Building indoor thermal comfort optimization method and system based on machine learning

Abstract

The invention relates to a method and a system for optimizing indoor thermal comfort of a building based on machine learning, and the method for optimizing the indoor thermal comfort of the building based on machine learning is used for maintaining the indoor thermal comfort of the building in cooperation with indoor temperature control equipment of the building. Comprising the following steps: S1, establishing a BIM three-dimensional information model of a building indoor structure; s2, acquiring indoor environment data of the building by using a sensor, and constructing a digital twin platform in combination with the BIM three-dimensional information model; s3, preprocessing the acquired indoor environment data by using a digital twin platform; according to the method, the indoor environment data of the building is analyzed and predicted by the machine learning technology after being preprocessed, the indoor future environment conditions of the building are accurately predicted, the adjustment data of the indoor temperature control equipment of the building in the future time period are obtained, and therefore the purpose of rapidly and accurately adjusting the thermal comfort degree in each time period is achieved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent management technology, and in particular to a method and system for optimizing indoor thermal comfort of a building based on machine learning. Background Art

[0002] With the advancement of construction technology, digital twin and building information modeling technologies are widely used in the design, construction and operation stages of buildings.

[0003] However, current technologies have some shortcomings in real-time monitoring and optimization of thermal comfort in buildings. The main problem is that real-time data is easily affected by the network or sensor failure, resulting in errors, which leads to low accuracy and efficiency of thermal comfort adjustment, affecting users' thermal comfort experience. Summary of the invention

[0004] The purpose of the present invention is to overcome the defects of the prior art and provide a method and system for optimizing indoor thermal comfort of buildings based on machine learning, so as to solve the problems of low accuracy and efficiency of indoor thermal comfort control of buildings in the prior art.

[0005] To achieve the above object, the present invention provides a method for optimizing indoor thermal comfort of a building based on machine learning, which is used to cooperate with indoor temperature control equipment of the building to maintain indoor thermal comfort of the building, and is characterized in that it includes the following steps:

[0006] S1. Establish a BIM three-dimensional information model of the building's interior structure;

[0007] S2. Use sensors to obtain indoor environmental data of buildings and build a digital twin platform in combination with the BIM three-dimensional information model;

[0008] S3. Use the digital twin platform to pre-process the acquired indoor environment data;

[0009] S4. Use machine learning technology to analyze the pre-processed indoor environment data and predict future data;

[0010] S5. Automatically adjust the settings of temperature control equipment according to the building's indoor environmental data and predicted data results to maintain thermal comfort indoors in the building.

[0011] By adopting this technical solution, the building's indoor BIM three-dimensional information model and environmental data are combined on the digital twin platform. After preprocessing to obtain accurate data, machine learning technology is used for analysis and prediction. The predicted data is generated as a basis for future adjustment of temperature control equipment, so that the corresponding temperature control equipment can be directly adjusted in subsequent time periods to complete the accurate and rapid adjustment of the building's indoor thermal comfort.

[0012] Furthermore, the specific process of step S1 is as follows:

[0013] Laser scanning is performed on the interior of the building to obtain laser scanning data, and a BIM three-dimensional information model of the building's interior structure is established based on the laser scanning data.

[0014] Furthermore, the specific process of step S2 is as follows:

[0015] Use IoT sensors to collect indoor environmental data of buildings, and use Autodesk Forge API to integrate and associate the indoor environmental data of buildings collected by IoT sensors with the BIM three-dimensional information model, and then build a digital twin platform based on these data.

[0016] Furthermore, the specific process of step S3 is as follows:

[0017] The digital twin platform cleans the acquired indoor environment data and uses interpolation methods to fill in the data missing due to network instability or sensor failure.

[0018] Furthermore, the specific process of step S4 is as follows:

[0019] Use machine learning technology to analyze the preprocessed indoor environmental data, apply time series analysis and prediction algorithms to calculate thermal comfort indicators, and identify the correlation and relationship between data points through statistical analysis and model training to predict future data.

[0020] The present invention also provides a building indoor thermal comfort optimization system based on machine learning, using the building indoor thermal comfort optimization method based on machine learning, including interconnected BIM modeling modules, sensor modules, cloud databases, digital twin platforms, data preprocessing modules, data analysis modules and execution adjustment modules;

[0021] The BIM modeling module is used to establish a BIM three-dimensional information model of the building interior;

[0022] The sensor module includes an IoT sensor for acquiring indoor environment data of a building;

[0023] The cloud database is used to store data, including BIM three-dimensional information model data and building indoor environment data;

[0024] The digital twin platform is used to process and display indoor 3D models of buildings and IoT sensor data;

[0025] The data preprocessing module is used to preprocess the building indoor environment data;

[0026] The data analysis module is used to analyze the pre-processed building indoor environment data;

[0027] The execution adjustment module is used to adjust the indoor temperature control equipment of the building according to the analysis results of the data analysis module.

[0028] Furthermore, it also includes a laser scanning module for scanning and acquiring indoor data of the building to send the data to the BIM modeling module for establishing a BIM three-dimensional information model of the indoor building.

[0029] Furthermore, it also includes a data integration module for integrating and associating the building indoor environment data collected by the IoT sensor with the BIM three-dimensional information model.

[0030] Furthermore, the data preprocessing module is used to process missing values ​​and abnormal values ​​of the building indoor environment data.

[0031] Furthermore, the data analysis module analyzes the pre-processed building indoor environment data based on machine learning technology.

[0032] Compared with the prior art, the present invention has the following beneficial effects:

[0033] 1. After preprocessing, the indoor environmental data of the building is analyzed and predicted by machine learning technology to accurately predict the future environmental conditions of the building's indoor environment, so as to obtain the adjustment data of the building's indoor temperature control equipment in the future period, so as to achieve the purpose of rapid and accurate adjustment of thermal comfort in each period; 2. Automatically adjust the temperature control equipment to reduce manual intervention and provide a seamless remote control experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 Schematic diagram of the steps of the method for optimizing indoor thermal comfort of a building based on machine learning in the present invention. DETAILED DESCRIPTION

[0035] The present invention will be further described below in conjunction with the accompanying drawings and specific embodiments.

[0036] The present invention provides a method for optimizing indoor thermal comfort of a building based on machine learning, which is used to cooperate with indoor temperature control equipment of the building to maintain indoor thermal comfort of the building, and comprises the following steps: S1, performing laser scanning on the indoor of the building to obtain laser scanning data, and establishing a BIM three-dimensional information model of the indoor structure of the building according to the laser scanning data; S2, using an IoT sensor to collect indoor environmental data of the building, and using an Autodesk Forge API to integrate and associate the indoor environmental data of the building collected by the IoT sensor with the BIM three-dimensional information model, and then building a digital twin platform based on these data; S3, the digital twin platform cleans the acquired indoor environmental data, and uses an interpolation method to fill in the data missing caused by network instability or sensor failure; S4, using machine learning technology to analyze the pre-processed indoor environmental data, applying time series analysis and prediction algorithms to calculate thermal comfort indicators, and identifying the correlation and relationship between data points through statistical analysis and model training, and predicting future data; S5, automatically adjusting the settings of the temperature control equipment according to the indoor environmental data of the building and the prediction data results to maintain the indoor thermal comfort of the building.

[0037] The present invention also provides a building indoor thermal comfort optimization system based on machine learning, using the building indoor thermal comfort optimization method based on machine learning, including interconnected BIM modeling modules, sensor modules, cloud databases, digital twin platforms, data preprocessing modules, data analysis modules and execution adjustment modules; the BIM modeling module is used to establish a BIM three-dimensional information model of the building indoors; the sensor module includes an IoT sensor for acquiring indoor environmental data of the building; the cloud database is used to store data, including BIM three-dimensional information model data and indoor environmental data of the building; the digital twin platform is used to process and display indoor 3D models of buildings and IoT sensor data; the data preprocessing module is used to preprocess the indoor environmental data of the building; the data analysis module is used to analyze the preprocessed indoor environmental data of the building; the execution adjustment module is used to adjust the indoor temperature control equipment of the building according to the analysis results of the data analysis module;

[0038] Furthermore, it also includes a laser scanning module for scanning and acquiring indoor data of the building to send to the BIM modeling module for establishing a BIM three-dimensional information model of the indoor building;

[0039] Furthermore, it also includes a data integration module for integrating and associating the building indoor environment data collected by the IoT sensor with the BIM three-dimensional information model;

[0040] Furthermore, the data preprocessing module is used to process missing values ​​and abnormal values ​​of the building indoor environment data;

[0041] Furthermore, the data analysis module analyzes the pre-processed building indoor environment data based on machine learning technology.

[0042] In order to meet the user's preferred thermal comfort needs, an AC unit is also included for users to adjust their comfort level independently to ensure that the performance of the temperature control equipment is consistent with actual needs.

[0043] The present invention is described in detail above in conjunction with the embodiments of the accompanying drawings. A person skilled in the art can make various variations of the present invention according to the above description. Therefore, certain details in the embodiments should not constitute a limitation of the present invention, and the scope of protection of the present invention shall be defined by the scope of the attached claims.

Claims

1. A method for optimizing indoor thermal comfort of a building based on machine learning, used to cooperate with indoor temperature control equipment of a building to maintain indoor thermal comfort of the building, characterized in that: The steps include: S1. Establish a BIM three-dimensional information model of the building's interior structure; S2. Use sensors to obtain indoor environmental data of buildings and build a digital twin platform in combination with the BIM three-dimensional information model; S3. Use the digital twin platform to pre-process the acquired indoor environment data; S4. Use machine learning technology to analyze the pre-processed indoor environment data and predict future data; S5. Automatically adjust the settings of temperature control equipment according to the building's indoor environmental data and predicted data results to maintain thermal comfort indoors in the building.

2. The method for optimizing indoor thermal comfort of a building based on machine learning according to claim 1, characterized in that: The specific process of step S1 is as follows: Laser scanning is performed on the interior of the building to obtain laser scanning data, and a BIM three-dimensional information model of the building's interior structure is established based on the laser scanning data.

3. The method for optimizing indoor thermal comfort of a building based on machine learning according to claim 1, characterized in that: The specific process of step S2 is as follows: Use IoT sensors to collect indoor environmental data of buildings, and use Autodesk Forge API to integrate and associate the indoor environmental data of buildings collected by IoT sensors with the BIM three-dimensional information model, and then build a digital twin platform based on these data.

4. The method for optimizing indoor thermal comfort of a building based on machine learning according to claim 1, characterized in that: The specific process of step S3 is as follows: The digital twin platform cleans the acquired indoor environment data and uses interpolation methods to fill in the data missing due to network instability or sensor failure.

5. The method for optimizing indoor thermal comfort of a building based on machine learning according to claim 1, characterized in that: The specific process of step S4 is as follows: Use machine learning technology to analyze the preprocessed indoor environmental data, apply time series analysis and prediction algorithms to calculate thermal comfort indicators, and identify the correlation and relationship between data points through statistical analysis and model training to predict future data.

6. A machine learning-based indoor thermal comfort optimization system for a building, using the machine learning-based indoor thermal comfort optimization method for a building as claimed in any one of claims 1 to 5, characterized in that: It includes interconnected BIM modeling modules, sensor modules, cloud databases, digital twin platforms, data preprocessing modules, data analysis modules, and execution adjustment modules; The BIM modeling module is used to establish a BIM three-dimensional information model of the building interior; The sensor module includes an IoT sensor for acquiring indoor environment data of a building; The cloud database is used to store data, including BIM three-dimensional information model data and building indoor environment data; The digital twin platform is used to process and display indoor 3D models of buildings and IoT sensor data; The data preprocessing module is used to preprocess the building indoor environment data; The data analysis module is used to analyze the pre-processed building indoor environment data; The execution adjustment module is used to adjust the indoor temperature control equipment of the building according to the analysis results of the data analysis module.

7. The method and system for optimizing indoor thermal comfort of a building based on machine learning according to claim 6, characterized in that: It also includes a laser scanning module for scanning and acquiring indoor data of the building to send the data to the BIM modeling module for establishing a BIM three-dimensional information model of the indoor building.

8. The method and system for optimizing indoor thermal comfort of a building based on machine learning according to claim 6, characterized in that: It also includes a data integration module for integrating and associating the building indoor environment data collected by the IoT sensor with the BIM three-dimensional information model.

9. The method and system for optimizing indoor thermal comfort of a building based on machine learning according to claim 6, characterized in that: The data preprocessing module is used to process missing values ​​and abnormal values ​​of building indoor environment data.

10. The method and system for optimizing indoor thermal comfort of a building based on machine learning according to claim 6, characterized in that: The data analysis module analyzes the preprocessed building indoor environment data based on machine learning technology.

Images