Intelligent building equipment linkage control method and system based on large model

Abstract

The invention discloses an intelligent building equipment linkage control method and system based on a large model, and relates to the technical field of linkage control. During operation of the system, high-precision photosensitive and temperature sensors are used for collecting related data of external and internal environments, the collected original data are preprocessed, a machine learning algorithm is applied, and the intelligent building equipment linkage control method and system based on the large model are obtained; a prediction model is established based on historical data to predict future environment changes, an intelligent sunshade efficiency index ISI is calculated, a specific execution control instruction is generated, a preliminary sunshade strategy is formulated, logic comparison and strategy formulation are carried out in combination with a mode prediction result and a preset threshold value, and according to the control strategy provided by the threshold value comparison and strategy generation module, the intelligent sunshade efficiency index ISI is calculated. The method comprises the following steps: automatically adjusting the position and angle of a sun shield, actually executing the adjustment operation of a sun-shading system, monitoring the execution effect of the sun-shading system, collecting the implemented indoor illumination and temperature data, comparing with an expected target, and adjusting a prediction model and a threshold value to optimize the performance.

Description

Technical Field

[0001] The present invention relates to the technical field of linkage control, and in particular to a linkage control method and system for intelligent building equipment based on a large model. Background Art

[0002] With advances in modern building technology, intelligent building equipment linkage control systems have gradually become a key technology for improving building efficiency, comfort, and energy management. These systems achieve intelligent environmental regulation and optimized resource utilization by integrating and controlling multiple devices and systems within a building, such as lighting, air conditioning, and security systems. While existing intelligent building equipment linkage control systems can achieve basic equipment linkage to a certain extent, they often lack sufficient flexibility and predictive capabilities, making it difficult to cope with complex or changing environmental conditions. For example, traditional systems may be unable to accurately predict the specific impact of external environmental changes on internal temperature and light, resulting in shading systems that are either unresponsive or overreact, affecting energy efficiency and indoor comfort. Furthermore, these systems are often unable to perform complex data processing and analysis, limiting their ability to optimize control strategies and failing to achieve truly "intelligent" control.

[0003] Because traditional intelligent building control systems often fail to fully leverage advanced data analysis and real-time feedback adjustments, they often exhibit sluggish response or inappropriate adjustments to sudden weather changes or irregular indoor activity patterns. For example, when a rainy day suddenly clears up, the system may fail to adjust the sunshades in time, causing the indoor temperature to rise rapidly and the air conditioning system to over-operate in an attempt to cool the room. This delayed response not only increases energy consumption but can also cause discomfort to occupants. Furthermore, system deficiencies can lead to uneven light distribution indoors, impacting visual comfort and work efficiency. These issues highlight the shortcomings of traditional systems in intelligent analysis and real-time adjustment, and underscore the necessity and urgency of adopting large-scale model-based intelligent control technologies. Summary of the Invention

[0004] In view of the deficiencies of the prior art, the present invention provides a method and system for controlling linkage of intelligent building equipment based on a large model, which solves the problems mentioned in the background art.

[0005] To achieve the above objectives, the present invention is implemented through the following technical solutions: a large-scale model-based intelligent building equipment linkage control system, including an environment perception module, a data processing module, a pattern prediction module, a strategy generation module, an execution control module and a performance feedback module; The environmental perception module is used to collect relevant data of the external and internal environment using high-precision light and temperature sensors, including indoor and outdoor lighting data, indoor and outdoor temperature data, and the energy efficiency of the shading system under the conditions of predetermined lighting and temperature regulation effects; The data processing module is used to pre-process the collected raw data, including cleaning, normalization and preliminary analysis. The processed environmental data is passed to the pattern prediction module; The pattern prediction module is used to apply machine learning algorithms to establish a prediction model based on historical data to predict future environmental changes, calculate the intelligent shading effectiveness index (ISPI), generate specific execution control instructions, and formulate preliminary shading strategies; The strategy generation module is used to combine the pattern prediction results and preset thresholds for logical comparison and strategy formulation; The execution control module is used to automatically adjust the position and angle of the sun visor according to the threshold comparison and the control strategy provided by the strategy generation module, and actually perform the adjustment operation of the sun visor system; The performance feedback module is used to monitor the performance of the shading system. By collecting indoor light and temperature data after implementation, the data are compared with the expected targets, and the prediction model and thresholds are adjusted to optimize performance.

[0006] Preferably, the environment perception module includes an external environment data acquisition unit and an internal environment data acquisition unit; The external environment data acquisition unit is equipped with a light intensity sensor for measuring the external light intensity Lext in real time, and a temperature sensor for measuring the external temperature Text; The internal environment data acquisition unit is equipped with a light intensity sensor to measure the indoor light intensity Lint, and a temperature sensor to record the indoor temperature Tint. By installing smart meters at the building's power input points and HVAC system, electricity consumption data, peak and valley consumption, and total electricity usage within a time period are recorded to obtain the total energy consumption Etotal.

[0007] Preferably, the data processing module includes a data pre-processing unit and a preliminary analysis unit; The data preprocessing unit is used to clean and normalize the raw data collected from the environmental perception module, remove noise, and correct errors; The preliminary analysis unit is used to perform preliminary analysis on the preprocessed data, identify patterns and trends in the data, and pass the processed environmental data to the pattern prediction module.

[0008] Preferably, the pattern prediction module includes a pattern recognition unit and a decision support unit; The pattern recognition unit is used to apply machine learning algorithms to analyze environmental data and identify key patterns and trends that affect system operations; The decision support unit is used to generate preliminary control strategies and decision recommendations based on pattern recognition results.

[0009] Preferably, the machine learning algorithm calculates the intelligent shading effectiveness index ISPI, the illumination adjustment coefficient IAC, the thermal comfort coefficient TCC and the energy efficiency coefficient EEC: The illumination adjustment coefficient IAC is calculated using the following formula: ; Where ΔL represents the change in indoor light intensity, which is the change in indoor light intensity after the shading system is adjusted relative to the change before adjustment. Lext represents the external light intensity, which is the light intensity measured by the light sensor outside the building and is used to evaluate the impact of external ambient light on indoor light. The thermal comfort coefficient TCC is calculated using the following formula: ; Where ΔT represents the adjustment range of the indoor temperature. After the shading system is adjusted, the change range of the indoor temperature refers to the difference between the temperature before and after adjustment. Text represents the external temperature, which is the temperature value measured by the external environment sensor. Tint represents the indoor temperature, which is the temperature value measured by the indoor environment sensor. The energy efficiency coefficient EEC is calculated using the following formula: ; Where ΔE represents the energy savings during the operation of the shading system, which is the reduction in energy consumption before and after the shading system is operated; Etotal represents the total energy consumption during the operation of the shading system, including the total energy use of air conditioning and lighting equipment during this period.

[0010] Preferably, the intelligent shading effectiveness index ISPI is calculated by the following formula: ; Where ω1, ω2, and ω3 are the weights of each coefficient, which are adjusted according to the specific needs and strategic priorities of the building.

[0011] Preferably, the policy generation module includes a policy generation unit; The strategy generation unit is used to set and manage key thresholds for shading system operations. It generates detailed shading and energy consumption control strategies based on predicted data and thresholds. By comparing the intelligent shading effectiveness index (ISPI) with the preset standard thresholds Z and X, it obtains a three-level threshold comparison evaluation strategy solution. When ISPI ≥ Z, it indicates that the performance of the shading system exceeds the expected standard by more than 10%. A real-time monitoring system is implemented to continuously track key performance indicators, including light intensity, indoor and outdoor temperature difference, and energy consumption. A high-precision sensor network is deployed using IoT technology to ensure real-time data updates and accuracy. When X ≤ ISPI < Z, it indicates that the system performance does not meet the qualified requirements. In response to the situation where the lighting and thermal comfort coefficients are not at their optimal states, adjust the sensitivity and response speed of the shading system, identify the specific areas with insufficient performance, including insufficient lighting adjustment or unsatisfactory thermal comfort, and conduct centralized adjustments for these areas. Adjust the key parameters in the control algorithm, including increasing the sensitivity of the sunshade adjustment or optimizing the response time of the sunshade; When ISPI < X, it indicates that the system performance is more than 10% lower than the minimum standard. Replace or re - design the main components of the system, replace with more efficient shading materials or install more advanced environmental sensing devices, and retrain the machine learning model.

[0012] Preferably, the execution control module includes an execution instruction generation unit and a control instruction issuing unit; The execution instruction generation unit is responsible for converting the high - level control strategy into specific execution instructions, which will directly control the physical components of the adaptive shading system. Analyze the control logic from the strategy generation module, determine the operations that the shading system needs to perform, adjust the angle of the sunshade or change the operation mode, and convert the parsed operations into code that can be executed by low - level machines. The code includes switch signals, PWM signals or other electronic control signals, ensuring that the generated instructions are compatible with various types of shading system hardware, including electric sunshades and automatic curtains; The control instruction issuing unit is used to accurately and error - free convey the control instructions generated by the execution instruction generation unit to each execution device of the shading system. Utilize the building automation network BACnet or Modbus standard to send the control instructions to the relevant execution devices, monitor the instruction transmission process, ensure that all instructions reach successfully along the predetermined path without packet loss, implement error - detection logic, and automatically re - send the instructions when an instruction transmission error or device non - response is found.

[0013] Preferably, the performance feedback module includes a performance monitoring unit and an optimization and adjustment unit; The performance monitoring unit is used to monitor the actual performance after the adaptive shading system is executed, collect and analyze the impact of the system operation on indoor lighting and temperature, use environmental sensors installed at key positions to collect the adjusted data in real - time, compare the environmental data before and after the system operation, and evaluate the adjustment effect using statistical analysis methods; The optimization and adjustment unit is used to dynamically adjust the control strategy and operation threshold of the system according to the performance monitoring results, implement feedback control logic, and adjust the future control strategy based on the actual operation results.

[0014] An intelligent building equipment linkage control method based on a large - model includes the following steps: Step 1: Use high-precision light and temperature sensors to collect relevant data on the external and internal environments, including indoor and outdoor lighting data, indoor and outdoor temperature data, and the energy efficiency of the shading system under the conditions of predetermined lighting and temperature regulation effects; Step 2: Preprocess the collected raw data, including cleaning, normalization and preliminary analysis, and pass the processed environmental data to the pattern prediction module; Step 3: Use machine learning algorithms to build a prediction model based on historical data to predict future environmental changes, calculate the intelligent shading effectiveness index (ISPI), generate specific execution control instructions, and formulate a preliminary shading strategy; Step 4: Combine the model prediction results with the preset thresholds for logical comparison and strategy formulation; Step 5: According to the control strategy provided by the threshold comparison and strategy generation module, the position and angle of the sun visor are automatically adjusted to actually perform the adjustment operation of the sun visor system; Step 6: Monitor the effectiveness of the shading system and collect indoor light and temperature data after implementation, compare them with the expected targets, and adjust the prediction model and thresholds to optimize performance.

[0015] The present invention provides a method and system for controlling linkage of intelligent building equipment based on a large model, which has the following beneficial effects: (1) When the system is running, high-precision photosensors and temperature sensors are used to collect relevant data on the external and internal environments. The collected raw data are preprocessed, and a machine learning algorithm is used to establish a prediction model based on historical data to predict future environmental changes. The intelligent shading effectiveness index (ISPI) is calculated, and specific execution control instructions are generated. A preliminary shading strategy is formulated. The pattern prediction results and the preset thresholds are combined for logical comparison and strategy formulation. According to the threshold comparison and the control strategy provided by the strategy generation module, the position and angle of the sunshade are automatically adjusted. The adjustment operation of the shading system is actually performed, and the execution effect of the shading system is monitored. By collecting the indoor light and temperature data after implementation and comparing them with the expected targets, the prediction model and threshold are adjusted to optimize performance.

[0016] (2) By implementing a large-scale model-based intelligent building equipment linkage control system, which includes six modules: environmental perception, data processing, pattern prediction, strategy generation, execution control, and performance feedback, we successfully achieved a series of beneficial effects and completed key tasks. First, the system provides real-time and accurate indoor and outdoor environmental data for the entire system through precise data collection in the environmental perception module, ensuring that all subsequent processing and decision-making are based on the most accurate information. Subsequently, the efficient preprocessing and analysis of the data processing module provides cleaned and normalized data for pattern prediction, enabling the prediction model to more accurately predict future environmental changes, thereby formulating more effective shading strategies.

[0017] (3) Compared with existing technologies, this system has made significant improvements in data processing and real-time response capabilities. The combination of the pattern prediction module and the strategy generation module not only enhances the system's adaptability to environmental changes, but also makes the shading strategy more intelligent and refined, and can be dynamically adjusted according to actual environmental needs, thereby reducing energy waste and improving indoor environmental quality. In addition, the efficient command issuance and precise control of the execution control module further ensure the correct execution of control commands, achieve highly automated shading adjustment, and improve the reliability of the overall system and user satisfaction.

[0018] (4) The introduction of the performance feedback module enables the entire system to not only implement planned operations but also to self-optimize based on the actual execution results. By continuously monitoring and evaluating the performance of the shading system and comparing it with the preset targets, the system can continuously adjust the prediction model and control strategy to gradually optimize its performance. This feedback-based optimization mechanism significantly improves the adaptability and efficiency of the system, enabling building managers to achieve a higher level of energy management and environmental comfort. In general, this intelligent building equipment linkage control system has effectively improved energy efficiency and optimized user experience through technological innovation and intelligent management, and has set a new benchmark for modern intelligent building facilities. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 This is a block diagram of a large-scale model-based intelligent building equipment linkage control system of the present invention; Figure 2 This is a schematic diagram of the steps of a large-scale model-based intelligent building equipment linkage control method of the present invention; Figure 3 The figure is a line graph showing the performance of the intelligent shading effectiveness index (ISPI) of the intelligent building equipment linkage control system based on a large model according to the present invention relative to preset thresholds Z and X under different performance categories. DETAILED DESCRIPTION

[0020] The following will provide a clear and complete description of the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0021] Example 1 The present invention provides a large-scale model-based intelligent building equipment linkage control system. Figure 1 , including environment perception module, data processing module, pattern prediction module, strategy generation module, execution control module and performance feedback module; The environmental perception module is used to collect relevant data of the external and internal environment using high-precision light and temperature sensors, including indoor and outdoor lighting data, indoor and outdoor temperature data, and the energy efficiency of the shading system under the conditions of predetermined lighting and temperature regulation effects; The data processing module is used to pre-process the collected raw data, including cleaning, normalization and preliminary analysis. The processed environmental data is passed to the pattern prediction module; The pattern prediction module is used to apply machine learning algorithms to establish a prediction model based on historical data to predict future environmental changes, calculate the intelligent shading effectiveness index (ISPI), generate specific execution control instructions, and formulate preliminary shading strategies; The strategy generation module is used to combine the pattern prediction results and preset thresholds for logical comparison and strategy formulation; The execution control module is used to automatically adjust the position and angle of the sun visor according to the threshold comparison and the control strategy provided by the strategy generation module, and actually perform the adjustment operation of the sun visor system; The performance feedback module is used to monitor the performance of the shading system. By collecting indoor light and temperature data after implementation, the data are compared with the expected targets, and the prediction model and thresholds are adjusted to optimize performance.

[0022] In this embodiment, high-precision photosensors and temperature sensors are used to collect relevant data on the external and internal environments, including indoor and outdoor lighting data, indoor and outdoor temperature data, and the energy efficiency of the shading system under the conditions of predetermined lighting and temperature adjustment effects. The collected raw data is preprocessed, including cleaning, normalization, and preliminary analysis. The processed environmental data is passed to the pattern prediction module. A machine learning algorithm is used to establish a prediction model based on historical data to predict future environmental changes, calculate the intelligent shading effectiveness index ISPI, generate specific execution control instructions, formulate a preliminary shading strategy, and combine the pattern prediction results with preset thresholds for logical comparison and strategy formulation. According to the threshold comparison and the control strategy provided by the strategy generation module, the position and angle of the sun visor are automatically adjusted, the adjustment operation of the shading system is actually performed, the execution effect of the shading system is monitored, and by collecting the indoor lighting and temperature data after implementation and comparing them with the expected targets, the prediction model and threshold are adjusted to optimize performance.

[0023] Example 2 This embodiment is explained in Example 1, please refer to Figure 1 ,Specifically: the environment perception module includes an external environment data ,acquisition unit and an internal environment data acquisition unit; The external environment data acquisition unit is equipped with a light intensity sensor for measuring the external light intensity Lext in real time, and a temperature sensor for measuring the external temperature Text; The internal environment data acquisition unit is equipped with a light intensity sensor to measure the indoor light intensity Lint, and a temperature sensor to record the indoor temperature Tint. By installing smart meters at the building's power input points and HVAC system, electricity consumption data, peak and valley consumption, and total electricity usage within a time period are recorded to obtain the total energy consumption Etotal.

[0024] The data processing module includes a data pre-processing unit and a preliminary analysis unit; The data preprocessing unit is used to clean and normalize the raw data collected from the environmental perception module, remove noise, and correct errors; The preliminary analysis unit is used to perform preliminary analysis on the preprocessed data, identify patterns and trends in the data, and pass the processed environmental data to the pattern prediction module.

[0025] In this embodiment, by integrating an environmental sensing module with a data processing module, the intelligent building equipment linkage control system effectively collects and processes key indoor and outdoor environmental data, including light intensity and temperature, as well as the building's energy consumption. This not only enhances the system's responsiveness to actual environmental conditions but also ensures data accuracy and reliability through precise data preprocessing and analysis. This provides high-quality input for model prediction, supports more precise shading system control strategies, and significantly improves energy efficiency and indoor environmental quality. This approach optimizes energy management, reduces operating costs, and enhances the comfort of living and working spaces.

[0026] Example 3 This embodiment is explained in Example 1, please refer to Figure 1 ,Specifically: the pattern prediction module includes a pattern recognition unit and a ,decision support unit; The pattern recognition unit is used to apply machine learning algorithms to analyze environmental data and identify key patterns and trends that affect system operations; The decision support unit is used to generate preliminary control strategies and decision recommendations based on pattern recognition results.

[0027] The machine learning algorithm calculates the intelligent shading effectiveness index (ISPI), the illumination adjustment coefficient (IAC), the thermal comfort coefficient (TCC), and the energy efficiency coefficient (EEC): The illumination adjustment coefficient IAC is calculated using the following formula: ; Where ΔL represents the change in indoor light intensity, which is the change in indoor light intensity after the shading system is adjusted relative to the change before adjustment. Lext represents the external light intensity, which is the light intensity measured by the light sensor outside the building and is used to evaluate the impact of external ambient light on indoor light. The thermal comfort coefficient TCC is calculated using the following formula: ; Where ΔT represents the adjustment range of the indoor temperature. After the shading system is adjusted, the change range of the indoor temperature refers to the difference between the temperature before and after adjustment. Text represents the external temperature, which is the temperature value measured by the external environment sensor. Tint represents the indoor temperature, which is the temperature value measured by the indoor environment sensor. The energy efficiency coefficient EEC is calculated using the following formula: ; Where ΔE represents the energy savings during the operation of the shading system, which is the reduction in energy consumption before and after the shading system is operated; Etotal represents the total energy consumption during the operation of the shading system, including the total energy use of air conditioning and lighting equipment during this period.

[0028] The intelligent shading effectiveness index ISPI is calculated using the following formula: ; Where ω1, ω2, and ω3 are the weights of each coefficient, which are adjusted according to the specific needs and strategic priorities of the building.

[0029] In this embodiment, the pattern prediction module greatly enhances the predictive capabilities and decision-making efficiency of the intelligent building equipment linkage control system by integrating a pattern recognition unit and a decision support unit. Utilizing advanced machine learning algorithms, this module can accurately analyze and identify key patterns and trends in environmental data, such as changes in light and temperature, thereby predicting future environmental conditions and formulating corresponding shading strategies. This advanced data-driven approach allows the system to dynamically adjust the sunshades based on real-time data, optimizing the illumination adjustment coefficient (IAC), thermal comfort coefficient (TCC), and energy efficiency coefficient (EEC), ensuring optimal energy use and indoor environmental quality. Through these precise adjustments, the intelligent shading effectiveness index (ISPI) can reflect the overall performance of the system in real time, guide continuous system optimization, significantly improve energy efficiency, reduce operating costs, and enhance the comfort of living and working spaces.

[0030] Example 4 This embodiment is explained in Example 1, please refer to Figure 1 ,Specifically: the policy generation module includes a policy generation unit; The strategy generation unit is used to set and manage key thresholds for shading system operations. It generates detailed shading and energy consumption control strategies based on predicted data and thresholds. By comparing the intelligent shading effectiveness index (ISPI) with the preset standard thresholds Z and X, it obtains a three-level threshold comparison evaluation strategy solution. When ISPI ≥ Z, it indicates that the performance of the shading system exceeds the expected standard by more than 10%. Implement a real-time monitoring system to continuously track key performance indicators, including light intensity, indoor-outdoor temperature difference, and energy consumption. Deploy a high-precision sensor network using IoT technology to ensure real-time data updates and accuracy. When X ≤ ISPI < Z, it indicates that the system performance does not meet the qualified requirements. In the case where the light and thermal comfort coefficients are not in the optimal state, adjust the sensitivity and response speed of the shading system, identify specific areas with insufficient performance, including insufficient light regulation or unsatisfactory thermal comfort, and make centralized adjustments for these areas. Adjust key parameters in the control algorithm, including increasing the sensitivity of the sunshade adjustment or optimizing the response time of the sunshade. When ISPI < X, it indicates that the system performance is below the minimum standard by more than 10%. Replace or redesign the main components of the system, replace with more efficient shading materials or install more advanced environmental sensing devices, and retrain the machine learning model.

[0031] The execution control module includes an execution instruction generation unit and a control instruction issuing unit. The execution instruction generation unit is responsible for converting the high-level control strategy into specific execution instructions, which will directly control the physical components of the adaptive shading system. Analyze the control logic from the strategy generation module, determine the operations that the shading system needs to perform, adjust the angle of the sunshade or change the operation mode, and convert the parsed operations into code that can be executed by low-level machines. The code includes switch signals, PWM signals, or other electronic control signals, ensuring that the generated instructions are compatible with various types of shading system hardware, including electric sunshades and automatic curtains. [[ID=??]] The control instruction issuing unit is used to accurately and errorlessly convey the control instructions generated by the execution instruction generation unit to each execution device of the shading system. Using the building automation network BACnet or Modbus standard, send the control instructions to the relevant execution devices, monitor the instruction transmission process, ensure that all instructions reach successfully along the predetermined path without packet loss, implement error detection logic, and automatically resend the instructions when an instruction transmission error or device non-response is found.

[0032] The performance feedback module includes a performance monitoring unit and an optimization and adjustment unit. The performance monitoring unit is used to monitor the actual performance after the adaptive shading system is executed, collect and analyze the impact of the system operation on indoor light and temperature, use environmental sensors installed at key positions to collect the adjusted data in real time, compare the environmental data before and after the system operation, and evaluate the adjustment effect using statistical analysis methods. [[ID=1??]]The optimization and adjustment unit is used to dynamically adjust the control strategy and operation threshold of the system according to the performance monitoring results, implement feedback control logic, and adjust the future control strategy according to the actual operation results. It should be noted that there seems to be a formatting issue in the original text where the "??" in the line numbers might be incorrect. I've translated it as best as possible based on the context. If you can correct the original text, it would be better for a more accurate translation.

[0033] In this embodiment, the strategy generation module, execution control module, and performance feedback module play a crucial role in the large-scale model-based intelligent building equipment linkage control system. Through their coordinated operation, the system not only optimizes the performance of the adaptive shading system but also significantly improves the energy efficiency and occupant comfort of the entire building. Through precise threshold setting and real-time data analysis, the strategy generation module dynamically adjusts shading strategies to ensure that energy efficiency requirements are met while maximizing natural light utilization and indoor temperature comfort. The execution control module precisely translates these strategies into specific operations. Through efficient command transmission and execution, it ensures system response speed and operational accuracy, avoids energy waste, and enhances system reliability. Finally, the performance feedback module continuously monitors and analyzes system execution results, providing data support for continuous system optimization. This allows control strategies to be adjusted based on actual performance, thereby achieving a highly adaptive and self-optimizing intelligent shading solution. The combined effect of these modules not only significantly improves the building's environmental quality and energy management efficiency, but also creates a healthier and more comfortable living and working environment for users.

[0034] Example 5 A method for controlling linkage of intelligent building equipment based on large models, please refer to Figure 2 , specifically: including the following steps: Step 1: Use high-precision light and temperature sensors to collect relevant data on the external and internal environments, including indoor and outdoor light data, indoor and outdoor temperature data, and the energy efficiency of the shading system under the conditions of predetermined light and temperature regulation effects; Step 2: Preprocess the collected raw data, including cleaning, normalization and preliminary analysis, and pass the processed environmental data to the pattern prediction module; Step 3: Use machine learning algorithms to build a prediction model based on historical data to predict future environmental changes, calculate the intelligent shading effectiveness index (ISPI), generate specific execution control instructions, and formulate a preliminary shading strategy; Step 4: Combine the model prediction results with the preset thresholds for logical comparison and strategy formulation; Step 5: According to the control strategy provided by the threshold comparison and strategy generation module, the position and angle of the sun visor are automatically adjusted to actually perform the adjustment operation of the sun visor system; Step 6: Monitor the effectiveness of the shading system and collect indoor light and temperature data after implementation, compare them with the expected targets, and adjust the prediction model and thresholds to optimize performance.

[0035] In this embodiment, by implementing the intelligent building equipment linkage control system using the six-step process described above, we achieved highly optimized and precise control of the adaptive shading system, significantly improving energy efficiency and indoor environmental quality. First, environmental data accurately collected by high-precision sensors provides the system with a reliable decision-making basis. Subsequently, data preprocessing and pattern prediction ensure the scientific and forward-looking nature of the control strategy, enabling the shading system to dynamically adjust based on real-time and predicted data to optimize light and temperature conditions. Furthermore, real-time monitoring of performance and comparison with expected targets ensures continuous performance improvement. By continuously adjusting the prediction model and control thresholds, the system not only responds more accurately but also self-learns and adapts to changing environmental conditions. Overall, this intelligent control approach not only enhances the building's energy management capabilities but also significantly improves the comfort and user satisfaction of living and working spaces.

[0036] While 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 these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. A large-scale model-based intelligent building equipment linkage control system, characterized by: It includes environment perception module, data processing module, pattern prediction module, strategy generation module, execution control module and performance feedback module; The environmental perception module is used to collect relevant data of the external and internal environment using high-precision light and temperature sensors, including indoor and outdoor lighting data, indoor and outdoor temperature data, and the energy efficiency of the shading system under the conditions of predetermined lighting and temperature regulation effects; The data processing module is used to pre-process the collected raw data, including cleaning, normalization and preliminary analysis. The processed environmental data is passed to the pattern prediction module; The pattern prediction module is used to apply machine learning algorithms to establish a prediction model based on historical data to predict future environmental changes, calculate the intelligent shading effectiveness index (ISPI), generate specific execution control instructions, and formulate preliminary shading strategies; The strategy generation module is used to combine the pattern prediction results and preset thresholds for logical comparison and strategy formulation; The execution control module is used to automatically adjust the position and angle of the sun visor according to the threshold comparison and the control strategy provided by the strategy generation module, and actually perform the adjustment operation of the sun visor system; The performance feedback module is used to monitor the performance of the shading system. By collecting indoor light and temperature data after implementation, the data are compared with the expected targets, and the prediction model and thresholds are adjusted to optimize the performance.

2. The large-scale model-based intelligent building equipment linkage control system according to claim 1, characterized in that: The environmental perception module includes an external environmental data acquisition unit and an internal environmental data acquisition unit; The external environment data acquisition unit is equipped with a light intensity sensor for measuring the external light intensity Lext in real time, and a temperature sensor for measuring the external temperature Text; The internal environment data acquisition unit is equipped with a light intensity sensor to measure the indoor light intensity Lint, and a temperature sensor to record the indoor temperature Tint. By installing smart meters at the building's power input points and HVAC system, electricity consumption data, peak and valley consumption, and total electricity usage within a time period are recorded to obtain the total energy consumption Etotal.

3. The large-scale model-based intelligent building equipment linkage control system according to claim 1, characterized in that: The data processing module includes a data pre-processing unit and a preliminary analysis unit; The data preprocessing unit is used to clean and normalize the raw data collected from the environmental perception module, remove noise, and correct errors; The preliminary analysis unit is used to perform preliminary analysis on the preprocessed data, identify patterns and trends in the data, and pass the processed environmental data to the pattern prediction module.

4. The large-scale model-based intelligent building equipment linkage control system according to claim 1, characterized in that: The pattern prediction module includes a pattern recognition unit and a decision support unit; The pattern recognition unit is used to apply machine learning algorithms to analyze environmental data and identify key patterns and trends that affect system operations; The decision support unit is used to generate preliminary control strategies and decision recommendations based on pattern recognition results.

5. The large-scale model-based intelligent building equipment linkage control system according to claim 4, characterized in that: The machine learning algorithm calculates the intelligent shading effectiveness index (ISPI), the illumination adjustment coefficient (IAC), the thermal comfort coefficient (TCC), and the energy efficiency coefficient (EEC): The illumination adjustment coefficient IAC is calculated using the following formula: ； In the formula, ΔL represents the change in indoor light intensity, which is the value of the indoor light intensity relative to that before the adjustment of the shading system. Lext represents the external light intensity, which is the light intensity measured by a light sensor outside the building and is used to evaluate the influence of the external environmental light on the indoor light. The thermal comfort coefficient TCC is calculated and obtained through the following formula: ； In the formula, ΔT represents the adjustment range of the indoor temperature, which is the change range of the indoor temperature after the adjustment of the shading system, referring to the difference between the temperature after adjustment and the temperature before adjustment; Text represents the external temperature, which is the temperature value measured by an external environmental sensor; Tint represents the indoor temperature, which is the temperature value measured by an indoor environmental sensor. The energy consumption efficiency coefficient EEC is calculated and obtained through the following formula: ； In the formula, ΔE represents the energy savings during the operation of the shading system, which is the reduction in energy consumption before and after the operation of the shading system; Etotal represents the total energy consumption during the operation of the shading system, including the total energy usage of air conditioners and lighting equipment during this period.

6. The large-scale model-based intelligent building equipment linkage control system according to claim 1, characterized in that: The intelligent shading performance index ISPI is calculated and obtained through the following formula: ； In the formula, ω1, ω2, and ω3 are the weights of each coefficient, which are adjusted according to the specific requirements of the building and the strategic priorities.

7. The large-scale model-based intelligent building equipment linkage control system according to claim 1, characterized in that: The strategy generation module includes a strategy generation unit; The strategy generation unit is used to set and manage the key thresholds for the operation of the shading system, generate detailed shading and energy consumption control strategies based on the prediction data and thresholds, and obtain three-level threshold comparison evaluation strategy schemes by comparing the intelligent shading performance index ISPI with the preset standard threshold Z and the preset standard threshold X; When ISPI ≥ Z, it indicates that the performance of the shading system exceeds the expected standard by more than 10%. Implement a real-time monitoring system to continuously track key performance indicators, including light intensity, indoor-outdoor temperature difference, and energy consumption. Deploy a high-precision sensor network using IoT technology to ensure the real-time update and accuracy of data; When X ≤ ISPI < Z, it indicates that the system performance does not meet the qualified requirements. For the situation where the light and thermal comfort coefficients do not reach the optimal state, adjust the sensitivity and response speed of the shading system, identify the specific areas with insufficient performance, including insufficient light adjustment or unsatisfactory thermal comfort, and make focused adjustments to these areas. Adjust the key parameters in the control algorithm, including increasing the sensitivity of the shading panel adjustment or optimizing the response time of the shading panel; When ISPI < X, it indicates that the system performance is lower than the minimum standard by more than 10%. Replace or re-design the main components of the system, replace more efficient shading materials or install more advanced environmental sensing equipment, and re-train the machine learning model.

8. The large-scale model-based intelligent building equipment linkage control system according to claim 1, characterized in that: The execution control module includes an execution instruction generation unit and a control instruction issuing unit; The execution instruction generation unit is responsible for converting high-level control strategies into specific execution instructions. These instructions will directly control the physical components of the adaptive sunshade system, parse the control logic from the strategy generation module, determine the operations that the sunshade system needs to perform, adjust the angle of the sunshade or change the operation mode, and convert the parsed operations into codes that can be executed by low-level machines. The codes include switch signals, PWM signals or other electronic control signals, ensuring that the generated instructions are compatible with various types of sunshade system hardware, including electric sunshades and automatic curtains; The control instruction issuing unit is used to ensure that the control instructions generated by the execution instruction generating unit can be accurately and correctly transmitted to each execution device of the sunshade system. It uses the building automation network BACnet or Modbus standard to send the control instructions to the relevant execution devices, monitor the instruction transmission process, ensure that all instructions arrive successfully along the predetermined path without packet loss, implement error detection logic, and automatically resend the instructions if an instruction transmission error is found or the device does not respond.

9. The large-scale model-based intelligent building equipment linkage control system according to claim 1, characterized in that: The performance feedback module includes a performance monitoring unit and an optimization and adjustment unit; The performance monitoring unit is used to monitor the actual performance of the adaptive shading system after implementation, collect and analyze the impact of system operation on indoor light and temperature, use environmental sensors installed in key locations to collect real-time data after adjustment, compare environmental data before and after system operation, and use statistical analysis methods to evaluate the adjustment effect; The optimization and adjustment unit is used to dynamically adjust the system's control strategy and operating threshold according to the performance monitoring results, implement feedback control logic, and adjust future control strategies according to actual operation results.

10. A method for controlling linkage of intelligent building equipment based on a large model, applied to a linkage control system of intelligent building equipment based on a large model according to any one of claims 1 to 9, characterized in that: The following steps are involved: Step 1: Use high-precision light and temperature sensors to collect relevant data on the external and internal environments, including indoor and outdoor lighting data, indoor and outdoor temperature data, and the energy efficiency of the shading system under the conditions of predetermined lighting and temperature regulation effects; Step 2: Preprocess the collected raw data, including cleaning, normalization and preliminary analysis, and pass the processed environmental data to the pattern prediction module; Step 3: Use machine learning algorithms to build a prediction model based on historical data to predict future environmental changes, calculate the intelligent shading effectiveness index (ISPI), generate specific execution control instructions, and formulate a preliminary shading strategy; Step 4: Combine the model prediction results with the preset thresholds for logical comparison and strategy formulation; Step 5: According to the control strategy provided by the threshold comparison and strategy generation module, the position and angle of the sun visor are automatically adjusted to actually perform the adjustment operation of the sun visor system; Step 6: Monitor the effectiveness of the shading system and collect indoor light and temperature data after implementation, compare them with the expected targets, and adjust the prediction model and thresholds to optimize performance.

Images