Broadcasting and television building air conditioning system control method based on spatio-temporal model predictive control

Abstract

The invention discloses a broadcast and television building air conditioning system control method based on spatio-temporal model predictive control. The method comprises the following steps that 1, environment parameter data such as temperature, humidity and air quality of multiple positions in a broadcast and television building at different time points are collected; 2, a spatio-temporal model is constructed through the data fusion technology; 3, according to the historical environment data and the air conditioner operation data, a prediction model capable of predicting the future environment state is trained through machine learning, and the optimal operation parameter combination of the air conditioner system for achieving the target is calculated; and a prediction control algorithm is adopted to automatically regulate and control the operation state of the building air-conditioning system unit. According to the method, the indoor environment parameter change trend and the energy consumption demand of the air conditioning system in a period of time in the future are accurately predicted, so that the air conditioning system is optimally controlled, and the problems of energy waste and unstable indoor environment quality in the prior art are solved.

Description

Technical Field

[0001] This invention relates to the field of intelligent control technology for building air conditioning systems, and in particular to a control method for broadcast building air conditioning systems based on spatiotemporal model predictive control, which aims to improve the energy efficiency of air conditioning systems and the comfort of indoor environments. Background Technology

[0002] With the development of modern smart buildings and the increasing demands for indoor environmental comfort, the energy consumption of building air conditioning systems accounts for a growing proportion of total building energy consumption. Traditional building air conditioning system control methods are mainly based on simple feedback control, which cannot accurately predict future environmental changes and energy demands. This leads to frequent start-ups and shutdowns of the air conditioning system, making it difficult to adapt to complex indoor and outdoor environmental changes and diverse user needs, resulting in energy waste and unstable indoor environmental quality. Furthermore, the differences in occupant flow and outdoor climate across different areas and time periods make it difficult for traditional control methods to achieve personalized and precise control. Therefore, a more intelligent and efficient building air conditioning system control method is needed to achieve the goals of energy conservation, emission reduction, and improved indoor environmental comfort. Summary of the Invention

[0003] The purpose of this invention is to provide a control method for air conditioning systems in broadcasting buildings based on spatiotemporal model predictive control. By establishing a spatiotemporal model of the broadcasting building and accurately predicting the changing trends of indoor environmental parameters and the energy consumption demand of the air conditioning system in the future, the invention achieves optimized control of the air conditioning system, improves energy utilization efficiency and indoor environmental comfort, and solves the problems of energy waste and unstable indoor environmental quality in the prior art.

[0004] To achieve the above objectives, the technical solution of the present invention is as follows:

[0005] This invention provides a control method for a broadcasting building air conditioning system based on spatiotemporal model predictive control. The method includes the following steps: acquiring environmental parameter data at multiple locations within the broadcasting building at different time points using acquisition equipment. The environmental parameters include at least temperature, humidity, and air quality data, as well as personnel distribution density data at different spatial and temporal locations; constructing a spatiotemporal model using data fusion technology, linking the broadcasting building environmental parameter data (including personnel distribution density data) with the building's spatial location and temporal information to form an environmental state model with spatiotemporal dimensions, wherein the building space is divided into multiple three-dimensional grid units, and each unit is assigned a corresponding time-series environmental data attribute; training a predictive model capable of predicting future environmental states through machine learning based on historical environmental data and air conditioning system operation data, and calculating the optimal combination of air conditioning system operating parameters to achieve a given future time period and a preset environmental comfort target, including cooling / heating power, air volume, air purification mode, and operating time interval; and automatically adjusting the operating state of the building air conditioning system units using a predictive control algorithm and a rolling optimization strategy according to the calculated optimal combination of air conditioning operating parameters.

[0006] The monitoring equipment uses local area network communication technology to transmit the collected data to the building air conditioning chiller intelligent control system in real time, and the collection frequency is set between every 30 minutes and every hour according to actual needs and system performance.

[0007] The data fusion technology includes calibration and fusion processing of data from different types of sensors to eliminate data errors and inconsistencies. The calibration error range for temperature data is controlled within ±3℃, and the calibration error range for humidity data is controlled within ±5%rh.

[0008] The spatiotemporal environmental state model adopts a three-dimensional geographic information system (GIS) modeling method to accurately map the physical structure and spatial layout of buildings into the spatiotemporal model, and the spatial resolution of each three-dimensional grid unit is no more than 15 cubic meters.

[0009] The machine learning training uses a deep neural network algorithm. The training dataset covers environmental data and air conditioning system operation data from at least the past 30 days. Cross-validation is used during training to ensure the accuracy and generalization ability of the model. The model prediction accuracy is no less than 90% on the validation set.

[0010] In the calculation of the optimal combination of operating parameters for the air conditioning system, outdoor environmental factors such as outdoor temperature, humidity, wind speed and solar radiation intensity are also considered. By establishing a correlation model with the outdoor environment, the air conditioning system operation strategy is adjusted in real time to reduce energy consumption. Under the same environmental comfort conditions, the energy saving is no less than 25% compared with the traditional control method.

[0011] The pre-defined future time period and preset environmental target parameters can be dynamically adjusted according to different scenario requirements. For example, during office hours, the temperature range of 24℃ to 27℃ and the humidity range of 45%rh to 65%rh can be set to meet human comfort.

[0012] The predictive control algorithm adopts a rolling optimization strategy. During the operation of the air conditioning system, it continuously monitors and evaluates the deviation between the actual environmental state and the predicted environmental state. When the deviation exceeds a preset threshold, it automatically triggers the model retraining and parameter optimization mechanism to ensure the accuracy and stability of the control. The deviation threshold is set to a temperature not exceeding ±2℃ and a humidity not exceeding ±5%rh.

[0013] The control method also includes establishing a remote monitoring and management platform. This platform can receive environmental state model data, prediction model data, and air conditioning system operation data, and can remotely adjust and optimize the control parameters of the air conditioning system. It also has a fault alarm function, which can promptly send alarm information to the management personnel and provide preliminary fault diagnosis suggestions when the air conditioning system malfunctions or operates abnormally.

[0014] The beneficial effects achieved by the embodiments of the present invention are as follows: This method can improve energy utilization efficiency by predicting future indoor environmental parameters and air conditioning system energy consumption, thereby achieving optimized control of the air conditioning system, reducing energy waste, and lowering operating costs; it can improve indoor environmental comfort by adjusting the operating parameters of the air conditioning system in real time according to user needs and changes in the indoor and outdoor environment, maintaining a stable and comfortable indoor environment; it can enhance the reliability and stability of the system by timely detecting and resolving system faults through real-time monitoring and control; and it has good adaptability and scalability, allowing for personalized configuration and adjustment according to different building structures and user needs, adapting to different application scenarios. Attached Figure Description

[0015] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying 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.

[0016] Figure 1 This is a flowchart illustrating a control method for a broadcast building air conditioning system based on spatiotemporal model predictive control according to the present invention. Detailed Implementation

[0017] 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 a part of the embodiments of the present invention, and not all of them. 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.

[0018] Please see Figure 1 As shown, the present invention also provides a flowchart of a control method for a broadcasting building air conditioning system based on spatiotemporal model predictive control, including steps 1, 2, 3, and 4, wherein...

[0019] Step 1: Collect environmental parameter data at multiple locations within the broadcasting building at different times. The environmental parameters include at least temperature, humidity, and air quality data, as well as personnel distribution density data at different spaces and times. Temperature, humidity, and air quality data are mainly collected using sensors, while personnel distribution density data are mainly collected based on the activity distribution of office staff in the building.

[0020] Step 2: Use data fusion technology to construct a spatiotemporal model, and associate the environmental parameter data and personnel distribution density data of the broadcasting building with the spatial location information and time information of the building to form an environmental state model with spatiotemporal dimensions.

[0021] Step 3: Based on historical environmental data and air conditioning system operation data, a predictive model that can predict future environmental conditions is trained through machine learning. This model, combined with a spatiotemporal model, can calculate the optimal combination of air conditioning system operating parameters to achieve a given future time period and a preset environmental comfort target.

[0022] Step 4: Based on the calculated optimal combination of operating parameters for the building air conditioning system, a predictive control algorithm and a rolling optimization strategy are used to automatically adjust the operating status of the building air conditioning system unit.

[0023] Compared with related technologies, the control method for air conditioning systems in broadcasting buildings based on spatiotemporal model predictive control provided by this invention has the following advantages: by optimizing the control of air conditioning systems in broadcasting buildings using this method, energy utilization efficiency and indoor environmental comfort can be improved, solving the problems of energy waste and unstable indoor environmental quality in existing technologies.

[0024] Although embodiments of the present invention have been disclosed above, they are not limited to the applications listed in the specification and embodiments. They can be applied to various fields suitable for the present invention. Other modifications can be easily made by those skilled in the art. Therefore, without departing from the general concept defined by the claims and their equivalents, the present invention is not limited to the specific details and the illustrations shown and described herein.

Claims

1. A control method for a broadcasting building air conditioning system based on spatiotemporal model predictive control, characterized in that, Includes the following steps: Environmental parameter data at different times for multiple spatial locations within the broadcasting building are acquired using data acquisition equipment. These environmental parameters include at least temperature, humidity, and air quality data, as well as personnel distribution density data at different spatial and temporal locations. A spatiotemporal model is constructed using data fusion technology, linking the broadcasting building's environmental parameter data (including personnel distribution density data) with the building's spatial location and temporal information to form a spatiotemporal environmental state model. This model divides the building space into multiple three-dimensional grid units, assigning each unit corresponding time-series environmental data attributes. Based on historical environmental data and air conditioning system operation data, a predictive model capable of predicting future environmental states is trained using machine learning. This model, combined with the spatiotemporal model, can calculate the optimal combination of air conditioning system operating parameters to achieve a given future time period and a preset environmental comfort target, including cooling / heating power, air volume, air purification mode, and operating time interval. Based on the calculated optimal combination of air conditioning operating parameters for the broadcasting building, a predictive control algorithm is used to automatically adjust the operating status of the building's air conditioning system units.

2. The control method for a broadcasting building air conditioning system based on spatiotemporal model predictive control according to claim 1, characterized in that, The monitoring equipment uses local area network communication technology to transmit the collected data to the building air conditioning chiller intelligent control system in real time, and the collection frequency is set between every 30 minutes and every hour according to actual needs and system performance.

3. The control method for a broadcasting building air conditioning system based on spatiotemporal model predictive control according to claim 1, characterized in that, The data fusion technology includes calibration and fusion processing of data from different types of sensors to eliminate data errors and inconsistencies. The calibration error range for temperature data is controlled within ±3℃, and the calibration error range for humidity data is controlled within ±5%rh.

4. The control method for a broadcasting building air conditioning system based on spatiotemporal model predictive control according to claim 1, characterized in that, The spatiotemporal environmental state model adopts a three-dimensional geographic information system (GIS) modeling method to accurately map the physical structure and spatial layout of buildings into the spatiotemporal model, and the spatial resolution of each three-dimensional grid unit is no more than 15 cubic meters.

5. The building air conditioning system control method based on spatiotemporal model predictive control according to claim 1, characterized in that, The machine learning training uses a deep neural network algorithm. The training dataset covers environmental data and air conditioning system operation data from at least the past 30 days. Cross-validation is used during training to ensure the accuracy and generalization ability of the model. The model prediction accuracy is no less than 90% on the validation set.

6. The control method for a broadcasting building air conditioning system based on spatiotemporal model predictive control according to claim 1, characterized in that, In the calculation of the optimal combination of operating parameters for the air conditioning system, outdoor environmental factors such as outdoor temperature, humidity, wind speed and solar radiation intensity are also considered. By establishing a correlation model with the outdoor environment, the air conditioning system operation strategy is adjusted in real time to reduce energy consumption. Under the same environmental comfort conditions, the energy saving is no less than 25% compared with the traditional control method.

7. The control method for a broadcasting building air conditioning system based on spatiotemporal model predictive control according to claim 1, characterized in that, The pre-defined future time period and preset environmental target parameters can be dynamically adjusted according to different scenario requirements. For example, during office hours, the temperature range of 24℃ to 27℃ and the humidity range of 45%rh to 65%rh can be set to meet human comfort.

8. The building air conditioning system control method based on spatiotemporal model predictive control according to claim 1, characterized in that, The predictive control algorithm continuously monitors and evaluates the deviation between the actual environmental state and the predicted environmental state during the operation of the air conditioning system. When the deviation exceeds a preset threshold, it automatically triggers the model retraining and parameter optimization mechanism to ensure the accuracy and stability of the control. The deviation threshold is set to a temperature not exceeding ±2℃ and a humidity not exceeding ±5%rh.

9. The building air conditioning system control method based on spatiotemporal model predictive control according to claim 1, characterized in that, It also includes establishing a remote monitoring and management platform that can receive environmental status model data, prediction model data, and air conditioning system operation data. It can remotely adjust and optimize the control parameters of the air conditioning system and has a fault alarm function. When the air conditioning system malfunctions or operates abnormally, it can promptly send alarm information to the management personnel and provide preliminary suggestions for fault diagnosis.

Images