Highway construction site carbon emission prediction method and system based on energy consumption data

Abstract

The application discloses a highway construction site carbon emission prediction method and system based on energy consumption data driving, and the method comprises the following steps: acquiring highway construction site data, establishing a multi-source data coupling relationship based on space-time correlation characteristics, extracting construction state characteristic parameters of the current construction stage, establishing a dynamic mapping relationship between the construction state characteristic parameters and energy consumption according to a mapping coefficient, and converting the construction state characteristic parameters into stage energy consumption representation; the stage carbon emission value is obtained by correlating and calculating the stage energy consumption representation and the carbon emission factor, a carbon emission regulation signal is generated when the deviation exceeds the set interval, the target construction state characteristic parameters are determined by inversely solving the dynamic mapping relationship, the construction element adjustment instruction is generated, the construction state characteristic parameters of the subsequent construction stage are updated according to the adjustment instruction, the updated predicted carbon emission value is calculated, and the construction element adjustment instruction is adjusted. The application improves the accuracy and regulation efficiency of carbon emission prediction.

Description

Technical Field

[0001] This invention relates to the field of carbon emission analysis and control technology, specifically to a method and system for predicting carbon emissions from highway construction sites based on energy consumption data. Background Technology

[0002] Carbon emission management is becoming increasingly important during highway construction. Construction sites involve multiple work areas and different construction processes operating simultaneously, resulting in spatial and temporal variations and dynamic changes in carbon emissions. Therefore, differentiated prediction and dynamic control based on actual site conditions are necessary.

[0003] Existing technologies generally employ carbon detection equipment for timed and fixed-point monitoring and predict carbon emissions based on historical data. However, they do not consider the dynamic changes in construction parameters during the construction period. Furthermore, factors such as changes in construction procedures, fluctuations in equipment load, adjustments to material transportation distances, changes in environmental conditions, and fluctuations in construction intensity all significantly impact carbon emissions. Some technical solutions attempt to predict carbon emissions by incorporating construction plans, but they still fail to fully consider the multi-source environmental factors at the construction site. Construction sites involve multi-dimensional heterogeneous data, including equipment operation status monitoring data, dynamic information on construction progress, real-time meteorological data, transportation route planning information, and personnel scheduling records. Existing technologies neither establish a precise dynamic mapping relationship between construction status parameters and carbon emissions nor effectively fuse multi-source heterogeneous data, leading to significant deviations in prediction results and reducing the accuracy and real-time performance of carbon emission predictions.

[0004] Therefore, it is necessary to design a carbon emission prediction method and system for highway construction sites based on energy consumption data that fully considers the impact of dynamic changes in construction-related parameters on carbon emissions, establishes an accurate energy consumption-carbon emission mapping relationship, effectively integrates multi-source heterogeneous information on site and forms a differentiated prediction mechanism, and realizes dynamic control. Summary of the Invention

[0005] To address the aforementioned technical problems, this invention provides the following technical solution: a carbon emission prediction method for highway construction sites based on energy consumption data, the method comprising the following steps: Acquire highway construction site data, establish multi-source data coupling relationship based on the spatiotemporal correlation characteristics of the construction site data, and extract construction status feature parameters of the current construction stage according to the coupling relationship; Based on the construction state characteristic parameters, a mapping coefficient is obtained, and a dynamic mapping relationship between the construction state characteristic parameters and energy consumption is established based on the mapping coefficient. The construction state characteristic parameters are then converted into stage energy consumption characterization quantities using the dynamic mapping relationship. The stage energy consumption characterization quantity is correlated with the carbon emission factor to obtain the stage carbon emission value. When the deviation of the stage carbon emission value from the preset carbon emission benchmark exceeds the set range, a carbon emission control signal is generated. In response to the carbon emission control signal, the target construction state characteristic parameters are determined by reverse solving the dynamic mapping relationship. The construction element adjustment instruction is generated based on the parameter difference between the target construction state characteristic parameters and the current construction state characteristic parameters. The construction status characteristic parameters of subsequent construction stages are updated according to the construction element adjustment instructions, and the updated predicted carbon emission value is calculated through the dynamic mapping relationship to adjust the construction element adjustment instructions.

[0006] According to the above technical solution, the association relationship between different data attributes in the preset database is retrieved. The association relationship includes the response time sequence and influence weight between data attributes. Data records with spatiotemporal consistency in the construction site data are matched according to the association relationship. The intersection position of the data records is determined as the data association node. The multi-source data coupling relationship is established based on the topological connection relationship of the data association node. Based on the data flow direction in the multi-source data coupling relationship, candidate construction state feature parameters are identified, and preset feature patterns corresponding to the candidate construction state feature parameters are extracted from the preset database. The preset feature patterns include the feature value distribution range and the constraint conditions between features. The measured feature values ​​of the candidate construction state feature parameters are matched and calculated with the feature value distribution range in the preset feature pattern to obtain a similarity that represents the degree of consistency between the two. When the similarity meets a set threshold, it is verified whether the candidate construction state feature parameters meet the feature constraints in the preset feature pattern. The candidate construction state feature parameters that pass the verification are marked as the construction state feature parameters.

[0007] According to the above technical solution, establishing a dynamic mapping relationship between the construction state characteristic parameters and energy consumption based on the mapping coefficient, and converting the construction state characteristic parameters into stage energy consumption characteristics using the dynamic mapping relationship includes: The construction status characteristic parameters are divided into direct impact characteristic parameters and indirect impact characteristic parameters according to their impact mechanism on energy consumption. Linear mapping coefficients are established for the direct impact characteristic parameters and nonlinear mapping coefficients are established for the indirect impact characteristic parameters. The dynamic mapping relationship is constructed based on the linear mapping coefficient and the nonlinear mapping coefficient. The linear mapping coefficient in the dynamic mapping relationship is directly proportional to the value of the directly affected class feature parameter, and the nonlinear mapping coefficient changes non-proportionally with the change of the value of the indirectly affected class feature parameter. The direct impact class feature parameters and the indirect impact class feature parameters are weighted and calculated respectively through the dynamic mapping relationship. The weighted result of the direct impact class feature parameters and the weighted result of the indirect impact class feature parameters are coupled and calculated to obtain the stage energy consumption characterization quantity.

[0008] According to the above technical solution, the stage energy consumption characterization quantity is correlated with the carbon emission factor to obtain the stage carbon emission value. When the deviation of the stage carbon emission value from the preset carbon emission benchmark exceeds a set range, a carbon emission control signal is generated, including: An energy structure vector is constructed based on the energy consumption ratio of different energy types in the stage energy consumption characterization quantity. The identification information of each energy type in the energy structure vector is extracted. The corresponding carbon emission factors are retrieved from the preset carbon emission factor library based on the identification information. The retrieved carbon emission factors are combined according to the arrangement order of the corresponding energy types in the energy structure vector to form a carbon emission conversion relationship. Based on the carbon emission conversion relationship, the stage energy consumption characterization quantity is converted into the stage carbon emission value, and the deviation between the stage carbon emission value and the preset carbon emission benchmark is calculated. When the deviation exceeds the set range, a control weight allocation scheme is determined based on the value of the deviation and the controllability of each energy type in the energy structure vector, and a carbon emission control signal carrying the control direction of energy type is generated based on the control weight allocation scheme.

[0009] According to the above technical solution, in response to the carbon emission control signal, the target construction state characteristic parameters are determined by inversely solving the dynamic mapping relationship, including: The energy type regulation direction and deviation information carried in the carbon emission regulation signal are analyzed, and the construction state characteristic parameters corresponding to the energy type that needs to be regulated are determined according to the energy type regulation direction. The target stage carbon emission value is calculated based on the deviation information, and the target stage carbon emission value is used as a reverse solution constraint and substituted into the dynamic mapping relationship. The mapping coefficients in the dynamic mapping relationship are reverse-operated, and the value range of the target construction state characteristic parameters is solved based on the carbon emission value of the target stage and the reverse operation result of the mapping coefficients. The parameter values ​​that meet the construction feasibility constraints are selected from the value range as the target construction state characteristic parameters.

[0010] According to the above technical solution, a construction element adjustment instruction is generated based on the parameter difference between the target construction state characteristic parameters and the current construction state characteristic parameters, including: Calculate the parameter difference between the target construction state feature parameter and the current construction state feature parameter, compare the parameter difference with a preset difference threshold, and classify the corresponding construction state feature parameter as a priority adjustment parameter when the parameter difference is greater than the preset difference threshold, otherwise classify it as a secondary adjustment parameter. For the priority adjustment parameters, construction elements that have a direct impact on the priority adjustment parameters are retrieved from the preset construction element library, and the adjustment direction and adjustment range of the construction elements are determined. For the secondary adjustment parameters, identify the association constraint relationship between the secondary adjustment parameters and the primary adjustment parameters, and determine the adjustment direction and adjustment range of the construction elements corresponding to the secondary adjustment parameters based on the association constraint relationship; Based on the adjustment direction and adjustment range of the construction elements corresponding to the priority adjustment parameters and the secondary adjustment parameters, an adjustment instruction for the construction elements, including the construction element identifier, adjustment direction, and adjustment range, is generated.

[0011] According to the above technical solution, the construction status characteristic parameters of subsequent construction stages are updated according to the construction element adjustment instructions, and the updated predicted carbon emission value is calculated through the dynamic mapping relationship, and the construction element adjustment instructions are adjusted, including: The construction element identifier, adjustment direction, and adjustment range in the construction element adjustment instruction are analyzed. The affected construction state characteristic parameters are determined according to the mapping rules between the construction element identifier and the construction state characteristic parameters. The affected construction state characteristic parameters are then updated according to the adjustment direction and the adjustment range to obtain the updated construction state characteristic parameters. The updated construction status characteristic parameters are input into the dynamic mapping relationship, and the updated predicted carbon emission value is calculated using the mapping coefficients in the dynamic mapping relationship. Determine whether the deviation between the updated predicted carbon emission value and the preset carbon emission benchmark meets the carbon emission control requirements. If the deviation does not meet the carbon emission control requirements, correct the adjustment range in the construction element adjustment instruction according to the direction and magnitude of the deviation, and generate an adjusted construction element adjustment instruction.

[0012] A second aspect of this application provides a carbon emission prediction system for highway construction sites based on energy consumption data, the system comprising: The status acquisition module is used to acquire construction site data of highway construction sites, establish multi-source data coupling relationship based on the spatiotemporal correlation characteristics of the construction site data, and extract construction status feature parameters of the current construction stage according to the coupling relationship. The energy consumption characterization module is used to obtain mapping coefficients based on the construction state characteristic parameters, establish a dynamic mapping relationship between the construction state characteristic parameters and energy consumption based on the mapping coefficients, and use the dynamic mapping relationship to convert the construction state characteristic parameters into stage energy consumption characterization quantities. The instruction adjustment module is used to correlate the stage energy consumption characterization quantity with the carbon emission factor to calculate the stage carbon emission value. When the deviation between the stage carbon emission value and the preset carbon emission benchmark exceeds a set range, a carbon emission control signal is generated. In response to the carbon emission control signal, the target construction state characteristic parameters are determined by reverse solving the dynamic mapping relationship. The construction element adjustment instruction is generated based on the parameter difference between the target construction state characteristic parameters and the current construction state characteristic parameters. The monitoring and update module is used to update the construction status characteristic parameters of subsequent construction stages according to the construction element adjustment instructions, calculate the updated predicted carbon emission value through the dynamic mapping relationship, and adjust the construction element adjustment instructions.

[0013] A third aspect of this application provides an electronic device including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, it causes the electronic device to perform the method described in the first aspect of this application.

[0014] A fourth aspect of this application provides a computer-readable storage medium for storing a computer program that, when run on a computer, causes the computer to perform the method described in the first aspect of this application.

[0015] Compared with existing technologies, the beneficial effects achieved by this invention are as follows: This invention collects multi-source heterogeneous data from construction sites, including information on equipment operating status, construction progress, meteorological environment, transportation routes, and personnel scheduling. It then performs spatiotemporal alignment and feature fusion processing on this multi-source heterogeneous data to generate construction status feature parameters containing panoramic information about the construction status. This solves the technical problem in existing technologies where the lack of effective processing of multi-source data leads to low prediction accuracy, thus improving the data foundation completeness and accuracy of carbon emission prediction. Furthermore, the invention categorizes construction status feature parameters into directly impacting and indirectly impacting types based on their influence mechanism on energy consumption. For each type of feature parameter, linear and nonlinear mapping coefficients are established to construct a dynamic mapping relationship. This solves the technical problem in existing technologies where a precise mapping relationship between energy consumption and carbon emissions is not established, achieving a precise dynamic correlation between construction status parameters and carbon emissions, and improving the energy consumption-carbon emission prediction accuracy. The accuracy of emission conversion is improved by correlating stage energy consumption characteristics with carbon emission factors to calculate stage carbon emission values. A carbon emission control signal is generated based on the deviation between the stage carbon emission value and the preset carbon emission benchmark. The dynamic mapping relationship is then reverse-engineered in response to the carbon emission control signal to determine the target construction state characteristic parameters, thereby generating construction element adjustment instructions. This solves the technical problem of existing technologies failing to consider dynamic changes in construction parameters, leading to the inability to control emissions in real time. It realizes a dynamic feedback control mechanism based on carbon emission deviation, improving the real-time nature and proactivity of carbon emission management. The construction state characteristic parameters of subsequent construction stages are updated based on the construction element adjustment instructions. The updated predicted carbon emission value is calculated through the dynamic mapping relationship, and the construction element adjustment instructions are adjusted, forming a closed-loop control mechanism. This solves the technical problem of existing technologies lacking differentiated prediction and dynamic control capabilities, achieving continuous optimization and precise control of carbon emissions during construction, and reducing the total carbon emissions during highway construction. Attached Figure Description

[0016] The accompanying drawings, which form part of this application, are used to provide a further understanding of this application. The illustrative embodiments and descriptions of this application are used to explain this application and do not constitute an undue limitation of this application. In the drawings: Figure 1 This is a flowchart of the steps of a method for predicting carbon emissions from highway construction sites based on energy consumption data, provided in the embodiments of this application.

[0017] Figure 2 This is a schematic diagram of the system modules for predicting carbon emissions at highway construction sites based on energy consumption data, according to an embodiment of this application.

[0018] Figure 3 This is a schematic diagram of an electronic device according to an embodiment of this application. Detailed Implementation

[0019] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other. This application will now be described in detail with reference to the accompanying drawings and embodiments.

[0020] It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases the steps shown or described may be executed in a different order than that shown here.

[0021] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0022] Please see Figure 1 This invention provides a technical solution: a carbon emission prediction method for highway construction sites based on energy consumption data, comprising: Acquire construction site data of highway construction sites, establish multi-source data coupling relationship based on the spatiotemporal correlation characteristics of construction site carbon emission prediction driven by energy consumption data, and extract construction status feature parameters of the current construction stage based on the coupling relationship of construction site carbon emission prediction driven by energy consumption data. Based on the characteristic parameters of the construction state of the highway construction site carbon emission prediction driven by energy consumption data, the mapping coefficient is obtained. The mapping coefficient of the highway construction site carbon emission prediction driven by energy consumption data establishes a dynamic mapping relationship between the characteristic parameters of the construction state of the highway construction site carbon emission prediction driven by energy consumption data and energy consumption. The dynamic mapping relationship of the highway construction site carbon emission prediction driven by energy consumption data is used to convert the characteristic parameters of the construction state of the highway construction site carbon emission prediction driven by energy consumption data into stage energy consumption characterization. The carbon emission value of a stage is obtained by correlating the energy consumption characterization quantity and carbon emission factor in the carbon emission prediction stage of highway construction sites based on energy consumption data. When the deviation between the carbon emission value of the stage of carbon emission prediction of highway construction sites based on energy consumption data and the preset carbon emission benchmark exceeds the set range, a carbon emission control signal is generated. In response to the carbon emission control signal of carbon emission prediction of highway construction sites based on energy consumption data, the target construction state characteristic parameters are determined by reverse solving the dynamic mapping relationship of carbon emission prediction of highway construction sites based on energy consumption data. The construction element adjustment instruction is generated based on the parameter difference between the target construction state characteristic parameters of carbon emission prediction of highway construction sites based on energy consumption data and the current construction state characteristic parameters. The construction status characteristic parameters of subsequent construction stages are updated according to the construction element adjustment instructions based on energy consumption data-driven highway construction site carbon emission prediction. The updated predicted carbon emission value is calculated through the dynamic mapping relationship of energy consumption data-driven highway construction site carbon emission prediction, and the construction element adjustment instructions based on energy consumption data-driven highway construction site carbon emission prediction are adjusted.

[0023] In some preferred embodiments, construction status characteristic parameters of the current construction stage are extracted based on the coupling relationship between energy consumption data-driven highway construction site carbon emission prediction and the following: Construction site data includes energy consumption attributes, equipment operation attributes, construction progress attributes, environmental condition attributes, and material flow attributes. The correlation between different data attributes in the preset database is retrieved. The correlation for carbon emission prediction of highway construction sites based on energy consumption data includes the response time sequence and influence weight between data attributes. Data records with spatiotemporal consistency in the construction site data are matched according to the correlation for carbon emission prediction of highway construction sites based on energy consumption data. The intersection of the data records for carbon emission prediction of highway construction sites based on energy consumption data is determined as data association nodes. The topological connection relationship of the data association nodes for carbon emission prediction of highway construction sites based on energy consumption data establishes a multi-source data coupling relationship for carbon emission prediction of highway construction sites based on energy consumption data. Based on the data flow direction in the multi-source data coupling relationship of carbon emission prediction for highway construction sites driven by energy consumption data, candidate construction state characteristic parameters are identified. The construction state characteristic parameters reflect the degree of influence of construction procedures, equipment load, material flow and environmental conditions on energy consumption. Preset feature patterns corresponding to the candidate construction state characteristic parameters of carbon emission prediction for highway construction sites driven by energy consumption data are extracted from the preset database of carbon emission prediction for highway construction sites driven by energy consumption data. The preset feature patterns of carbon emission prediction for highway construction sites driven by energy consumption data include the distribution range of feature values ​​and the constraints between features. The measured feature values ​​of candidate construction state feature parameters for carbon emission prediction of highway construction sites based on energy consumption data are matched and calculated with the feature value distribution range in the preset feature mode for carbon emission prediction of highway construction sites based on energy consumption data to obtain the similarity that characterizes the degree of consistency between the two. When the similarity of carbon emission prediction of highway construction sites based on energy consumption data meets the set threshold, it is verified whether the candidate construction state feature parameters for carbon emission prediction of highway construction sites based on energy consumption data meet the feature inter-constraint conditions in the preset feature mode for carbon emission prediction of highway construction sites based on energy consumption data. The candidate construction state feature parameters that pass the verification are marked as construction state feature parameters for carbon emission prediction of highway construction sites based on energy consumption data.

[0024] For example, the association relationships between different data attributes in a preset database are retrieved. These relationships record the response time sequence and influence weight of each data attribute. Based on the response time sequence recorded in the association relationships, data records with spatiotemporal consistency in the construction site data are matched. Specifically, when the time difference between the collection times of data records with different attributes is less than 5 seconds and the distance between their collection locations is less than 10 meters, the group of data records is determined to have spatiotemporal consistency. The intersection of the spatiotemporally consistent data records is determined as a data association node. Directed connections between nodes are established based on the data transmission direction between them, forming a data flow topology. Multi-source data coupling relationships are then established based on the connection relationships between nodes in the topology.

[0025] Candidate construction state feature parameters are identified based on the data flow direction in the multi-source data coupling relationship. Specifically, each data-related node in the topology is traversed, and the in-degree and out-degree of each node are counted. When the in-degree of a node is greater than 2 and the out-degree is greater than 1, the data attribute corresponding to that node is used as a candidate construction state feature parameter. Preset feature patterns corresponding to the candidate construction state feature parameters are extracted from a preset database. The preset feature patterns include the feature value distribution range and the constraints between features. The feature value distribution range is obtained from historical construction data statistics, and the constraints between features reflect the impact mechanism of construction procedures, equipment load, material flow, and environmental conditions on energy consumption.

[0026] The measured feature values ​​of candidate construction state characteristic parameters are matched with the feature value distribution range in the preset feature pattern to obtain the similarity. The similarity calculation process is as follows: the proportion of data points whose measured feature values ​​fall within the feature value distribution range to the total number of data points is counted, and this proportion is the similarity. When the similarity is greater than 0.85, it is verified whether the candidate construction state characteristic parameters meet the feature constraints in the preset feature pattern. The constraint verification process includes: extracting the feature constraints recorded in the preset feature pattern, which are represented by numerical ratios or logical dependencies between feature parameters; substituting the measured feature values ​​of the candidate construction state characteristic parameters into the constraint relationships for calculation; and determining that the verification is successful when the calculation result meets the requirements of the constraint relationships. The verified candidate construction state characteristic parameters are marked as the construction state characteristic parameters of the current construction stage.

[0027] The above technical solution enables spatiotemporal alignment and correlation analysis of multi-source heterogeneous construction site data, establishes coupling relationships between data attributes, and identifies construction status characteristic parameters that significantly impact energy consumption based on data flow topology. By matching and verifying measured characteristic values ​​with preset characteristic patterns, interfering parameters that do not conform to construction logic and energy consumption impact mechanisms are eliminated. The extracted construction status characteristic parameters accurately reflect the energy consumption status of the current construction stage, providing a reliable data foundation for subsequent establishment of dynamic mapping relationships and carbon emission prediction, thus improving the accuracy of carbon emission prediction.

[0028] In some preferred embodiments, a dynamic mapping relationship is established between the construction status characteristic parameters of highway construction sites and energy consumption based on the energy consumption data-driven carbon emission prediction mapping coefficient. This dynamic mapping relationship is then used to convert the construction status characteristic parameters of highway construction sites into stage-specific energy consumption metrics, including: The construction status characteristic parameters of highway construction site carbon emission prediction based on energy consumption data are divided into direct impact characteristic parameters and indirect impact characteristic parameters according to their impact mechanism on energy consumption. Linear mapping coefficients are established for the direct impact characteristic parameters of highway construction site carbon emission prediction based on energy consumption data, and nonlinear mapping coefficients are established for the indirect impact characteristic parameters of highway construction site carbon emission prediction based on energy consumption data. A dynamic mapping relationship for carbon emission prediction of highway construction sites based on energy consumption data is constructed using linear and nonlinear mapping coefficients. The linear mapping coefficients are directly proportional to the values ​​of the feature parameters that directly affect the carbon emission prediction of highway construction sites, while the nonlinear mapping coefficients change non-proportionally with the values ​​of the feature parameters that indirectly affect the carbon emission prediction of highway construction sites. By using the dynamic mapping relationship of carbon emission prediction for highway construction sites driven by energy consumption data, the direct and indirect impact characteristic parameters of carbon emission prediction for highway construction sites driven by energy consumption data are weighted and calculated separately. The weighted results of the direct impact characteristic parameters of carbon emission prediction for highway construction sites driven by energy consumption data are coupled with the weighted results of the indirect impact characteristic parameters of carbon emission prediction for highway construction sites driven by energy consumption data to obtain the energy consumption characterization quantity of the carbon emission prediction stage of highway construction sites driven by energy consumption data.

[0029] For example, construction status characteristic parameters are classified according to their impact mechanism on energy consumption. Specifically, the physical relationship between each construction status characteristic parameter and energy consumption is analyzed. When there is a direct physical or chemical process link between changes in construction status characteristic parameters and changes in energy consumption, the parameter is classified as a directly affected characteristic parameter. For example, parameters such as equipment power and operating time directly determine the amount of electricity consumed. When construction status characteristic parameters indirectly affect energy consumption by influencing other intermediate factors, the parameter is classified as an indirectly affected characteristic parameter. For example, ambient temperature affects energy consumption by influencing equipment heat dissipation efficiency, and material transportation distance affects fuel consumption by influencing the travel time of transport vehicles.

[0030] Linear mapping coefficients are established for directly impacting characteristic parameters. Corresponding records of these parameters and actual energy consumption are obtained from historical construction data. Linear regression analysis is performed on these records to obtain the proportional relationship between the directly impacting characteristic parameters and energy consumption; the slope of this proportional relationship is the linear mapping coefficient. Nonlinear mapping coefficients are established for indirectly impacting characteristic parameters. The rate of change in energy consumption corresponding to different value ranges of indirectly impacting characteristic parameters in historical construction data is statistically analyzed. The type of nonlinear mapping function is determined based on the distribution pattern of the rate of change, preferably a polynomial or exponential function. The coefficients of the nonlinear mapping function are determined by fitting historical data; these coefficients are the nonlinear mapping coefficients.

[0031] A dynamic mapping relationship is constructed based on linear and nonlinear mapping coefficients. This dynamic mapping relationship is represented as a functional relationship between stage energy consumption characteristics and construction state characteristic parameters. Directly influencing characteristic parameters are associated with stage energy consumption characteristics through linear mapping coefficients, while indirectly influencing characteristic parameters are associated with stage energy consumption characteristics through nonlinear mapping coefficients. Specifically, the dynamic mapping relationship can be expressed as follows: Where E is the energy consumption characteristic of the stage, in kilowatt-hours; m is the number of directly influential class feature parameters; P i Let be the value of the i-th directly influential class feature parameter; is the linear mapping coefficient corresponding to the i-th directly influential class feature parameter; n is the number of indirectly influential class feature parameters; Let be the value of the feature parameter of the j-th indirect influence class; Let be the nonlinear mapping function corresponding to the feature parameter of the j-th indirect influence class.

[0032] The direct and indirect impact characteristic parameters are weighted separately using a dynamic mapping relationship. The measured values ​​of each direct impact characteristic parameter in the current construction stage are substituted into the corresponding linear mapping coefficients for multiplication to obtain the weighted result of each direct impact characteristic parameter. The total contribution of all direct impact characteristic parameters is then summed. Similarly, the measured values ​​of each indirect impact characteristic parameter in the current construction stage are substituted into the corresponding nonlinear mapping function for calculation to obtain the weighted result of each indirect impact characteristic parameter. The total contribution of all indirect impact characteristic parameters is then summed.

[0033] The total contribution of directly influencing characteristic parameters and the total contribution of indirectly influencing characteristic parameters are coupled to obtain the stage energy consumption characterization. The coupling operation involves summing the two values, and the result is the stage energy consumption characterization for the current construction stage. This stage energy consumption characterization comprehensively reflects the combined effect of direct and indirect influencing factors on energy consumption at the construction site.

[0034] Through the above technical solution, differentiated mapping coefficients were established based on the different impact mechanisms of construction status characteristic parameters on energy consumption. For directly impacting characteristic parameters, linear mapping coefficients accurately reflect the direct proportional relationship between them and energy consumption. For indirectly impacting characteristic parameters, nonlinear mapping coefficients accurately characterize their non-proportional impact on energy consumption. The constructed dynamic mapping relationship organically combines linear and nonlinear mappings, achieving precise conversion of construction status characteristic parameters into stage-specific energy consumption metrics. This improves the accuracy of energy consumption prediction and provides a reliable energy consumption data foundation for subsequent carbon emission calculations.

[0035] In some preferred embodiments, the stage carbon emission value is obtained by correlating the energy consumption characterization quantity of the carbon emission prediction stage of highway construction sites based on energy consumption data with carbon emission factors. When the deviation between the stage carbon emission value of the carbon emission prediction stage of highway construction sites based on energy consumption data and the preset carbon emission benchmark exceeds a set range, a carbon emission control signal is generated, including: An energy structure vector is constructed based on the energy consumption proportion of different energy types in the energy consumption characterization of the carbon emission prediction stage of highway construction sites driven by energy consumption data. The identification information of each energy type in the energy structure vector of the carbon emission prediction of highway construction sites driven by energy consumption data is extracted. The corresponding carbon emission factors are retrieved in the preset carbon emission factor library based on the identification information of the carbon emission prediction of highway construction sites driven by energy consumption data. The retrieved carbon emission factors are combined according to the arrangement order of the corresponding energy types in the energy structure vector of the carbon emission prediction of highway construction sites driven by energy consumption data to form a carbon emission conversion relationship. The carbon emission conversion relationship of the carbon emission prediction of highway construction sites based on energy consumption data converts the energy consumption characterization quantity of the carbon emission prediction stage of highway construction sites based on energy consumption data into the carbon emission value of the carbon emission prediction stage of highway construction sites based on energy consumption data, and calculates the deviation between the carbon emission value of the carbon emission prediction stage of highway construction sites based on energy consumption data and the preset carbon emission benchmark of the carbon emission prediction of highway construction sites based on energy consumption data. When the deviation of the carbon emission prediction for highway construction sites driven by energy consumption data exceeds the set range of the carbon emission prediction for highway construction sites driven by energy consumption data, a control weight allocation scheme is determined based on the value of the deviation of the carbon emission prediction for highway construction sites driven by energy consumption data and the controllability of each energy type in the energy structure vector of the carbon emission prediction for highway construction sites driven by energy consumption data. The control weight allocation scheme of the carbon emission prediction for highway construction sites driven by energy consumption data generates a carbon emission control signal for the carbon emission prediction for highway construction sites driven by energy consumption data, which carries the control direction of energy type.

[0036] For example, an energy structure vector is constructed based on the energy consumption proportion of different energy types in the stage energy consumption representation. Specifically, the energy types included in the stage energy consumption representation and their corresponding energy consumption values ​​are identified. Energy types include electricity, diesel, gasoline, and natural gas. The proportion of each energy type's energy consumption value to the total value of the stage energy consumption representation is calculated. The energy consumption proportions of each energy type are combined according to the order of energy types to form the energy structure vector. The identification information of each energy type in the energy structure vector is extracted. The identification information includes the energy type name and energy consumption. The corresponding carbon emission factor is retrieved from a preset carbon emission factor library based on the identification information. The carbon emission factor library stores the carbon emissions corresponding to the unit consumption of each energy type. For example, the carbon emission corresponding to each kilowatt-hour of electricity is 0.785 kg of CO2 equivalent, and the carbon emission corresponding to each liter of diesel is 2.63 kg of CO2 equivalent. The retrieved carbon emission factors are combined according to the order of the corresponding energy types in the energy structure vector to form a carbon emission conversion relationship. The carbon emission conversion relationship establishes the correspondence between the energy consumption and carbon emissions of each energy type.

[0037] Based on the carbon emission conversion relationship, the stage energy consumption characterization quantity is converted into the stage carbon emission value. The energy consumption of each energy type in the energy structure vector is multiplied by its corresponding carbon emission factor to obtain the carbon emission amount for each energy type. The carbon emission amounts of all energy types are summed, and the sum is the stage carbon emission value, expressed in kilograms of carbon dioxide equivalent. The deviation between the stage carbon emission value and a preset carbon emission benchmark is calculated. The preset carbon emission benchmark is pre-set based on the construction plan and carbon emission control targets. The deviation is obtained by subtracting the preset carbon emission benchmark from the stage carbon emission value. A positive deviation indicates that the actual carbon emission exceeds the benchmark value, while a negative deviation indicates that the actual carbon emission is lower than the benchmark value.

[0038] Determine if the deviation exceeds the set range. The upper limit of the set range is set to 5% to 8% of the preset carbon emission benchmark, and the lower limit is set to -5% to -8% of the preset carbon emission benchmark. When the absolute value of the deviation is greater than the upper or lower limit of the set range, it is determined that the deviation exceeds the set range. Determine the controllability weight allocation scheme based on the deviation value and the controllability of each energy type in the energy structure vector. Controllability reflects the ease with which each energy type can be adjusted under current construction conditions. The controllability value is determined by evaluating the substitutability of energy types, the flexibility of equipment adjustment, and the variability of the construction process. The controllability value ranges from 0 to 1; a larger value indicates that the energy type is easier to control. Calculate the controllability weight for each energy type. The controllability weight is proportional to the energy consumption proportion of that energy type in the energy structure vector and the controllability value. Specifically, the controllability weight is expressed as... , in, R represents the control weight of the s-th energy type; h represents the total number of energy types; R s Let A be the energy consumption percentage of the s-th energy type in the energy structure vector; s Let be the controllability value for the s-th energy type. A control weight allocation scheme is formed based on the control weights of each energy type, indicating the proportion of control each energy type should bear when regulating carbon emissions.

[0039] A carbon emission control signal carrying the control direction of energy type is generated based on the control weight allocation scheme. The carbon emission control signal includes the energy type identifier to be controlled, the control direction, and the control magnitude. The control direction is determined by the sign of the deviation; when the deviation is positive, the control direction is to reduce energy consumption; when the deviation is negative, the control direction is to maintain or increase energy consumption. The control magnitude is calculated based on the absolute value of the deviation and the control weight of the corresponding energy type. The carbon emission control signal is output to the construction management terminal to guide energy use adjustments at the construction site.

[0040] Through the above technical solution, an energy structure vector was established based on the consumption structure of different energy types in the stage energy consumption characterization. A carbon emission factor library was used to achieve accurate conversion from energy consumption to carbon emissions, obtaining a stage carbon emission value that reflects the current carbon emission level of the construction stage. By calculating the deviation between the stage carbon emission value and the preset carbon emission benchmark and determining whether it exceeds a set range, timely identification of abnormal carbon emission states was achieved. When the deviation exceeds the set range, a control weight allocation scheme was determined based on the energy consumption proportion and controllability of each energy type, generating a carbon emission control signal with a clear control direction. This provides a precise decision-making basis for carbon emission control at the construction site, improving the real-time performance and effectiveness of carbon emission management.

[0041] In some preferred embodiments, in response to the carbon emission prediction and control signal of highway construction site driven by energy consumption data, the target construction state characteristic parameters are determined by inversely solving the dynamic mapping relationship of highway construction site carbon emission prediction driven by energy consumption data, including: This paper analyzes the energy type regulation direction and deviation information carried in the carbon emission prediction and regulation signal of highway construction site based on energy consumption data, and determines the construction status characteristic parameters corresponding to the energy type that needs to be regulated based on the energy type regulation direction of the carbon emission prediction of highway construction site based on energy consumption data. The carbon emission value of the target stage is calculated based on the deviation information of carbon emission prediction of highway construction site driven by energy consumption data. The carbon emission value of the target stage of carbon emission prediction of highway construction site driven by energy consumption data is used as the inverse solution constraint and substituted into the dynamic mapping relationship of carbon emission prediction of highway construction site driven by energy consumption data. The mapping coefficients in the dynamic mapping relationship of carbon emission prediction for highway construction sites driven by energy consumption data are reverse-engineered. Based on the reverse-engineering results of the carbon emission values ​​of the target stage of carbon emission prediction for highway construction sites driven by energy consumption data and the mapping coefficients of carbon emission prediction for highway construction sites driven by energy consumption data, the value range of the characteristic parameters of the target construction state of carbon emission prediction for highway construction sites driven by energy consumption data is solved. From the value range of carbon emission prediction for highway construction sites driven by energy consumption data, the parameter values ​​that meet the construction feasibility constraints are selected as the characteristic parameters of the target construction state of carbon emission prediction for highway construction sites driven by energy consumption data.

[0042] For example, the energy type control direction and deviation information carried in the carbon emission control signal are analyzed. The energy type control direction indicates the specific energy type that needs to be controlled, and the deviation information records the numerical value and direction of the deviation between the stage carbon emission value and the preset carbon emission benchmark. Based on the energy type control direction, the corresponding energy type is located in the energy structure vector, and the construction status characteristic parameters associated with that energy type in the dynamic mapping relationship are queried. Specifically, when the energy type control direction is electricity, the construction status characteristic parameters that need to be controlled include the operating power, operating time, and number of electric drive equipment; when the energy type control direction is diesel, the construction status characteristic parameters that need to be controlled include the load rate, transportation distance, and operation frequency of fuel-powered equipment.

[0043] The target stage carbon emission value is calculated based on deviation information. The deviation value in the deviation information is subtracted from the preset carbon emission benchmark to obtain the target stage carbon emission value. The target stage carbon emission value represents the carbon emission level that should be achieved to bring the stage carbon emission value back to the preset carbon emission benchmark range. The target stage carbon emission value is then converted into a target stage energy consumption characteristic using a carbon emission conversion relationship. The conversion process involves dividing the target stage carbon emission value by the carbon emission factor of the corresponding energy type to obtain the target energy consumption for that energy type. This target stage energy consumption characteristic is then substituted into the dynamic mapping relationship as a back-solved constraint. The constraint limits the numerical relationships that each construction state characteristic parameter should satisfy, provided that the target stage carbon emission value is met.

[0044] The mapping coefficients in the dynamic mapping relationship are processed in reverse. For the linear mapping coefficients corresponding to the directly affecting characteristic parameters, the target value of the directly affecting characteristic parameter is obtained by dividing the target energy consumption by the linear mapping coefficient. For the nonlinear mapping coefficients corresponding to the indirect affecting characteristic parameters, the nonlinear mapping function is transformed by an inverse function, and the target energy consumption is substituted into the inverse function to obtain the target value of the indirect affecting characteristic parameter. Since the dynamic mapping relationship contains multiple construction state characteristic parameters, the inverse operation yields the range of values ​​for the target construction state characteristic parameters, rather than a unique solution. The range of values ​​satisfies the mathematical condition that the stage energy consumption characterization reaches the target value.

[0045] Parameter values ​​that meet the construction feasibility constraints are selected from the range of possible values ​​as target construction state characteristic parameters. These constraints include equipment performance constraints, construction process constraints, and safety regulations constraints. Equipment performance constraints limit equipment operating parameters to within the rated operating range. Construction process constraints require that parameter adjustments still guarantee construction quality and schedule requirements. Safety regulations constraints ensure that parameter adjustments will not cause construction safety hazards. Feasibility verification is performed on each parameter value within the range. Specifically, it checks whether the equipment operating power is within 30% to 95% of the rated power, whether adjusting the operating frequency meets the construction schedule requirements, and whether adjusting the equipment load rate will lead to overheating or increased mechanical wear. Parameter values ​​that do not meet the construction feasibility constraints are eliminated, and those that meet all constraints are retained. From the retained parameters, the value with the least impact on the construction process and the lowest implementation difficulty is selected as the target construction state characteristic parameter. The target construction state characteristic parameter achieves both carbon emission control targets and ensures the normal progress of construction.

[0046] The target construction state characteristic parameters are output to the construction management terminal to guide parameter adjustments at the construction site. Based on these parameters, the terminal generates specific equipment control instructions and construction organization adjustment plans, such as reducing the operating power of some electrically driven equipment, optimizing material transportation routes to shorten transportation distances, and adjusting construction work periods to utilize lower ambient temperatures and reduce equipment heat dissipation energy consumption. After parameter adjustments are implemented, construction site data is re-collected, and new stage carbon emission values ​​are calculated. These new values ​​are compared with preset carbon emission benchmarks to verify the effectiveness of the parameter adjustments. When the deviation between the new stage carbon emission value and the preset benchmark is within a set range, the parameter adjustments have achieved the expected results, and construction continues according to the target construction state characteristic parameters. If the deviation still exceeds the set range, the reverse calculation process is repeated to further optimize the values ​​of the target construction state characteristic parameters.

[0047] Based on the energy type control direction and deviation information in the carbon emission control signal, a reverse solution path was established from the target carbon emission level to the target construction state characteristic parameters. By performing inverse calculations on the mapping coefficients in the dynamic mapping relationship, precise tracing from the energy consumption level to the construction parameter level was achieved, obtaining the value range of construction state characteristic parameters that can meet the carbon emission control target. Through the screening of construction feasibility constraints, the feasibility of the target construction state characteristic parameters in engineering practice was ensured. A complete closed-loop control mechanism was established from carbon emission monitoring, deviation identification, control signal generation to parameter adjustment implementation, improving the intelligence level and control accuracy of carbon emission management at highway construction sites.

[0048] In some preferred embodiments, a construction element adjustment instruction is generated based on the parameter difference between the target construction state characteristic parameters of the highway construction site carbon emission prediction driven by energy consumption data and the current construction state characteristic parameters, including: Calculate the parameter difference between the target construction state characteristic parameters of the carbon emission prediction of the highway construction site based on energy consumption data and the current construction state characteristic parameters of the carbon emission prediction of the highway construction site based on energy consumption data. Compare the parameter difference of the carbon emission prediction of the highway construction site based on energy consumption data with a preset difference threshold. When the parameter difference of the carbon emission prediction of the highway construction site based on energy consumption data is greater than the preset difference threshold of the carbon emission prediction of the highway construction site based on energy consumption data, the corresponding construction state characteristic parameter is classified as a priority adjustment parameter; otherwise, it is classified as a secondary adjustment parameter. For the priority adjustment parameters of carbon emission prediction of highway construction sites based on energy consumption data, construction elements that have a direct impact on the priority adjustment parameters of carbon emission prediction of highway construction sites based on energy consumption data are retrieved from the preset construction element library, and the adjustment direction and adjustment range of the construction elements of carbon emission prediction of highway construction sites based on energy consumption data are determined. For secondary adjustment parameters of carbon emission prediction for highway construction sites driven by energy consumption data, the correlation and constraint relationship between secondary adjustment parameters and priority adjustment parameters of carbon emission prediction for highway construction sites driven by energy consumption data is identified. Based on the correlation and constraint relationship of carbon emission prediction for highway construction sites driven by energy consumption data, the adjustment direction and adjustment range of the construction elements corresponding to the secondary adjustment parameters of carbon emission prediction for highway construction sites driven by energy consumption data are determined. Based on the adjustment direction and adjustment range of the construction elements corresponding to the priority adjustment parameters and secondary adjustment parameters of the carbon emission prediction of highway construction sites driven by energy consumption data, an adjustment instruction for construction elements of carbon emission prediction of highway construction sites driven by energy consumption data is generated, which includes the construction element identifier, adjustment direction and adjustment range.

[0049] For example, the parameter difference between the target construction state characteristic parameter and the current construction state characteristic parameter is calculated. For each construction state characteristic parameter, the value of the target construction state characteristic parameter is subtracted from the value of the current construction state characteristic parameter to obtain the corresponding parameter difference. This parameter difference is then compared with a preset difference threshold. The preset difference threshold is set based on the sensitivity of each construction state characteristic parameter to energy consumption. For directly impactful characteristic parameters, the preset difference threshold is set to 8% to 12% of the normal range of that parameter. For example, the normal range for equipment operating power is... to The corresponding preset difference threshold is set to For indirectly affecting characteristic parameters, the preset difference threshold is set to 15% to 20% of the normal range of the parameter. For example, the normal range of ambient temperature is -10℃ to 40℃, and the corresponding preset difference threshold is set to 8℃. When the absolute value of the parameter difference is greater than the preset difference threshold, the corresponding construction state characteristic parameter is classified as a priority adjustment parameter, indicating that the current value of the parameter deviates significantly from the target value and needs to be adjusted first. When the absolute value of the parameter difference is less than or equal to the preset difference threshold, the corresponding construction state characteristic parameter is classified as a secondary adjustment parameter, indicating that the current value of the parameter deviates slightly from the target value and can be adjusted after the priority adjustment parameters have been adjusted.

[0050] For priority adjustment parameters, construction elements that directly influence these parameters are retrieved from a pre-set construction element library. This library stores the mapping relationships between various construction state characteristic parameters and construction elements, including equipment configuration, work procedures, material supply, and personnel arrangement. Specifically, when the priority adjustment parameter is equipment operating power, the corresponding construction elements are equipment gear settings and load distribution methods; when the priority adjustment parameter is work frequency, the corresponding construction elements are work schedules and shift rotation cycles. The adjustment direction and magnitude of the construction elements are determined based on the value and direction of the parameter difference. The adjustment direction is determined by the sign of the parameter difference: a positive difference increases the intensity of the construction element's effect, while a negative difference decreases its effect. The adjustment magnitude is calculated based on the ratio of the parameter difference to a pre-set difference threshold; a larger ratio results in a larger adjustment magnitude. For example, when the parameter difference for equipment operating power is negative... The preset difference threshold is A ratio of 2 corresponds to an adjustment that reduces the equipment speed from level three to level two, resulting in a power reduction of approximately [missing information]. .

[0051] For secondary adjustment parameters, the correlation constraints between secondary and primary adjustment parameters are identified. These constraints reflect the mutual influence mechanism between characteristic parameters of different construction states. The correlation constraints are obtained by analyzing the node connections in the multi-source data coupling relationship. Specifically, when the secondary adjustment parameter is material transportation distance and the primary adjustment parameter is vehicle load rate, the correlation constraint means that the adjustment of transportation distance must be coordinated with the adjustment of vehicle load rate to avoid a situation where a decrease in vehicle load rate but an increase in transportation distance leads to an increase in total energy consumption. Based on the correlation constraints, the adjustment direction and magnitude of the corresponding construction elements for the secondary adjustment parameters are determined. The adjustment direction should be consistent with or complementary to the adjustment direction of the primary adjustment parameters. The adjustment magnitude is obtained by multiplying the parameter difference of the secondary adjustment parameters by the correlation constraint coefficient. The correlation constraint coefficient reflects the adjustment ratio of the secondary adjustment parameters relative to the primary adjustment parameters. The value of the correlation constraint coefficient ranges from 0.3 to 0.7, with a value close to 0.7 when the correlation constraint is strong and close to 0.3 when the correlation constraint is weak.

[0052] Based on the adjustment direction and magnitude of the construction elements corresponding to the priority adjustment parameters and secondary adjustment parameters, construction element adjustment instructions are generated. Each construction element adjustment instruction includes three pieces of information: construction element identifier, adjustment direction, and adjustment magnitude. The construction element identifier uniquely identifies the construction element requiring adjustment; the adjustment direction indicates whether the effect of the construction element should be enhanced or weakened; and the adjustment magnitude represents the degree to which the construction element should be adjusted, expressed as a specific value or level. For construction elements corresponding to priority adjustment parameters, a priority identifier is marked in the construction element adjustment instruction to ensure that this type of instruction is executed first. For construction elements corresponding to secondary adjustment parameters, the corresponding priority adjustment parameter identifier is associated with the construction element adjustment instruction to ensure that secondary adjustments are executed only after priority adjustments are completed, avoiding parameter conflicts caused by incorrect adjustment order. The construction element adjustment instructions are output to the construction management terminal, which generates specific operation instructions based on the instruction content. For example, when the instruction is to adjust the excavator's operating power from third gear to second gear, the generated operation instructions would instruct the excavator operator to push the gear control lever from the third gear position to the second gear position and monitor whether the equipment power display value reaches the target range.

[0053] After the construction element adjustment command is executed, new construction site data is collected and new current construction status characteristic parameters are extracted. These new current construction status characteristic parameters are compared with the target construction status characteristic parameters, and the adjusted parameter difference is calculated. When the adjusted parameter difference is less than 50% of the preset difference threshold, the construction element adjustment is deemed to have achieved the expected effect, and construction continues according to the adjusted construction element configuration. When the adjusted parameter difference is still greater than 50% of the preset difference threshold, the reasons for the poor adjustment effect are analyzed. Possible reasons include insufficient adjustment range, delayed response of construction elements, or the existence of unidentified interference factors. Based on the analysis results, the adjustment range is recalculated or supplementary adjustment measures are added, a new construction element adjustment command is generated, and executed.

[0054] Based on the above technical solution, a conversion mechanism from construction state characteristic parameters to construction elements was established using the parameter difference between the target construction state characteristic parameters and the current construction state characteristic parameters. By comparing the parameter difference with a preset difference threshold, priority was assigned to the construction state characteristic parameters that needed adjustment, ensuring that adjustment resources were prioritized for parameters with the greatest impact on carbon emissions. By identifying the correlation and constraint relationships between secondary adjustment parameters and priority adjustment parameters, mutual interference during the parameter adjustment process was avoided, ensuring the coordination and effectiveness of adjustment measures. This formed a complete control path from carbon emission deviation identification and target parameter solution to the implementation of construction element adjustments, achieving precise control of carbon emissions at highway construction sites.

[0055] In some preferred embodiments, the construction status characteristic parameters of subsequent construction stages are updated according to the energy consumption data-driven highway construction site carbon emission prediction construction element adjustment instructions. The updated predicted carbon emission values ​​are calculated through the energy consumption data-driven highway construction site carbon emission prediction dynamic mapping relationship, and the energy consumption data-driven highway construction site carbon emission prediction construction element adjustment instructions are adjusted, including: This paper analyzes the construction element identifier, adjustment direction, and adjustment range in the construction element adjustment instruction of the carbon emission prediction of highway construction sites based on energy consumption data. According to the mapping rule between the construction element identifier and the construction status characteristic parameters of the carbon emission prediction of highway construction sites based on energy consumption data, the affected construction status characteristic parameters are determined. The affected construction status characteristic parameters are then numerically updated according to the adjustment direction and adjustment range of the carbon emission prediction of highway construction sites based on energy consumption data, and the updated construction status characteristic parameters are obtained. The updated construction status characteristic parameters of the highway construction site carbon emission prediction based on energy consumption data are input into the dynamic mapping relationship of the highway construction site carbon emission prediction based on energy consumption data. The updated predicted carbon emission value of the highway construction site carbon emission prediction based on energy consumption data is calculated through the mapping coefficient in the dynamic mapping relationship of the highway construction site carbon emission prediction based on energy consumption data. Determine whether the deviation between the updated predicted carbon emission value of the highway construction site carbon emission prediction driven by energy consumption data and the preset carbon emission benchmark of the highway construction site carbon emission prediction driven by energy consumption data meets the carbon emission control requirements. When the deviation of the highway construction site carbon emission prediction driven by energy consumption data does not meet the carbon emission control requirements of the highway construction site carbon emission prediction driven by energy consumption data, correct the adjustment range in the construction element adjustment instruction of the highway construction site carbon emission prediction driven by energy consumption data according to the direction and magnitude of the deviation of the highway construction site carbon emission prediction driven by energy consumption data, and generate the adjusted construction element adjustment instruction.

[0056] For example, the construction element identifier, adjustment direction, and adjustment range in the construction element adjustment instruction are parsed. Each construction element identifier uniquely corresponds to a construction element, such as excavator gear setting, transport vehicle travel path, or concrete mixing plant feeding frequency. The affected construction state characteristic parameters are determined based on the mapping rules between the construction element identifier and construction state characteristic parameters. These mapping rules are stored in a preset construction element library, recording the influence of each construction element on the construction state characteristic parameters. Specifically, when the construction element is excavator gear setting, the affected construction state characteristic parameters include equipment operating power and operating efficiency. When the excavator is adjusted from gear three to gear two, the equipment operating power decreases from 150kW to 105kW, and the operating efficiency correspondingly decreases from 80 cubic meters per hour to 60 cubic meters per hour. The affected construction state characteristic parameters are updated according to the adjustment direction and magnitude. When the adjustment direction is decreasing and the magnitude is 30%, the current value of the affected construction state characteristic parameter is multiplied by 0.7 to obtain the updated value. When the adjustment direction is increasing and the magnitude is 20%, the current value of the affected construction state characteristic parameter is multiplied by 1.2 to obtain the updated value. In cases where multiple construction elements simultaneously affect the same construction state characteristic parameter, the changes in value generated by each construction element are summed to obtain the total update amount for that construction state characteristic parameter. The current value is then added to the total update amount to obtain the updated construction state characteristic parameter.

[0057] The updated construction status characteristic parameters are input into the dynamic mapping relationship, and the updated predicted carbon emission values ​​are calculated using the mapping coefficients in the dynamic mapping relationship. For directly influential characteristic parameters, the updated parameter value is multiplied by the corresponding linear mapping coefficient to obtain the energy consumption contribution of that parameter; for indirectly influential characteristic parameters, the updated parameter value is substituted into the corresponding nonlinear mapping function for calculation to obtain the energy consumption contribution of that parameter. The energy consumption contributions corresponding to all construction status characteristic parameters are summed to obtain the updated stage energy consumption characterization. Based on the proportion of each energy type in the energy structure vector, the stage energy consumption characterization is allocated to each energy type to obtain the predicted energy consumption of each energy type. The predicted energy consumption of each energy type is multiplied by the corresponding carbon emission factor to obtain the predicted carbon emission of each energy type. The predicted carbon emission of all energy types is summed to obtain the updated predicted carbon emission value, in kilograms of carbon dioxide equivalent.

[0058] To determine whether the deviation between the updated predicted carbon emission value and the preset carbon emission benchmark meets the carbon emission control requirements, the difference between the updated predicted carbon emission value and the preset carbon emission benchmark is calculated to obtain the predicted deviation. The carbon emission control requirement is set so that the absolute value of the predicted deviation does not exceed 3% of the preset carbon emission benchmark. For example, when the preset carbon emission benchmark is 5000 kg CO2 equivalent, the allowable range of the predicted deviation is -150 kg CO2 equivalent to +150 kg CO2 equivalent. When the absolute value of the predicted deviation is less than or equal to 3% of the preset carbon emission benchmark, the updated predicted carbon emission value is determined to meet the carbon emission control requirements, and the current construction element adjustment command remains unchanged and is executed. When the absolute value of the predicted deviation is greater than 3% of the preset carbon emission benchmark, the updated predicted carbon emission value is determined not to meet the carbon emission control requirements, and the adjustment range in the construction element adjustment command needs to be corrected.

[0059] The adjustment range in the construction element adjustment command is corrected based on the direction and magnitude of the predicted deviation. When the predicted deviation is positive, it indicates that the updated predicted carbon emission value is still higher than the preset carbon emission benchmark, requiring a further increase in the adjustment range of the construction elements to reduce energy consumption. When the predicted deviation is negative, it indicates that the updated predicted carbon emission value is lower than the preset carbon emission benchmark, allowing for a slight reduction in the adjustment range of the construction elements to avoid excessive adjustment affecting the construction schedule. The adjustment range correction factor is calculated. The correction factor is determined by the ratio of the predicted deviation to the upper limit of the carbon emission control requirement. When the ratio is greater than 1.5, the correction factor is set to 1.3 to 1.5; when the ratio is between 1 and 1.5, the correction factor is set to 1.1 to 1.3; and when the ratio is between 0.5 and 1, the correction factor is set to 0.9 to 1.1. The original adjustment range in the construction element adjustment command is multiplied by the correction factor to obtain the corrected adjustment range. For example, if the original adjustment range is 30% and the correction factor is 1.4, the corrected adjustment range is 42%. The construction element adjustment instructions are regenerated based on the revised adjustment range. The revised construction element adjustment instructions retain the construction element identifier and adjustment direction, and only update the adjustment range value.

[0060] The adjusted construction element adjustment instructions are then input back into the construction status characteristic parameter update process. This process of parameter updating, predicted carbon emission value calculation, and deviation judgment is repeated until the updated predicted carbon emission value meets carbon emission control requirements. To avoid the adjustment process falling into a cycle of repeated corrections, an upper limit of 5 iterations is set. If the carbon emission control requirements are still not met after reaching the upper limit, the feasibility of the construction element adjustment instructions is analyzed. Possible reasons include limited adjustment capabilities of a single construction element, the existence of high-energy-consuming links not included in the adjustment scope, or overly strict preset carbon emission benchmarks. Supplementary measures are taken based on the analysis results, including increasing the types of construction elements to be adjusted, expanding the adjustment scope of construction elements, or appropriately relaxing the constraints of carbon emission control requirements. After taking supplementary measures, the generation and correction process of construction element adjustment instructions is re-executed to ensure that the final generated construction element adjustment instructions not only meet carbon emission control requirements but also guarantee the normal progress of construction.

[0061] The construction element adjustment instructions that meet carbon emission control requirements are output to the construction management terminal and their execution is monitored. During the execution of these instructions, real-time data is collected from the construction site, actual construction status characteristic parameters are extracted, and actual stage carbon emission values ​​are calculated. These actual stage carbon emission values ​​are then compared with the updated predicted carbon emission values ​​to assess prediction accuracy. When the deviation between the actual stage carbon emission value and the updated predicted carbon emission value is less than 5% of the predicted value, it indicates that the dynamic mapping relationship is effective, and the current mapping coefficients continue to be used. When the deviation is greater than or equal to 5% of the predicted carbon emission value, it indicates that the dynamic mapping relationship needs optimization. New historical construction data is collected to re-perform linear regression analysis and nonlinear function fitting, updating the mapping coefficient values ​​to improve the accuracy of subsequent predictions.

[0062] Through the above technical solution, predictive updates of construction status characteristic parameters for subsequent construction stages are achieved based on construction element adjustment commands. The updated construction status characteristic parameters are converted into predicted carbon emission values ​​through a dynamic mapping relationship, enabling pre-assessment of the adjustment effect of construction elements. By determining whether the predicted carbon emission values ​​meet carbon emission control requirements and correcting the adjustment range based on deviations, an iterative feedback mechanism is established from adjustment command generation to effect prediction and command optimization. This ensures the effectiveness and accuracy of construction element adjustment measures, achieving dynamic prediction and proactive control of carbon emissions at highway construction sites.

[0063] Please see Figure 2 Similar to the embodiments described above, this application also provides a carbon emission prediction system for highway construction sites based on energy consumption data, comprising: The status acquisition module is used to acquire construction site data of highway construction sites. Based on the spatiotemporal correlation characteristics of construction site data driven by energy consumption data, it establishes a multi-source data coupling relationship and extracts the construction status feature parameters of the current construction stage according to the coupling relationship of carbon emission prediction of highway construction sites driven by energy consumption data. The energy consumption characterization module is used to obtain mapping coefficients based on the construction status characteristic parameters of the highway construction site carbon emission prediction driven by energy consumption data. The mapping coefficients of the highway construction site carbon emission prediction driven by energy consumption data establish a dynamic mapping relationship between the construction status characteristic parameters of the highway construction site carbon emission prediction driven by energy consumption data and energy consumption. The dynamic mapping relationship of the highway construction site carbon emission prediction driven by energy consumption data is used to convert the construction status characteristic parameters of the highway construction site carbon emission prediction driven by energy consumption data into stage energy consumption characterization quantities. The instruction adjustment module is used to correlate the energy consumption characterization quantity and carbon emission factor of the carbon emission prediction stage of highway construction site based on energy consumption data to obtain the stage carbon emission value. When the deviation between the stage carbon emission value of the carbon emission prediction stage of highway construction site based on energy consumption data exceeds the preset carbon emission benchmark, a carbon emission control signal is generated. In response to the carbon emission control signal of the carbon emission prediction of highway construction site based on energy consumption data, the module reversely solves the dynamic mapping relationship of the carbon emission prediction of highway construction site based on energy consumption data to determine the target construction state characteristic parameters. Based on the parameter difference between the target construction state characteristic parameters of the carbon emission prediction of highway construction site based on energy consumption data and the current construction state characteristic parameters, an instruction for adjusting construction elements is generated. The monitoring and update module is used to update the construction status characteristic parameters of subsequent construction stages according to the construction element adjustment instructions based on energy consumption data-driven highway construction site carbon emission prediction. It calculates the updated predicted carbon emission value through the dynamic mapping relationship of energy consumption data-driven highway construction site carbon emission prediction and adjusts the construction element adjustment instructions based on energy consumption data-driven highway construction site carbon emission prediction.

[0064] It should be noted that although several units or sub-units of the device have been mentioned in the detailed description above, this division is merely exemplary and not mandatory. In fact, according to embodiments of this application, the features and functions of two or more units described above can be embodied in one unit. Conversely, the features and functions of one unit described above can be further divided and embodied by multiple units.

[0065] Based on the same inventive concept as the above method embodiments, this application also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it enables the electronic device to implement the control method described in the above embodiments.

[0066] In one embodiment, the electronic device may be a server, and in this embodiment, the structure of the electronic device may be as follows: Figure 3 As shown, it includes a memory 2001, a communication module 2003, and one or more processors 2002.

[0067] The memory 2001 is used to store computer programs executed by the processor 2002. The memory 2001 may mainly include a program storage area and a data storage area. The program storage area may store the operating system and programs required to run instant messaging functions, etc.; the data storage area may store various instant messaging information and operation instruction sets, etc.

[0068] Memory 2001 can be volatile memory, such as random access memory. ;Memory 2001 can also be non-volatile memory. Such as read-only memory, flash memory, hard disk drive (HDD), or solid-state drive. Alternatively, memory 2001 may be any other medium capable of carrying or storing a desired computer program having the form of instructions or data structures and accessible by a computer, but is not limited thereto. Memory 2001 may be a combination of the above-described memories.

[0069] Processor 2002 may include one or more central processing units (CPUs) or digital processing units, etc. Processor 2002 is used to implement the above-mentioned audio data processing method when calling computer programs stored in memory 2001.

[0070] The communication module 2003 is used to communicate with terminal devices and other servers.

[0071] This application embodiment does not limit the specific connection medium between the memory 2001, communication module 2003, and processor 2002. This application embodiment... Figure 3 The memory 2001 and the processor 2002 are connected via a bus 2004, which is in... Figure 3 The connections between other components are illustrated with arrows and are for illustrative purposes only, not as limiting information. The Bus 2004 can be divided into address bus, data bus, control bus, etc. For ease of description, Figure 3 The text uses only one arrow to describe it, but does not indicate that there is only one bus or one type of bus.

[0072] Based on the same inventive concept as the above-described method embodiments, embodiments of the present invention also provide a computer-readable storage medium for storing a computer program. When the computer program is run on a computer, it enables the electronic device to implement the control method described in the above embodiments. The computer-readable storage medium can be a readable signal medium or a readable storage medium. A readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: an electrical connection having one or more wires, a portable disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, and portable compact disk read-only memory. Optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0073] Based on the same inventive concept as the above-described method embodiments, embodiments of the present invention also provide a computer program product, which includes a computer program that, when run on an electronic device, causes the electronic device to perform the steps of the control methods described above according to various exemplary embodiments of this application. The program product may take the form of any combination of one or more readable media. These computer program commands can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing device to produce a machine, such that the commands executed by the processor of the computer or other programmable data processing device generate a process for implementing... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0074] Although preferred embodiments of this application have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of this application.

[0075] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

[0076] Finally, it should be noted that the above are merely preferred embodiments of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or make equivalent substitutions for some of the technical features. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for predicting carbon emissions from highway construction sites based on energy consumption data, characterized by: The method includes the following steps: Acquire highway construction site data, establish multi-source data coupling relationship based on the spatiotemporal correlation characteristics of the construction site data, and extract construction status feature parameters of the current construction stage according to the coupling relationship; Based on the construction state characteristic parameters, a mapping coefficient is obtained, and a dynamic mapping relationship between the construction state characteristic parameters and energy consumption is established based on the mapping coefficient. The construction state characteristic parameters are then converted into stage energy consumption characterization quantities using the dynamic mapping relationship. The stage energy consumption characterization quantity is correlated with the carbon emission factor to obtain the stage carbon emission value. When the deviation of the stage carbon emission value from the preset carbon emission benchmark exceeds the set range, a carbon emission control signal is generated. In response to the carbon emission control signal, the target construction state characteristic parameters are determined by reverse solving the dynamic mapping relationship. The construction element adjustment instruction is generated based on the parameter difference between the target construction state characteristic parameters and the current construction state characteristic parameters. The construction status characteristic parameters of subsequent construction stages are updated according to the construction element adjustment instructions, and the updated predicted carbon emission value is calculated through the dynamic mapping relationship to adjust the construction element adjustment instructions.

2. The method for predicting carbon emissions from highway construction sites based on energy consumption data as described in claim 1, characterized in that: Based on the coupling relationship, the construction status characteristic parameters of the current construction stage are extracted, including: The association relationship between different data attributes in the preset database is retrieved. The association relationship includes the response time sequence and influence weight between data attributes. Data records with spatiotemporal consistency in the construction site data are matched according to the association relationship. The intersection of the data records is determined as the data association node. The multi-source data coupling relationship is established based on the topological connection relationship of the data association node. Based on the data flow direction in the multi-source data coupling relationship, candidate construction state feature parameters are identified, and preset feature patterns corresponding to the candidate construction state feature parameters are extracted from the preset database. The preset feature patterns include the feature value distribution range and the constraint conditions between features. The measured feature values ​​of the candidate construction state feature parameters are matched and calculated with the feature value distribution range in the preset feature pattern to obtain a similarity that represents the degree of consistency between the two. When the similarity meets a set threshold, it is verified whether the candidate construction state feature parameters meet the feature constraints in the preset feature pattern. The candidate construction state feature parameters that pass the verification are marked as the construction state feature parameters.

3. The method for predicting carbon emissions from highway construction sites based on energy consumption data as described in claim 1, characterized in that: Based on the mapping coefficient, a dynamic mapping relationship is established between the construction state characteristic parameters and energy consumption. The construction state characteristic parameters are then converted into stage energy consumption metrics using this dynamic mapping relationship. The construction status characteristic parameters are divided into direct impact characteristic parameters and indirect impact characteristic parameters according to their impact mechanism on energy consumption. Linear mapping coefficients are established for the direct impact characteristic parameters and nonlinear mapping coefficients are established for the indirect impact characteristic parameters. The dynamic mapping relationship is constructed based on the linear mapping coefficient and the nonlinear mapping coefficient. The linear mapping coefficient in the dynamic mapping relationship is directly proportional to the value of the directly affected class feature parameter, and the nonlinear mapping coefficient changes non-proportionally with the change of the value of the indirectly affected class feature parameter. The direct impact class feature parameters and the indirect impact class feature parameters are weighted and calculated respectively through the dynamic mapping relationship. The weighted result of the direct impact class feature parameters and the weighted result of the indirect impact class feature parameters are coupled and calculated to obtain the stage energy consumption characterization quantity.

4. The method for predicting carbon emissions from highway construction sites based on energy consumption data as described in claim 1, characterized in that: The stage energy consumption characterization quantity is correlated with the carbon emission factor to calculate the stage carbon emission value. When the deviation of the stage carbon emission value from the preset carbon emission benchmark exceeds a set range, a carbon emission control signal is generated, including: An energy structure vector is constructed based on the energy consumption ratio of different energy types in the stage energy consumption characterization quantity. The identification information of each energy type in the energy structure vector is extracted. The corresponding carbon emission factors are retrieved from the preset carbon emission factor library based on the identification information. The retrieved carbon emission factors are combined according to the arrangement order of the corresponding energy types in the energy structure vector to form a carbon emission conversion relationship. Based on the carbon emission conversion relationship, the stage energy consumption characterization quantity is converted into the stage carbon emission value, and the deviation between the stage carbon emission value and the preset carbon emission benchmark is calculated. When the deviation exceeds the set range, a control weight allocation scheme is determined based on the value of the deviation and the controllability of each energy type in the energy structure vector, and a carbon emission control signal carrying the control direction of energy type is generated based on the control weight allocation scheme.

5. The method for predicting carbon emissions from highway construction sites based on energy consumption data as described in claim 1, characterized in that: In response to the carbon emission control signal, the target construction state characteristic parameters are determined by inversely solving the dynamic mapping relationship, including: The energy type regulation direction and deviation information carried in the carbon emission regulation signal are analyzed, and the construction state characteristic parameters corresponding to the energy type that needs to be regulated are determined according to the energy type regulation direction. The target stage carbon emission value is calculated based on the deviation information, and the target stage carbon emission value is used as a reverse solution constraint and substituted into the dynamic mapping relationship. The mapping coefficients in the dynamic mapping relationship are reverse-operated, and the value range of the target construction state characteristic parameters is solved based on the carbon emission value of the target stage and the reverse operation result of the mapping coefficients. The parameter values ​​that meet the construction feasibility constraints are selected from the value range as the target construction state characteristic parameters.

6. The method for predicting carbon emissions from highway construction sites based on energy consumption data as described in claim 1, characterized in that: Based on the parameter difference between the target construction state characteristic parameters and the current construction state characteristic parameters, a construction element adjustment instruction is generated, including: Calculate the parameter difference between the target construction state feature parameter and the current construction state feature parameter, compare the parameter difference with a preset difference threshold, and classify the corresponding construction state feature parameter as a priority adjustment parameter when the parameter difference is greater than the preset difference threshold, otherwise classify it as a secondary adjustment parameter. For the priority adjustment parameters, construction elements that have a direct impact on the priority adjustment parameters are retrieved from the preset construction element library, and the adjustment direction and adjustment range of the construction elements are determined. For the secondary adjustment parameters, identify the association constraint relationship between the secondary adjustment parameters and the primary adjustment parameters, and determine the adjustment direction and adjustment range of the construction elements corresponding to the secondary adjustment parameters based on the association constraint relationship; Based on the adjustment direction and adjustment range of the construction elements corresponding to the priority adjustment parameters and the secondary adjustment parameters, an adjustment instruction for the construction elements, including the construction element identifier, adjustment direction, and adjustment range, is generated.

7. The method for predicting carbon emissions from highway construction sites based on energy consumption data as described in claim 1, characterized in that: The construction element adjustment instructions are used to update the construction status characteristic parameters of subsequent construction stages, calculate the updated predicted carbon emission values ​​through the dynamic mapping relationship, and adjust the construction element adjustment instructions accordingly, including: The construction element identifier, adjustment direction, and adjustment range in the construction element adjustment instruction are analyzed. The affected construction state characteristic parameters are determined according to the mapping rules between the construction element identifier and the construction state characteristic parameters. The affected construction state characteristic parameters are then updated according to the adjustment direction and the adjustment range to obtain the updated construction state characteristic parameters. The updated construction status characteristic parameters are input into the dynamic mapping relationship, and the updated predicted carbon emission value is calculated using the mapping coefficients in the dynamic mapping relationship. Determine whether the deviation between the updated predicted carbon emission value and the preset carbon emission benchmark meets the carbon emission control requirements. If the deviation does not meet the carbon emission control requirements, correct the adjustment range in the construction element adjustment instruction according to the direction and magnitude of the deviation, and generate an adjusted construction element adjustment instruction.

8. A carbon emission prediction system for highway construction sites based on energy consumption data, using the carbon emission prediction method for highway construction sites based on energy consumption data as described in any one of claims 1-7, characterized in that, Includes the following modules: The status acquisition module is used to acquire construction site data of highway construction sites, establish multi-source data coupling relationship based on the spatiotemporal correlation characteristics of the construction site data, and extract construction status feature parameters of the current construction stage according to the coupling relationship. The energy consumption characterization module is used to obtain mapping coefficients based on the construction state characteristic parameters, establish a dynamic mapping relationship between the construction state characteristic parameters and energy consumption based on the mapping coefficients, and use the dynamic mapping relationship to convert the construction state characteristic parameters into stage energy consumption characterization quantities. The instruction adjustment module is used to correlate the stage energy consumption characterization quantity with the carbon emission factor to calculate the stage carbon emission value. When the deviation between the stage carbon emission value and the preset carbon emission benchmark exceeds a set range, a carbon emission control signal is generated. In response to the carbon emission control signal, the target construction state characteristic parameters are determined by reverse solving the dynamic mapping relationship. The construction element adjustment instruction is generated based on the parameter difference between the target construction state characteristic parameters and the current construction state characteristic parameters. The monitoring and update module is used to update the construction status characteristic parameters of subsequent construction stages according to the construction element adjustment instructions, calculate the updated predicted carbon emission value through the dynamic mapping relationship, and adjust the construction element adjustment instructions.

9. An electronic device, characterized in that, include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the computer program, implements the steps of the method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer program instructions that, when executed by a processor, implement the steps of the method as described in any one of claims 1 to 7.

Images