Power grid transmission line construction scheme planning method and system based on knowledge graph

Abstract

The invention belongs to the technical field of construction planning, and particularly relates to a power grid transmission line construction scheme planning method and system based on a knowledge graph, and the method comprises the steps: firstly constructing a knowledge graph model of a mechanical construction scheme and a standardized adaptation principle; obtaining a power transmission line project construction task, constructing a construction data integration set, inputting the construction data integration set into the mechanical construction scheme knowledge graph model, generating a power transmission line mechanical construction scheme, and screening out a standardized construction scheme based on an optimized MOPSO algorithm; according to the method, the knowledge graph and the three-dimensional construction scene are constructed, the multi-target problem is solved by optimizing the MOPSO algorithm, the optimal construction scheme is obtained, the construction process is simulated, the construction process is optimized, and the construction efficiency is improved. Therefore, standardized processing of different construction projects is achieved, the construction efficiency is improved, and the construction quality is guaranteed.

Description

Technical Field

[0001] The present invention belongs to the technical field of construction planning, and specifically relates to a method and system for planning a construction plan for a power grid transmission line based on a knowledge graph. Background Art

[0002] Construction planning refers to the formulation of reasonable construction plans and programs based on the requirements and actual conditions of the project before construction to ensure the smooth progress of the construction process and the achievement of construction quality. A good construction plan can effectively improve construction efficiency and quality, reduce construction risks, and ensure that the project can be completed on time. Traditional construction planning is mainly formulated by the construction unit and the design institute according to the project goals and requirements. The various resources required for the construction process, such as human resources, material resources, equipment resources, etc., are mostly evaluated and analyzed based on construction experience, which inevitably leads to problems such as difficulty in controlling construction quality and low construction efficiency. Summary of the invention

[0003] The purpose of the present invention is to address the above-mentioned problems existing in the prior art and to provide a method and system for planning power grid transmission line construction plans based on a knowledge graph, which improves construction quality and construction efficiency by obtaining standardized construction plans.

[0004] To achieve the above objectives, the technical solution of the present invention is as follows:

[0005] In a first aspect, the present invention provides a method for planning a construction plan for a power transmission line based on a knowledge graph, the method comprising:

[0006] Construct a knowledge graph model of mechanized construction solutions and standardized adaptation principles;

[0007] Obtain the construction tasks of the transmission line project, build an integrated set of construction data, input the integrated set of construction data into the knowledge graph model of the mechanized construction plan, generate the mechanized construction plan of the transmission line, and select the standardized construction plan based on the optimized MOPSO algorithm;

[0008] Construct a three-dimensional scene for the standardized construction plan, perform simulation based on the constructed three-dimensional scene, and output construction prompt information.

[0009] Preferably, the steps of constructing a knowledge graph model of a mechanized construction plan and a standardized adaptation principle include:

[0010] Obtain original construction data, extract knowledge elements from the original construction data, and build a knowledge graph model;

[0011] Extract entities, attributes, and relationships between entities, and obtain the knowledge system and update mechanism of the knowledge graph model through knowledge calculation;

[0012] Constraints are extracted from the digital model of the construction scene, and the input parameters of the knowledge graph model are constructed based on the constraints to generate standardized adaptation principles suitable for the mechanized construction of transmission lines.

[0013] Preferably, the steps of obtaining original construction data, extracting knowledge elements from the original construction data, and constructing a knowledge graph model include:

[0014] Collect data sets including design documents, construction logs, and material usage records from project management and field measurement equipment to generate construction original data sets;

[0015] The original construction data set is preprocessed according to the following formula, which includes data cleaning and format standardization:

[0016]

[0017] In the above formula, W s represents the preprocessed construction data, x s represents the error rate of the original data i, μ represents the average error rate, and k is the adjustment coefficient, which is used to control the sensitivity of weight adjustment;

[0018] Based on the preprocessed construction data, key information is extracted, including process, material usage, and equipment status, to build a knowledge graph model;

[0019] The extraction of entities, attributes and relationships between entities, and obtaining a knowledge system and an update mechanism through knowledge calculation, include:

[0020] Organize and classify the extracted entities, attributes, and relationship data between entities, establish a basic classification system based on the functions of entities and the characteristics of attributes, identify direct and indirect relationships between multiple entities, and generate a preliminary knowledge structure system according to the following formula:

[0021]

[0022] In the above formula, R ij Represents the relationship density between quantitative entities, n ij represents the number of co-occurrences between entity i and entity j, and N is the total number of entity pairs in the dataset;

[0023] Based on the preliminary knowledge structure system, a deepened knowledge system is generated according to the following formula to optimize the impact of active entities and their relationships:

[0024]

[0025] In the above formula, K new represents the deepened knowledge system, E irepresents the knowledge contribution of entity i, α i is a weight factor adjusted based on the activity of the entity, and n is the total number of entities;

[0026] In combination with the deepened knowledge system and user interaction feedback, a knowledge updating mechanism is designed. The knowledge updating mechanism refers to dynamically adjusting the entity weights and relationship strengths in the knowledge system according to newly acquired data and user needs to obtain a sustainably updated knowledge system.

[0027] Preferably, the construction of the integrated construction data set includes: obtaining the construction tasks of the transmission line project, and constructing a digital project model, a construction personnel model, a construction machine model, a surrounding real-life environment model, and a structure model based on the construction tasks of the transmission line project, thereby obtaining an integrated construction data set.

[0028] Preferably, the method of selecting a standardized construction plan based on the optimized MOPSO algorithm includes: constructing a decision tree for the mechanized construction plan of the transmission line, establishing the basic framework of the multi-objective optimization model, and determining the objectives and constraints of the optimization model; optimizing the MOPSO algorithm by using a fitness function improvement strategy, an inertia weight improvement strategy, and a learning factor improvement strategy, wherein:

[0029] The fitness function improvement strategy is:

[0030] f(I1,I2,...,I M )=k1 I1+k2 I2+...k i I i ...+k M I M 0<k i <1;

[0031] In the above formula, k i The weight coefficient of the i-th optimization objective represents the importance of the i-th optimization objective to the entire standardized construction plan. The fitness function f(I1, I2, ..., I M ) minimum value; I i represents the i-th optimization target; M represents the total number of optimization targets;

[0032] The inertia weight improvement strategy adopts an improvement method in which the inertia weight w decreases nonlinearly with the iteration number Iter:

[0033]

[0034] In the above formula, w max 、w min are the maximum and minimum values ​​of the inertia weight respectively, and α is the nonlinear adjustment constant.

[0035] The learning factor improvement strategy is as follows:

[0036]

[0037] In the above formula, c1 and c2 are both learning factors, c1 represents the self-cognition of the particle, and c2 represents the social cognition of the particle; 1e 、c 2e They represent the initial values ​​of the self-learning factor and the social learning factor, respectively, 1e 、c 2e Set to 2.

[0038] In a second aspect, the present invention provides a power grid transmission line construction plan planning system based on a knowledge graph, the system comprising:

[0039] Knowledge graph model building module, used to build the knowledge graph model of mechanized construction scheme and standardized adaptation principles;

[0040] The standardized construction plan generation and screening module is used to obtain the construction tasks of the transmission line project, build the integrated construction data set, input the integrated construction data set into the mechanized construction plan knowledge graph model, generate the mechanized construction plan of the transmission line, and screen out the standardized construction plan based on the optimized MOPSO algorithm;

[0041] The simulation calculation module is used to construct a three-dimensional scene for the standardized construction plan, perform simulation based on the constructed three-dimensional scene, and output construction prompt information.

[0042] The knowledge graph model building module builds the knowledge graph model of the mechanized construction plan and the standardized adaptation principle according to the following steps:

[0043] Obtain original construction data, extract knowledge elements from the original construction data, and build a knowledge graph model;

[0044] Extract entities, attributes, and relationships between entities, and obtain the knowledge system and update mechanism of the knowledge graph model through knowledge calculation;

[0045] Constraints are extracted from the digital model of the construction scene, and the input parameters of the knowledge graph model are constructed based on the constraints to generate standardized adaptation principles suitable for the mechanized construction of transmission lines.

[0046] The knowledge graph model building module obtains the original construction data, extracts knowledge elements from the original construction data, and builds a knowledge graph model according to the following steps:

[0047] Collect data sets including design documents, construction logs, and material usage records from project management and field measurement equipment to generate construction raw data sets;

[0048] The original construction data set is preprocessed according to the following formula, which includes data cleaning and format standardization:

[0049]

[0050] In the above formula, W s represents the preprocessed construction data, x s represents the error rate of the original data i, μ represents the average error rate, and k is the adjustment coefficient, which is used to control the sensitivity of weight adjustment;

[0051] Based on the preprocessed construction data, key information is extracted, including process, material usage, and equipment status, to build a knowledge graph model;

[0052] The knowledge graph model building module extracts entities, attributes, and relationships between entities according to the following steps, and obtains the knowledge system and update mechanism through knowledge calculation:

[0053] Organize and classify the extracted entities, attributes, and relationship data between entities, establish a basic classification system based on the functions of entities and the characteristics of attributes, identify direct and indirect relationships between multiple entities, and generate a preliminary knowledge structure system according to the following formula:

[0054]

[0055] In the above formula, R ij Represents the relationship density between quantitative entities, n ij represents the number of co-occurrences between entities i and j, and N is the total number of entity pairs in the dataset;

[0056] Based on the preliminary knowledge structure system, a deepened knowledge system is generated according to the following formula to optimize the impact of active entities and their relationships:

[0057]

[0058] In the above formula, K new Indicates the deepened knowledge system; E i represents the knowledge contribution of entity i; α i is a weight factor adjusted based on the activity of the entity; n is the total number of entities;

[0059] In combination with the deepened knowledge system and user interaction feedback, a knowledge updating mechanism is designed. The knowledge updating mechanism refers to dynamically adjusting the entity weights and relationship strengths in the knowledge system according to newly acquired data and user needs to obtain a sustainably updated knowledge system.

[0060] The standardized construction plan generation and screening module constructs a construction data integration set according to the following steps:

[0061] Acquire the construction tasks of the transmission line project, and build the digital model of the project, the construction personnel model, the construction equipment model, the surrounding real environment model and the structure model based on the construction tasks of the transmission line project, so as to obtain the integrated set of construction data.

[0062] The simulation calculation module is used to select a standardized construction plan based on the optimized MOPSO algorithm according to the following steps:

[0063] Construct a decision tree for the mechanized construction plan of transmission lines, establish the basic framework of the multi-objective optimization model, and determine the objectives and constraints of the optimization model; optimize the fitness function improvement strategy, inertia weight improvement strategy, and learning factor improvement strategy in the MOPSO algorithm;

[0064] Among them, the fitness function improvement strategy is:

[0065] f(I1,I2,...,I M )=k1 I1+k2 I2+...k i I i ...+k M I M 0<k i <1;

[0066] In the above formula, k i The weight coefficient of the i-th optimization objective represents the importance of the i-th optimization objective to the entire standardized construction plan. The fitness function f(I1, I2, ..., I M ) minimum value; I i represents the i-th optimization target; M represents the total number of optimization targets;

[0067] The inertia weight improvement strategy adopts an improvement method in which the inertia weight w decreases nonlinearly with the iteration number Iter:

[0068]

[0069] In the above formula, w max 、w min are the maximum and minimum values ​​of inertia weight respectively; α is the nonlinear adjustment constant; Iter max Indicates the maximum number of iterations;

[0070] The learning factor improvement strategy is as follows:

[0071]

[0072] In the above formula, c1 and c2 are both learning factors, c1 represents the self-cognition of the particle, and c2 represents the social cognition of the particle; 1e、c 2e They represent the initial values ​​of the self-learning factor and the social learning factor, respectively, 1e 、c 2e Set to 2.

[0073] In the third aspect, the present invention provides a knowledge graph-based power grid transmission line construction plan planning device, the device includes a memory and a processor; the memory is used to store computer program code and transfer the computer program code to the processor; the processor is used to execute the aforementioned method according to the instructions in the computer program code.

[0074] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program implements the aforementioned method when executed by a processor.

[0075] Compared with the prior art, the present invention has the following beneficial effects:

[0076] The knowledge graph-based power grid transmission line construction plan planning method of the present invention first constructs a knowledge graph model of a mechanized construction plan and a standardized adaptation principle; then obtains the transmission line project construction task, constructs a construction data integration set, inputs the construction data integration set into the mechanized construction plan knowledge graph model, generates a transmission line mechanized construction plan, and screens out a standardized construction plan based on the optimized MOPSO algorithm; then a three-dimensional scene is constructed for the standardized construction plan, a simulation is performed based on the constructed three-dimensional scene, and construction prompt information is output; the above method realizes the simulation of the construction process by constructing a knowledge graph and a three-dimensional construction scene, and completes the solution of the multi-objective problem by optimizing the MOPSO algorithm, and seeks the best construction plan, thereby realizing standardized processing of different construction projects, improving construction efficiency, and ensuring construction quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0077] Figure 1 This is a flow chart of the method described in Example 1.

[0078] Figure 2 This is a structural block diagram of the system described in Example 2.

[0079] Figure 3 This is a structural block diagram of the device described in Example 3. DETAILED DESCRIPTION

[0080] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0081] Embodiment 1:

[0082] See also Figure 1 , a method for planning a construction plan of a power transmission line based on a knowledge graph, comprising the following steps:

[0083] Construct a knowledge graph model of mechanized construction solutions based on digital models and standardized adaptation principles:

[0084] In this step, the knowledge base of mechanized construction plans and standard specifications is determined; first, the work instructions, construction plans, and corresponding construction procedures and guidelines for foundation construction, tower assembly and line construction are sorted out, and key data such as engineering conditions, equipment and facilities, construction technology, construction tools, personnel, work efficiency, quality, safety and environment are analyzed to obtain structured, semi-structured and unstructured data; then, a large language model is used, combined with expert knowledge, to extract knowledge elements from the original data, namely entity relationships, including basic attribute knowledge, association knowledge, event knowledge, time series knowledge, resource knowledge, etc.; finally, according to the set semantic relationships, with the help of a graph database, a knowledge base of mechanized construction plans and standard specifications is constructed.

[0085] Data sets including design documents, construction logs, and material usage records are collected from project management and on-site measurement equipment to generate original construction data sets. The specific operations are as follows: Use digital tools such as sensors and RFID tags to capture detailed information on real-time construction activities, such as workers' working time records, the operating status of mechanical equipment, and material consumption rates. The data are stored in the form of spreadsheets or databases, forming a series of data entries in the data set. Each entry contains a timestamp, data type, and specific value to ensure data integrity and traceability. The collected data is used for subsequent data cleaning and analysis steps.

[0086] Preprocess the original construction data set, including data cleaning and format standardization, and apply the formula:

[0087]

[0088] In the above formula, W s represents the preprocessed construction data, x s represents the error rate of the original data i, μ represents the average error rate, and k is the adjustment coefficient, which is used to control the sensitivity of weight adjustment;

[0089] For example: there is a set of data with an error rate of x i =[0.05, 0.20, 0.15, 0.10], average error rate μ = 0.125, set k = 3;, calculate the weight of each data item according to the following formula:

[0090] e -3(0.05-0.125) =e 0.225≈1.252,

[0091] e -3(0.20-0.125) =e -0.225 ≈0.798,

[0092] e -3(0.15-0.125) =e -0.075 ≈0.928,

[0093] e -3(0.10-0.125) =e 0.075 ≈1.078,

[0094] The result shows that the data item x2 (error rate 0.20) has the highest weight (0.556), which means that more attention needs to be paid to this data item during the data cleaning process to ensure the overall quality of the dataset.

[0095] Based on the preprocessed construction data, key information is extracted, including process, material usage, and equipment status, to build a knowledge graph model;

[0096] Based on the preprocessed construction data, key information is extracted. The detailed operations include: using data mining technology to perform pattern recognition on the data set, identifying outliers, trends and correlations in the data, such as using cluster analysis to find out equipment failure modes, and association rule mining to discover the dependency between material usage and processes. Each discovered pattern or relationship is recorded as an information entity, which is then used to build a knowledge graph.

[0097] Extract entities, attributes, and relationships between entities, integrate new knowledge, and obtain knowledge systems and update mechanisms through knowledge calculation, including:

[0098] Organize and classify the extracted entities, attributes, and relationship data between entities, establish a basic classification system based on the functions of entities and the characteristics of attributes, and identify direct and indirect relationships between multiple entities; the formal expression of this process is:

[0099]

[0100] In the above formula, R ij Represents the relationship density between quantitative entities, n ij represents the number of co-occurrences between entity i and entity j, and N is the total number of entity pairs in the dataset;

[0101] By quantifying the number of co-occurrences between entities, we can accurately measure the strength of the connection between entities, thereby more effectively building and optimizing the association network of the knowledge system. For example, in the data set, entity A and entity B co-occur 50 times, and the total number of co-occurrences of entity pairs in the entire data set is 1000 times. Then the association strength between entity A and B is:

[0102]

[0103] This result indicates the degree of association between entity i and entity j, providing a quantitative basis for the link between these two entities in the knowledge system, which helps to optimize the structure of the knowledge system and ensure that it reflects the actual connection density between entities.

[0104] Based on the preliminary knowledge structure system, the formula is adopted:

[0105]

[0106] In the above formula, K new represents the deepened knowledge system, E i represents the knowledge contribution of entity i, α i is a weight factor adjusted based on the activity of the entity, and n is the total number of entities;

[0107] For example, there are three entities, whose knowledge contribution E values ​​are 1.0, 2.0, and 1.5 respectively, and whose association strength R values ​​are 0.5, 0.3, and 0.7 respectively. The weight factors α are set to 0.8, 0.6, and 0.9 respectively. Substitute them into the formula for calculation:

[0108] For the first entity:

[0109] a1·(E1+R1) 2 =0.8·(1.0+0.5) 2 =0.2;

[0110] For the second entity:

[0111] α2·(E2+R2) 2 =0.6·(2.0+0.3) 2 =0.216;

[0112] For the third entity:

[0113] α3·(E3+R3) 2 =0.9·(1.5+0.7) 2 =0.992;

[0114] sum:

[0115] K new =0.2+0.216+0.992=1.408;

[0116] The results show that after weighted square processing, the overall contribution of each entity and its associations is effectively amplified, among which the third entity and its relationships contribute the most to the knowledge system due to their higher activity and association strength.

[0117] Combining the deepened knowledge system with user interaction feedback, a knowledge updating mechanism is designed. The mechanism dynamically adjusts the entity weights and relationship strengths in the knowledge system according to newly acquired data and user needs, thus obtaining a continuously updated knowledge system.

[0118] An adaptive knowledge updating mechanism is designed based on the deepened knowledge system and user interaction feedback. User feedback and newly acquired data are analyzed to identify outdated or inaccurate parts of the knowledge system and automatically adjust entity weights and relationship strengths. For example, when new data shows that the relevance of an entity is enhanced, the weight of the entity is increased accordingly, and vice versa. This dynamic adjustment ensures that the knowledge system is continuously updated and adapts to changing needs, maintains its relevance and accuracy in practical applications, and generates a knowledge system.

[0119] Construct a knowledge graph for mechanized construction of transmission lines and generate a knowledge graph model:

[0120] Entities, attributes, and relationships between entities are extracted from various types of data sources, and on this basis, ontological knowledge expressions are formed. After obtaining new knowledge, it is necessary to integrate it to eliminate contradictions and ambiguities. For example, some entities may have multiple expressions, and a specific title may correspond to multiple different entities. Through knowledge computing, a structured, networked knowledge system and update mechanism are obtained. Knowledge computing mainly includes four aspects: ontology construction, knowledge reasoning, quality assessment, and knowledge update.

[0121] Among them, ontology construction is to complete the automated ontology construction through the calculation of entity parallel relationship similarity, entity hierarchical relationship extraction, and ontology generation, so as to realize the classification of data into artificial concept sets / conceptual frameworks, such as "people", "things", "objects", etc.; knowledge reasoning is to deal with the missing relationship values ​​between knowledge graphs through logic-based reasoning, graph-based reasoning, and deep learning-based reasoning, and complete further knowledge discovery; quality assessment can quantify the credibility of knowledge and ensure the quality of the knowledge base by discarding knowledge with low confidence; after the actual application of knowledge graphs, a large amount of data will flow in and be updated, so knowledge updating is very necessary. Updates include updates at the concept layer and data layer. The update of the concept layer means that new concepts are obtained after adding new data, and the new concepts need to be automatically added to the concept layer of the knowledge base. The update of the data layer mainly adds or updates entities, relationships, and attribute values. To update the data layer, it is necessary to consider reliable data sources such as the reliability of the data source, the consistency of the data (whether there are contradictions or redundancy), and select facts and attributes that appear frequently in each data source to be added to the knowledge base. Through the iterative update of knowledge, the optimization of the knowledge graph model is achieved.

[0122] Generate standardized adaptation principles for foundation construction, tower assembly, and line construction based on digital models and knowledge graphs:

[0123] In order to restore the construction scene in a full-element real-life scenario, a digital model of the construction scene including a 3D design model, a geological model, and a surface model is constructed. The 3D design model includes graphic information and data parameters. The graphic information includes 3D design models of objects such as transmission lines, towers, conductors, and foundations. The topography, geology, and line information of the project are extracted from the digital model of the construction scene. Combined with the constraints of foundation construction, tower assembly, wire construction plan, project progress, project safety, quality, and environment, the input parameter set of the knowledge graph model is constructed. The knowledge graph model is used for calculation and knowledge discovery to obtain the recommended construction plan.

[0124] Based on the knowledge and recommended solutions discovered by the knowledge graph model and combined with expert experience, the existing construction solutions are improved and standardized adaptation principles suitable for mechanized construction of transmission lines are proposed;

[0125] Build an integrated set of construction data to obtain the construction tasks of the transmission line project, generate a mechanized construction plan for the transmission line based on the integrated set of construction data, and select a standardized construction plan based on the optimized MOPSO algorithm;

[0126] In this step, the construction data integration set is built based on the engineering digital model:

[0127] Obtain the construction tasks of the power transmission line project and clarify the basic engineering digital models involved in the project; comprehensively analyze the geological conditions, climate environment, construction technology and construction management requirements involved in the mechanized construction process of the power transmission line, and simultaneously build models of construction personnel, construction machinery and tools, surrounding real-life environment and temporary structures; form an integrated set of construction data including engineering digital models, construction personnel, construction machinery and tools, surrounding real-life environment and temporary structure models, and provide a comprehensive and real basic model library for 3D construction planning. Ensure the accuracy and reliability of the planning scheme.

[0128] Planning construction plans based on knowledge graphs and standardized adaptation principles:

[0129] According to the integrated set of construction data and the multi-objective problems involved in the mechanized construction of transmission lines, three-dimensional planning work such as construction transportation plan preparation and site layout planning is carried out before construction, and then the data such as process methods, procedures and operation contents are associated during the construction process. The standardized construction plan is adapted through the quality and safety specification content relationship for process methods in the knowledge graph. Finally, a mechanized construction plan for transmission lines that meets management requirements is generated.

[0130] Establish the basic framework of the multi-objective optimization model, clarify the main optimization objectives and constraints of the optimization model, and complete the construction of the multi-objective intelligent model. The objective functions and constraints of the multi-objective problem are as follows:

[0131] The objective function includes:

[0132] Minimize total cost:

[0133]

[0134] Where C represents the total cost, c i represents the unit cost of the ith activity in the construction plan, P i It represents the number or size of the ith activity in the construction plan, and n is the number of activities in the construction plan.

[0135] Minimize construction period:

[0136]

[0137] Where, T represents the construction period; S i and d i are the start time and duration of the ith activity respectively, and N is the set of all activities.

[0138] Maximum safety:

[0139]

[0140] Where S represents the safety factor; vk represents the weight or utility of the kth security measure, y k is a binary variable (0 or 1) indicating whether the kth safety measure is taken, and m is the number of safety measures.

[0141] The constraints include:

[0142] Resource constraints:

[0143]

[0144] Among them, r ij is the demand for the jth resource from the ith activity, R j is the total amount of resources of the jth category; is for all resource types j;

[0145] Time-dependent constraints:

[0146]

[0147] Where D is the set of dependencies between activities, ensuring that activity i will not start before activity i is completed, S i is the start time of the ith activity, d i is the duration of the ith activity, s j is the start time of dependent activity j, is for all activity pairs;

[0148] Safety rules compliance constraints:

[0149]

[0150] Among them, K l is the set of security measures that must satisfy security rule l. This constraint ensures that at least one measure is taken to satisfy each security rule. is for all safety rules l, y k is a binary variable indicating whether the kth safety measure is taken, and at least one measure is taken to satisfy each safety rule.

[0151] The input of the multi-objective intelligent model mainly includes the description of the construction task, such as the required technology, equipment usage, material requirements and scheduled processes; objectives such as cost control, time management, safety assurance, quality requirements, etc.; environmental protection laws and regulations that must be followed and related social and economic considerations; construction data, accident records and risk assessment reports of previous similar projects; and geographical, climatic and other physical conditions of the actual construction site.

[0152] The output of the multi-objective intelligent model includes: based on the input multi-optimization objective requirements (total cost, construction period, safety), the model will provide one or more optimized construction plans. For each construction plan, the model will output its score under different evaluation dimensions (feasibility, scientificity, reliability and sustainability). Based on risk data and prediction models, the model will output the main risks and their likelihood that each construction plan may face, and screen out construction plans that meet all set standards (technical, economic, regulatory, environmental, etc.).

[0153] The three-dimensional planning work for pre-construction preparations such as construction transportation plan preparation and site layout planning is as follows:

[0154] Obtain detailed data on the topography, existing buildings, and transmission lines at the construction site, collect data on machinery and human resources related to the project, integrate the collected data into the knowledge graph, standardize the data format, and ensure data consistency and availability;

[0155] Use 3D modeling software (such as AutoCAD, Revit, etc.) to create accurate 3D models of transmission lines and related facilities, ensuring that the models reflect real-world dimensions, locations, and terrain relationships; review 3D models with engineers and project management teams to ensure all elements are accurate, modify and optimize models to meet construction specifications and safety standards;

[0156] Prepare detailed construction plans based on the 3D model and project requirements, including the sequence of operations, required resources and timetable, use simulation technology to predict possible problems during construction and develop solutions, and use the 3D model to plan the layout of the construction site, including the optimal layout of material storage, machinery and equipment placement and personnel flow, to ensure that the site layout meets safety regulations and construction efficiency requirements;

[0157] Combine the construction plan with the knowledge map of quality and safety specifications to ensure that all construction activities meet standardization requirements, adjust the construction plan to adapt to regulatory changes or new safety requirements, conduct cost-benefit analysis on the construction plan to ensure that the project cost and completion time are within an acceptable range, optimize resource utilization and construction sequence to reduce waste and improve construction efficiency, and finally approve the plan. After obtaining all necessary approvals and permits, prepare the construction site, including the implementation of safety measures, arrangement of equipment and training of personnel, and officially start construction activities;

[0158] After carrying out 3D planning, standard processes and methods for various construction activities are established, including required materials, equipment and execution standards, and all processes included in the project, such as earthwork, foundation construction, structural installation, etc., and the start and end conditions of each process are clearly defined. Detailed documents or databases are created to record the standard operating procedures for all processes and methods;

[0159] Directly mark relevant process information in the 3D model, use BIM software to link resources such as text instructions and instructional videos to the corresponding parts of the model, regularly check the accuracy of the model with the construction team, and ensure that all annotations are consistent with actual construction standards.

[0160] Using knowledge graphs and database technology, a dynamic association between processes and work content is established. For example, when a process is updated, the related work content will also be automatically updated. Access rights are set to ensure that personnel at different levels of the construction site can access relevant information as needed. Through mobile devices or handheld terminals, on-site workers can view and confirm process information in real time.

[0161] Use sensors and Internet of Things (IoT) technology to monitor the execution of construction site processes in real time. Through an integrated system, check whether the actual construction is consistent with the planned process methods and procedures. Establish a feedback mechanism to allow on-site personnel to report inconsistencies with the process methods and procedures, and adjust and optimize the process methods and procedures based on the actual construction situation and the feedback collected.

[0162] To use knowledge graphs to generate standardized construction plans, relevant data including process methods, safety specifications, historical construction data, environmental impact assessments, and regulatory requirements must be collected. A knowledge graph is constructed based on these data. Each node represents a data point, and edges represent the relationship between data points. Next, the logical relationship between data is established in the graph, and rules for automatically extracting and generating standardized plans are defined. Finally, a decision engine is applied to automatically generate construction plans using preset rules, and the plans are optimized and adjusted based on real-time feedback and on-site conditions to ensure the practicality and efficiency of the construction plans.

[0163] The process of generating construction data and standardized data based on knowledge graphs first requires integrating existing construction-related data from various sources, classifying and labeling the data for indexing and retrieval. Subsequently, new data is added to the knowledge graph, and existing nodes and relationships are updated and maintained. At the same time, data standardization is performed. By using graph query and analysis tools to mine the correlation information and patterns between data, construction reports and insights can be generated, thereby providing strong data support and decision-making assistance for project management, and improving the overall execution quality and efficiency of the project.

[0164] Construct a multi-objective driven construction scheme evaluation system:

[0165] Through data analysis and machine learning, according to the content characteristics of the construction plan and the mechanized construction goals of the transmission line, the construction of a decision tree for the mechanized construction plan of the transmission line with multiple target results is completed. A plan evaluation system is constructed around the four dimensions of construction feasibility, scientificity, reliability and sustainability. The specific evaluation indicators of each evaluation dimension are clarified, among which feasibility includes technical, economic, time and regulatory evaluation; scientificity includes technology, equipment, materials and risk evaluation; reliability includes structure, safety, quality and operation evaluation; sustainability includes environmental, resource and social impact evaluation. Evaluate the multi-target construction plan and finally select the construction plan that meets the standardized construction requirements.

[0166] First, determine the evaluation indicators, including economic indicators, time indicators, regulatory indicators, equipment indicators, etc., collect data related to each evaluation indicator, including historical data, simulation data and forecast data, use statistical methods and machine learning models to process the collected data, conduct quantitative analysis on each indicator, set weights for each indicator, adjust the weights according to the specific needs of the project and strategic preferences, calculate the score of each plan under each indicator, combine the score of each indicator with its weight, and calculate the total score of each construction plan.

[0167] All plans are ranked from high to low according to the total score of the comprehensive evaluation. The top-ranked plans are reviewed in detail to check whether all key indicators have reached the minimum standards. While considering the total score, the risk sensitivity and adaptability of the plan to uncertainty must also be considered. Plans with balanced performance on multiple key indicators are selected, and feasibility tests are conducted on the top-screened plans, including on-site evaluation and preliminary resource allocation. Based on the comprehensive evaluation results, risk analysis, and feasibility test results, the most economical, safest and sustainable construction plan that best meets the project goals is selected.

[0168] The MOPSO algorithm is a multi-objective particle swarm optimization algorithm. During its execution, each particle in the search space is regarded as a potential feasible solution. Each particle has two characteristics: position and velocity. Assume that the exploration space is a D-dimensional space and the particle population size is N. First, the positions and velocities of N particles are randomly generated to form an initial group. Then, each particle flies in the search space based on its own flight experience and the flight experience of the group to obtain the global optimal or adjacent position. Suppose the position of the i-th particle at the t-th iteration is: The velocity of the i-th particle is The best historical position of the i-th particle is The best position for the group is The update formula of the velocity and position of the i-th particle at the t-th iteration is as follows;

[0169]

[0170]

[0171] In the above formula, w is the inertia weight, which controls the degree to which the particle is affected by the past velocity; c1 and c2 are usually called learning factors, which are used to control the speed at which particles move to individual extreme values ​​and group extreme values; r1 and r2 are random numbers between [0, 1], which are used to introduce randomness when updating the velocity.

[0172] The specific process of the MOPSO algorithm is as follows:

[0173] Set the problem dimension D, population size, number of iterations, inertia weight, learning factor and other parameters;

[0174] Initialize the population, generate multiple particles for the multiple objectives in the construction plan (construction quality, safety, construction period, cost, etc.), and set initial values ​​for each objective so that each particle in the population has an initialized speed and position;

[0175] Establish a fitness function according to the optimization problem to be solved, and calculate the fitness value of all particles in the population according to the fitness function, and record the individual extreme value and group extreme value in the population;

[0176] The speed and position of all particles in the population are updated according to the speed and position update formula. The corresponding fitness value of the updated particles is calculated, and the corresponding individual extreme value and group extreme value are updated.

[0177] Determine whether the stopping condition is met. If so, output the population extreme value; if not, continue iterating.

[0178] The present invention improves the MOPSO algorithm, which is specifically divided into three improvement strategies, namely:

[0179] Fitness function improvement strategy:

[0180] For the mechanized construction of transmission lines, in the planning stage, it is necessary to ensure that the project cost and construction period are as low as possible under the condition of construction quality and safety. For this purpose, a fitness function is set to control the balance between multiple objectives to achieve the most cost-effective construction planning. The fitness function is improved as follows:

[0181] f(I1,I2,...,I M )=k1I1+k2I2+...k i I i ...+k M I M 0<k i <1;

[0182] In the above formula, k iThe weight coefficient of the i-th optimization objective represents the importance of the i-th optimization objective to the entire standardized construction plan. The fitness function f(I1, I2, ..., I M ) minimum value; I i represents the i-th optimization target; M represents the total number of optimization targets;

[0183] Inertia weight improvement strategy:

[0184] In order to achieve the global optimal solution of multiple optimization objectives, the weight coefficient w has a larger value in the early stage and its value gradually decreases in the later stage, thereby enhancing the local optimization ability in the later stage. Therefore, an improved method in which the inertia weight w decreases nonlinearly with the iteration number Iter is given:

[0185]

[0186] In the above formula, w max 、w min are the maximum and minimum values ​​of inertia weight respectively; α is the nonlinear adjustment constant; Iter max Indicates the maximum number of iterations;

[0187] Learning factor improvement strategy:

[0188] In the digital planning of mechanized construction of transmission lines, multi-objective optimization needs to achieve the optimal solution for the whole world, so it is necessary to continuously reduce the learning factor c1 and increase the learning factor c2 in iterations. The idea of ​​this strategy is that in the early stage of the algorithm, the group extreme value is unlikely to be in the vicinity of the optimal solution, and the particle flight is mainly guided by its own historical optimal position, that is, the individual extreme value, to ensure its strong global search ability; in the later stage of the algorithm, the group extreme value has searched the vicinity of the optimal solution, and the particle flight is mainly guided by the historical optimal position of the population, that is, the group extreme value, to accelerate the convergence speed of the algorithm; the learning factor improvement strategy is as follows:

[0189]

[0190] In the above formula, c1 and c2 are both learning factors, c1 represents the self-cognition of the particle, and c2 represents the social cognition of the particle; 1e 、c 2e Represent the initial values ​​of the self-learning factor and the social learning factor, respectively. Usually c 1e 、c 2e Set to 2.

[0191] The multi-objective particle swarm optimization algorithm after the above improvements can transform the multi-objective optimization problem in construction planning into a process of finding the optimal solution and obtain the most cost-effective construction plan.

[0192] A three-dimensional scene is constructed for the standardized construction plan based on the integrated set of construction data, and a simulation is performed based on the constructed three-dimensional scene to output construction prompt information.

[0193] In this step, a dynamic construction simulation scenario of new technologies such as prefabricated micropiles, mobile crossing frames, and high-altitude rapid wire lifting by electric tensioning machines is constructed in complex geological terrain and crossing scenarios. Relying on the construction data integration set determined in the construction planning stage, the physical simulation and simulation technology of the three-dimensional engine is used as a means to quickly build a static construction simulation scenario. Then, the action design of the scene is combined with the information such as the process, machinery and personnel of each link in the construction process. In combination with the construction management requirements, the output of management information such as safety, progress, quality and cost in the simulation scenario is carried out to determine the construction method of dynamic construction scenarios of new technologies in complex scenarios.

[0194] The present invention provides a mechanized construction simulation method for the application of new technologies such as prefabricated micro-piles, mobile crossing frames, and electric tensioning machines for high-altitude rapid wire lifting in scenes with complex geological terrain and crossings. Relying on professional 3D design engines such as Unity, the terrain, geology, and line body information are visualized in the form of a 3D model, which serves as the background for construction scene simulation. According to the scene actions designed during the construction process, a dynamic simulation of the construction process is performed. According to the standardized adaptation principle of the knowledge graph, key points are prompted for the risk points, safety and quality measures involved in the standardized procedures of the new process, and the key business information output in the construction simulation process is completed, so as to realize mechanized construction simulation for complex scenes and solve the control problems in the efficiency, quality and safety of transmission line construction in complex scenes.

[0195] In the process of simulating three-dimensional scenes, the capping analysis algorithm and bounding box collision detection algorithm are used to detect line collisions during construction simulation. Through the capping analysis algorithm, the severity of the conductor capping phenomenon in the transmission line can be evaluated, providing a reference for the design and maintenance of the transmission line. Using the bounding box collision detection algorithm, it is possible to quickly detect whether there is a collision between the tower, conductor, insulator, and hardware, as well as the collision between the tower and the surrounding buildings. At the same time, corresponding measures can be taken according to the analysis results, such as adjusting the position of the conductor, strengthening the support of the conductor, etc., to ensure the safe operation of the transmission line.

[0196] The gland analysis algorithm is an algorithm used to analyze the gland phenomenon of conductors in transmission lines. Gland refers to the phenomenon that when a conductor is affected by external forces such as wind and gravity, the distance between the conductor and the ground becomes smaller, forming a phenomenon similar to covering the ground. The gland analysis algorithm mainly models and analyzes the conductors in the transmission line, calculates the gland height and gland area of ​​the conductor, and thus evaluates the impact of the gland phenomenon on the transmission line. The specific process of the gland analysis algorithm is as follows:

[0197] Model building:

[0198] Create a physical model of the transmission line, including the length, suspension height, tension, and cross-sectional properties of the conductors;

[0199] Environmental parameter settings:

[0200] Set relevant environmental parameters such as wind speed, wind direction, temperature and ice load according to geographic location;

[0201] External force calculation:

[0202] F = q·L;

[0203] Among them, F is the total wind force or gravity acting on the wire, q is the wind pressure or gravity per unit length, and L is the span length of the wire.

[0204] Deformation calculation, using the catenary equation to simulate the deformation of the wire under external forces:

[0205]

[0206] Where y is the vertical displacement of the wire, x is the horizontal position, and a and b are constants determined by the boundary conditions and the magnitude of the force;

[0207] Gland height calculation, find the vertical position of the lowest point of the wire:

[0208] H min =min(y);

[0209] Among them, H min is the gland height, i.e. the height of the lowest point of the conductor relative to the ground under the action of external force;

[0210] Estimation of the gland area, calculate the projection area of ​​the conductor at the lowest point:

[0211] A=L·(H init -H min );

[0212] Where A is the gland area; H init is the initial height of the wire when no external force is applied;

[0213] Compare the calculated minimum gland height with the safe distance from the ground, analyze the potential impact of the conductor on the surrounding environment and safety based on the gland area and height, and summarize the gland phenomenon, prediction results and recommended preventive measures of the conductor.

[0214] Evaluate the impact of conductor gland height and gland area on transmission lines to ensure safe operation of transmission lines and prevent safety accidents or operation interruptions caused by conductors being too close to the ground.

[0215] The impact assessment of gland height includes: the calculated minimum gland height H min Compared with the minimum permissible height specified in safety standards or regulations, if H min If the height is lower than the specified height (for example, 15 meters), this indicates a potential safety risk and safety protection measures should be taken immediately. The potential safety risks it brings are physical damage. The low voltage cover height may cause the wires to contact the ground or other objects, causing physical damage or power outages. Electromagnetic interference. Wires close to the ground may increase electromagnetic interference and affect nearby communication facilities or other sensitive equipment.

[0216] The impact assessment of the covered area includes:

[0217] The size of the gland area A reflects the range of ground areas that may be affected or endangered by the conductor. A larger gland area may mean a wider potential impact. The potential safety risks it brings refer to fire risks. If the conductor contacts flammable materials, such as dry vegetation, the fire risk may increase. Ecological impacts: low-hanging conductors may interfere with wildlife activities, especially in forests or other sensitive ecological areas.

[0218] Safety protection measures that can be taken include: improving the wind resistance of conductors or replacing them with conductors that are more suitable for current environmental conditions; increasing the safe distance of conductors by adjusting the height of transmission towers or changing the line layout; deploying more monitoring equipment and analysis software to monitor the status of transmission lines in real time and respond quickly to potential risks.

[0219] The bounding box collision detection algorithm is a common collision detection algorithm. Its basic idea is to use a slightly larger cuboid (i.e., bounding box) with sides parallel to the coordinate axis to approximate complex geometric objects. By comparing whether the bounding boxes intersect, non-intersecting objects can be quickly excluded, thereby narrowing the collision detection range and improving the detection efficiency. Common bounding box types include AABB (Axis-Aligned Bounding Box), bounding sphere, OBB (Oriented Bounding Box), etc. Among them, AABB is the earliest bounding box with advantages such as simple structure and small storage space, but its compactness is poor. For irregular geometric shapes, the redundant space is large, and when the object rotates, it cannot be rotated accordingly. The collision detection of the bounding sphere mainly compares the radius between the two spheres and the distance from the center of the sphere. OBB is a more commonly used bounding box type, which can be rotated according to the shape of the object, so as to more tightly surround the object. In the collision analysis of transmission lines, the bounding box collision detection algorithm can be used to perform collision detection on objects such as conductors, insulators, and hardware in the line to ensure the safe operation of the line.

[0220] Embodiment 2:

[0221] See also Figure 2 , a power grid transmission line construction plan planning system based on knowledge graph, including a knowledge graph model building module, a standardized construction plan generation and screening module, and a simulation calculation module; the knowledge graph model building module is used to build a knowledge graph model of a mechanized construction plan and a standardized adaptation principle;

[0222] Specifically, the knowledge graph model and standardized adaptation principles of the mechanized construction plan are constructed according to the following steps:

[0223] Obtain original construction data, extract knowledge elements from the original construction data, and build a knowledge graph model;

[0224] Extract entities, attributes, and relationships between entities, and obtain the knowledge system and update mechanism of the knowledge graph model through knowledge calculation;

[0225] Constraints are extracted from the digital model, and the input parameters of the knowledge graph model are constructed based on the constraints to generate standardized adaptation principles suitable for the mechanized construction of transmission lines.

[0226] The knowledge graph model building module obtains the original construction data, extracts knowledge elements from the original construction data, and builds a knowledge graph model according to the following steps:

[0227] Collect data sets including design documents, construction logs, and material usage records from project management and field measurement equipment to generate construction raw data sets;

[0228] The original construction data set is preprocessed according to the following formula, which includes data cleaning and format standardization:

[0229]

[0230] In the above formula, W i represents the preprocessed construction data, where X i represents the error rate of data i, μ represents the average error rate, and k is the adjustment coefficient, which is used to control the sensitivity of weight adjustment;

[0231] Based on the preprocessed construction data, key information is extracted, including process, material usage, and equipment status, to build a knowledge graph model;

[0232] Specifically, the following steps are used to extract entities, attributes, and relationships between entities, and obtain the knowledge system and update mechanism through knowledge calculation:

[0233] Organize and classify the extracted entities, attributes, and relationship data between entities, establish a basic classification system based on the functions of entities and the characteristics of attributes, identify direct and indirect relationships between multiple entities, and generate a preliminary knowledge structure system according to the following formula:

[0234]

[0235] In the above formula, R ij Represents the relationship density between quantitative entities, n ij represents the number of co-occurrences between entities i and j, and N is the total number of entity pairs in the dataset;

[0236] Based on the preliminary knowledge structure system, a deepened knowledge system is generated according to the following formula to optimize the impact of active entities and their relationships:

[0237]

[0238] In the above formula, E i represents the knowledge contribution of entity i; α i is a weight factor adjusted based on the activity of the entity, and n is the total number of entities;

[0239] Combining the deepened knowledge system with user interaction feedback, design a knowledge update mechanism, which dynamically adjusts the entity weights and relationship strengths in the knowledge system according to newly acquired data and user needs to obtain a continuously updated knowledge system;

[0240] The standardized construction plan generation and screening module is used to obtain the construction tasks of the transmission line project, build an integrated set of construction data, input the integrated set of construction data into the mechanized construction plan knowledge graph model, generate a mechanized construction plan for the transmission line, and screen out a standardized construction plan based on the optimized MOPS0 algorithm;

[0241] The construction data integration set is constructed according to the following steps:

[0242] Obtain the construction tasks of the transmission line project, and build the digital model of the project, the construction personnel model, the construction equipment model, the surrounding real-life environment model, and the structure model based on the construction tasks of the transmission line project, thereby obtaining an integrated set of construction data;

[0243] The simulation calculation module is used to construct a three-dimensional scene for the standardized construction plan, perform simulation based on the constructed three-dimensional scene, and output construction prompt information; specifically, the standardized construction plan is screened out based on the optimized MOPSO algorithm according to the following steps:

[0244] Construct a decision tree for the mechanized construction plan of transmission lines, establish the basic framework of the multi-objective optimization model, and determine the objectives and constraints of the optimization model; optimize the fitness function improvement strategy, inertia weight improvement strategy, and learning factor improvement strategy in the MOPSO algorithm;

[0245] Among them, the fitness function improvement strategy is:

[0246] f(x1, x2, ..., x N )=k1x1+k2x2+...+k N x N 0<k i <1;

[0247] In the above formula, k i represents the weight coefficient of the ith goal, indicating the importance of the ith goal to the entire project. The fitness function f(x1, x2, ..., x N ) minimum value; x N express;

[0248] The inertia weight improvement strategy adopts an improvement method in which the inertia weight w decreases nonlinearly with the iteration number Iter:

[0249]

[0250] In the above formula, w max 、w min are the maximum and minimum values ​​of inertia weight respectively; α is the nonlinear adjustment constant; Iter max Indicates the maximum number of iterations;

[0251] The learning factor improvement strategy is as follows:

[0252]

[0253] In the above formula, c1 and c2 are both learning factors, c1 represents the self-cognition of the particle, and c2 represents the social cognition of the particle; 1e 、c 2e They represent the initial values ​​of the self-learning factor and the social learning factor, respectively, 1e 、c 2e Set to 2.

[0254] Embodiment 3:

[0255] See also Figure 3, a knowledge graph-based power grid transmission line construction plan planning device, comprising a memory and a processor; the memory is used to store computer program code and transmit the computer program code to the processor; the processor is used to execute the method in Example 1 according to the instructions in the computer program code.

[0256] Embodiment 4:

[0257] A computer-readable storage medium having a computer program stored thereon, wherein the computer program implements the method in embodiment 1 when executed by a processor.

[0258] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can adopt the form of complete hardware embodiments, complete software embodiments, or embodiments in combination with software and hardware. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code. The scheme in the embodiments of the present application can be implemented in various computer languages, for example, object-oriented programming language Java and literal scripting language JavaScript, etc.

[0259] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0260] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0261] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0262] Although the preferred embodiments of the present application have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the present application.

[0263] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A method for planning a construction plan for a power transmission line based on a knowledge graph, characterized in that: The method comprises: Construct a knowledge graph model of mechanized construction solutions and standardized adaptation principles; Obtain the construction tasks of the transmission line project, build an integrated set of construction data, input the integrated set of construction data into the knowledge graph model of the mechanized construction plan, generate the mechanized construction plan of the transmission line, and select the standardized construction plan based on the optimized MOPSO algorithm; Construct a three-dimensional scene for the standardized construction plan, perform simulation based on the constructed three-dimensional scene, and output construction prompt information.

2. The method for planning a construction plan for a power transmission line based on a knowledge graph according to claim 1, characterized in that: The steps of constructing the knowledge graph model of the mechanized construction plan and the standardized adaptation principle include: Obtain original construction data, extract knowledge elements from the original construction data, and build a knowledge graph model; Extract entities, attributes, and relationships between entities, and obtain the knowledge system and update mechanism of the knowledge graph model through knowledge calculation; Constraints are extracted from the digital model of the construction scene, and the input parameters of the knowledge graph model are constructed based on the constraints to generate standardized adaptation principles suitable for the mechanized construction of transmission lines.

3. The method for planning a construction plan for a power transmission line based on a knowledge graph according to claim 2, characterized in that: The obtaining of original construction data, extracting knowledge elements from the original construction data, and constructing a knowledge graph model includes: Collect data sets including design documents, construction logs, and material usage records from project management and field measurement equipment to generate construction raw data sets; The original construction data set is preprocessed according to the following formula, which includes data cleaning and format standardization: In the above formula, W S represents the preprocessed construction data, x S represents the error rate of the original data i, μ represents the average error rate, and k is the adjustment coefficient, which is used to control the sensitivity of weight adjustment; Based on the preprocessed construction data, key information is extracted, including process, material usage, and equipment status, to build a knowledge graph model; The extraction of entities, attributes and relationships between entities, obtaining a knowledge system through knowledge calculation and an update mechanism include: Organize and classify the extracted entities, attributes, and relationship data between entities, establish a basic classification system based on the functions of entities and the characteristics of attributes, identify direct and indirect relationships between multiple entities, and generate a preliminary knowledge structure system according to the following formula: In the above formula, R ij Represents the relationship density between quantitative entities, n ij represents the number of co-occurrences between entities i and j, and N is the total number of entity pairs in the dataset; Based on the preliminary knowledge structure system, a deepened knowledge system is generated according to the following formula to optimize the impact of active entities and their relationships: In the above formula, K new Indicates the deepened knowledge system; E i represents the knowledge contribution of entity i; α i is a weight factor adjusted based on the activity of the entity; n is the total number of entities; In combination with the deepened knowledge system and user interaction feedback, a knowledge updating mechanism is designed. The knowledge updating mechanism refers to dynamically adjusting the entity weights and relationship strengths in the knowledge system according to newly acquired data and user needs to obtain a sustainably updated knowledge system.

4. The method for planning a construction plan for a power transmission line based on a knowledge graph according to claim 1, characterized in that: The construction data integration set includes: obtaining the transmission line project construction tasks, constructing the project digital model, construction personnel model, construction equipment model, surrounding real environment model and structure model based on the transmission line project construction tasks, and then obtaining the construction data integration set.

5. The method for planning a construction plan for a power transmission line based on a knowledge graph according to claim 1, characterized in that: The method of selecting a standardized construction plan based on the optimized MOPSO algorithm includes: constructing a decision tree for the mechanized construction plan of the transmission line, establishing the basic framework of the multi-objective optimization model, and determining the objectives and constraints of the optimization model; optimizing the MOPSO algorithm by using a fitness function improvement strategy, an inertia weight improvement strategy, and a learning factor improvement strategy; Among them, the fitness function improvement strategy is: f(I1,I2,...,I M )=k1I1+k2I2+...k i I i …+k M I M 0<k i <1; In the above formula, k i The weight coefficient of the i-th optimization objective represents the importance of the i-th optimization objective to the entire standardized construction plan. The fitness function f(I1, I2, ..., I M ) minimum value; I i represents the i-th optimization target; M represents the total number of optimization targets; The inertia weight improvement strategy adopts an improvement method in which the inertia weight w decreases nonlinearly with the iteration number Iter: In the above formula, w max 、w min are the maximum and minimum inertia weight respectively, α is the nonlinear adjustment constant, Iter max Indicates the maximum number of iterations; The learning factor improvement strategy is as follows: In the above formula, c1 and c2 are both learning factors, c1 represents the self-cognition of the particle, and c2 represents the social cognition of the particle; 1e 、c 2e They represent the initial values ​​of the self-learning factor and the social learning factor, respectively, 1e 、c 2e Set to 2.

6. A power grid transmission line construction plan planning system based on knowledge graph, characterized by: The system comprises: Knowledge graph model building module, used to build the knowledge graph model of mechanized construction scheme and standardized adaptation principles; The standardized construction plan generation and screening module is used to obtain the construction tasks of the transmission line project, build the integrated construction data set, input the integrated construction data set into the mechanized construction plan knowledge graph model, generate the mechanized construction plan of the transmission line, and screen out the standardized construction plan based on the optimized MOPSO algorithm; The simulation calculation module is used to construct a three-dimensional scene for the standardized construction plan, perform simulation based on the constructed three-dimensional scene, and output construction prompt information.

7. The power grid transmission line construction plan planning system based on knowledge graph according to claim 6 is characterized by: The knowledge graph model building module builds the knowledge graph model of the mechanized construction plan and the standardized adaptation principle according to the following steps: Obtain original construction data, extract knowledge elements from the original construction data, and build a knowledge graph model; Extract entities, attributes, and relationships between entities, and obtain the knowledge system and update mechanism of the knowledge graph model through knowledge calculation; Constraints are extracted from the digital model of the construction scene, and the input parameters of the knowledge graph model are constructed based on the constraints to generate standardized adaptation principles suitable for the mechanized construction of transmission lines.

8. The power grid transmission line construction plan planning system based on knowledge graph according to claim 7 is characterized in that: The knowledge graph model building module obtains the original construction data, extracts knowledge elements from the original construction data, and builds a knowledge graph model according to the following steps: Collect data sets including design documents, construction logs, and material usage records from project management and field measurement equipment to generate construction raw data sets; The original construction data set is preprocessed according to the following formula, which includes data cleaning and format standardization: In the above formula, W s represents the preprocessed construction data, x s represents the error rate of the original data i, μ represents the average error rate, and k is the adjustment coefficient, which is used to control the sensitivity of weight adjustment; Based on the preprocessed construction data, key information is extracted, including process, material usage, and equipment status, to build a knowledge graph model; The knowledge graph model building module extracts entities, attributes, and relationships between entities according to the following steps, and obtains the knowledge system and update mechanism through knowledge calculation: Organize and classify the extracted entities, attributes, and relationship data between entities, establish a basic classification system based on the functions of entities and the characteristics of attributes, identify direct and indirect relationships between multiple entities, and generate a preliminary knowledge structure system according to the following formula: In the above formula, R ij Represents the relationship density between quantitative entities, n ij represents the number of co-occurrences between entities i and j, and N is the total number of entity pairs in the dataset; Based on the preliminary knowledge structure system, a deepened knowledge system is generated according to the following formula to optimize the impact of active entities and their relationships: In the above formula, K new represents the deepened knowledge system, E i represents the knowledge contribution of entity i, α i is a weight factor adjusted based on the activity of the entity, and n is the total number of entities; In combination with the deepened knowledge system and user interaction feedback, a knowledge updating mechanism is designed. The knowledge updating mechanism refers to dynamically adjusting the entity weights and relationship strengths in the knowledge system according to newly acquired data and user needs to obtain a sustainably updated knowledge system.

9. The power grid transmission line construction plan planning system based on knowledge graph according to claim 6 is characterized by: The standardized construction plan generation and screening module constructs a construction data integration set according to the following steps: Acquire the construction tasks of the transmission line project, and build the digital model of the project, the construction personnel model, the construction equipment model, the surrounding real environment model and the structure model based on the construction tasks of the transmission line project, so as to obtain the integrated set of construction data.

10. The power grid transmission line construction plan planning system based on knowledge graph according to claim 6, characterized in that: The simulation calculation module is used to select a standardized construction plan based on the optimized MOPSO algorithm according to the following steps: Construct a decision tree for the mechanized construction plan of transmission lines, establish the basic framework of the multi-objective optimization model, and determine the optimization objectives and constraints of the optimization model; optimize the fitness function improvement strategy, inertia weight improvement strategy, and learning factor improvement strategy in the MOPSO algorithm; Among them, the fitness function improvement strategy is: f(I1,I2,...,I M )=k1I1+k2I2+...k i I i ...+k M I M 0<k i <1; In the above formula, k i The weight coefficient of the i-th optimization objective represents the importance of the i-th optimization objective to the entire standardized construction plan. The fitness function f(I1, I2, ..., I M ) minimum value; I i represents the i-th optimization target; M represents the total number of optimization targets; The inertia weight improvement strategy adopts an improvement method in which the inertia weight w decreases nonlinearly with the iteration number Iter: In the above formula, w max 、w min are the maximum and minimum inertia weight respectively, α is the nonlinear adjustment constant, Iter max Indicates the maximum number of iterations; The learning factor improvement strategy is as follows: In the above formula, c1 and c2 are both learning factors, c1 represents the self-cognition of the particle, and c2 represents the social cognition of the particle; 1e , C 2e They represent the initial values ​​of the self-learning factor and the social learning factor, respectively, 1e 、c 2e Set to 2.

Images