Pumped storage power station tunnel construction carbon emission prediction model

Abstract

The invention discloses a pumped storage power station tunnel construction carbon emission prediction model, and belongs to the technical field of pumped storage power station tunnel construction. Ventilating and exhausting smoke; tunnel deslagging; supporting the tunnel; lighting power consumption; and emission sum: integrating the carbon emission data of each construction link to obtain the total carbon emission amount of the whole tunnel construction process so as to construct a carbon emission prediction model. According to the method, a plurality of key construction procedures such as drilling excavation, ventilation and smoke exhaust, tunnel deslagging, tunnel supporting and lighting power consumption are covered, and a comprehensive and systematized carbon emission prediction method is provided, so that a construction manager can master the carbon emission condition in the whole construction process more accurately; by summarizing the carbon emission data of each construction link, a construction manager can comprehensively understand the carbon emission condition of the whole construction process and formulate scientific and reasonable energy conservation and emission reduction measures.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of pumped storage power station tunnel construction, and particularly relates to a pumped storage power station tunnel construction carbon emission prediction model. BACKGROUND

[0002] A pumped storage power station is a special type of hydropower station that uses excess electricity during off-peak hours to pump water from a lower reservoir to an upper reservoir for storage, and then releases the water to generate electricity during peak demand periods. In the construction process of a pumped storage power station, tunnel construction is one of the most important links. With the increasing emphasis on environmental protection and sustainable development worldwide, reducing carbon emissions has become an important task for all industries. In the field of energy infrastructure construction, especially in the process of pumped storage power station tunnel construction, carbon emission management is particularly important.

[0003] However, the existing carbon emission estimation methods have many shortcomings and cannot meet the current needs of fine management. The existing carbon emission estimation methods are usually based on the data and empirical formulas of highway tunnel or subway tunnel construction, which do not fully consider the uniqueness of pumped storage power station tunnel construction. For example, pumped storage power station tunnel construction often involves complex geological conditions, special equipment requirements (such as high-power air compressors, large fans, etc.), and there may be large temperature changes in the construction environment. If a general method is used to estimate the carbon emissions of pumped storage power station tunnel construction, significant errors may occur, and due to inaccurate prediction, the energy-saving and emission-reducing measures developed may not be suitable for the actual construction situation. SUMMARY

[0004] The purpose of the present application is to provide a pumped storage power station tunnel construction carbon emission prediction model to solve the problems raised in the background art.

[0005] To achieve the above-mentioned purpose, the present application provides the following technical solution: a pumped storage power station tunnel construction carbon emission prediction model, comprising the following steps: Drilling excavation: according to the rated power of the air compressor, the number of air compressors required, the drilling operation time, and the electric-carbon conversion coefficient, the carbon emissions generated by drilling are calculated, and based on the amount of explosives used for blasting and its carbon conversion coefficient, the carbon emissions generated by the blasting process are calculated; Ventilation and smoke exhaust: according to the fan power and the ventilation duration of the tunnel construction in the first excavation cycle, combined with the electric-carbon conversion coefficient, the carbon emissions generated in the construction ventilation process are calculated; Tunnel mucking: by calculating the fuel consumption of the loader and the transport vehicle during the mucking process, and combining with the oil-carbon conversion coefficient, the carbon emissions of the mucking stage are determined; Tunnel support: considering the amount of materials such as concrete and steel required for tunnel support and their carbon emission coefficients in the production process, the carbon emissions of the support stage are calculated; Lighting power consumption: According to the total lighting power of the tunnel face and the intermediate section and the lighting time, combined with the carbon conversion coefficient, the carbon emission during lighting is calculated; Total emissions: The carbon emission data of each construction link is integrated to obtain the total carbon emission of the entire tunnel construction process to build a carbon emission prediction model.

[0006] Preferably, the model includes a data acquisition module: for real-time acquisition of relevant parameters of each construction link, including but not limited to air compressor power, fan power, transportation vehicle fuel consumption, material consumption; Data processing unit: clean up and normalize the collected data, and input it into the carbon emission prediction model; Calculation module: calculate the carbon emissions of each construction link; Summary unit: summarize the carbon emissions of each construction link to obtain the total carbon emissions of the entire construction process; Visual display system: for displaying the carbon emissions of each construction link in the form of charts or reports, helping managers intuitively understand the carbon emission distribution in the construction process; Early warning module: set a carbon emission threshold, and issue a warning signal when the actual carbon emission exceeds the threshold; Optimal scheduling unit: generate the optimal equipment scheduling scheme based on carbon emission data to minimize carbon emissions.

[0007] Preferably, the model also includes a sensor network: various sensors deployed at the construction site for real-time monitoring of equipment operating conditions, environmental conditions and other parameters; Data transmission unit: transmit the data collected by the sensors to the central server through wireless communication technology (such as Wi-Fi, LoRaWAN); Data cleaning module: remove outliers and missing values to ensure data integrity and consistency; Feature engineering module: select features related to carbon emissions and perform standardization or normalization to provide high-quality data support for subsequent calculations.

[0008] Preferably, in the drilling and excavation, the air drill consumes electric energy when producing compressed air, and the carbon emissions of the drilling are: (1) In the formula, is the rated power of the air compressor (kW); is the number of air compressors required for drilling, which can be calculated according to the cross-sectional area, air loss and emissions; is the operating time of the drill in one excavation cycle (h); The electric carbon conversion coefficient (kW h / kg) is determined by the formula (3) and the formula (4) and the formula (5) and the formula (6). The blasting process mainly produces carbon emissions when the explosive is exploded: (2) In the formula, The explosive quantity (kg) used for blasting can be estimated according to the blasting volume and the hardness of the rock; The dimensionless explosive carbon conversion coefficient is the carbon emission quantity generated by unit explosive blasting; According to the formula (1) and the formula (2), the total carbon emission quantity generated by excavation in one cycle is : (3) In the formula, The first cycle in one construction paragraph is determined by the formula (4) and the formula (5) and the formula (6).

[0009] Preferably, the fan power in the ventilation and smoke exhaust depends on the air volume and the air pressure, and the air volume and the air pressure need to be calculated according to the corresponding tunnel construction technical specification in combination with the specific ventilation mode, so as to determine the fan power. The electric energy consumption of the construction ventilation in the tunnel is: (4) In the formula, The fan power (kW) is determined by the formula (5) and the formula (6). The tunnel construction ventilation time (h) in one excavation cycle is the smoke exhaust time after blasting.

[0010] Preferably, the carbon emission pathways in the tunnel slagging mainly include the carbon emission generated by fuel combustion in the two processes of stone slag loading and transportation, and the oil consumption of the loader can be calculated by the formula (5): (5) In the formula, The slag loading time (h) in one cycle is determined by the formula (6). The loader oil consumption (L / h) is determined by the formula (6). The fuel consumption quantity (L) in the transportation process is: (6) In the formula, The distance (m) from the working face to the tunnel portal is determined by the formula (5) and the formula (6). The distance (m) from the tunnel portal to the abandoned slag field is determined by the formula (5) and the formula (6). , The oil consumption quantities (L / km) of the transportation vehicle in the empty state and in the full state respectively are determined by the formula (5) and the formula (6).​ is the number of times of slag removal in one cycle, which can be estimated according to the excavation volume; From formulas (5) and (6), the carbon emission generated in the slag removal stage in one cycle is : (7) Preferably, in the tunnel support, the support type is obtained through a tunnel design drawing, including the number, length, steel arch support spacing, and lining thickness of steel anchor cables, the amount of steel and the amount of concrete are calculated, and the carbon emission generated by the materials and material processing in the first construction section is : (8) In the formula, is the tunnel construction section number; are shotcrete, inverted arch concrete, and secondary lining concrete, respectively; , are the steel-carbon conversion coefficient and the concrete carbon emission coefficient, both of which are dimensionless quantities, representing the carbon emission generated by producing each kilogram of steel and concrete, including the carbon emission generated by raw material processing and transportation.

[0011] Preferably, in the lighting power consumption, the tunnel construction lighting is divided into a tunnel face and an intermediate section, and the total lighting power consumption of the tunnel is : (13) In the formula, is the total tunnel face lighting power (kW); is the total tunnel intermediate section lighting power (kW); is the lighting duration in one cycle (h).

[0012] Preferably, the material emission, excavation cycle emission, and secondary lining cycle emission are summarized according to the required cycle number of each construction section to obtain the total construction emission of the tunnel.

[0013] Preferably, the model utilizes historical construction data and real-time monitoring data, dynamically optimizes the carbon emission prediction model through machine learning algorithms (such as random forest, support vector machine, or neural network), automatically adjusts the prediction results according to the actual parameter changes in different stages of the construction process, provides more accurate carbon emission prediction, and at the same time establishes a collaborative management platform integrating multiple data sources (such as sensor data, equipment operation data, and weather data), integrates these information into a unified database through data fusion technology, and provides more comprehensive data support for the carbon emission prediction model.​

[0014] Compared with the prior art, the technical effects and advantages of the present application are: The tunnel construction carbon emission prediction model of the pumped storage power station comprehensively covers multiple key construction processes such as drilling and excavation, ventilation and smoke exhaust, tunnel slagging, tunnel support, and lighting power consumption, and provides a comprehensive and systematic carbon emission prediction method, which enables the construction manager to more accurately master the carbon emission situation in the entire construction process. By summarizing the carbon emission data of each construction link, the construction manager can comprehensively understand the carbon emission situation of the entire construction process and develop scientific and reasonable energy-saving and emission-reducing measures.

[0015] By accurately calculating the carbon emissions of each construction link (such as drilling and excavation, ventilation and smoke exhaust, etc.), not only the current project carbon emission management can be realized, but also valuable data accumulation can be provided for subsequent projects. These historical data can be used to train machine learning models, thereby improving the carbon emission prediction accuracy of future projects. BRIEF DESCRIPTION OF DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the specific embodiments or the prior art of the present application, the drawings needed in the specific embodiments or the prior art description will be briefly introduced as follows. Obviously, the drawings in the following description are some embodiments of the present application, and those skilled in the art can also obtain other drawings according to these drawings without creative labor.

[0017] Fig. 1 A flowchart of the tunnel construction carbon emission prediction model of the pumped storage power station of the present application; Fig. 2 A schematic diagram of the tunnel construction carbon emission estimation of the present application; Fig. 3 A detailed architecture flowchart of the tunnel construction carbon emission prediction model of the pumped storage power station of the present application. DETAILED DESCRIPTION

[0018] In the following description, a large number of specific details are given in order to provide a more thorough understanding of the present application. However, it is obvious to those skilled in the art that the present application can be implemented without one or more of these details. In other examples, in order to avoid obscuring the present application, some technical features known in the art are not described.

[0019] Unless the direction indicated by the definition alone, the directions such as up, down, left, right, front, back, inside and outside involved in this paper are based on the directions such as up, down, left, right, front, back, inside and outside in the drawings shown by the present application, which are explained herein.

[0020] The present embodiment provides aFigs. 1 to 3 The tunnel construction carbon emission prediction model of a pumped storage power station shown includes the following steps: Drilling: Calculate the carbon emissions generated by drilling based on the rated power of the air compressor, the number of air compressors required, the drilling operation time, and the electric carbon conversion coefficient. Meanwhile, based on the amount of explosives used for blasting and its carbon conversion coefficient, calculate the carbon emissions generated by the blasting process; Ventilation and smoke exhaust: Calculate the carbon emissions generated during the construction ventilation process based on the fan power and the ventilation duration in the first excavation cycle, combined with the electric carbon conversion coefficient; Tunnel slagging: Determine the carbon emissions in the slagging stage by calculating the fuel consumption of loaders and transport vehicles during the slagging process, combined with the oil carbon conversion coefficient; Tunnel support: Calculate the carbon emissions in the support stage by considering the amount of materials such as concrete and steel required for tunnel support and their carbon emission coefficients during the production process; Lighting power consumption: Calculate the carbon emissions during lighting based on the total lighting power of the tunnel face and the intermediate section and the lighting duration, combined with the electric carbon conversion coefficient; Emission total: Integrate the carbon emission data of each construction link to obtain the total carbon emissions of the entire tunnel construction process to build the carbon emission prediction model.

[0021] In this embodiment, the model includes: Data acquisition module: used for real-time acquisition of relevant parameters of each construction link, including but not limited to air compressor power, fan power, transport vehicle fuel consumption, and material consumption; Data processing unit: cleans and normalizes the collected data and inputs it into the carbon emission prediction model; Calculation module: calculates the carbon emissions of each construction link; Summary unit: summarizes the carbon emissions of each construction link to obtain the total carbon emissions of the entire construction process; Visual display system: used to display the carbon emissions of each construction link in the form of charts or reports, helping managers intuitively understand the carbon emission distribution in the construction process; Early warning module: set a carbon emission threshold and issue a warning signal when the actual carbon emissions exceed the threshold; Optimal scheduling unit: generate an optimal equipment scheduling scheme based on carbon emission data to minimize carbon emissions.

[0022] In this embodiment, the model also includes: Sensor network: various sensors deployed at the construction site for real-time monitoring of equipment operating conditions and environmental condition parameters; Data transmission unit: transmit the data collected by sensors to the central server through wireless communication technology (such as Wi-Fi, LoRaWAN); Data cleaning module: remove outliers and missing values to ensure data integrity and consistency; Feature engineering module: select features related to carbon emissions and perform standardization or normalization to provide high-quality data support for subsequent calculations.

[0023] In this embodiment, drilling excavation: The air compressor consumes electric energy when producing compressed air, and the carbon emissions of drilling are: (1) where, P is the rated power of the air compressor (kW); N is the number of air compressors required for drilling, which can be calculated based on the cross-sectional area, air loss, and emissions; T is the operating time of the drilling rig in one excavation cycle (h); is the electric carbon conversion coefficient .

[0024] The blasting process mainly produces carbon emissions when explosives explode: (2) where, Q is the amount of explosives used for blasting (kg), which can be estimated based on the blasting volume and the hardness of the rock; is the dimensionless explosive carbon conversion coefficient, i.e., the carbon emissions generated by unit explosive blasting.

[0025] From equations (1) and (2), the total carbon emissions generated by excavation in one cycle are: (3) where, n is the nth cycle in a construction section.

[0026] In this embodiment, ventilation and smoke exhaust: Normal construction of the tunnel requires supporting measures such as ventilation and lighting. The fan power depends on the air volume and air pressure, and the required air volume and air pressure need to be calculated according to the corresponding tunnel construction technical specifications when calculating, and then the fan power is determined. The electric energy consumption of ventilation for construction in the tunnel is: (4) where: P is the fan power (kW); ​It is the ventilation time (h) of tunnel construction in one excavation cycle, that is, the smoke exhaust time after blasting.

[0027] In this embodiment, the tunnel slag discharge is: The main sources of carbon emissions during tunnel slag removal operations are fuel combustion during the loading and transportation of slag materials. It can be calculated by formula (5): (5) Where, is the slag loading time in one cycle (h); is the fuel consumption of the loader (L / h).

[0028] The slag truck consumes a certain amount of fuel during the slag discharge process, including the two processes of transporting the slag from the tunnel to the abandoned slag yard and returning to the tunnel to the tunnel face empty. The amount of fuel consumed during the transportation process is for: (6) Where, is the distance from the tunnel face to the tunnel opening (m); is the distance from the tunnel entrance to the waste dump (m); 、 are the fuel consumption of the transport vehicle when empty and fully loaded (L / km); It is the number of times slag is transported in one cycle (times), which can be estimated based on the volume of excavation.

[0029] From formula (5) and (6), we can know that the carbon emissions generated in the slag discharge stage in one cycle are for: (7) In this embodiment, tunnel support: After tunnel excavation, support is required. This stage consumes a lot of materials (mainly steel and concrete). The materials consumed in tunnel support are related to the grade of the tunnel surrounding rock. In specific calculations, the support type, such as the number and length of steel anchor cables, the spacing between steel arch supports, and the lining thickness, can be obtained from the tunnel design drawings to calculate the amount of steel used. and concrete consumption. Carbon emissions from materials used and material processing in each construction section for: (8) Where, The serial number of the tunnel construction section; They are shotcrete, inverted arch concrete and secondary lining concrete; 、 Steel carbon conversion factor and concrete carbon emission factor, both are dimensionless, representing the carbon emission of producing per kilogram of steel and concrete, including the carbon emission of raw material processing and transportation.

[0030] In addition, the materials used in tunnel support need to go through the process of vehicle transportation, and the carbon emission of vehicle fuel consumption is: (9) In the formula, is the distance from the material transportation to the work site (km); is the number of concrete transportation times (times), which can be estimated by mass; is the number of steel transportation times (times).

[0031] Therefore, the carbon emission caused by material consumption and transportation in 1 construction section in the support stage is: (10) In the formula, is the tunnel construction section number, which can be divided according to the type of tunnel support.

[0032] For a certain part of the tunnel, it needs to go through both excavation cycle and secondary lining cycle, and the footage of the two is different, so it is convenient to calculate separately. The primary support belongs to the excavation cycle, and the carbon emission is mainly the oil consumption and electricity consumption caused by the walking and spraying state of the wet spraying machine, as well as the electricity consumption caused by the construction of steel anchor cable, the welding of steel mesh and the steel arch. Therefore, the carbon emission caused by 1 excavation cycle support is: (11) In the formula, is the oil consumption of the wet spraying machine (L / km); , are the power of the wet spraying machine and the electric welding machine (kW), respectively; , are the use time of the wet spraying machine and the electric welding machine in 1 excavation cycle (h), respectively.

[0033] The secondary lining support belongs to the secondary lining cycle. When the secondary lining is constructed, the main energy consumption in the tunnel is the formwork trolley, the maintenance trolley and the electric welding machine. Therefore, the carbon emission caused by 1 secondary lining cycle is: (12) In the formula, is the secondary lining cycle number in the construction section; , are the rated power of the formwork trolley and the maintenance trolley (kW), respectively; , 、 The template trolley, maintenance trolley, and electric welding machine usage time (h) in one secondary lining cycle are obtained by statistics, respectively.

[0034] In this embodiment, the lighting power consumption is: As the tunnel continues to excavate, the lighting lamps along the way continue to increase. Assuming that the tunnel construction lighting is divided into tunnel face and intermediate section, the overall lighting power consumption of the tunnel is: (13) In the formula, is the total tunnel face lighting power (kW); is the total tunnel intermediate section lighting power (kW); is the lighting time in one cycle (h).

[0035] In this embodiment, the total emissions are: Finally, according to the required cycle times of each construction section, the material emissions, excavation cycle emissions, and secondary lining cycle emissions are summarized to obtain the total emissions of the tunnel construction. Conversion factors can be obtained from various databases, government organizations, professional institutions, and related literature queries, and mechanical parameters are obtained from mechanical manufacturers. Among them, the carbon conversion factor is shown in Table 1. Using the above carbon emission calculation system, the carbon emissions of the tunnel construction phase can be obtained, and the calculation results are used as the original data set. Based on the principles of various deep learning algorithms and error evaluation indexes, the best prediction model for carbon emissions of pumped storage power station tunnel construction is finally constructed.

[0036] Table 1: Tunnel construction carbon emission conversion parameter table In this embodiment, in the actual construction process, various parameters (such as equipment running time, environmental temperature, humidity, etc.) will change constantly, which will affect the accuracy of carbon emission prediction. In order to improve the prediction accuracy, we introduce machine learning algorithm for dynamic optimization, specifically: Data collection: (1) Historical data: Collect relevant data from previous construction projects, including but not limited to equipment running time, energy consumption, material consumption, weather conditions; (2) Real-time monitoring data: Real-time acquisition of various parameters (such as air compressor power, fan power, transportation vehicle fuel consumption) in the current construction process through sensors and monitoring systems.

[0037] Data preprocessing: (1) Clean data: Remove outliers and missing values to ensure data integrity and consistency; (2) Feature engineering: Select features related to carbon emissions (such as equipment type, working time, environmental temperature, etc.), and perform standardization or normalization processing. ​

[0038] Select the desired machine learning algorithm: (1) Random Forest: suitable for handling large feature data, with high accuracy and robustness; or (2) Neural Network: capable of automatically extracting complex features, suitable for modeling nonlinear relationships.

[0039] Model training: Use historical data to train the selected machine learning algorithm, adjust model parameters to minimize prediction error. For example, when using the Random Forest algorithm, cross-validation can be used to select the optimal number of trees and depth.

[0040] Model evaluation: Use test set data to evaluate the performance of the model, common evaluation indicators include Mean Squared Error (MSE), Root Mean Squared Error (RMSE) and Determination Coefficient (R 2 ). If the model performs poorly, return to step to try other algorithms or adjust parameters.

[0041] Dynamic optimization: During construction, new data is obtained in real time and input into the trained model for prediction. Adjust model parameters according to new data to make prediction results more accurate.

[0042] In this embodiment, multiple data sources are involved in the construction process (such as sensor data, equipment operation data, weather data), and effective integration of these data and support for carbon emission prediction is the key, specifically: Data source identification: (1) Sensor data: including the running parameters of air compressors, fans, loaders and other equipment; (2) Equipment operation data: recording the working time, energy consumption and maintenance of equipment; (3) Weather data: obtaining real-time weather information (such as temperature, humidity, wind speed) at the construction site; (4) Other data: such as personnel attendance, material consumption.

[0043] Data collection and transmission: Use IoT devices to collect data in real time, and transmit data to the central server through wireless communication (such as Wi-Fi, LoRaWAN, etc.).

[0044] Data storage and management: Store all data in a unified database, you can choose a relational database (such as MySQL) or a NoSQL database (such as MongoDB), design a reasonable data structure to ensure that data from different sources can be seamlessly connected.

[0045] Data fusion and processing: Use ETL (Extract, Transform, Load) tools to clean, transform and load data. Apply data fusion techniques (such as Kalman filtering, weighted average, etc.) to integrate data from different sources into consistent information.

[0046] Data Visualization and Analysis: Develop a user-friendly interface to display various types of data and their associated analysis results. Provide charts (such as line graphs, bar graphs), dashboard functions to help managers quickly understand the construction progress and carbon emissions.

[0047] For example: During construction, it is found that the energy consumption of some equipment is abnormally high. Through the multi-source data fusion platform, you can simultaneously view the historical operation data, current working state, and surrounding environmental conditions (such as temperature, humidity) of the equipment. If it is found that the high temperature leads to a decrease in equipment efficiency, cooling measures or replacement of equipment can be taken in time to avoid unnecessary energy waste.

[0048] In this embodiment, the carbon emissions during construction need to be monitored in real time, and a warning will be issued when the preset threshold is reached. At the same time, an optimal device scheduling scheme is automatically generated through an optimization scheduling algorithm, specifically: Real-time monitoring of carbon emissions: (1) Deploy sensors at the construction site to monitor the energy consumption and carbon emissions of each device in real time; (2) Transmit these data to the central server and combine them with the carbon emission prediction model to calculate the current carbon emissions in real time.

[0049] Set the warning threshold: According to the environmental protection requirements of the construction project, set the warning threshold for carbon emissions. When the real-time monitored carbon emissions approach or exceed the threshold, the system automatically sends a warning signal (such as a text message, email, or APP notification).

[0050] Optimization scheduling algorithm: (1) Genetic algorithm: simulates the natural selection process to find the optimal solution through selection, crossover, and mutation operations; (2) Ant colony algorithm: simulates the foraging behavior of ants to search for the optimal path by using pheromone concentration. Use the above algorithms to generate an optimal device scheduling scheme to minimize carbon emissions.

[0051] Execute the optimization scheme: The system automatically adjusts the working time and order of the devices according to the scheme generated by the optimization scheduling algorithm. At the same time, a detailed scheduling plan is generated and notified to the relevant personnel through the management system for execution.

[0052] Feedback and adjustment: Collect feedback data regularly to evaluate the effectiveness of the optimization scheme, and adjust the algorithm parameters or regenerate the scheduling scheme according to the actual situation to ensure continuous optimization. When the carbon emissions of the construction section are about to exceed the set threshold, the system will immediately issue a warning. At this time, the optimization scheduling system will analyze the status of all available devices and generate a scheduling scheme, such as prioritizing the use of low-energy electric devices or adjusting the work order to reduce unnecessary transportation distance. This not only effectively controls carbon emissions but also improves construction efficiency.

[0053] It has to be noted that, in the present document, the terms "comprising", "including", and "having" should be interpreted as specifying the presence of the stated features but not precluding the presence of one or more other features. It should also be noted that, in the present document, the term "or" should be interpreted as the logical or, i.e. requiring at least one of the presented options to be true.

[0054] While the embodiments of the application have been shown and described herein, it will be understood by those skilled in the art that many changes, modifications, substitutions, and alterations to these embodiments can be made without departing from the principles and spirit of the application. This application is intended to cover any and all adaptations or variations of these embodiments resulting in out following claims, and their equivalents.

Claims

1. A carbon emission prediction model for tunnel construction of a pumped storage power station, characterized by: The following steps are involved: Drilling and excavation: The carbon emissions from drilling are calculated based on the rated power of the air compressor, the number of air compressors required, the drilling rig operating time, and the electricity-to-carbon conversion coefficient. The carbon emissions from the blasting process are also calculated based on the amount of explosives used and their carbon conversion coefficient. Ventilation and smoke exhaust: Calculate the carbon emissions generated during the construction ventilation process based on the fan power and the tunnel construction ventilation duration in one excavation cycle, combined with the electricity-to-carbon conversion coefficient; Tunnel slagging: By calculating the fuel consumption of loaders and transport vehicles during the slagging process and combining it with the oil-to-carbon conversion coefficient, the carbon emissions during the slagging stage are determined; Tunnel support: Considering the amount of concrete, steel and other materials required for tunnel support and the carbon emission coefficient during their production process, calculate the carbon emissions during the support phase; Lighting power consumption: Based on the total lighting power and lighting duration of the tunnel face and middle section, combined with the electricity-to-carbon conversion coefficient, the carbon emissions during the lighting period are calculated; Total emissions: The carbon emission data of each construction link is integrated to obtain the total carbon emissions of the entire tunnel construction process, thereby constructing a carbon emission prediction model.

2. A pumped storage power station tunnel construction carbon emission prediction model according to claim 1, characterized in that: The model includes a data acquisition module, a data processing unit, a calculation module: calculating the carbon emissions of each construction link, a summary unit, a visual display system, an early warning module and an optimization and scheduling unit.

3. A pumped storage power station tunnel construction carbon emission prediction model according to claim 2, characterized in that: The model also includes a sensor network: used to monitor parameters such as equipment operating status and environmental conditions in real time; Data transmission unit: transmits the data collected by the sensor to the central server through wireless communication technology (such as Wi-Fi, LoRaWAN); Data cleaning module: removes outliers and missing values ​​to ensure data integrity and consistency; Feature Engineering Module: Selects features related to carbon emissions and performs standardization or normalization to provide high-quality data support for subsequent calculations.

4. The carbon emission prediction model for tunnel construction of a pumped storage power station according to claim 1 is characterized by: The drilling process uses a pneumatic drill to produce compressed air, which consumes electricity. The carbon emissions from drilling are for: (1) Where, is the rated power of the air compressor (kW); The number of air compressors required for drilling can be calculated based on the cross-sectional area, wind loss and emissions; is the operating time of the drilling rig in one excavation cycle (h); is the electricity-to-carbon conversion coefficient ; The blasting process mainly produces carbon emissions when explosives explode: (2) Where, The amount of explosives used for blasting (kg) can be estimated based on the volume of blasting and the hardness of the rock; is the dimensionless explosive carbon conversion coefficient, i.e., the carbon emission generated by blasting per unit of explosive; From formula (1) and (2), we can see that the total carbon emissions generated by excavation in one cycle is for: (3) Where, For the first construction section Second cycle.

5. The carbon emission prediction model for tunnel construction of a pumped storage power station according to claim 1 is characterized by: The fan power in the ventilation and smoke exhaust depends on the air volume and pressure. When calculating, it is necessary to combine the specific ventilation method with the corresponding tunnel construction technical specifications to calculate the required air volume and pressure, and then determine the fan power. for: (4) Where: is the fan power (kW); It is the ventilation time (h) of tunnel construction in one excavation cycle, that is, the smoke exhaust time after blasting.

6. The carbon emission prediction model for tunnel construction of a pumped storage power station according to claim 1 is characterized by: The carbon emissions generated in the tunnel slag discharge are mainly from the carbon emissions generated by the fuel combustion in the two processes of slag material loading and transportation, and the fuel consumption of the loader. It can be calculated by formula (5): (5) Where, is the slag loading time in one cycle (h); is the fuel consumption of the loader (L / h). The slag truck consumes a certain amount of fuel during the slag discharge process, including the two processes of transporting the residue from the tunnel to the abandoned slag yard and returning to the tunnel to the tunnel face empty. The amount of fuel consumed during the transportation process is for: (6) Where, is the distance from the tunnel face to the tunnel opening (m); is the distance from the tunnel entrance to the waste dump (m); 、 are the fuel consumption of the transport vehicle when empty and fully loaded (L / km); The number of times slag is transported in one cycle (times), which can be estimated based on the volume of excavation; From formula (5) and (6), we can know that the carbon emissions generated in the slag discharge stage in one cycle are for: (7)。 7. The carbon emission prediction model for tunnel construction of a pumped storage power station according to claim 1 is characterized by: In the tunnel support, the support type is obtained through the tunnel design drawing, including the number and length of steel anchor cables, the spacing between steel arch supports, and the thickness of the lining, and the amount of steel used is calculated. and concrete consumption, Carbon emissions from materials used and material processing in each construction section for: (8) Where, The serial number of the tunnel construction section; They are shotcrete, inverted arch concrete and secondary lining concrete; 、 They are the steel-carbon conversion coefficient and concrete carbon emission coefficient, respectively. Both are dimensionless quantities, representing the carbon emissions generated by the production of each kilogram of steel and concrete, including carbon emissions from raw material processing and transportation.

8. The carbon emission prediction model for tunnel construction of a pumped storage power station according to claim 1 is characterized by: In the lighting power consumption, the tunnel construction lighting is divided into the tunnel face and the middle section. The overall lighting power consumption of the tunnel is for: (13) Where, is the total lighting power of the tunnel face (kW); is the total lighting power in the middle section of the tunnel (kW); is the lighting duration in one cycle (h).

9. The carbon emission prediction model for tunnel construction of a pumped storage power station according to claim 1, characterized in that: The material emissions, excavation cycle emissions, and secondary lining cycle emissions were summarized according to the number of cycles required for each construction section to obtain the total construction emissions of the tunnel.

10. A pumped storage power station tunnel construction carbon emission prediction model according to claim 9, characterized in that: The model uses historical construction data and real-time monitoring data to dynamically optimize the carbon emission prediction model through machine learning algorithms. At the same time, it establishes a collaborative management platform that integrates multiple data sources and integrates this information into a unified database through data fusion technology to provide data support for the carbon emission prediction model.

Images