Subway station diaphragm wall construction carbon emission prediction method, equipment, medium and product

Abstract

The invention discloses a subway station diaphragm wall construction carbon emission prediction method and device, a medium and a product, and relates to the technical field of carbon emission prediction, and the method comprises the steps: obtaining a plurality of important parameter indexes of a subway station construction diaphragm wall construction scheme as a to-be-predicted important parameter index group; inputting the to-be-predicted important parameter index group into the total carbon emission prediction model to obtain the total carbon emission prediction quantity of the diaphragm wall construction scheme; the total carbon emission prediction model is obtained by training the BP neural network model by using a plurality of historical diaphragm wall construction schemes constructed by the subway station, and carbon emission generated in the diaphragm wall construction process constructed by the subway station can be predicted by constructing the total carbon emission prediction model.

Description

Technical Field

[0001] The present application relates to the technical field of carbon emission prediction, and in particular to a method, equipment, medium and product for predicting carbon emission during the construction of ground-anchored walls in subway stations. Background Art

[0002] Global warming has disrupted the balance of the earth's ecological environment, affecting human survival and social development, and has become a focus of attention. Industry, construction and transportation are currently the three major sources of carbon emissions, and urban rail transit systems have become the main development direction of urban transportation due to their more convenient and efficient characteristics. The scale of construction is constantly expanding, and the use of a large amount of energy-intensive materials such as concrete and steel and heavy construction equipment during its construction will generate a large amount of carbon emissions, and the environmental burden caused cannot be ignored.

[0003] Open-cut method is often used in the construction of subway stations. The setting of retaining structure is particularly important in the open-cut method. The construction of ground-anchored walls is the main process in the retaining structure, which uses a large amount of concrete, steel bars and other materials and heavy construction equipment, and will produce a large amount of carbon emissions. Therefore, it is of great significance to predict the carbon emissions generated by the construction process of ground-anchored walls, and provide ideas for carbon emission reduction in the construction process of subway stations. Summary of the invention

[0004] The purpose of this application is to provide a method, equipment, medium and product for predicting carbon emissions from the construction of ground-anchored walls in subway stations, which can predict the carbon emissions generated during the construction of ground-anchored walls in subway stations.

[0005] To achieve the above objectives, this application provides the following solutions:

[0006] In a first aspect, the present application provides a method for predicting carbon emissions from ground-anchored wall construction in a subway station, comprising:

[0007] A plurality of important parameter indicators of the ground-connected wall construction scheme of the subway station construction are obtained as the important parameter indicator group to be predicted;

[0008] The important parameter index group to be predicted is input into the total carbon emission prediction model to obtain the total carbon emission prediction of the ground-anchored wall construction scheme; the total carbon emission prediction model is obtained by training the BP neural network model using multiple historical ground-anchored wall construction schemes for subway station construction.

[0009] Optionally, after inputting the important parameter index group to be predicted into the total carbon emission prediction model to obtain the total carbon emission prediction of the ground-connected wall construction scheme, the method further includes:

[0010] Adjust the ground-anchored wall construction plan based on the total carbon emission forecast.

[0011] Optionally, before obtaining a plurality of important parameter indicators of the ground-connected wall construction scheme for the subway station construction as the important parameter indicator group to be predicted, the method further includes:

[0012] Obtain multiple historical diaphragm wall construction plans;

[0013] The carbon emission coefficient method is used to determine and calculate the total carbon emissions of each historical ground-connected wall construction plan as the historical total carbon emissions;

[0014] Use the correlation coefficient method to determine multiple important parameter indicators;

[0015] Obtain multiple important parameter indicators from each historical ground-connected wall construction plan to obtain multiple historical important parameter indicator groups;

[0016] The BP neural network model is trained with the historical important parameter indicator group as input and the historical total carbon emissions as output to obtain a total carbon emissions prediction model.

[0017] Optionally, the carbon emission coefficient method is:

[0018] C dlq =C jc +C jx +C ys +C rg ;

[0019] Among them, C dlq is the total carbon emissions, C jc is the carbon emissions from the use of building materials during the construction of the ground-connected wall, C jx is the carbon emissions generated by the use of machinery during the construction of the ground-connected wall, C ys is the carbon emissions generated by the transportation during the construction of the ground-connected wall, C rg Carbon emissions artificially generated during the construction of the ground-connected wall;

[0020]

[0021] Among them, n 1 is the total number of raw material types, For the i 1 The consumption of raw materials, To produce the i 1 Carbon emission factor of raw materials, E jg,j is the consumption of the jth energy in the raw material processing process, EF j is the carbon emission factor of the j-th energy source;

[0022]

[0023] in, For the i 2The consumption of the jth energy source of the machine;

[0024]

[0025] in, For the i 3 The total amount of transported substances, For the i 3 The transport distance of the substance, For the i 3 Carbon emission factors of the material transport modes;

[0026] C rg =n 2 oeLh rg ;

[0027] Among them, n 2 is the number of construction personnel, t is the construction time, EF rg is the artificial carbon emission factor.

[0028] In a second aspect, the present application provides a computer device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the above-mentioned method for predicting carbon emissions from ground-anchored wall construction in subway stations.

[0029] In a third aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the above-mentioned method for predicting carbon emissions from ground-anchored wall construction in subway stations.

[0030] In a fourth aspect, the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the above-mentioned method for predicting carbon emissions from ground-anchored wall construction in subway stations.

[0031] According to the specific embodiments provided in this application, this application discloses the following technical effects:

[0032] The present application provides a method, equipment, medium and product for predicting carbon emissions from ground-anchored wall construction at a subway station. According to the ground-anchored wall construction processes of a station in a subway construction project, the emission coefficient method is used to calculate the total carbon emissions from the construction of each ground-anchored wall. Subsequently, data cleaning is performed, and the input parameters are screened using the correlation coefficient, and standardization and normalization are performed. Important parameter indicators with large weights are selected to establish a data set of important parameter indicators for ground-anchored wall construction. The BP neural network model is trained using the data set of important parameter indicators for ground-anchored wall construction, with the selected important parameter indicators as input and the total carbon emissions of each ground-anchored wall as output. Finally, the trained BP neural network model is used to predict the carbon emissions from ground-anchored wall construction at the station of the subway construction project, and compared with the theoretical calculated value to verify the prediction accuracy of the BP model, providing a basis for energy conservation and emission reduction in subway station construction. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0034] Figure 1 This is a flow chart of a method for predicting carbon emissions from ground-connected wall construction in a subway station in one embodiment of the present application;

[0035] Figure 2 This is a schematic diagram of a method for predicting carbon emissions from ground-connected wall construction in a subway station in one embodiment of the present application;

[0036] Figure 3 This is a flow chart of a total carbon emission prediction model training method in one embodiment of the present application;

[0037] Figure 4 A schematic diagram of the structure of a computer device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0038] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0039] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below with reference to the accompanying drawings and specific implementation methods.

[0040] In an exemplary embodiment, Figure 1 As shown, a method for predicting carbon emissions from ground-anchored wall construction in a subway station is provided, comprising:

[0041] Step 101: obtaining a plurality of important parameter indicators of the ground-connected wall construction plan for the subway station construction as an important parameter indicator group to be predicted.

[0042] Step 102: Input the important parameter index group to be predicted into the total carbon emission prediction model to obtain the total carbon emission prediction of the ground-connected wall construction scheme. The total carbon emission prediction model is obtained by training the BP neural network model using multiple historical ground-connected wall construction schemes for subway station construction.

[0043] Step 103: Adjust the ground-connected wall construction plan based on the predicted total carbon emissions.

[0044] Before step 101, the method further includes:

[0045] Step 104: Obtain multiple historical ground-connected wall construction plans.

[0046] Step 105: Use the carbon emission coefficient method to determine and calculate the total carbon emissions of each historical ground-connected wall construction plan as the historical total carbon emissions.

[0047] Step 106: Determine multiple important parameter indicators using the correlation coefficient method.

[0048] Step 107: Obtain multiple important parameter indicators from each historical ground-connected wall construction plan to obtain multiple historical important parameter indicator groups.

[0049] Step 108: Using the historical important parameter indicator group as input and the historical total carbon emissions as output, the BP neural network model is trained to obtain a total carbon emissions prediction model.

[0050] Among them, the carbon emission coefficient method is:

[0051] C dlq =C jc +C jx +C ys +C rg .

[0052] Among them, C dlq is the total carbon emissions, C jc is the carbon emissions from the use of building materials during the construction of the ground-connected wall, C jx is the carbon emissions generated by the use of machinery during the construction of the ground-connected wall, C ys is the carbon emissions generated by the transportation during the construction of the ground-connected wall, C rg It is the carbon emissions artificially generated during the construction process of the ground-connected wall.

[0053]

[0054] Among them, n 1 is the total quantity of raw material types; For the i 1 The consumption of raw materials. To produce the i 1 The carbon emission factor of the raw material. jg,j EF is the consumption of the jth energy in the raw material processing process. j is the carbon emission factor of the j-th energy source.

[0055]

[0056] in, For the i 2 The consumption of the jth energy of a machine.

[0057]

[0058] in, For the i 3 The total amount of transported substances. For the i 3 The distance a substance is transported. For the i 3 Carbon emission factors of various modes of material transportation.

[0059] C rg =n 2 oeLh rg .

[0060] Among them, n 2 is the number of construction personnel. t is the construction duration. EF rg is the artificial carbon emission factor.

[0061] like Figure 2For subway construction projects, this application divides the carbon emissions from ground-anchored wall construction into four sources: building materials production, transportation, on-site construction, and manual carbon emissions, based on the construction processes of the ground-anchored wall in station construction. The carbon emission coefficient method is used to calculate the total carbon emissions from the construction of each ground-anchored wall. According to the nonlinear mapping relationship between the total carbon emissions and the construction parameters of the ground-anchored wall in subway station construction, the input parameters are screened and normalized using the correlation coefficient, and data cleaning is performed at the same time. The ground-anchored wall construction parameters include engineering parameters, engineering quantities, and material energy consumption during the construction process. A data set containing the total carbon emissions and important parameter indicators of the ground-anchored wall construction is established. The BP neural network model is trained using the data set, with the input of the model being the selected important parameter indicators, and the output being the total carbon emissions from the ground-anchored wall construction. The total carbon emissions from the ground-anchored wall construction of the station in the subway project are predicted using the trained BP neural network model, and the prediction accuracy is verified by comparing it with the theoretical calculated value.

[0062] The method for screening important parameter indicators includes: screening parameter indicators related to carbon emissions in the construction process of ground-anchored walls in subway station construction, namely engineering parameters, engineering quantities and material energy consumption in the construction process of ground-anchored walls, using correlation coefficients, performing standardization and normalization processing, and performing data cleaning at the same time to screen out important parameter indicators as input data. After standardization, the dimensional differences between different features are eliminated, so that each feature has the same numerical influence on the model.

[0063] The normalization formula is:

[0064]

[0065] In the formula, z is the standardized value. x is the original feature value. mean and std are the mean and standard deviation of the feature respectively.

[0066] The BP neural network model (BPNN, Back Propagation Neural Network) contains multiple linear layers and activation function ReLU. The input layer of the model has 6 nodes, corresponding to the selected important parameter indicators, and the output layer has 1 node, corresponding to the predicted result of the total carbon emissions of a ground-connected wall construction plan. The mean square error (MSE) is defined as the loss function for model training, and the parameters of the model are optimized using the Adam optimizer. The preprocessed training data is used to train the defined model, and the predicted value is obtained through forward propagation, and the loss between the predicted value and the true value is calculated. Then, back propagation is performed to calculate the gradient of the loss to the model parameters, and the optimizer is used to update the parameters of the model. A total of 200 rounds of model parameter training were performed above. After the training is completed, the model is set to evaluation mode to predict the test set. After the prediction results are processed, the mean square error (MSE), root mean square error (RMSE), mean absolute error (MAE) and goodness of fit (R 2 ) is used as the standard to evaluate the accuracy of the BP neural network prediction model. The BP neural network model training process is as follows Figure 3 shown.

[0067] Next, based on the actual construction carbon emission data of 132 ground-anchored walls during the construction of a certain Guangzhou Metro station, data standardization and data cleaning were carried out, and after BP neural network model training, a machine learning-based carbon emission prediction method for ground-anchored walls in subway station construction was formed.

[0068] According to the life cycle theory, the carbon emissions of ground-anchored wall construction in subway station construction are divided into four parts: building materials use, construction machinery use, transportation and labor carbon emissions. The carbon emissions of 132 ground-anchored walls are calculated using the carbon emission coefficient method. Through accounting and inspection, it is found that the main building materials that cause carbon emissions in the construction of ground-anchored walls in subway station construction are steel bars and concrete. The main large-scale machinery used are rotary drilling rigs, double-wheel milling machines and crawler cranes, all of which use diesel. The main transported materials are steel bars, concrete, and slag, all of which are transported by highway diesel trucks. Other influencing factors include the volume of the ground-anchored wall, the amount of slag, the number of construction workers and working days, and the transportation distance. The specific parameter indicators are shown in Table 1.

[0069] Table 1 Specific parameter index table

[0070] Energy and material usage Project Quantity Other parameter indicators Steel bar consumption (t) <![CDATA[Volume of muck (m 3 )]]> Steel bar transportation distance (km) <![CDATA[Concrete consumption (m 3 )]]> <![CDATA[Diaphragm wall volume (m 3 )]]> Concrete transportation distance (km) Diesel consumption (kg) Construction time (man-days) Distance of soil transportation (km)

[0071] The data is dimensionless processed to eliminate the dimensional differences between different features, so that each feature has the same influence on the model in terms of numerical value. At the same time, the data is cleaned. Since the transportation distances of steel bars, concrete and slag vary greatly among different projects and change due to different construction project addresses, the accuracy of the results predicted by the model is low. Therefore, this application does not select transportation distance as an important parameter indicator. Six parameter indicators, including steel bar usage, concrete usage, diesel consumption, ground-connected wall volume, slag generation and construction time, are selected as independent variables. The total carbon emissions of each ground-connected wall are used as the dependent variable to jointly construct a BP neural network prediction model. The main selected parameter indicators are shown in Table 2.

[0072] Table 2 Selected important parameter indicators

[0073] Energy and material usage Project Quantity Steel bar consumption (t) <![CDATA[Volume of muck (m 3 )]]> <![CDATA[Concrete consumption (m 3 )]]> <![CDATA[Diaphragm wall volume (m 3 )]]> Diesel consumption (kg) Construction time (man-days)

[0074] A total of 132 ground-connected wall data were selected, of which 70% were used to establish the model and 30% were used to verify the accuracy of the model. Some of the data sets are shown in Table 3.

[0075] Table 3 Carbon emission dataset of ground-connected wall

[0076]

[0077]

[0078] Subsequently, the data is brought into the BP neural network model for training. The BP neural network is mainly divided into several model training processes including forward propagation, loss calculation, back propagation, parameter update, and gradient clearing. Its mathematical principles are as follows:

[0079] x (l+1) =W l x l +b l .

[0080]

[0081] Among them, W l is the weight matrix of the lth layer, and the bias term is b l , the input is x l , the output is x (l+1) . For the i 4 True value, For the i 4 Predicted values; n 3 is the number of predicted values.

[0082] The BP neural network model training process is as follows Figure 3After the prediction results are processed, the mean square error (MSE), root mean square error (RMSE), mean absolute error (MAE) and goodness of fit (R 2 ) is used as the standard to evaluate the accuracy of the BP neural network prediction model.

[0083]

[0084] Among them, n 4 is the sample size, is the predicted value of carbon emissions, is the average carbon emission value. The evaluation results of the BP neural network prediction model are shown in Table 4.

[0085] Table 4 Model accuracy evaluation results

[0086] MSE RMSE MAE <![CDATA[R 2 ]]> 0.10004 0.31629 0.09762 0.86420

[0087] Among them, the smaller the MSE, RMSE and MAE values ​​are, the higher the model accuracy is. 2 The closer it is to 1, the higher the model accuracy. From Table 4, we can see that R 2 ≥0.85, it can be considered that the established BP neural network prediction model is relatively accurate and can be used to predict carbon emissions from ground-connected wall construction in subway stations. The BP neural network prediction model was used to predict data that did not participate in model training (15 groups of data were randomly selected). The model's prediction of carbon emissions was compared with the actual value, as shown in Table 5.

[0088] Table 5 Carbon emission prediction table of ground-connected wall

[0089]

[0090] According to the prediction error percentage of the above 15 sets of data, the error between the predicted carbon emissions and the actual carbon emissions is less than 5%. It can be seen that the prediction effect of this prediction model is good and can be used for carbon emission prediction of subsequent ground-anchored wall construction in subway stations.

[0091] In an exemplary embodiment, a computer device is provided. The computer device may be a server or a terminal. The internal structure diagram thereof may be as follows: Figure 4As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. Among them, the processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for predicting carbon emissions from the construction of ground-connected walls in subway stations is implemented.

[0092] Those skilled in the art will understand that Figure 4 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components. In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above-mentioned method embodiments when executing the computer program.

[0093] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0094] In an exemplary embodiment, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0095] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0096] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM may be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0097] The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. The non-relational database may include a distributed database based on blockchain, etc., but is not limited thereto. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but is not limited thereto.

[0098] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0099] The present application uses specific examples to illustrate the principles and implementation methods of the present application. The above examples are only used to help understand the method and core ideas of the present application. At the same time, for those skilled in the art, according to the ideas of the present application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting the present application.

Claims

1. A method for predicting carbon emissions from underground wall construction in subway stations, characterized in that: include: A plurality of important parameter indicators of the ground-connected wall construction scheme of the subway station construction are obtained as the important parameter indicator group to be predicted; The important parameter index group to be predicted is input into the total carbon emission prediction model to obtain the total carbon emission prediction of the ground-anchored wall construction scheme; the total carbon emission prediction model is obtained by training the BP neural network model using multiple historical ground-anchored wall construction schemes for subway station construction.

2. The method for predicting carbon emissions from underground wall construction in subway stations according to claim 1 is characterized in that: After the important parameter index group to be predicted is input into the total carbon emission prediction model to obtain the total carbon emission prediction of the ground-connected wall construction scheme, the method further includes: Adjust the ground-anchored wall construction plan based on the total carbon emission forecast.

3. The method for predicting carbon emissions from underground wall construction in subway stations according to claim 1 is characterized in that: Before obtaining multiple important parameter indicators of the ground-connected wall construction plan for the subway station construction as the important parameter indicator group to be predicted, it also includes: Obtain multiple historical diaphragm wall construction plans; The carbon emission coefficient method is used to determine and calculate the total carbon emissions of each historical ground-connected wall construction plan as the historical total carbon emissions; Use the correlation coefficient method to determine multiple important parameter indicators; Obtain multiple important parameter indicators from each historical ground-connected wall construction plan to obtain multiple historical important parameter indicator groups; The BP neural network model is trained with the historical important parameter indicator group as input and the historical total carbon emissions as output to obtain a total carbon emissions prediction model.

4. The method for predicting carbon emissions from underground wall construction in subway stations according to claim 3 is characterized in that: The carbon emission coefficient method is: C dlq =C jc +C jx +C ys +C rg ; Among them, C dlq is the total carbon emissions, C jc is the carbon emissions from the use of building materials during the construction of the ground-connected wall, C jx is the carbon emissions generated by the use of machinery during the construction of the ground-connected wall, C ys is the carbon emissions generated by the transportation during the construction of the ground-connected wall, C rg Carbon emissions artificially generated during the construction of the ground-connected wall; Among them, n1 is the total number of raw material types, is the consumption of the i1th raw material, is the carbon emission factor for producing the i1th raw material, E jg，j is the consumption of the jth energy in the raw material processing process, EF j is the carbon emission factor of the j-th energy source; in, is the consumption of the jth energy source of the i2th machine; in, is the total transport volume of the ith substance, is the transport distance of the ith substance, is the carbon emission factor of the third material transport mode; C rg =n2tEF rg ; Among them, n2 is the number of construction personnel, t is the construction time, EF rg is the artificial carbon emission factor.

5. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the method for predicting carbon emissions from ground-anchored wall construction in a subway station as described in any one of claims 1-4.

6. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for predicting carbon emissions from construction of ground-anchored walls in subway stations described in any one of claims 1 to 4 is implemented.

7. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the method for predicting carbon emissions from construction of ground-anchored walls in subway stations described in any one of claims 1 to 4 is implemented.

Images