Green building carbon emission monitoring system

Abstract

The invention relates to a green building carbon emission monitoring system. The system is characterized in that a specific monitoring method comprises the following steps: obtaining previous building construction carbon emission activity data and a corresponding carbon emission statistical table; a building construction carbon emission deep learning prediction model based on the recurrent neural network is constructed; training the model by adopting the preprocessed previous building construction carbon emission activity data and the corresponding carbon emission statistical table; acquiring real-time building construction carbon emission activity data, and performing preprocessing to obtain to-be-predicted basic data; inputting to-be-predicted basic data into the trained model, and outputting to obtain a required carbon emission statistical table; and carrying out privacy security processing on the required carbon emission statistical table, and sending the processed carbon emission statistical table to a corresponding control center. According to the method, the deep learning model is utilized, carbon emission modes of different building constructions can be automatically learned and adapted, higher precision and timeliness are realized, and meanwhile, the privacy security of data is ensured by adopting privacy protection measures.

Description

Technical Field

[0001] The present invention relates to the technical field of green buildings, and in particular to a green building carbon emission monitoring system. Background Art

[0002] Construction refers to the production activities during the implementation stage of engineering construction. It is the construction process of various buildings. It can also be said to be the process of turning various lines on the design drawings into physical objects at designated locations.

[0003] At present, a carbon emission monitoring system is installed in the construction site to detect carbon emission data in real time. When the current data is displayed, a display device is needed for auxiliary operation. When the current display device is installed on the construction site, due to the heavy dust at the construction site, a large amount of dust will be absorbed on the surface of the display device. The accumulation of dust will make it difficult to clearly view the data inside the display device. The current carbon emission monitoring and management of construction generally faces the following problems: 1. Incomplete and untimely data collection: Traditional carbon emission monitoring methods mainly rely on regular manual monitoring and reporting, which often have problems such as delayed data, incomplete data and low accuracy. Due to the lack of real-time monitoring data, it is impossible to identify and respond to sudden carbon emission events in a timely manner.

[0004] 2. Lack of multi-dimensional comprehensive assessment: The impact of carbon emissions is not only reflected in the amount of emissions, but also involves comprehensive changes in environmental quality. However, current monitoring methods usually only focus on a single emission source or a single pollutant, lacking a comprehensive assessment method for multiple pollutants and different emission sources, and cannot fully reflect the actual impact of carbon emissions on regional environmental quality.

[0005] 3. Insufficient intelligence: Most existing carbon emission monitoring systems rely on manual analysis and decision-making, lack intelligent means, and are difficult to dynamically adjust and optimize management based on real-time data. However, with the development of big data and artificial intelligence technology, the use of intelligent means to accurately monitor and manage carbon emissions has become an inevitable trend. Summary of the invention

[0006] The technical problem to be solved by the present invention is to provide a green building carbon emission monitoring system, which aims to overcome the limitations of traditional methods and provide a more accurate, real-time, privacy-safe and adaptable carbon emission monitoring solution.

[0007] In order to solve the above technical problems, the technical solution of the present invention is: a green building carbon emission monitoring system, the innovation of which is: the specific monitoring system is as follows: S1. Obtain previous building carbon emission activity data and corresponding carbon emission statistics, and perform pre-processing including cleaning, standardization and time series on the collected data. The carbon emission statistics include building construction information and carbon emission statistics corresponding to the building construction information. The carbon emission statistics include several time periods and the carbon emissions corresponding to each time period. S2. Construct a deep learning prediction model for carbon emissions from construction based on recurrent neural networks; S3. Use the pre-processed previous construction carbon emission activity data and the corresponding carbon emission statistics table to train the construction carbon emission deep learning prediction model. The input of the model is the construction carbon emission activity data, and the output is the carbon emission statistics table. The final trained model parameters are saved. S4. Obtain real-time construction carbon emission activity data, and perform data cleaning, standardization and time series processing to obtain basic data to be predicted; S5. Input the basic data to be predicted into the trained deep learning prediction model for construction carbon emissions, and output the required carbon emissions statistics table; S6. Perform privacy and security processing on the required carbon emission statistics, including data desensitization, encryption and access control processing; S7. For the dissemination of construction carbon emission information, the corresponding carbon emission statistical data is sent to the corresponding management center according to the construction data in the required carbon emission statistical table.

[0008] Furthermore, in step S1, the construction carbon emission activity data includes construction equipment information, energy usage data, traffic data, waste management data, material usage data, meteorological data, and time series data.

[0009] Furthermore, in step S2, a long short-term memory network is used as a recurrent neural network architecture, and the recurrent neural network architecture includes an input layer, an LSTM layer, and an output layer.

[0010] Furthermore, step S3 specifically includes the following steps: S31, dividing the pre-processed previous construction carbon emission activity data into a training set and a validation set; S32. Using the training set to train the deep learning prediction model for carbon emissions from construction; S33. Based on the mean square error, the validation set is used to evaluate the performance of the deep learning prediction model for carbon emissions from construction; S34. Adjust the hyperparameters of the deep learning prediction model for construction carbon emissions based on the evaluation results; S35. Save the parameters of the deep learning prediction model for construction carbon emissions.

[0011] Furthermore, in step S5, the carbon emission statistics table finally obtained is stored locally and in the cloud.

[0012] Furthermore, in step S5, the real-time basic data to be predicted that has been used to generate the carbon emission statistical table is marked as processed.

[0013] Furthermore, in step S6, data desensitization processing includes field replacement, character masking, generalization and data disturbance processing.

[0014] The advantages of the present invention are: 1) The present invention introduces a monitoring method based on deep learning, which can automatically learn and adapt to the carbon emission patterns of different construction projects. Compared with traditional methods, this method provides higher monitoring accuracy and can more accurately predict the carbon emissions of construction projects, which helps decision makers to formulate emission reduction strategies and evaluate their effects more scientifically. By using a deep learning model, this patent enables real-time monitoring of carbon emissions from construction projects, reducing the lag of monitoring results, which is crucial for timely response to carbon emission events and implementation of emergency measures, and helps to minimize carbon emissions. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] The present invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0016] Figure 1 The present invention is a method flow chart of a green building carbon emission monitoring system.

[0017] Figure 2 This is a training flow chart of a green building carbon emission deep learning prediction model of the present invention. DETAILED DESCRIPTION

[0018] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings here can be arranged and designed in various different configurations.

[0019] Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the invention claimed for protection, but merely represents selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0020] like Figure 1A green building carbon emission monitoring system is shown, and the specific monitoring system is as follows: S1. Obtain previous building carbon emission activity data and corresponding carbon emission statistics, and perform pre-processing including cleaning, standardization and time series on the collected data. The carbon emission statistics include building construction information and carbon emission statistics corresponding to the building construction information. The carbon emission statistics include several time periods and the carbon emissions corresponding to each time period. S2. Construct a deep learning prediction model for carbon emissions from construction based on recurrent neural networks; S3. Use the pre-processed previous construction carbon emission activity data and the corresponding carbon emission statistics table to train the construction carbon emission deep learning prediction model. The input of the model is the construction carbon emission activity data, and the output is the carbon emission statistics table. The final trained model parameters are saved. S4. Obtain real-time construction carbon emission activity data, and perform data cleaning, standardization and time series processing to obtain basic data to be predicted; S5. Input the basic data to be predicted into the trained deep learning prediction model for construction carbon emissions, and output the required carbon emissions statistics table; S6. Perform privacy and security processing on the required carbon emission statistics, including data desensitization, encryption and access control processing; S7. For the dissemination of construction carbon emission information, the corresponding carbon emission statistical data is sent to the corresponding management center according to the construction data in the required carbon emission statistical table.

[0021] In step S1, the construction carbon emission activity data includes construction equipment information, energy usage data, traffic data, waste management data, material usage data, meteorological data, and time series data.

[0022] In S2, a long short-term memory network is used as the recurrent neural network architecture, which includes an input layer, an LSTM layer, and an output layer.

[0023] Step S3 specifically includes the following steps: S31, dividing the pre-processed previous construction carbon emission activity data into a training set and a validation set; S32. Using the training set to train the deep learning prediction model for carbon emissions from construction; S33. Based on the mean square error, the validation set is used to evaluate the performance of the deep learning prediction model for carbon emissions from construction; S34. Adjust the hyperparameters of the deep learning prediction model for construction carbon emissions based on the evaluation results; S35. Save the parameters of the deep learning prediction model for construction carbon emissions.

[0024] In step S5, the final carbon emission statistics table is stored locally and in the cloud.

[0025] Furthermore, in step S5, the real-time basic data to be predicted that has been used to generate the carbon emission statistical table is marked as processed.

[0026] In step S6, data desensitization processing includes field replacement, character masking, generalization and data disturbance processing.

[0027] Those skilled in the art should understand that the present invention is not limited to the above-mentioned embodiments. The above-mentioned embodiments and descriptions are only for explaining the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention may be subject to various changes and improvements, and these changes and improvements shall all fall within the scope of the present invention claimed for protection.

Claims

1. A green building carbon emission monitoring system, characterized by: The specific monitoring system is as follows: S1. Obtain previous building carbon emission activity data and corresponding carbon emission statistics, and perform pre-processing including cleaning, standardization and time series on the collected data. The carbon emission statistics include building construction information and carbon emission statistics corresponding to the building construction information. The carbon emission statistics include several time periods and the carbon emissions corresponding to each time period. S2. Construct a deep learning prediction model for carbon emissions from construction based on recurrent neural networks; S3. Use the pre-processed previous construction carbon emission activity data and the corresponding carbon emission statistics table to train the construction carbon emission deep learning prediction model. The input of the model is the construction carbon emission activity data, and the output is the carbon emission statistics table. The final trained model parameters are saved. S4. Obtain real-time construction carbon emission activity data, and perform data cleaning, standardization and time series processing to obtain basic data to be predicted; S5. Input the basic data to be predicted into the trained deep learning prediction model for construction carbon emissions, and output the required carbon emissions statistics table; S6. Perform privacy and security processing on the required carbon emission statistics, including data desensitization, encryption and access control processing; S7. For the dissemination of construction carbon emission information, the corresponding carbon emission statistical data is sent to the corresponding management center according to the construction data in the required carbon emission statistical table.

2. A green building carbon emission monitoring system according to claim 1, characterized in that: In step S1, the construction carbon emission activity data includes construction equipment information, energy usage data, traffic data, waste management data, material usage data, meteorological data, and time series data.

3. A green building carbon emission monitoring system according to claim 1, characterized in that: In step S2, a long short-term memory network is used as a recurrent neural network architecture, and the recurrent neural network architecture includes an input layer, an LSTM layer, and an output layer.

4. A green building carbon emission monitoring system according to claim 3, characterized in that: Step S3 specifically includes the following steps: S31, dividing the pre-processed previous construction carbon emission activity data into a training set and a validation set; S32. Using the training set to train the deep learning prediction model for carbon emissions from construction; S33. Based on the mean square error, the validation set is used to evaluate the performance of the deep learning prediction model for carbon emissions from construction; S34. Adjust the hyperparameters of the deep learning prediction model for construction carbon emissions based on the evaluation results; S35. Save the parameters of the deep learning prediction model for construction carbon emissions.

5. A green building carbon emission monitoring system according to claim 4, characterized in that: In step S5, the final carbon emission statistics table is stored locally and in the cloud.

6. A green building carbon emission monitoring system according to claim 4, characterized in that: In step S5, the real-time basic data to be predicted that has been used to generate the carbon emission statistical table is marked as processed.

7. A green building carbon emission monitoring system according to claim 1, characterized in that: In step S6, data desensitization processing includes field replacement, character masking, generalization and data disturbance processing.

Images