Engineering project carbon emission prediction method based on knowledge graph

Abstract

The invention discloses an engineering project carbon emission prediction method based on a knowledge graph, and belongs to the technical field of carbon emission processing, and the method comprises the following steps: S1, determining a plurality of entity nodes and a plurality of edges according to the carbon emission of transportation equipment and construction equipment in an engineering project, and constructing the knowledge graph for the engineering project; s2, determining knowledge graph factors of the engineering project according to the characteristic parameters of the knowledge graph corresponding to the engineering project; and S3, according to the knowledge graph factors, generating a carbon emission prediction result for the engineering project. According to the method, the knowledge graph factors are used for prediction, compared with some complex multi-factor comprehensive prediction models, unnecessary calculation links are reduced, the prediction efficiency is improved, a carbon emission prediction result can be provided for an engineering project in a short time, and the requirement for rapid decision support in actual engineering is met.

Description

Technical Field

[0001] The present invention belongs to the technical field of carbon emission treatment, and specifically relates to a method for predicting carbon emissions of engineering projects based on a knowledge graph. Background Art

[0002] As an important field of energy consumption and carbon emissions, accurate prediction of carbon emissions in engineering projects is crucial for formulating scientific and reasonable energy conservation and emission reduction strategies and achieving sustainable development. Accurate carbon emission prediction can help project managers in engineering projects plan resource allocation in advance, optimize construction processes, select low-carbon equipment and technologies, thereby effectively reducing the carbon emission intensity of engineering projects and reducing the negative impact on the environment.

[0003] Currently, the prediction of carbon emissions in engineering projects mainly relies on traditional statistical models and empirical formulas. These methods usually rely on historical data and simple linear regression analysis. Although they can provide estimated values of carbon emissions to a certain extent, there are many limitations.

[0004] Traditional methods rely on limited historical data, but it is difficult to comprehensively consider factors such as equipment types, resulting in a large deviation between the prediction results and the actual situation. In addition, during the implementation of engineering projects, the carbon emission situation will change dynamically with factors such as construction progress and equipment usage status. Traditional methods usually adopt static prediction models, which cannot reflect these dynamic changes in real time and are difficult to meet the requirements of accurate carbon emission management in engineering projects.

[0005] As an emerging knowledge representation and management technology, a knowledge graph can effectively represent and process complex knowledge and relationships by organizing and storing entities and relationships in the form of a graph structure. In recent years, knowledge graph technology has been widely applied in many fields, such as intelligent search, recommendation systems, and medical diagnosis, and has achieved remarkable results. In the field of engineering projects, a knowledge graph can integrate various information of engineering projects, including equipment information, etc., to form a comprehensive and systematic knowledge system. Through the knowledge graph, the association relationships between various elements in engineering projects can be clearly displayed, providing strong support for in-depth analysis and understanding of the carbon emission mechanism of engineering projects. Therefore, the present invention proposes a method for predicting carbon emissions of engineering projects based on a knowledge graph. Summary of the Invention

[0006] In order to solve the above problems, the present invention proposes a method for predicting carbon emissions of engineering projects based on a knowledge graph.

[0007] The technical solution of the present invention is: A method for predicting carbon emissions of engineering projects based on a knowledge graph includes the following steps: S1. Determine a number of entity nodes and a number of edges based on the carbon emissions of transportation equipment and construction equipment in the engineering project, and construct a knowledge graph for the engineering project; S2. Determine the knowledge graph factors of the engineering project according to the characteristic parameters of the knowledge graph corresponding to the engineering project; S3. Generate a carbon emission prediction result for the engineering project according to the knowledge graph factors.

[0008] Further, S1 includes the following sub-steps: S11. Take the transportation equipment that generates carbon emissions in the engineering project as the transportation equipment ontology set, and take the construction equipment that generates carbon emissions in the engineering project as the construction equipment ontology set; S12. Construct attribute relationships for each ontology in the transportation equipment ontology set; S13. Construct attribute relationships for each ontology in the construction equipment ontology set; S14. Take all the ontologies in the transportation equipment ontology set and the construction equipment ontology set as the entity nodes of the knowledge graph, and take the attribute relationships as the edges of the knowledge graph to construct the knowledge graph of the engineering project.

[0009] The beneficial effect of the above further solution is: In the present invention, the construction equipment entity set includes the construction equipment that has generated carbon emissions in the engineering project so far (such as excavators, crane excavators, concrete mixing stations, and welders, etc.). The transportation equipment includes trucks, cranes, and pump trucks, etc. Taking the equipment ontology as the entity node and the attribute relationship as the edge, combining the equipment in the actual engineering project with the knowledge graph structure can intuitively present the association relationships between the equipment and between the equipment attributes, facilitating the integration and analysis of information related to the carbon emissions of the engineering project.

[0010] Further, in S12, take the attribute value of the ontology in the transportation equipment ontology set as the attribute relationship, and its attribute value The calculation formula is: ; In the formula, represents the actual carbon emission value generated by the ontology in the transportation equipment ontology set at time, represents the total time, represents the average value of the actual carbon emission values generated by the ontology in the transportation equipment ontology set at the total time, represents the exponential function.

[0011] Further, S13 includes the following sub-steps: S131. Obtain the actual carbon emission sequence and the predicted carbon emission sequence of the ontology in the construction equipment set; where and respectively represent the true carbon emission value and the estimated carbon emission value of the main body in the construction equipment set at time 1, and respectively represent the true carbon emission value and the estimated carbon emission value of the main body in the construction equipment set at time 2, and respectively represent the true carbon emission value and the estimated carbon emission value of the main body in the construction equipment set at time 3, and respectively represent the true carbon emission value and the estimated carbon emission value of the main body in the construction equipment set at time 4, and respectively represent the true carbon emission value and the estimated carbon emission value of the main body in the construction equipment set at time, and respectively represent the true carbon emission value and the estimated carbon emission value of the main body in the construction equipment set at time, and respectively represent the true carbon emission value and the estimated carbon emission value of the main body in the construction equipment set at time, represents the total time; S132. Calculate the root mean square error between the true carbon emission sequence and the predicted carbon emission sequence; S133. Calculate the absolute value of the difference between the true carbon emission value of each time of the main body in the construction equipment main body set and the root mean square error, and determine the time corresponding to the minimum absolute value; S134. Calculate the attribute value of the main body according to the time corresponding to the minimum absolute value; S135. Use the attribute value of the main body in the transportation equipment main body set as the attribute relationship.

[0012] The beneficial effect of the above further solution is: In the present invention, before a modern engineering device is put into operation, a life test will be carried out, and at the same time, the carbon emission amount will also be tested. Therefore, each device has its own estimated carbon emission amount at each time. The true carbon emission sequence and the predicted carbon emission sequence at different times cover data of multiple time points from the initial time to the total time K. By calculating the absolute value of the difference between the true carbon emission value of each time and the root mean square error, and determining the time corresponding to the minimum absolute value, it is possible to accurately find the time closest to the root mean square error, so as to map the attribute value of the construction equipment main body to the transportation equipment main body set, form an attribute relationship, and reflect the attribute characteristics of the device under the optimal prediction performance.

[0013] Further, in S134, the attribute value of the main body in the construction equipment main body set has the following calculation formula:

[0014] In the formula, represents the carbon emission change curve of the ontology in the construction equipment ontology set, represents the moment corresponding to the minimum absolute value, represents the total moment, represents the true carbon emission value of the ontology at time 1, represents the ontology at the true carbon emission value at the moment, represents the operation of calculating the mean value of the true carbon emission values over a period of time.

[0015] Constructing the data into a curve helps to intuitively understand the data change trend and assist in selecting an appropriate integration method. The upper and lower limits of the integration can be adjusted appropriately.

[0016] Further, S2 includes the following sub-steps: S21. Determine the entity granularity of the knowledge graph corresponding to the engineering project; S22. Extract the node degrees of each node in the knowledge graph corresponding to the engineering project; S23. Use the ratio of the node degree of each node to the entity granularity as the weighted weight of the node, and perform a weighted sum of the betweenness centrality of all nodes to obtain the knowledge graph factor of the engineering project.

[0017] The beneficial effects of the above further solution are as follows: In the present invention, the frequency of a node as the shortest path bridge measures its control force in carbon emission propagation. Using the ratio of the node degree to the entity granularity as the weighted weight takes into account the relative importance of the node in the knowledge graph and combines the overall scale (entity granularity) of the knowledge graph at the same time. This weighting method can balance the importance differences of nodes in knowledge graphs of different scales to a certain extent. The betweenness centrality of a node reflects the ability of the node to connect other node pairs as a "bridge" in the knowledge graph network. Performing a weighted sum of the betweenness centrality of all nodes to obtain the knowledge graph factor attempts to comprehensively consider the importance of each node in the overall structure of the knowledge graph, so as to obtain a factor that can represent the overall characteristics of the knowledge graph, providing a quantitative index based on the knowledge graph structure for subsequent carbon emission prediction. Setting the optimal time period and calculating the mean value of the total true carbon emissions within this time period takes into account the time dynamic changes of the carbon emissions of the engineering project. By selecting a representative time period for mean value calculation, it can smooth the data fluctuations to a certain extent and make the prediction result more stable.

[0018] Further, in S21, extract the adjacency matrix of the knowledge graph of the engineering project, and use the row and column values of the adjacency matrix as the entity granularity of the knowledge graph.

[0019] The relationships between vertices in a knowledge graph are represented using a two-dimensional matrix. An adjacency matrix is a data structure for representing a graph structure, where the rows and columns respectively correspond to entities in the knowledge graph, and the elements in the matrix represent the connection relationships between entities.

[0020] Further, in S3, an optimal time period is set, and the product of the average value of the total actual carbon emissions of the engineering project within the optimal time period and the knowledge graph factor is used as the carbon emission prediction result of the engineering project.

[0021] The optimal time period can be set manually. For example, the last three moments can be used as the optimal time period, or the last five moments can be used as the optimal time period. It is advisable to select a relatively stable period at the end as the optimal time period.

[0022] The beneficial effects of the present invention are as follows: (1) Based on the carbon emissions of transportation equipment and construction equipment, the present invention determines entity nodes and edges to construct a knowledge graph, which can effectively integrate carbon emission-related information of these two types of key equipment in an engineering project; the carbon emission data of different equipment have different characteristics and sources, and through the knowledge graph, they can be uniformly organized to achieve data association and fusion; (2) The present invention determines the knowledge graph factor according to the characteristic parameters of the knowledge graph, deeply excavates the information contained in the knowledge graph, extracts relationship data containing a large number of nodes and edges, and can convert complex graph structure information into quantitative indicators for prediction, giving full play to the role of the knowledge graph in analysis and prediction; (3) The present invention uses the knowledge graph factor for prediction. Compared with some complex multi-factor comprehensive prediction models, it reduces unnecessary calculation links, improves the prediction efficiency, can provide carbon emission prediction results for engineering projects in a relatively short time, and meets the needs of rapid decision-making support in actual projects. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 It is a flowchart of a carbon emission prediction method for an engineering project based on a knowledge graph. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0024] The embodiments of the present invention will be further described below with reference to the accompanying drawings.

[0025] As Figure 1 shown, the present invention provides a carbon emission prediction method for an engineering project based on a knowledge graph, including the following steps: S1. Determine a number of entity nodes and a number of edges based on the carbon emissions of transportation equipment and construction equipment in the engineering project, and construct a knowledge graph for the engineering project; S2. Determine the knowledge graph factor of the engineering project according to the characteristic parameters of the knowledge graph corresponding to the engineering project; S3. Generate carbon emission prediction results for the engineering project according to the knowledge graph factors.

[0026] In the embodiment of the present invention, S1 includes the following sub-steps: S11. Take the transportation equipment that generates carbon emissions in the engineering project as the transportation equipment body set, and take the construction equipment that generates carbon emissions in the engineering project as the construction equipment body set; S12. Construct attribute relationships for each body in the transportation equipment body set; S13. Construct attribute relationships for each body in the construction equipment body set; S14. Take all the bodies in the transportation equipment body set and the construction equipment body set as the entity nodes of the knowledge graph, and take the attribute relationships as the edges of the knowledge graph to construct the knowledge graph of the engineering project.

[0027] In the present invention, the construction equipment entity set includes the construction equipment that has generated carbon emissions in the engineering project so far (such as excavators, crane excavators, concrete mixing stations, and welding machines, etc.). The transportation equipment includes trucks, cranes, and pump trucks, etc. Taking the equipment body as the entity node and the attribute relationship as the edge, combining the equipment in the actual engineering project with the knowledge graph structure can intuitively present the association relationships between the equipment and between the equipment attributes, facilitating the integration and analysis of information related to carbon emissions in the engineering project.

[0028] In the embodiment of the present invention, in S12, take the attribute value of the body in the transportation equipment body set as the attribute relationship, and its attribute value The calculation formula is: ; In the formula, represents the actual carbon emission value generated by the body in the transportation equipment body set at time, represents the total time, represents the average value of the actual carbon emission values generated by the body in the transportation equipment body set at the total time, represents the exponential function.

[0029] In the embodiment of the present invention, S13 includes the following sub-steps: S131. Obtain the actual carbon emission sequence and the predicted carbon emission sequence of the body in the construction equipment set; where and respectively represent the actual carbon emission value and the estimated carbon emission value of the body in the construction equipment set at time 1, and respectively represent the actual carbon emission value and the estimated carbon emission value of the body in the construction equipment set at time 2, and respectively represent the true carbon emission value and the estimated carbon emission value of the main body in the construction equipment set at time 3. and respectively represent the true carbon emission value and the estimated carbon emission value of the main body in the construction equipment set at time 4. and respectively represent the true carbon emission value and the estimated carbon emission value of the main body in the construction equipment set at time. and respectively represent the true carbon emission value and the estimated carbon emission value of the main body in the construction equipment set at time. and respectively represent the true carbon emission value and the estimated carbon emission value of the main body in the construction equipment set at time. represents the total time; S132. Calculate the root mean square error between the true carbon emission sequence and the predicted carbon emission sequence; S133. Calculate the absolute value of the difference between the true carbon emission value of each main body in the construction equipment main body set and the root mean square error, and determine the time corresponding to the minimum absolute value; S134. Calculate the attribute value of the main body according to the time corresponding to the minimum absolute value; S135. Use the attribute value of the main body in the transportation equipment main body set as the attribute relationship.

[0030] In the present invention, before modern engineering equipment is put into operation, a life test will be carried out, and at the same time, the carbon emission will also be tested. Therefore, each equipment has its own estimated carbon emission at each moment. The true carbon emission sequence and the predicted carbon emission sequence at different moments cover data of multiple time points from the initial moment to the total moment K. By calculating the absolute value of the difference between the true carbon emission value of each moment and the root mean square error, and determining the time corresponding to the minimum absolute value, the time closest to the root mean square error can be accurately found, so as to map the attribute value of the construction equipment main body to the transportation equipment main body set, form an attribute relationship, and reflect the attribute characteristics of the equipment under the optimal prediction performance.

[0031] In the embodiment of the present invention, in S134, the attribute value of the main body in the construction equipment main body set

[0032] In the formula, represents the carbon emission change curve of the main body in the construction equipment main body set, represents the time corresponding to the minimum absolute value, represents the total time, Represents the true carbon emission value of the ontology at time 1, Represents the ontology at The true carbon emission value at the moment, Represents the mean operation of the true carbon emission values over a period of time.

[0033] Constructing the data into a curve helps to intuitively understand the data change trend and assist in selecting an appropriate integration method. The upper and lower limits of the integration can be adjusted appropriately.

[0034] In the embodiment of the present invention, S2 includes the following sub-steps: S21. Determine the entity granularity of the knowledge graph corresponding to the engineering project; S22. Extract the node degrees of each node in the knowledge graph corresponding to the engineering project; S23. Take the ratio of the node degree of each node to the entity granularity as the weighted weight of the node, and perform a weighted sum of all node betweenness centralities to obtain the knowledge graph factor of the engineering project.

[0035] In the present invention, the frequency of a node as a bridge of the shortest path measures its control force in carbon emission propagation. Using the ratio of the node degree to the entity granularity as the weighted weight takes into account the relative importance of the node in the knowledge graph and combines the overall scale (entity granularity) of the knowledge graph at the same time. This weighting method can balance the importance differences of nodes in knowledge graphs of different scales to a certain extent. The node betweenness centrality reflects the ability of a node to connect other node pairs as a "bridge" in the knowledge graph network. Performing a weighted sum of all node betweenness centralities to obtain the knowledge graph factor attempts to comprehensively consider the importance of each node in the overall structure of the knowledge graph, so as to obtain a factor that can represent the overall characteristics of the knowledge graph, providing a quantitative index based on the knowledge graph structure for subsequent carbon emission prediction. Setting the optimal time period and calculating the mean value of the total true carbon emissions within this time period takes into account the time dynamic changes of the carbon emissions of the engineering project. By selecting a representative time period for mean value calculation, it can smooth the data fluctuations to a certain extent and make the prediction result more stable.

[0036] In the embodiment of the present invention, in S21, extract the adjacency matrix of the knowledge graph of the engineering project, and use the row and column values of the adjacency matrix as the entity granularity of the knowledge graph.

[0037] Use a two-dimensional matrix to represent the relationship between vertices in the knowledge graph. The adjacency matrix is a data structure used to represent a graph structure, where the rows and columns respectively correspond to entities in the knowledge graph, and the elements in the matrix represent the connection relationships between entities.

[0038] In the embodiment of the present invention, in S3, an optimal time period is set, and the product of the average value of the total true carbon emission value of the engineering project within the optimal time period and the knowledge graph factor is used as the carbon emission prediction result of the engineering project.

[0039] The optimal time period can be set manually. For example, the last three moments can be used as the optimal time period, or the last five moments can be used as the optimal time period. Try to select the last stable period as the optimal time period.

[0040] Those of ordinary skill in the art will realize that the embodiments described herein are for helping the reader understand the principles of the present invention, and it should be understood that the protection scope of the present invention is not limited to such specific statements and embodiments. Those of ordinary skill in the art can make various other specific deformations and combinations without departing from the essence of the present invention according to these technical revelations disclosed by the present invention, and these deformations and combinations are still within the protection scope of the present invention.

Claims

1. A carbon emission prediction method for engineering projects based on a knowledge graph, characterized in that, It includes the following steps: S1. Determine a number of entity nodes and a number of edges according to the carbon emissions of transportation equipment and construction equipment in the engineering project, and construct a knowledge graph for the engineering project; S2. Determine the knowledge graph factor of the engineering project according to the characteristic parameters of the knowledge graph corresponding to the engineering project; S3. Generate a carbon emission prediction result for the engineering project according to the knowledge graph factor.

2. The method for predicting carbon emissions of engineering projects based on a knowledge graph according to claim 1, wherein The S1 includes the following sub-steps: S11. Take the transportation equipment that generates carbon emissions in the engineering project as the transportation equipment ontology set, and take the construction equipment that generates carbon emissions in the engineering project as the construction equipment ontology set; S12. Construct attribute relationships for each ontology in the transportation equipment ontology set; S13. Construct attribute relationships for each ontology in the construction equipment ontology set; S14. Take all the ontologies in the transportation equipment ontology set and the construction equipment ontology set as the entity nodes of the knowledge graph, and take the attribute relationships as the edges of the knowledge graph to construct the knowledge graph of the engineering project.

3. The method for predicting carbon emissions of engineering projects based on a knowledge graph according to claim 2, wherein, In S12, the attribute value of the main body in the set of transportation equipment main bodies is used as the attribute relationship, and its attribute value The calculation formula is as follows: ； In the formula, represents the true carbon emission value generated by the body in the time in the set of transportation equipment bodies, represents the total time, represents the average value of the true carbon emission values generated by the body at the total time in the set of transportation equipment bodies, represents the exponential function.

4. The method for predicting carbon emissions of engineering projects based on a knowledge graph according to claim 2, wherein The S13 includes the following sub-steps: S131. Obtain the true carbon emission sequence of the ontology in the construction equipment set and the predicted carbon emission sequence ; where and respectively represent the true carbon emission value and the estimated carbon emission value of the ontology in the construction equipment set at time 1, and respectively represent the true carbon emission value and the estimated carbon emission value of the ontology in the construction equipment set at time 2, and respectively represent the true carbon emission value and the estimated carbon emission value of the ontology in the construction equipment set at time 3, and respectively represent the true carbon emission value and the estimated carbon emission value of the ontology in the construction equipment set at time 4, and respectively represent the true carbon emission value and the estimated carbon emission value of the ontology in the construction equipment set at time, and respectively represent the true carbon emission value and the estimated carbon emission value of the ontology in the construction equipment set at time, and respectively represent the true carbon emission value and the estimated carbon emission value of the ontology in the construction equipment set at time, represents the total time; S132. Calculate the root mean square error between the real carbon emission sequence and the predicted carbon emission sequence; S133. Calculate the absolute value of the difference between the real carbon emission value of each moment of the ontology in the construction equipment ontology set and the root mean square error, and determine the moment corresponding to the minimum absolute value; S134. Calculate the attribute value of the ontology according to the moment corresponding to the minimum absolute value; S135. Take the attribute value of the ontology in the transportation equipment ontology set as the attribute relationship.

5. The method for predicting carbon emissions of engineering projects based on a knowledge graph according to claim 4, wherein In the above S134, the attribute value of the main body in the construction equipment main body set The calculation formula is as follows: In the formula, represents the carbon emission change curve of the body in the set of construction equipment bodies, represents the moment corresponding to the minimum absolute value, represents the total moment, represents the true carbon emission value of the body at time 1, represents the body at the true carbon emission value at the moment, represents the operation of calculating the average value of the true carbon emission value over a period of time.

6. The method for predicting carbon emissions of engineering projects based on a knowledge graph according to claim 1, characterized in that, The S2 includes the following sub-steps: S21. Determine the entity granularity of the knowledge graph corresponding to the engineering project; S22. Extract the node degrees of each node in the knowledge graph corresponding to the engineering project; S23. Take the ratio of the node degree of each node to the entity granularity as the weighted weight of the node, and perform a weighted sum of all node betweenness centralities to obtain the knowledge graph factor of the engineering project.

7. The method for predicting carbon emissions of engineering projects based on a knowledge graph according to claim 6, wherein In the S21, extract the adjacency matrix of the knowledge graph of the engineering project, and take the row and column values of the adjacency matrix as the entity granularity of the knowledge graph.

8. The method for predicting carbon emissions of engineering projects based on a knowledge graph according to claim 1, wherein In the S3, set the optimal time period, and take the product of the mean value of the total real carbon emission value of the engineering project within the optimal time period and the knowledge graph factor as the carbon emission prediction result of the engineering project.

Images