Carbon Emission Monitoring System and Method Based on Road and Bridge Construction

Abstract

The present application discloses a carbon emission monitoring system and method based on road and bridge construction, which relates to the fields of green transportation infrastructure and carbon measurement technology, and solves the technical problems that the existing technology lacks the prediction of the output of carbon emissions and the optimization scheme after the excess situation occurs, resulting in low efficiency of the carbon emission monitoring system; calculating the actual value of carbon emissions according to stage data, material data, equipment data and environmental data; calculating a number of predicted adjustment time windows according to the carbon emission data and the actual value of carbon emissions; generating a number of carbon emission prediction values according to the number of predicted adjustment time windows; generating a carbon optimization scheme according to the number of carbon emission prediction values; adjusting according to the carbon optimization scheme, comparing the error of the current stage with the error range within the current time window, and dynamically adjusting the size of the prediction time window to more accurately predict the carbon emissions, providing data support for the carbon optimization scheme after the carbon emissions exceed the standard, and improving the accuracy and efficiency of the carbon emission monitoring system.

Description

Technical Field

[0001] This application belongs to the technical field of green transportation infrastructure and carbon measurement, specifically a carbon emission monitoring system and method based on road and bridge construction. Background Art

[0002] Road and bridge construction refers to the construction activities of roads and bridges carried out to improve traffic conditions and promote economic development. It includes the whole process from project establishment, design, construction to completion acceptance, as well as subsequent maintenance and management; the scope of road and bridge construction is extensive, not only involving the construction of roads and bridges, but also including related tunnels, municipal facilities, etc. Carbon emission refers to the process in which carbon dioxide and other greenhouse gases enter the atmosphere during human activities. These greenhouse gases mainly come from the combustion of fossil fuels such as coal, oil and natural gas, which are used for power generation, transportation, industrial production, etc. There is a close relationship between road and bridge construction and carbon emissions. As an important part of infrastructure construction, a large amount of carbon emissions will be generated during the construction and operation of road and bridge construction.

[0003] The prior art (a patent application for invention with the publication number of CN117007747A) discloses a carbon emission monitoring system and method during the highway construction period, belonging to the technical field of traffic carbon emission monitoring. The carbon emission monitoring system during the highway construction period includes a collection device, a transmission device, a data analysis device and a data storage device; the collection device is used to collect the first type of data in a preset area during the highway construction period, and the first type of data includes energy consumption measurement data and tail gas emission data; the transmission device is communicatively connected to the collection device and the data analysis device, and is used to transmit the first type of data to the data analysis device; the data analysis device is used to analyze and calculate the first type of data to obtain the first carbon emission data corresponding to the first type of data; the data storage device is communicatively connected to the data analysis device and is used to store the first carbon emission data.

[0004] The above solution calculates and sums the carbon emissions of each part during the highway construction period to obtain the final carbon emissions, realizing the automatic collection, calculation and analysis of carbon emissions; however, the carbon emissions have already occurred. If the carbon emissions exceed the limit, it will cause adverse consequences, lacking the foresight of carbon emissions, lacking the prediction of the carbon emission output and the optimization plan after the excess situation, resulting in low efficiency of the carbon emission monitoring system; therefore, the carbon emission monitoring system still needs further improvement. Summary of the Invention

[0005] This application aims to solve at least one of the technical problems existing in the prior art; for this purpose, this application proposes a carbon emission monitoring system and method based on road and bridge construction, which is used to solve the technical problems that the prior art lacks the prediction of the output of carbon emissions and the optimization plan after the excess situation occurs, resulting in low efficiency of the carbon emission monitoring system.

[0006] To achieve the above object, the first aspect of this application provides a carbon emission monitoring system based on road and bridge construction, including: a data acquisition module, a data analysis module, an early warning module and a database;

[0007] The data acquisition module: obtains phase data, material data, equipment data, environmental data and carbon emission data through data acquisition devices;

[0008] The data analysis module: calculates the actual carbon emission value according to the phase data, material data, equipment data and environmental data; calculates a number of predicted adjustment time windows according to the carbon emission data and the actual carbon emission value; generates a number of carbon emission prediction values according to the number of predicted adjustment time windows; generates a carbon optimization plan according to the number of carbon emission prediction values; and adjusts according to the carbon optimization plan;

[0009] The early warning module: makes a prompt according to the alarm signal and contacts the management personnel;

[0010] The database is used to store the data collected by the acquisition device and the historical data required for storing the training model.

[0011] In the above steps of this application, the emission error in the current stage is compared and analyzed with the error limit within the time window, and accordingly, the scale of the prediction time window is flexibly adjusted to improve the accuracy of carbon emission prediction; it provides a solid data basis for formulating an optimization strategy for coping with excessive carbon emissions, thereby enhancing the accuracy and operation efficiency of the carbon emission monitoring system.

[0012] Further, the calculation of the actual carbon emission value according to the phase data, material data, equipment data and environmental data includes:

[0013] Obtain phase data, material data, equipment data and environmental data; the phase data includes a phase ID and a phase label; the phase label includes a production label, a transportation label and a construction label; the environmental data includes temperature, humidity, rainfall, average road slope and weather forecast data; the material data includes a number of material parameters;

[0014] Through the formula Calculate the actual production carbon emission value STS; where i represents the material number, M represents the material mass, and EF 材,i Represents the material production carbon emission factor when the i-th material is produced; And They are respectively represented as the difference between the actual average temperature and the reference temperature during material production and the difference between the actual average humidity and the reference humidity during material production; α i and β i are respectively represented as the temperature sensitivity coefficient and the humidity sensitivity coefficient;

[0015] The actual value of transportation carbon emissions YTS is calculated through the formula ; where JL is the transportation distance, RX is the fuel efficiency of the transportation vehicle, γ is the rainfall influence coefficient, ε is the slope influence coefficient, and γ and ε ∈ (0, 1); is the flatness slope of the road, positive for uphill and negative for downhill;

[0016] The actual value of construction carbon emissions JTS is calculated through the formula ; where m represents the number of power equipment during construction, n represents the number of fuel equipment, DL represents the electricity consumption, RL represents the fuel quantity, COP(W m ) represents the energy efficiency ratio of the equipment at temperature W; μ(P n ) represents the air pressure correction coefficient; EF represents the carbon emission factor.

[0017] Further, calculating several prediction adjustment time windows according to the carbon emission data and the actual value of carbon emissions includes:

[0018] Obtain carbon emission data and several actual values of carbon emissions TPS; the carbon emission data includes several predicted values of carbon emissions TPY;

[0019] Calculate the emission error PW through the formula ; where j represents the stage number and t represents the time number; j,t ;

[0020] Judge whether the emission error is within its corresponding error range; the error range is calculated through historical emission errors;

[0021] Yes, do nothing;

[0022] No, generate several prediction adjustment time windows according to the emission error.

[0023] Further, calculating the error range through historical emission errors includes:

[0024] Obtain the historical emission errors corresponding to several stage labels; the historical emission errors are several historical emission errors within the current time window;

[0025] Arrange several historical emission errors within the current time window from smallest to largest to obtain the error sequence WL j ;

[0026] Obtain WLj the median Med j and the interquartile range IQR j ;

[0027] the error range WF j is expressed as WF j ∈ [Med j - IQR j , Med j + IQR j .

[0028] Through the above steps, this application calculates a series of historical emission errors within the current time window to determine an adaptive error range, where the time window itself has the characteristic of dynamic adjustment; enabling the error range to flexibly adapt to different situations, thereby providing a more accurate error definition and providing a solid data basis for the adaptive adjustment of the time window during the prediction process.

[0029] Further, generating a number of prediction adjustment time windows according to the emission error includes:

[0030] Obtain the emission error PW j,t and the error range WF j ; the error range includes the error range boundary value WFB j ;

[0031] Calculate the prediction adjustment time window SC through the formula j,t+1 ; where σ is expressed as the adjustment coefficient, σ ∈ (0, 1); SC j,max and SC j,min respectively represent the maximum and minimum values of the jth stage time window; is expressed as the ceiling symbol; when the emission error is greater than the maximum value in its corresponding error range, the value of WFB j is equal to the maximum value in the error range, and when the emission error is less than the minimum value in its corresponding error range, the value of WFB j is equal to the minimum value in the error range.

[0032] Further, generating a number of carbon emission prediction values according to a number of prediction adjustment time windows includes:

[0033] Obtain a number of prediction sequences and stage labels; the prediction sequences include material data, equipment data, and environmental data within a number of prediction adjustment time windows and their corresponding actual carbon emission values;

[0034] Input a number of prediction sequences and stage labels into the carbon emission prediction model to obtain the carbon emission prediction values corresponding to the stage labels; the carbon emission prediction model is constructed through a machine learning model.

[0035] Further, the carbon emission prediction model is constructed by a machine learning model, including:

[0036] Obtain a number of historical prediction sequences, historical stage labels, and their corresponding actual historical carbon emissions;

[0037] Divide a number of historical prediction sequences, historical stage labels, and their corresponding actual historical carbon emissions into a training set, a test set, and a validation set;

[0038] Select a machine learning model as the basic model;

[0039] Train the basic model with the training set, and adjust the learning rate or other hyperparameters on the validation set to obtain a pre-trained model;

[0040] Verify the pre-trained model on the test set, and finally obtain a carbon emission prediction model with several prediction sequences and stage labels as inputs and the carbon emission prediction values corresponding to the stage labels as outputs.

[0041] Further, generating a carbon optimization plan according to several carbon emission prediction values includes:

[0042] Obtain several carbon emission prediction values;

[0043] Judge whether several carbon emission prediction values are greater than their corresponding stage thresholds;

[0044] Yes, generate a carbon emission exceeding alarm signal; obtain the stage label corresponding to the carbon emission prediction value; obtain a carbon optimization plan according to the rule base corresponding to the stage label;

[0045] No, do nothing.

[0046] Further, obtaining a carbon optimization plan according to the rule base corresponding to the stage label includes the following steps:

[0047] Step 1: Obtain the stage label corresponding to the carbon emission prediction value and the rule base corresponding to the stage label;

[0048] Step 2: Create a stage temporary rule base; the stage temporary rule base is consistent with the rule base corresponding to the stage label;

[0049] Step 3: Find several carbon optimization methods for the material data and equipment data corresponding to the stage label in the stage temporary rule base; delete the several carbon optimization methods and their corresponding rule priorities from the stage temporary rule base;

[0050] Step 4: Sequentially extract the carbon optimization method corresponding to the highest rule priority value in the rule library; generate an optimized prediction value by using the carbon optimization method through the carbon emission prediction model corresponding to the stage label; delete the carbon optimization method and its corresponding rule priority from the stage temporary rule library; determine whether the optimized prediction value is less than the stage threshold; if yes, organize several carbon optimization methods into a carbon optimization plan; if not, determine whether the stage temporary rule library is empty; if yes, generate an alarm signal indicating that there is no optimizable plan for the time being; if not, go to Step 4.

[0051] Another aspect of the present invention provides a carbon emission monitoring method based on road and bridge construction, including:

[0052] S0: Obtain stage data, material data, equipment data, environmental data, and carbon emission data;

[0053] S1: Calculate the actual carbon emission value according to the stage data, material data, equipment data, and environmental data;

[0054] S2: Calculate several prediction adjustment time windows according to the carbon emission data and the actual carbon emission value; generate several carbon emission prediction values according to the several prediction adjustment time windows;

[0055] S3: Generate a carbon optimization plan according to the several carbon emission prediction values; adjust according to the carbon optimization plan;

[0056] S4: Make a prompt according to the alarm signal and contact the management personnel.

[0057] Compared with the prior art, the beneficial effects of the present application are:

[0058] 1. The present application calculates the actual carbon emission value according to the stage data, material data, equipment data, and environmental data; calculates several prediction adjustment time windows according to the carbon emission data and the actual carbon emission value; generates several carbon emission prediction values according to the several prediction adjustment time windows; generates a carbon optimization plan according to the several carbon emission prediction values; adjusts according to the carbon optimization plan, compares the error of the current stage with the error range within the current time window, and dynamically adjusts the size of the prediction time window, so as to more accurately predict the carbon emission amount, provide data support for the carbon optimization plan after the carbon emission exceeds the standard, and improve the accuracy and efficiency of the carbon emission monitoring system.

[0059] 2. The present application divides the carbon emission of road and bridge construction into stages, calculates the carbon emission through different parameters for each stage, and simultaneously considers the influence of environmental factors on carbon emission, so that the actual carbon emission value of each stage can be more accurate, and the accuracy of the actual carbon emission value is improved.

[0060] 3. In this application, the error range is calculated based on several historical emission errors within the current time window, and the time window also changes dynamically, making the error range adaptive and capable of providing a more accurate error range, providing accurate data support for predicting and adjusting the adaptive change of the time window. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] In order to more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of this application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0062] Figure 1 Schematic diagram of the carbon emission monitoring system based on road and bridge construction for this application;

[0063] Figure 2 Flowchart for generating the carbon optimization plan for this application;

[0064] Figure 3 Flowchart of the carbon emission monitoring method based on road and bridge construction for this application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0065] The following will clearly and completely describe the technical solutions of this application in combination with the embodiments. Obviously, the described embodiments are only some embodiments of this application, rather than all embodiments. Based on the embodiments in this application, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of this application.

[0066] Please refer to Figure 1 , the first aspect embodiment of this application provides a carbon emission monitoring system based on road and bridge construction, including: a data acquisition module, a data analysis module, an early warning module, and a database;

[0067] Data acquisition module: Obtain phase data, material data, equipment data, environmental data, and carbon emission data through data acquisition devices; the data acquisition devices include several sensors, etc.

[0068] Data analysis module: Calculate the actual carbon emission value based on the stage data, material data, equipment data, and environmental data. The actual carbon emission value refers to the numerical value of the carbon emissions actually generated in each stage; Calculate several prediction adjustment time windows based on the carbon emission data and the actual carbon emission value; The prediction adjustment time window refers to the range of the prediction sequence required for carbon emission prediction in each stage; Generate several carbon emission prediction values based on the several prediction adjustment time windows. The carbon emission prediction value refers to the generated numerical value of the predicted carbon emissions; Generate a carbon optimization plan based on the several carbon emission prediction values. The carbon optimization plan refers to the optimization plan that needs to be made when the carbon emission prediction value exceeds the set stage threshold; Adjust according to the carbon optimization plan.

[0069] Warning module: Make a prompt according to the alarm signal and contact the management personnel; The alarm signals include the alarm signal of no optimizable plan temporarily and the alarm signal of carbon emission exceeding the standard, etc.

[0070] The database is used to store the data collected by the acquisition device and the historical data required for storing the training model.

[0071] Calculating the actual carbon emission value according to the stage data, material data, equipment data, and environmental data in this embodiment includes:

[0072] Obtain the stage data, material data, equipment data, and environmental data; The stage data includes the stage ID and the stage label; The stage label includes production label, transportation label, construction label, etc.; The environmental data includes temperature, humidity, rainfall, average road slope, and weather forecast data; The material data includes several material parameters.

[0073] Through the formula Calculate the actual production carbon emission value STS; Where, i represents the material number, M represents the material mass, EF 材,i Represents the material production carbon emission factor during the production of the i-th material, and the specific value is set according to the material parameters. The material production carbon emission factors of different materials are all different; And Respectively represent the difference between the actual average temperature and the reference temperature during material production, and the difference between the actual average humidity and the reference humidity during material production. The settings of the reference temperature and the reference humidity are set according to experience. In this embodiment, the reference temperature and the reference humidity are set to 25°C and 60% respectively; α i And β iThey are respectively represented as the temperature sensitivity coefficient and the humidity sensitivity coefficient. The temperature sensitivity coefficient refers to the change ratio of the carbon emission factor when the actual average temperature deviates from the reference temperature by 1°C. The humidity sensitivity coefficient refers to the change ratio of the carbon emission factor when the actual average humidity deviates from the reference humidity by 1%. The settings of the temperature sensitivity coefficient and the humidity sensitivity coefficient are based on experience. The temperature sensitivity coefficient and the humidity sensitivity coefficient in the production process of different materials are different. In this embodiment, the temperature sensitivity coefficient during the production of steel materials is set to 0.003, and the temperature sensitivity coefficient during the production of concrete materials is set to 0.005. When the type of material produced is fixed, as the mass of the material produced increases and the deviation of temperature and humidity becomes larger, the actual value of production carbon emissions will also increase accordingly.

[0074] The actual value of transportation carbon emissions YTS is calculated through the formula ; where JL is the transportation distance, RX is the fuel efficiency of the transportation vehicle, and the fuel efficiency corresponding to different transportation vehicles is different, and the specific value is set according to experience. In this embodiment, the fuel efficiency of the transportation vehicle is set to 0.25 km / L, that is, the fuel efficiency of a fuel truck. γ is the rainfall influence coefficient, ε is the slope influence coefficient, and γ and ε ∈ (0, 1), and the specific value is set according to experience. When driving on roads with different slopes and different rainfall amounts, the fuel consumption required by the transportation vehicle is different, and the impact on carbon emissions is also different. In this embodiment, ε is set to 0.12. is the flatness slope of the road, positive for uphill and negative for downhill; the greater the rainfall, the longer the transportation distance, and the transportation section is in an uphill state, and at this time the actual value of transportation carbon emissions will increase accordingly.

[0075] The actual value of construction carbon emissions JTS is calculated through the formula ; where m represents the number of power equipment during construction, n represents the number of fuel equipment, DL represents the electricity consumption, RL represents the fuel quantity, COP(W m ) represents the energy efficiency ratio of the equipment at temperature W. For example, when the temperature is 25°C, COP = 1; μ(P n ) represents the air pressure correction coefficient, the influence coefficient of altitude air pressure on fuel efficiency; EF represents the carbon emission factor, and the carbon emission factors corresponding to different forms of energy are inconsistent, and the specific value is set according to experience. On the basis of keeping the energy efficiency ratio and altitude air pressure unchanged, as the electricity consumption and fuel quantity increase, the carbon content emitted through energy will increase at this time, so the actual value of construction carbon emissions will increase accordingly.

[0076] In this embodiment, the carbon emissions during the road and bridge construction process are implemented with stage-by-stage segmentation, and differential parameters are used for each stage to calculate the carbon emissions in detail. During this process, the potential impact of environmental factors on carbon emissions is fully incorporated, thereby ensuring a high degree of accuracy in the actual carbon emissions values for each stage and significantly improving the accuracy of the overall carbon emissions assessment.

[0077] In this embodiment, several prediction adjustment time windows are calculated based on the carbon emissions data and the actual carbon emissions values, including:

[0078] Obtain the carbon emissions data and several actual carbon emissions values TPS; the carbon emissions data includes several predicted carbon emissions values TPY;

[0079] Through the formula Calculate the emission error PW j,t ; where j represents the stage number and t represents the time number; the greater the gap between the actual carbon emissions value and the predicted carbon emissions value, the greater the emission error;

[0080] Judge whether the emission error is within its corresponding error range; the error range is calculated through the historical emission error;

[0081] Yes, do nothing; that is, the emission error can be ignored, and at this time, no change needs to be made to the prediction time window;

[0082] No, generate several prediction adjustment time windows according to the emission error.

[0083] In this embodiment, the error range is calculated through the historical emission error, including:

[0084] Obtain the historical emission errors corresponding to several stage labels; the historical emission errors are several historical emission errors within the current time window; the number of historical sequences existing within the current time window is equal to the number of historical emission errors;

[0085] Arrange several historical emission errors within the current time window in ascending order to obtain the error sequence WL j ; the error sequence WL j Represents the error sequence corresponding to the jth stage;

[0086] Obtain the median Med j in WL j and the interquartile range IQR j ; the calculation of the median Med j can be obtained as follows: if the error sequence has an odd number of emission errors, the median Med j is equal to the emission error corresponding to the middle value of the error sequence; if the error sequence has an even number of emission errors, the median Med jHalf of the sum of the two emission errors in the middle part of the equivalent error sequence; Interquartile Range IQR j It can be calculated by a method based on linear interpolation;

[0087] Error range WF j Denoted as WF j ∈[Med j -IQR j , Med j +IQR j .

[0088] Generating a number of predicted adjustment time windows according to the emission error in this embodiment includes:

[0089] Obtain the emission error PW j,t and the error range WF j ; The error range includes the error range boundary value WFB j ;

[0090] Through the formula Calculate the predicted adjustment time window SC j,t+1 ; where σ is denoted as the adjustment coefficient, representing the sensitivity of the control adjustment, σ ∈ (0, 1), and the specific value is set according to experience; SC j,max and SC j,min respectively represent the maximum and minimum values of the jth stage time window, and the specific values are set according to experience. In this embodiment, the SC j,max and SC j,min of the production stage are set to 72 days and 6 days respectively; Denoted as the ceiling symbol. Using the ceiling symbol is to make the predicted adjustment time window an integer, which is convenient for subsequent processes; when the emission error is greater than the maximum value in its corresponding error range, the value of WFB j is equal to the maximum value in the error range. When the emission error is less than the minimum value in its corresponding error range, the value of WFB j is equal to the minimum value in the error range; as the emission error is more greater than the maximum value in the error range, it indicates that the historical carbon emission prediction value corresponding to the current actual carbon emission value is not accurate enough, and more historical sequences are needed for prediction. Therefore, the predicted adjustment time window will increase accordingly.

[0091] Through the above steps, this embodiment dynamically generates a predicted adjustment time window based on the deviation degree of the current emission error within the error range, so that the prediction effect for future moments can be more accurate. At the same time, it is ensured that the predicted adjustment time window can be adjusted within a certain range to avoid the problem of low prediction efficiency caused by too large or too small time windows, improving the accuracy and efficiency of prediction.

[0092] In this embodiment, generating a number of carbon emission prediction values according to a number of predicted adjustment time windows includes:

[0093] Obtain a number of prediction sequences and stage labels; the prediction sequences include material data, equipment data, and environmental data within a number of predicted adjustment time windows and their corresponding actual carbon emission values;

[0094] Input the number of prediction sequences and stage labels into the carbon emission prediction model to obtain the carbon emission prediction values corresponding to the stage labels; the carbon emission prediction model is constructed through a machine learning model.

[0095] In this embodiment, the carbon emission prediction model is constructed through a machine learning model, including:

[0096] Obtain a number of historical prediction sequences, historical stage labels, and their corresponding historical actual carbon emission values;

[0097] Divide the number of historical prediction sequences, historical stage labels, and their corresponding historical actual carbon emission values into a training set, a test set, and a validation set; the ratio between the training set, the test set, and the validation set is 7:2:1;

[0098] Select a machine learning model as the basic model; the machine learning model includes an LSTM model, etc.;

[0099] Train the basic model through the training set, and adjust the learning rate or other hyperparameters on the validation set to obtain a pre-trained model;

[0100] Verify the pre-trained model on the test set, and finally obtain a carbon emission prediction model with the input being a number of prediction sequences and stage labels and the output being the carbon emission prediction values corresponding to the stage labels.

[0101] In this embodiment, generating a carbon optimization plan according to a number of carbon emission prediction values includes:

[0102] Obtain a number of carbon emission prediction values;

[0103] Judge whether a number of carbon emission prediction values are greater than their corresponding stage thresholds; the stage thresholds are set according to experience, and the stage thresholds in different stages are different;

[0104] Yes, generate a carbon emission exceeding standard alarm signal; obtain the stage label corresponding to the carbon emission prediction value; obtain the carbon optimization plan according to the rule base corresponding to the stage label; the rule base is constructed by experts according to low-carbon methods;

[0105] No, do nothing.

[0106] Please refer to Figure 2 , obtaining the carbon optimization plan according to the rule base corresponding to the stage label in this embodiment includes the following steps:

[0107] Step 1: Obtain the phase label corresponding to the carbon emission prediction value and the rule library corresponding to the phase label;

[0108] Step 2: Create a phase temporary rule library; the phase temporary rule library is consistent with the rule library corresponding to the phase label; creating the phase temporary rule library is to preserve the integrity of the original rule library and prevent data incompleteness during operations on the rule library;

[0109] Step 3: Find several carbon optimization methods for the material data and equipment data corresponding to the phase label in the phase temporary rule library; delete several carbon optimization methods and their corresponding rule priorities from the phase temporary rule library; that is, the currently implemented solution may have used some carbon optimization methods in the rule library, and removing the already used carbon optimization methods can reduce the number of repeated uses and improve the generation efficiency of the carbon optimization plan;

[0110] Step 4: Sequentially extract the carbon optimization method corresponding to the highest rule priority value in the rule library; generate an optimized prediction value for the carbon optimization method through the carbon emission prediction model corresponding to the phase label; delete the carbon optimization method and its corresponding rule priority from the phase temporary rule library; determine whether the optimized prediction value is less than the phase threshold; if yes, organize several carbon optimization methods into a carbon optimization plan; if not, determine whether the phase temporary rule library is empty; if yes, generate an alarm signal indicating that there is no optimizable plan; if not, enter Step 4; when the phase temporary rule library is empty, it means that all existing carbon optimization methods cannot adjust the carbon emission prediction value corresponding to the current phase to the target state.

[0111] In this embodiment, after predicting that the carbon emission prediction value exceeds the phase threshold, by searching for carbon optimization methods in the preset rule library according to the rule priority, and sequentially selecting the method corresponding to the highest rule priority value for prediction until the carbon emission prediction value can meet the target requirements, it can respond in real time, meet the dynamic adjustment of the engineering state, and improve the efficiency of the carbon emission monitoring system.

[0112] Please refer to Figure 3 , another embodiment of the present application provides a carbon emission monitoring method based on road and bridge construction, including:

[0113] S0: Obtain phase data, material data, equipment data, environmental data, and carbon emission data;

[0114] S1: Calculate the actual carbon emission value according to the phase data, material data, equipment data, and environmental data;

[0115] S2: Calculate several prediction adjustment time windows according to the carbon emission data and the actual carbon emission value; generate several carbon emission prediction values according to the several prediction adjustment time windows;

[0116] S3: Generate a carbon optimization plan based on several carbon emission prediction values; make adjustments according to the carbon optimization plan;

[0117] S4: Give a prompt according to the alarm signal and contact the management personnel.

[0118] Some data in the above formula is calculated by taking its numerical value after removing the dimension. The formula is obtained by software simulation of a large amount of collected data to get a formula closest to the actual situation; the preset parameters and preset thresholds in the formula are set by those skilled in the art according to the actual situation or obtained through simulation of a large amount of data.

[0119] The working principle of this application: Obtain stage data, material data, equipment data, environmental data and carbon emission data; calculate the actual carbon emission value according to the stage data, material data, equipment data and environmental data; calculate several prediction adjustment time windows according to the carbon emission data and the actual carbon emission value; generate several carbon emission prediction values according to the several prediction adjustment time windows; generate a carbon optimization plan according to the several carbon emission prediction values; make adjustments according to the carbon optimization plan; give a prompt according to the alarm signal and contact the management personnel, compare the error at the current stage with the error range within the current time window, and dynamically adjust the size of the prediction time window to more accurately predict the carbon emission amount, provide data support for the carbon optimization plan after the carbon emission exceeds the standard, improve the accuracy and efficiency of the carbon emission monitoring system, and avoid the problems that some technologies lack the prediction of the carbon emission output and the optimization plan after the excess situation occurs, resulting in a low efficiency of the carbon emission monitoring system.

[0120] The above embodiments are only used to illustrate the technical method of this application and not to limit it. Although this application has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical method of this application can be modified or equivalently replaced without departing from the spirit and scope of the technical method of this application.

Claims

1. The carbon emission monitoring system based on road and bridge construction is characterized by: include: Data collection module, data analysis module, early warning module and database; The data acquisition module acquires stage data, material data, equipment data, environmental data and carbon emission data through data acquisition equipment; The data analysis module: calculates the actual value of carbon emissions according to stage data, material data, equipment data and environmental data; calculates a number of forecast adjustment time windows according to the carbon emission data and the actual value of carbon emissions; generates a number of carbon emission estimation values ​​according to the number of forecast adjustment time windows; generates a carbon optimization plan according to the number of carbon emission estimation values; Adjust according to the carbon optimization plan; The generating of a carbon optimization scheme based on a number of carbon emission estimates includes: Determine whether certain carbon emission estimates are greater than their corresponding stage thresholds; If yes, generate a carbon emission exceeding standard alarm signal; obtain a stage label corresponding to the carbon emission estimate; and obtain a carbon optimization plan according to a rule base corresponding to the stage label; No, do nothing; The step of obtaining a carbon optimization solution according to a rule base corresponding to the stage label includes the following steps: Step 1: Obtain the stage label corresponding to the carbon emission estimate and the rule base corresponding to the stage label; Step 2: Create a temporary rule base for the stage; the temporary rule base for the stage is consistent with the rule base corresponding to the stage label; Step 3: Searching for several carbon optimization methods in the stage temporary rule base for the material data and equipment data corresponding to the stage label; deleting the several carbon optimization methods and their corresponding rule priorities from the stage temporary rule base; Step 4: Extract the carbon optimization methods corresponding to the highest rule priority values ​​in the rule base in turn; generate an optimized estimated value for the carbon optimization method through the carbon emission estimation model corresponding to the stage label; delete the carbon optimization method and its corresponding rule priority from the stage temporary rule base; determine whether the optimized estimated value is less than the stage threshold; if yes, organize several of the carbon optimization methods into a carbon optimization plan; if no, determine whether the stage temporary rule base is empty, if yes, generate an alarm signal that there is no optimization plan; if no, proceed to step 4.

2. The carbon emission monitoring system based on road and bridge construction according to claim 1 is characterized in that: The actual value of carbon emissions is calculated based on stage data, material data, equipment data and environmental data, including: Acquire stage data, material data, equipment data and environmental data; the stage data includes stage ID and stage tag; the stage tag includes production tag, transportation tag and construction tag; the environmental data includes temperature, humidity, rainfall, average road slope and weather forecast data; the material data includes several material parameters; By formula Calculate the actual value of production carbon emissions STS; where i represents the material number, M represents the material mass, EF 材,i It is expressed as the carbon emission factor of material production when the i-th material is produced; W i and S i They are respectively expressed as the difference between the actual average temperature and the reference temperature during material production and the difference between the actual average humidity and the reference humidity during material production; α i and β i They are expressed as temperature sensitivity coefficient and humidity sensitivity coefficient respectively; By formula Calculate the actual value of transportation carbon emissions YTS; where JL is the transportation distance, RX is the fuel efficiency of the transportation tool, γ is the rainfall influence coefficient, ε is the slope influence coefficient, γ and ε∈(0,1); PD i is the road flatness and slope, uphill is positive and downhill is negative; By formula Calculate the actual value of construction carbon emissions JTS; where m represents the number of power equipment during construction, n represents the number of fuel equipment, DL represents the power consumption, RL represents the fuel volume, COP (W m ) is the energy efficiency ratio of the equipment at temperature W; μ(P n ) is the air pressure correction factor; EF is the carbon emission factor.

3. The carbon emission monitoring system based on road and bridge construction according to claim 1 is characterized in that: The calculation of a plurality of forecast adjustment time windows according to the carbon emission data and the actual carbon emission value includes: Obtaining carbon emission data and a number of carbon emission actual values ​​TPS; the carbon emission data includes a number of carbon emission estimated values ​​TPY; By formula Calculate the emission error PW j,t ; Wherein, j represents the stage number and t represents the time number; Determine whether the emission error is within its corresponding error range; the error range is calculated based on historical emission errors; Yes, do nothing; No, generate several forecast adjustment time windows based on emissions errors.

4. The carbon emission monitoring system based on road and bridge construction according to claim 3 is characterized in that: The error range is calculated using historical emissions errors, including: Obtaining historical emission errors corresponding to several stage labels; the historical emission errors are several historical emission errors within the current time window; Arrange several historical emission errors in the current time window from small to large to obtain the error sequence WL j ; Get WL j The median Med j and interquartile range IQR j ; Error range WF j WF j ∈[Med j -IQR j , Med j +IQR j ].

5. The carbon emission monitoring system based on road and bridge construction according to claim 3 is characterized in that: The generating of a plurality of prediction adjustment time windows according to the emission error comprises: Get the emission error PW j,t and error margin WF j ; The error range includes the error range boundary value WFB j ; By formula Calculate the forecast adjustment time window SC j,t+1 ; Where σ represents the adjustment coefficient, σ∈(0,1); SC j,max and SC j,min They are respectively represented as the maximum and minimum values ​​of the j-th stage time window; Indicated as rounded up symbol; when the emission error is greater than the maximum value in its corresponding error range, WFB j The value of is equal to the maximum value in the error range. When the emission error is less than the minimum value in the corresponding error range, WFB j The value is equal to the minimum value in the error range.

6. The carbon emission monitoring system based on road and bridge construction according to claim 1 is characterized in that: The generating of a plurality of carbon emission estimates according to a plurality of forecast adjustment time windows comprises: Acquire a number of forecast sequences and stage labels; the forecast sequences include material data, equipment data and environmental data within a number of forecast adjustment time windows and their corresponding actual carbon emission values; Several prediction sequences and stage labels are input into a carbon emission estimation model to obtain carbon emission estimation values ​​corresponding to the stage labels; the carbon emission estimation model is constructed through a machine learning model.

7. The carbon emission monitoring system based on road and bridge construction according to claim 6 is characterized in that: The carbon emission estimation model is constructed through a machine learning model, including: Obtain several historical forecast sequences, historical stage labels and their corresponding historical carbon emission actual values; Divide several historical prediction sequences, historical stage labels and their corresponding historical carbon emission actual values ​​into training sets, test sets and validation sets; Select a machine learning model as the base model; Train the basic model with the training set, and adjust the learning rate or other hyperparameters on the validation set to obtain the pre-trained model; By verifying the pre-trained model on the test set, we finally obtain a carbon emission estimation model whose input is a number of prediction sequences and stage labels, and whose output is the carbon emission estimation value corresponding to the stage label.

8. A carbon emission monitoring method based on road and bridge construction, applied to a carbon emission monitoring system based on road and bridge construction as claimed in any one of claims 1 to 7, characterized in that: include: S0: Acquire phase data, material data, equipment data, environmental data and carbon emission data; S1: Calculate the actual value of carbon emissions based on stage data, material data, equipment data and environmental data; S2: Calculate a number of forecast adjustment time windows based on carbon emission data and actual carbon emission values; generate a number of carbon emission estimates based on the number of forecast adjustment time windows; S3: Generate a carbon optimization plan based on several carbon emission estimates; Adjust according to the carbon optimization plan; The generating of a carbon optimization scheme based on a number of carbon emission estimates includes: Determine whether certain carbon emission estimates are greater than their corresponding stage thresholds; If yes, generate a carbon emission exceeding standard alarm signal; obtain a stage label corresponding to the carbon emission estimate; and obtain a carbon optimization plan according to a rule base corresponding to the stage label; No, do nothing; The step of obtaining a carbon optimization solution according to a rule base corresponding to the stage label includes the following steps: Step 1: Obtain the stage label corresponding to the carbon emission estimate and the rule base corresponding to the stage label; Step 2: Create a temporary rule base for the stage; the temporary rule base for the stage is consistent with the rule base corresponding to the stage label; Step 3: Searching for several carbon optimization methods in the stage temporary rule base for the material data and equipment data corresponding to the stage label; deleting the several carbon optimization methods and their corresponding rule priorities from the stage temporary rule base; Step 4: Extract the carbon optimization methods corresponding to the highest rule priority values ​​in the rule base in turn; generate an optimized estimated value for the carbon optimization method through the carbon emission estimation model corresponding to the stage label; delete the carbon optimization method and its corresponding rule priority from the stage temporary rule base; determine whether the optimized estimated value is less than the stage threshold; if yes, organize several of the carbon optimization methods into a carbon optimization plan; if no, determine whether the stage temporary rule base is empty, if yes, generate an alarm signal that there is no optimization plan; if no, proceed to step 4.

Images