photovoltaic power source is a photovoltaic circuit board; the photovoltaic management module has an internal battery power source consisting of several 12V lithium batteries; the grid power source is 220V AC; and the building energy consumption analysis module integrates multi-dimensional data such as building orientation, thermal performance of the building envelope, indoor occupancy density, and equipment operation patterns to construct an energy consumption simulation model. During the design phase, the design parameters for the area ratio of the photovoltaic curtain wall, ventilation layout, and material selection are iteratively optimized to predict its cooling load, heating load, and lighting energy consumption in different seasons and at different times.

[0020] A further improvement is that the preprocessed dataset in the AI ​​prediction model module is divided into a training set and a test set, with 70% used for training and 30% used for testing.

[0021] A further improvement is made in that: when the photovoltaic power supply reaches 50% of its total capacity, a medium-level danger signal is sent to the building design line management module; when the photovoltaic power supply reaches 30% of its total capacity, a medium-high danger signal is sent to the building design line management module; and when the photovoltaic power supply reaches 10% of its total capacity, a high danger signal is sent to the building design line management module.

[0022] The beneficial effects of this invention are as follows: By classifying power lines, the photovoltaic power generation system can differentiate power supply based on the importance level and power consumption of electrical appliances after a power outage. The AI ​​prediction module analyzes historical data and real-time environmental factors, and the AI ​​model can accurately predict photovoltaic power generation and building ventilation needs, thereby optimizing system performance. The photovoltaic management module is responsible for real-time monitoring of the working status and power generation efficiency of photovoltaic panels to ensure maximum resource collection. The building design line management module monitors current and voltage in real time to ensure that the system operates within a safe range and avoids equipment damage caused by overload or short circuit. The current regulation module can accurately adjust the output current according to real-time needs and photovoltaic power generation to ensure the stability of the system in different working modes. By combining photovoltaic power and grid power, the continuity and stability of power supply are guaranteed. Attached Figure Description

[0023] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art 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.

[0024] Figure 1 This is a system flowchart of the present invention. Detailed Implementation

[0025] 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, and 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.

[0026] In the description of this invention, it should be noted that, unless otherwise explicitly specified and limited, the terms installation, connection, and linking should be interpreted broadly. For example, they can refer to fixed connections, detachable connections, or integral connections; they can refer to mechanical connections or electrical connections; they can refer to direct connections or indirect connections through an intermediate medium; and they can refer to the internal communication between two components. Those skilled in the art can understand the specific meaning of the above terms in this invention based on the specific circumstances.

[0027] In document CN119743077A, a wave-shaped support plate is used to support photovoltaic modules. The distance between adjacent wave crests is adjusted to be less than the width of a construction worker's foot or the width of the construction equipment's wheels. This ensures the support plate provides sufficient support to improve the photovoltaic panels' compressive strength and prevent breakage. Furthermore, adhesive grooves are used to connect the photovoltaic modules to the support plate, and support connecting sleeves are installed to connect adjacent photovoltaic modules. This connection and fixing method avoids friction and tearing of the roof and photovoltaic panels by clamps, thus improving the lifespan of the photovoltaic modules. Additionally, bending... The wave-shaped support plate is used to support photovoltaic modules and connect to the roof. Compared with the horizontal whole plate and the additional clamps required for fixation, it is lighter in weight. Semi-flexible crystalline silicon lightweight photovoltaic modules can be used to further reduce the weight of photovoltaic modules, thereby reducing the amount of steel used in the field of new steel structure buildings. However, the system in this application operates independently and cannot be reasonably allocated by AI prediction models, resulting in the system not being able to efficiently schedule energy use within a reasonable time. In this application, by classifying the power lines, the photovoltaic power generation system can differentiate power supply according to the importance level and power consumption of electrical appliances after a power outage, solving the problem that the existing photovoltaic power generation system cannot supply power according to the importance of electrical appliances.

[0028] Example 1

[0029] according to Figure 1 As shown, this embodiment provides a photovoltaic ventilation integrated curtain wall building design system that integrates AI prediction models, including an AI prediction model module, a photovoltaic management module, a building design circuit management module, a current regulation module, a photovoltaic power supply, and a grid power supply;

[0030] The AI ​​prediction model module, based on machine learning and deep learning algorithms, establishes predictive models for photovoltaic power generation, ventilation efficiency, and indoor environmental quality.

[0031] The photovoltaic management module monitors the operating status of photovoltaic modules in real time, including key parameters such as power generation, efficiency, temperature, and irradiance.

[0032] The building design circuit management module divides the circuit into low-power charging circuits, high-power electrical appliance circuits, low-power electrical circuits, and necessary electrical appliance circuits.

[0033] The current regulation module monitors the current values ​​of the photovoltaic system and ventilation equipment in real time, including the output current of the photovoltaic modules and the input current of the load.

[0034] Photovoltaic power supply, which is a photovoltaic circuit board, uses solar energy to convert it into electrical energy;

[0035] Grid power, through its collaboration with photovoltaic systems, helps achieve dynamic energy balance.

[0036] The AI ​​prediction model module inputs real-time collected environmental data into the trained AI prediction model for real-time prediction. The model's prediction results are then applied to system control to predict photovoltaic power generation and building ventilation demand over a future period. This prediction is used for current regulation and load management, and the system can dynamically adjust its operating strategies based on factors such as weather and seasonal changes, thereby improving the system's adaptability and flexibility.

[0037] The photovoltaic management module acquires current regulation and load information. When the current regulation information is a power outage signal, the server sends a verification request to the photovoltaic management module and receives the verification information transmitted from the photovoltaic management module. When the verification information indicates that power generation is not possible, the server sends a medium-level danger signal to the building design line management module. When the verification information indicates that power generation is possible, the server sends a low-level danger signal to the building design line management module. This allows for timely detection of photovoltaic module faults or performance degradation, and reduces maintenance costs and downtime through an early warning mechanism.

[0038] The building design circuit management module receives signals from the AI ​​prediction model module and the photovoltaic management module to control circuit opening and closing. When a low-level danger signal is received, the building design circuit management module will disconnect the high-power electrical appliance circuit, while keeping the low-power charging circuit, low-power household electrical circuit, and other appliance circuit connected. When a medium-level danger signal is received, the building design circuit management module will disconnect the high-power electrical appliance circuit and the low-power household electrical circuit, while keeping the low-power charging circuit and necessary appliance circuit connected. When a medium-to-high-level danger signal is received from the server, the building design circuit management module will disconnect the high-power electrical appliance circuit and the low-power household electrical circuit, while keeping the dedicated internet terminal circuit and necessary appliance circuit connected, and intermittently connecting the low-power charging circuit. When a high-level danger signal is received, the building design circuit management module will disconnect the high-power electrical appliance circuit and the low-power household electrical circuit, while keeping the dedicated internet terminal circuit connected, and intermittently connecting the low-power charging circuit and necessary appliance circuit.

[0039] The current regulation module is used to connect the photovoltaic power source and the grid power source; when the internal battery power source is low on power, the current regulation module connects to the grid power source to charge the battery power source.

[0040] The building energy consumption analysis module integrates multi-dimensional data such as building orientation, thermal performance of the building envelope, indoor occupancy density, and equipment operation patterns to construct an energy consumption simulation model. During the design phase, it can iteratively optimize design parameters such as the area ratio of photovoltaic curtain walls, ventilation layout, and material selection, and predict their cooling load, heating load, and lighting energy consumption in different seasons and at different times. This provides a quantitative basis for the economic efficiency and energy conservation of the curtain wall structure. At the same time, combined with the photovoltaic power generation prediction results output by the AI ​​prediction model module, it analyzes the energy supply and demand balance of the building itself.

[0041] When the photovoltaic panel generates 20% of its rated power, the photovoltaic management module sends a message indicating that it cannot generate power. When the photovoltaic panel generates 70% of its rated power, the photovoltaic management module sends a message indicating that it can generate power. By intelligently adjusting the current, it minimizes energy waste and improves overall energy efficiency. It can automatically adapt to different types of load demands, ensuring that users can obtain a stable power supply under any circumstances.

[0042] The photovoltaic power supply is a photovoltaic circuit board, and the photovoltaic management module has an internal battery power supply consisting of several 12V lithium batteries; the grid power supply is 220V AC.

[0043] In the AI ​​prediction model module, the preprocessed dataset is divided into a training set and a test set, with 70% used for training and 30% used for testing.

[0044] When the photovoltaic power supply reaches 50% of its total capacity, it sends a medium-level danger signal to the building design circuit management module. When the photovoltaic power supply reaches 30% of its total capacity, it sends a medium-high danger signal to the building design circuit management module. When the photovoltaic power supply reaches 10% of its total capacity, it sends a high danger signal to the building design circuit management module.

[0045] Example 2

[0046] Building upon Example 1, the AI ​​prediction model module, when predicting photovoltaic power generation, innovatively introduces a photovoltaic curtain wall surface cleanliness parameter in addition to considering conventional environmental factors such as irradiance, temperature, humidity, and wind speed. This is achieved by installing miniature image acquisition devices and dust sensors at specific locations on the photovoltaic curtain wall to monitor the degree of dust accumulation on the surface in real time. This dust accumulation is then incorporated into the prediction model as input features. The model learns the impact of dust accumulation on photovoltaic conversion efficiency using historical data, determining the percentage decrease in power generation when dust thickness reaches a certain threshold, thus more accurately correcting the predicted power generation value. For predicting building ventilation demand, in addition to traditional factors such as indoor-outdoor temperature difference, humidity, and number of people, this… The AI ​​model in this embodiment also integrates indoor CO2 concentration and VOCs concentration air quality parameters. When indoor CO2 concentration or VOCs concentration exceeds the standard, the model predicts in advance that the ventilation system needs to increase its operating intensity to ensure indoor air quality. This realizes the expansion of ventilation demand prediction from simple thermal comfort demand to comprehensive environmental quality demand. In terms of model training, this embodiment 2 adopts the transfer learning method. When long-term historical data of new buildings is lacking, the basic model is pre-trained using historical data of buildings of the same type and climate zone. Then, it is fine-tuned using short-term measured data of new buildings, which greatly shortens the convergence time of the model and improves the prediction accuracy and generalization ability of the model in new building scenarios.

[0047] Table 1. Line and Power Management and AI Prediction Information

[0048]

[0049] The foregoing has shown and described the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The embodiments and descriptions in the specification are merely illustrative of the principles of the invention. Various changes and modifications can be made to the invention without departing from its spirit and scope, and all such changes and modifications fall within the scope of the present invention as claimed. The scope of protection of the present invention is defined by the appended claims and their equivalents.

Claims

1. A photovoltaic ventilation integrated curtain wall building design system incorporating AI prediction models, characterized in that, It includes an AI prediction model module, a photovoltaic management module, a building design circuit management module, a current regulation module, a photovoltaic power supply, and a grid power supply; The AI ​​prediction model module, based on machine learning and deep learning algorithms, establishes predictive models for photovoltaic power generation, ventilation efficiency, and indoor environmental quality. The photovoltaic management module monitors the operating status of photovoltaic modules in real time, including key parameters such as power generation, efficiency, temperature, and irradiance. The building design circuit management module divides the circuit into low-power charging circuits, high-power electrical appliance circuits, low-power electrical circuits, and necessary electrical appliance circuits. The current regulation module monitors the current values ​​of the photovoltaic system and ventilation equipment in real time, including the output current of the photovoltaic modules and the input current of the load. The building energy consumption analysis module assesses the building's energy consumption needs and uses AI models to predict energy consumption performance under different design schemes. Photovoltaic power supply, which is a photovoltaic circuit board, uses solar energy to convert it into electrical energy; Grid power, through its collaboration with photovoltaic systems, helps achieve dynamic energy balance.

2. The photovoltaic ventilation integrated curtain wall building design system integrating AI prediction model as described in claim 1, characterized in that: The AI ​​prediction model module inputs the real-time collected environmental data into the trained AI prediction model for real-time prediction. The prediction results of the model are then applied to system control to predict the photovoltaic power generation and building ventilation demand in the future, for use in current regulation and load management.

3. The photovoltaic ventilation integrated curtain wall building design system integrating AI prediction model as described in claim 1, characterized in that: The photovoltaic management module acquires current regulation and load information. When the current regulation information is a power outage signal, the server sends a verification request to the photovoltaic management module and receives the verification information transmitted from the photovoltaic management module. When the verification information indicates that power generation is not possible, the server sends a medium-level danger signal to the building design line management module. When the verification information indicates that power generation is possible, the server sends a low-level danger signal to the building design line management module.

4. The photovoltaic ventilation integrated curtain wall building design system integrating AI prediction model as described in claim 1, characterized in that: The building design line management module receives signals from the AI ​​prediction model module and the photovoltaic management module to control the opening and closing of the lines.

5. The photovoltaic ventilation integrated curtain wall building design system integrating AI prediction model according to claim 1, characterized in that: The current regulation module is used to connect the photovoltaic power source and the grid power source; when the internal battery power source is low on power, the current regulation module connects to the grid power source to charge the battery power source.

6. The photovoltaic ventilation integrated curtain wall building design system integrating AI prediction model according to claim 1, characterized in that: The building energy consumption analysis module integrates multi-dimensional data such as building orientation, thermal performance of the building envelope, indoor occupancy density, and equipment operation patterns to construct an energy consumption simulation model. During the design phase, it iteratively optimizes the design parameters of the photovoltaic curtain wall area ratio, ventilation layout, and material selection to predict its cooling load, heating load, and lighting energy consumption in different seasons and at different times.

7. The photovoltaic ventilation integrated curtain wall building design system integrating AI prediction model according to claim 1, characterized in that: When the photovoltaic power generation is 20% of the rated power generation, the photovoltaic management module sends a message to the photovoltaic management module indicating that it cannot generate electricity.

8. The photovoltaic ventilation integrated curtain wall building design system integrating AI prediction model according to claim 1, characterized in that: The photovoltaic power source is a photovoltaic circuit board; the photovoltaic management module has a battery pack consisting of several 12V lithium batteries; the grid power source is 220V AC.

9. The photovoltaic ventilation integrated curtain wall building design system integrating AI prediction model according to claim 1, characterized in that: The AI ​​prediction model module divides the preprocessed dataset into a training set and a test set, with 70% used for training and 30% used for testing.

10. The photovoltaic ventilation integrated curtain wall building design system integrating AI prediction model according to claim 1, characterized in that: When the photovoltaic power supply reaches 50% of its total capacity, a medium-level danger signal is sent to the building design circuit management module. When the photovoltaic power supply reaches 30% of its total capacity, a medium-high danger signal is sent to the building design circuit management module. When the photovoltaic power supply reaches 10% of its total capacity, a high danger signal is sent to the building design circuit management module.

Images