Distribution network monomer engineering intelligent splitting method and device based on K-means clustering algorithm

Abstract

The invention relates to a K-means clustering algorithm-based distribution network monomer project intelligent splitting method and apparatus. The method comprises the following steps of obtaining project general situation data of a monomer project in a project settlement auditing link; classifying the project general situation data to obtain project type mapping data; performing data cleaning and preprocessing on the project general situation data, and performing feature extraction based on a preset splitting demand to obtain single project feature data; constructing a splitting model based on a K-means clustering algorithm in combination with the single engineering feature data and the engineering type mapping data; splitting the current project general situation data, dividing the current project general situation data into different sub-project units, and performing accuracy evaluation on the split sub-project units; and for each split sub-engineering unit, determining an equipment type selection scheme in combination with a mapping relationship of engineering types. According to the method, intelligent splitting of the single project is realized, and the splitting accuracy and stability are improved.

Description

Technical Field

[0001] The invention relates to a method and a device for intelligently splitting a distribution network monomer project based on a K-means clustering algorithm, and belongs to the technical field of engineering project management. Background Art

[0002] In distribution network projects, accurate calculation of project cost is crucial. Since distribution networks are usually composed of multiple subsystems, such as substations, switch stations, cable lines, etc., it is necessary to split the cost analysis data of distribution network single projects. This split is carried out according to the project splitting requirements, with the purpose of splitting the existing single project into the single units required for cost analysis, that is, the cost analysis single unit.

[0003] At present, the main method used for cost analysis data splitting is to organize experts to work together. These experts identify each core material in the project based on the completion drawings, material lists, settlement statements and other information. Then, based on the experts' experience, the materials are combined and the cost is split and calculated.

[0004] However, this method has some obvious shortcomings. First, organizing experts to split data is a difficult and inefficient task, and lacks the strong support of AI technology. Secondly, there is an important problem in splitting based on expert experience, that is, the lack of unified standards. Due to the lack of unified standards, the accuracy of the splitting results is difficult to guarantee, which may lead to inaccuracy and instability in cost analysis. Therefore, the present invention proposes a method and device for intelligent splitting of distribution network monomer projects based on K-means clustering algorithm. Summary of the invention

[0005] In order to solve the above problems, the present invention proposes a method and device for intelligent splitting of distribution network monomer projects based on K-means clustering algorithm, which can solve the problem of difficulty in identifying core materials and combining materials during the splitting process of monomer projects.

[0006] The technical solution adopted by the present invention to solve the technical problem is:

[0007] In a first aspect, an embodiment of the present invention provides a method for intelligently splitting a single distribution network project based on a K-means clustering algorithm, comprising the following steps:

[0008] Step S1, obtaining engineering overview data of a single project in the project settlement and review phase, wherein the engineering overview data includes historical engineering overview data and current engineering overview data;

[0009] Step S2, classifying the project overview data according to the preset mapping relationship of different project types and equipment to obtain project type mapping data;

[0010] Step S3, performing data cleaning and preprocessing on the project overview data based on the project type mapping data, and performing feature extraction based on the preset splitting requirements to obtain single project feature data;

[0011] Step S4, combining the single project feature data and the project type mapping data, and building a splitting model based on the K-means clustering algorithm;

[0012] Step S5, splitting the current project overview data according to the splitting model, dividing the current project overview data into different sub-project units, and performing accuracy evaluation on the split sub-project units;

[0013] Step S6: for each of the split sub-project units, determine the equipment selection scheme in combination with the mapping relationship of the project type.

[0014] As a possible implementation of this embodiment, in step S1, the historical project overview data at least records the past construction, equipment selection and material usage information of the project, and the current project overview data is the current status and requirements of the project.

[0015] As a possible implementation of this embodiment, in step S2, classifying the engineering overview data includes the following steps:

[0016] The project overview data is classified into two parts, namely the transformer part and the line engineering part;

[0017] The transformer part and the line engineering part are divided into Class A and Class B respectively. Class A is the same material but with different models, and Class B is the material with only one selection;

[0018] Class A is further classified according to material type.

[0019] As a possible implementation of this embodiment, in step S3, the data cleaning and preprocessing of the engineering overview data includes the following steps:

[0020] Carry out data cleaning and standardization on project profile data;

[0021] According to the equipment mapping relationship, different types of equipment and materials in the processed engineering profile data are mapped into a unified category.

[0022] As a possible implementation of this embodiment, in step S3, the preset splitting requirement refers to the splitting standards and requirements predetermined in the process of splitting the single project to support the cost analysis work.

[0023] As a possible implementation of this embodiment, step S4 includes the following steps:

[0024] Integrate the single project feature data with the project type mapping data to build a comprehensive data set;

[0025] Extracting features from the data set, wherein the features include quantity, type and specification of the single engineering feature data;

[0026] Select an appropriate K value, use the K-means algorithm to perform cluster analysis on the data set, divide the individual projects into different categories, and obtain cluster analysis results;

[0027] The results of cluster analysis are combined with the engineering type mapping data to construct a split model. The split model is expressed by the proportion of engineering types in each cluster. The proportion of each engineering type in each cluster is determined according to the number of samples in each cluster and the number of units in the engineering type mapping data, and a split plan is formulated accordingly.

[0028] As a possible implementation of this embodiment, clustering the data set using the K-means algorithm includes the following steps:

[0029] Randomly initialize K cluster centers and assign each sample to the nearest cluster center;

[0030] Update each cluster center to the average value of its member samples;

[0031] Repeat the above steps until the cluster center no longer changes or the maximum number of iterations is reached;

[0032] Use internal or external evaluation metrics to evaluate the quality of clustering results;

[0033] Adjust the K value according to the evaluation results and re-perform clustering analysis until the optimal clustering effect is achieved.

[0034] As a possible implementation of this embodiment, the formulating of the splitting plan includes the following steps:

[0035] For each cluster, the proportion of each engineering type in the cluster is calculated based on the number of units in the engineering type mapping data and the number of samples in the cluster;

[0036] Based on these proportions, determine how many units should be allocated to each engineering type in each cluster;

[0037] According to the distribution of each project type in each cluster, a specific splitting plan is formulated, and the splitting plan includes determining the specific splitting quantity, splitting order and splitting time arrangement of each project type.

[0038] As a possible implementation of this embodiment, step S5 includes the following steps:

[0039] According to the results of the K-means clustering algorithm, each sample data is assigned to the corresponding cluster;

[0040] For the sample data in each cluster, determine the project type to which it belongs according to the project type mapping data;

[0041] According to the project type and the number of samples in the cluster, the current project profile data is divided into different sub-project units;

[0042] The properties and characteristics of each sub-project unit are determined, wherein the properties and characteristics of the sub-project unit include project quantity, equipment, and implementation method.

[0043] As a possible implementation of this embodiment, step S6 includes the following steps:

[0044] For each split sub-project unit, extract the engineering quantity, equipment requirements and implementation methods;

[0045] According to the engineering type mapping relationship table, each sub-engineering unit is matched to the corresponding engineering type, and the equipment selection category to which it belongs is determined, and the equipment selection category includes category A and category B;

[0046] For each project type and equipment selection category, determine the best equipment selection solution based on actual needs and project requirements.

[0047] In a second aspect, an embodiment of the present invention provides a device for intelligently splitting a single-unit distribution network project based on a K-means clustering algorithm, comprising:

[0048] The data acquisition module is used to obtain the engineering overview data of the single project in the project settlement and review phase, and the engineering overview data includes historical engineering overview data and current engineering overview data;

[0049] A data classification module is used to classify the project overview data according to the preset mapping relationship between different project types and equipment to obtain project type mapping data;

[0050] The data processing module is used to clean and preprocess the project profile data based on the project type mapping data, and to extract features based on the preset splitting requirements to obtain the feature data of the single project;

[0051] The model building module is used to combine the single project feature data and project type mapping data to build a split model based on the K-means clustering algorithm;

[0052] The data splitting module is used to split the current project overview data according to the splitting model, divide the current project overview data into different sub-project units, and conduct accuracy evaluation on the split sub-project units;

[0053] The solution determination module is used to determine the equipment selection solution for each split sub-project unit in combination with the mapping relationship of the project type.

[0054] In a third aspect, an embodiment of the present invention provides a computer device, comprising a processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor. When the computer device is running, the processor communicates with the memory through the bus, and the processor executes the machine-readable instructions to perform any of the steps of the above-mentioned method for intelligent splitting of distribution network monomer projects based on the K-means clustering algorithm.

[0055] In a fourth aspect, an embodiment of the present invention provides a storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of any of the above-mentioned methods for intelligent splitting of distribution network monomer projects based on the K-means clustering algorithm are executed.

[0056] The beneficial effects of the technical solution of the embodiment of the present invention are as follows:

[0057] The technical solution of the embodiment of the present invention is a method for intelligent splitting of distribution network monomer projects based on K-means clustering algorithm. The clustering algorithm is used to extract features from engineering data, perform data clustering and generate splitting rules, thereby realizing intelligent splitting of monomer projects. The present invention accurately splits the monomer projects into monomers required for cost analysis, thereby improving the accuracy and stability of the splitting. Compared with traditional methods, the present invention can save labor costs, improve splitting efficiency, and reduce the risk of human errors, and has important application prospects in the cost management of power transmission and transformation projects.

[0058] The present invention utilizes advanced clustering algorithms and data processing technologies to automatically extract engineering data features, implement data clustering, and generate splitting rules, thereby realizing intelligent splitting of single projects. This makes the splitting process more accurate and stable, and greatly improves the splitting efficiency.

[0059] The present invention adopts automatic splitting technology, and through artificial intelligence algorithm, it can effectively identify and split the distribution network engineering data, avoiding the tediousness and subjectivity of traditional manual splitting. This technology is not affected by the personal experience and subjective judgment of experts, and improves the accuracy and consistency of splitting. The automatic splitting technology of the present invention covers two major types of engineering, namely, substation engineering and line engineering, and realizes more comprehensive and efficient splitting, thereby solving the splitting problem for different types of engineering in the prior art.

[0060] A device for intelligent splitting of distribution network monomer projects based on the K-means clustering algorithm in the technical solution of an embodiment of the present invention has the same beneficial effects as a method for intelligent splitting of distribution network monomer projects based on the K-means clustering algorithm in the technical solution of an embodiment of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] Figure 1 It is a flow chart of a method for intelligent splitting of a single project of a distribution network based on a K-means clustering algorithm according to an exemplary embodiment;

[0062] Figure 2 It is a structural schematic diagram of a distribution network monomer project intelligent splitting device based on K-means clustering algorithm according to an exemplary embodiment. DETAILED DESCRIPTION

[0063] In order to more clearly illustrate the technical features of the solution of the present invention, the present invention is described in detail below through specific implementation methods and in conjunction with the accompanying drawings.

[0064] like Figure 1 As shown, an embodiment of the present invention provides a method for intelligently splitting a single-unit distribution network project based on a K-means clustering algorithm, comprising the following steps:

[0065] Step S1, obtaining engineering overview data of a single project in the project settlement and review phase, wherein the engineering overview data includes historical engineering overview data and current engineering overview data;

[0066] Step S2, classifying the project overview data according to the preset mapping relationship of different project types and equipment to obtain project type mapping data;

[0067] Step S3, performing data cleaning and preprocessing on the project overview data based on the project type mapping data, and performing feature extraction based on the preset splitting requirements to obtain single project feature data;

[0068] Step S4, combining the single project feature data and the project type mapping data, and building a splitting model based on the K-means clustering algorithm;

[0069] Step S5, splitting the current project overview data according to the splitting model, dividing the current project overview data into different sub-project units, and performing accuracy evaluation on the split sub-project units;

[0070] Step S6: for each of the split sub-project units, determine the best equipment selection scheme in combination with the mapping relationship of the project type.

[0071] As a possible implementation of this embodiment, in step S1, the historical project overview data at least records the past construction, equipment selection and material usage information of the project, and the current project overview data is the current status and requirements of the project.

[0072] As a possible implementation of this embodiment, in step S2, classifying the engineering overview data includes the following steps:

[0073] The project overview data is classified into two parts, namely the transformer part and the line engineering part;

[0074] The transformer part and the line engineering part are divided into Class A and Class B respectively. Class A is the same material but with different models, and Class B is the material with only one selection;

[0075] Class A is further classified according to material type.

[0076] As a possible implementation of this embodiment, in step S3, the data cleaning and preprocessing of the engineering overview data includes the following steps:

[0077] Carry out data cleaning and standardization on project profile data;

[0078] According to the equipment mapping relationship, different types of equipment and materials in the processed engineering profile data are mapped into a unified category.

[0079] As a possible implementation of this embodiment, in step S3, the preset splitting requirement refers to the splitting standards and requirements predetermined in the process of splitting the single project to support the cost analysis work.

[0080] As a possible implementation of this embodiment, step S4 includes the following steps:

[0081] Integrate the single project feature data with the project type mapping data to build a comprehensive data set;

[0082] Extracting features from the data set, wherein the features include quantity, type and specification of the single engineering feature data;

[0083] Select an appropriate K value, use the K-means algorithm to perform cluster analysis on the data set, divide the individual projects into different categories, and obtain cluster analysis results;

[0084] The results of cluster analysis are combined with the engineering type mapping data to construct a split model. The split model is expressed by the proportion of engineering types in each cluster. The proportion of each engineering type in each cluster is determined according to the number of samples in each cluster and the number of units in the engineering type mapping data, and a split plan is formulated accordingly.

[0085] As a possible implementation of this embodiment, clustering the data set using the K-means algorithm includes the following steps:

[0086] Randomly initialize K cluster centers and assign each sample to the nearest cluster center;

[0087] Update each cluster center to the average value of its member samples;

[0088] Repeat the above steps until the cluster center no longer changes or the maximum number of iterations is reached;

[0089] Use internal or external evaluation metrics to evaluate the quality of clustering results;

[0090] Adjust the K value according to the evaluation results and re-perform clustering analysis until the optimal clustering effect is achieved.

[0091] As a possible implementation of this embodiment, the formulating of the splitting plan includes the following steps:

[0092] For each cluster, the proportion of each engineering type in the cluster is calculated based on the number of units in the engineering type mapping data and the number of samples in the cluster;

[0093] Based on these proportions, determine how many units should be allocated to each engineering type in each cluster;

[0094] According to the distribution of each project type in each cluster, a specific splitting plan is formulated, and the splitting plan includes determining the specific splitting quantity, splitting order and splitting time arrangement of each project type.

[0095] As a possible implementation of this embodiment, step S5 includes the following steps:

[0096] According to the results of the K-means clustering algorithm, each sample data is assigned to the corresponding cluster;

[0097] For the sample data in each cluster, determine the project type to which it belongs according to the project type mapping data;

[0098] According to the project type and the number of samples in the cluster, the current project profile data is divided into different sub-project units;

[0099] The properties and characteristics of each sub-project unit are determined, wherein the properties and characteristics of the sub-project unit include project quantity, equipment, and implementation method.

[0100] As a possible implementation of this embodiment, step S6 includes the following steps:

[0101] For each split sub-project unit, extract the engineering quantity, equipment requirements and implementation methods;

[0102] According to the engineering type mapping relationship table, each sub-engineering unit is matched to the corresponding engineering type, and the equipment selection category to which it belongs is determined, and the equipment selection category includes category A and category B;

[0103] For each project type and equipment selection category, determine the best equipment selection solution based on actual needs and project requirements.

[0104] In a second aspect, an embodiment of the present invention provides a device for intelligently splitting a single-unit distribution network project based on a K-means clustering algorithm, comprising:

[0105] The data acquisition module is used to obtain the engineering overview data of the single project in the project settlement and review phase, and the engineering overview data includes historical engineering overview data and current engineering overview data;

[0106] A data classification module is used to classify the project overview data according to the preset mapping relationship between different project types and equipment to obtain project type mapping data;

[0107] The data processing module is used to clean and preprocess the project profile data based on the project type mapping data, and to extract features based on the preset splitting requirements to obtain the feature data of the single project;

[0108] The model building module is used to combine the single project feature data and project type mapping data to build a split model based on the K-means clustering algorithm;

[0109] The data splitting module is used to split the current project overview data according to the splitting model, divide the current project overview data into different sub-project units, and conduct accuracy evaluation on the split sub-project units;

[0110] The solution determination module is used to determine the best equipment selection solution for each split sub-project unit based on the mapping relationship of the project type.

[0111] The specific process of performing intelligent splitting of distribution network monomer projects using a distribution network monomer project intelligent splitting device based on a K-means clustering algorithm provided by an embodiment of the present invention is as follows.

[0112] 1. Obtain engineering overview data of individual projects from the project settlement review phase.

[0113] During the project settlement and review phase, the project overview data of a single project includes historical project overview data and current project overview data; the historical project overview data records the project's past construction, equipment selection, material usage and other information, while the current project overview data is the project's current status and requirements.

[0114] During the initial review of the project or the project settlement audit, the relevant appraisal unit shall fill in the corresponding unit or project package and fill in the corresponding unit and project package under the single project overview to help improve the accuracy of the split.

[0115] 2. Classify the project overview data according to the preset equipment mapping relationship of different project types to obtain project type mapping data.

[0116] The specific method of classifying project profile data is as follows:

[0117] First, the project overview data is classified into two parts, namely the transformer part and the line engineering part; then each part is divided into two categories, A and B. Category A is the same material but with different models, and category B is the material with only one selection; finally, category A is further classified according to the material type;

[0118] The specific method of device mapping is as follows:

[0119] The mapping relationship is sorted according to the unit quantity, and the actual project settlement quantity is taken as variable N, which is filled in by the settlement link;

[0120] The selection in the project is based on (A+B) matching, and the actual project settlement quantity is realized based on N(A+B); unmatched materials or excess materials are not considered;

[0121] It should be noted that each part is divided into two categories, A and B, because the same materials exist in the construction and selection process of the distribution network project, corresponding to different models are selected, and the design and construction units in the construction process will also make independent choices within the range of optional equipment and materials; the actual project settlement quantity is taken as the variable N. For example, if there are 5 racks of the same model in a single project, then the variable N=5.

[0122] During the construction and selection process of distribution network projects, the same materials exist and corresponding models are selected, and the design and construction units during the construction process will also make independent choices within the range of optional equipment and materials.

[0123] The equipment mapping relationships are shown in Table 1 and Table 2. Table 1 is the transformer mapping relationship table, and Table 2 is the line engineering mapping relationship table.

[0124] Table 1: Transformer mapping relationship

[0125]

[0126]

[0127]

[0128] Table 2: Line engineering mapping relationship

[0129]

[0130]

[0131]

[0132]

[0133]

[0134] 3. Based on the engineering type mapping data, the engineering overview data is cleaned and preprocessed, and feature extraction is performed based on the preset splitting requirements to obtain the feature data of the single project.

[0135] The characteristic data of a single project includes engineering quantity data, equipment data, and implementation method data.

[0136] Preprocessing means that before using the K-means algorithm to cluster data, the original data is preprocessed according to the equipment mapping relationship, and different types of equipment and materials are mapped into a unified category, thereby reducing the complexity and noise of the data and improving the effect and accuracy of clustering.

[0137] The objective function of the K-means algorithm is:

[0138]

[0139] The center of the cluster β i The specific calculation formula is as follows;

[0140]

[0141] In the formula, s j is the feature vector of sample j; MB is the objective function (intra-cluster sum of squares), k is the number of clusters, C i is the i-th cluster, β i represents the center of the i-th cluster, O is the clustering cluster and is the Euclidean distance.

[0142] It should be noted that when processing engineering profile data, data cleaning and standardization are crucial; cleaning and standardizing data can ensure the quality and consistency of data, and provide a reliable basis for subsequent analysis and modeling; by cleaning data, missing values, outliers and duplicates in the data can be identified and processed, thereby improving the accuracy and completeness of the data; at the same time, standardized data can convert data in different formats and units into a unified standard format and dimension, making the data comparable and interpretable; using these methods for data cleaning and standardization can help reduce errors and deviations in the data analysis process, improve the credibility and stability of the analysis results, and provide reliable support for project decision-making.

[0143] There are many methods for data cleaning and standardization of engineering profile data. Among them, data cleaning methods include removing duplicate data, processing missing values, processing outliers, processing inconsistent data formats, etc.; statistical methods, machine learning algorithms or professional data cleaning tools can be used for data cleaning; and data standardization methods include converting data into the same unit, range or format, which can be performed using methods including minimum-maximum standardization, z-score standardization, and decimal calibration standardization; the selection of an appropriate method depends on the characteristics of the data and the needs of the analysis, taking into account factors such as data volume, data type, and data quality; through data cleaning and standardization, the consistency and accuracy of the data can be ensured, providing a reliable data foundation for subsequent feature extraction and analysis.

[0144] The preset splitting requirements refer to the splitting standards and requirements predetermined in the process of splitting a single project to support the cost analysis work; the requirements of this application are based on the analysis and understanding of engineering quantity data, equipment data and implementation method data, and aim to divide the single project into more detailed units for more accurate cost analysis and cost control; because the splitting requirements include classifying the total engineering quantity according to different engineering types, geographical locations or construction stages, the single project characteristic data includes engineering quantity data; because the splitting requirements involve dividing different types of equipment according to functions and specifications, the single project characteristic data includes equipment data; because it is necessary to split according to process flow, construction methods or technical standards, the single project characteristic data includes implementation method data; through the preset splitting requirements, key information can be extracted in a targeted manner during the splitting process to ensure that the splitting results meet the requirements of cost analysis, thereby providing reliable data support for management decisions.

[0145] Based on the project type mapping data, the project overview data is cleaned and preprocessed, and feature extraction is performed based on the preset splitting requirements to obtain the feature data of the single project;

[0146] The specific method of the pretreatment is as follows:

[0147] According to the equipment mapping relationship, different types of equipment and materials in the original data are mapped to a unified category. This can be achieved by establishing a category mapping table for equipment. For example, different types of transformers, cables, insulators and other equipment are mapped to corresponding categories.

[0148] Device mapping relationship processing: construct a device mapping relationship table = {(device name 1, category 1), (device name 2, category 2)...}.

[0149] 4. Construct a splitting model based on the K-means clustering algorithm according to the feature data of individual projects combined with the project type mapping data.

[0150] Integrate the single project feature data with the project type mapping data to build a comprehensive dataset. Ensure that the dataset contains all the required feature and label information.

[0151] Extract features from the data set to facilitate subsequent cluster analysis. Common feature extraction methods include principal component analysis (PCA), linear discriminant analysis (LDA), etc. Specifically, appropriate feature vectors can be extracted based on the quantity, type, specification and other features in the feature data of the single project.

[0152] The appropriate K value (the number of cluster centers) can usually be determined by the Elbow Method or Silhouette Score. Then, the K-means algorithm is used to cluster the data set and divide the individual projects into different categories.

[0153] The calculation formula of the silhouette coefficient is as follows:

[0154]

[0155] The specific calculation formula for the average distance between the sample and other samples in the same cluster is as follows:

[0156] a ij =||s j -β i ||

[0157] The specific calculation formula for the average distance between a sample and all samples in the nearest other clusters is as follows:

[0158]

[0159] Where Lk is the silhouette coefficient, a ij represents the average distance between a sample and other samples in the same cluster, b i Represents the average distance between a sample and all samples in the nearest cluster.

[0160] Randomly initialize K cluster centers; assign each sample to the nearest cluster center;

[0161] Update each cluster center to the average value of its member samples;

[0162] Repeat the above steps until the cluster center no longer changes or the maximum number of iterations is reached.

[0163] Use internal evaluation indicators (such as silhouette coefficient) or external evaluation indicators (such as mutual information) to evaluate the quality of clustering results. Adjust the K value according to the evaluation results and re-perform clustering analysis until the optimal clustering effect is achieved.

[0164] The results of cluster analysis are combined with the engineering type mapping data to construct a split model, which is represented by the proportion of engineering types in each cluster:

[0165]

[0166] Where P ij is the proportion of project type j in cluster i, R ij is the number of project type j in cluster i, R i Represents the total number of samples in cluster i.

[0167] The specific calculation method for the number of engineering type j in cluster i is:

[0168]

[0169] Among them, m is the total number of samples, δ jk is an indicator function, which takes the value of 1 when sample k belongs to engineering type j and is assigned to cluster i, otherwise it takes the value of 0.

[0170] Specifically, the proportion of each engineering type in each cluster can be determined according to the number of samples in each cluster and the number of units in the engineering type mapping data, and a splitting plan can be formulated accordingly.

[0171] The specific feasible steps for formulating the splitting plan are as follows: First, for each cluster, the proportion of each engineering type in the cluster is calculated based on the number of units in the engineering type mapping data and the number of samples in the cluster. Secondly, based on these proportions, it can be determined how many units should be allocated to each engineering type in each cluster. This allocation process can be carried out based on weights, which can be a comprehensive consideration of factors such as the importance of the engineering type and the distribution in historical data. Finally, based on the allocation of each engineering type in each cluster, a specific splitting plan is formulated, including determining the specific number of splits for each engineering type, the order of splits, the time schedule for splits, etc. The formulation of this plan requires comprehensive consideration of various factors to ensure that the split single project can meet the needs, while also considering the effective use of resources and the feasibility of the splitting process.

[0172] 5. Split the current project overview data according to the splitting model, divide the current project overview data into different sub-project units, and evaluate the accuracy of the split sub-project units.

[0173] The specific steps of dividing the current project overview data into different sub-project units are:

[0174] According to the results of the K-means clustering algorithm, each sample data is assigned to the corresponding cluster;

[0175] For the sample data in each cluster, determine the project type to which it belongs according to the project type mapping data;

[0176] According to the project type and the number of samples in the cluster, the current project profile data is divided into different sub-project units. Usually, each sub-project unit contains similar types and quantities of project items for subsequent construction and management.

[0177] Determine the properties and characteristics of each sub-project unit, including information such as project quantity, equipment, and implementation method.

[0178] 6. For each split sub-engineering unit, determine the best equipment selection plan based on the mapping relationship of the engineering type.

[0179] Specifically, for each split sub-engineering unit, extract its characteristic information such as engineering quantity, equipment requirements, implementation methods, etc., to facilitate subsequent equipment selection decisions;

[0180] According to the engineering type mapping table, each sub-engineering unit is matched to the corresponding engineering type, and the equipment selection category (Class A or Class B) is determined;

[0181] For each project type and equipment selection category, determine the best equipment selection scheme based on actual needs and project requirements. This involves considering factors such as equipment performance, quality, cost, and applicability to ensure that the selection scheme can meet project needs and achieve the expected results;

[0182] According to the actual situation, optimize and adjust the parameters in the selection scheme to make it more in line with the actual engineering needs and project requirements. This may involve fine-tuning the equipment parameters or selecting different equipment models to obtain better performance and results;

[0183] Evaluate and confirm the equipment selection scheme to ensure that it can effectively meet the project requirements and achieve the expected results. This may involve simulation or field testing to verify the feasibility and effectiveness of the selection scheme.

[0184] Intelligent splitting of distribution network monomer projects based on the K-means clustering algorithm has the following benefits and impacts:

[0185] 1) Improve efficiency: The K-means algorithm can cluster engineering data according to specific features, making the engineering splitting process more automated and efficient. Compared with manual splitting, using algorithms for splitting can save a lot of manpower and time costs.

[0186] 2) Reduce subjective interference: Automatic splitting through algorithms can reduce the impact of human subjective interference, avoid differences in the interpretation of engineering data by different personnel, and improve the objectivity and accuracy of the splitting results.

[0187] 3) Improve splitting accuracy: The K-means algorithm can divide the data into different clusters according to its characteristics, which can better identify the different parts and characteristics of the project, thereby improving the precision and accuracy of the splitting.

[0188] 4) Optimize resource allocation: By intelligently splitting the project, we can better understand the structure and composition of the project, which helps to optimize the allocation and utilization of resources and improve the overall efficiency and economy of the project.

[0189] 5) Support decision-making: The split project data is clearer and helps decision makers better understand the characteristics and needs of the project, thereby supporting more reasonable decision-making and planning arrangements.

[0190] 6) Split the current project overview data according to the splitting model, divide the current project overview data into different sub-project units, and evaluate the accuracy of the split sub-project units.

[0191] In general, intelligent splitting based on the K-means clustering algorithm can improve the efficiency and accuracy of engineering management, provide more reliable data support for engineering planning and implementation, and thus bring better engineering implementation effects and economic benefits.

[0192] The effects that the present invention can achieve are:

[0193] 1. Social effects:

[0194] Improve work efficiency: According to preliminary evaluation, the present invention can theoretically reduce the time of expert intervention from 80% to 40%. Considering the optimization of user interaction, it is expected to be reduced to 30%. This means that more splitting work can be completed in the same time, improving the efficiency of distribution network cost analysis.

[0195] Reduce labor costs: Automated splitting technology reduces dependence on experts, saves expert human resources, reduces labor costs, and also reduces the occurrence of human errors and improves work quality and accuracy.

[0196] 2. Economic effect:

[0197] Cost savings: It reduces the time required for experts to intervene in the splitting process and reduces labor costs. From an economic perspective, this will save the company a lot of splitting costs and human resource investment.

[0198] Improved efficiency: Due to the improved accuracy and consistency of the split, the results of the distribution network cost analysis are more reliable and precise, which helps the company make more accurate decisions and thus improve the overall economic benefits.

[0199] 3. Technical effects:

[0200] Improve data processing capabilities: Automated splitting technology can process a large amount of distribution network engineering data in a shorter time, improving data processing and analysis capabilities.

[0201] Optimize user experience: Considering the optimization of user interaction, the operation is made simpler and easier, the usage threshold is lowered, and the user's operating comfort and satisfaction are enhanced.

[0202] A computer device provided in an embodiment of the present invention includes a processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor. When the device is running, the processor communicates with the memory through the bus, and the processor executes the machine-readable instructions to perform any step of the above-mentioned method for intelligent splitting of distribution network monomer projects based on the K-means clustering algorithm.

[0203] Specifically, the above-mentioned memory and processor can be general-purpose memory and processor, which are not specifically limited here. When the processor runs the computer program stored in the memory, it can execute the above-mentioned intelligent splitting method of distribution network monomer projects based on the K-means clustering algorithm.

[0204] Those skilled in the art will appreciate that the structure of the computer device does not constitute a limitation on the computer device, and may include more or fewer components than shown in the figure, or combine certain components, or split certain components, or arrange the components differently.

[0205] In some embodiments, the computer device may also include a touch screen that can be used to display a graphical user interface (e.g., a startup interface of an application) and receive user operations on the graphical user interface (e.g., startup operations for an application). The specific touch screen may include a display panel and a touch panel. The display panel may be configured in the form of LCD (Liquid Crystal Display), OLED (Organic Light-Emitting Diode), etc. The touch panel may collect the user's contact or non-contact operations on or near it, and generate pre-set operation instructions, for example, the user uses any suitable object such as a finger or stylus to operate on or near the touch panel. In addition, the touch panel may include two parts: a touch detection device and a touch controller. The touch detection device detects the user's touch position and posture, detects the signal brought by the touch operation, and transmits the signal to the touch controller; the touch controller receives the touch information from the touch detection device, converts it into information that the processor can process, and then sends it to the processor, and can receive and execute commands sent by the processor. In addition, the touch panel can be implemented by various types such as resistive, capacitive, infrared and surface acoustic wave, and any technology developed in the future can also be used to implement the touch panel. Further, the touch panel can cover the display panel, and the user can operate on or near the touch panel covered on the display panel according to the graphical user interface displayed on the display panel. After the touch panel detects the operation on or near it, it is transmitted to the processor to determine the user input, and then the processor provides corresponding visual output on the display panel in response to the user input. In addition, the touch panel and the display panel can be implemented as two independent components or integrated.

[0206] Corresponding to the method for starting the above-mentioned application, an embodiment of the present invention further provides a storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of any of the above-mentioned methods for intelligent splitting of distribution network monomer projects based on the K-means clustering algorithm are executed.

[0207] The application startup device provided in the embodiment of the present application can be specific hardware on the device or software or firmware installed on the device. The device provided in the embodiment of the present application, its implementation principle and the technical effect produced are the same as those in the aforementioned method embodiment. For the sake of brief description, the parts not mentioned in the device embodiment can refer to the corresponding contents in the aforementioned method embodiment. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working processes of the systems, devices and units described above can all refer to the corresponding processes in the aforementioned method embodiment, and will not be repeated here.

[0208] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0209] In the embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of modules is only a logical function division. There may be other division methods in actual implementation. For example, multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, indirect coupling or communication connection of devices or modules, which can be electrical, mechanical or other forms.

[0210] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical modules, that is, they may be located in one place or distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0211] In addition, each functional module in the embodiments provided in the present application may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.

[0212] 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.

[0213] 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 including 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.

[0214] 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 A step that specifies a function in one or more boxes.

[0215] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A method for intelligent splitting of distribution network monomer projects based on K-means clustering algorithm, characterized in that: The steps include: Step S1, obtaining engineering overview data of a single project in the project settlement and review phase, wherein the engineering overview data includes historical engineering overview data and current engineering overview data; Step S2, classifying the project overview data according to the preset mapping relationship of different project types and equipment to obtain project type mapping data; Step S3, performing data cleaning and preprocessing on the project overview data based on the project type mapping data, and performing feature extraction based on the preset splitting requirements to obtain single project feature data; Step S4, combining the single project feature data and the project type mapping data, and building a splitting model based on the K-means clustering algorithm; Step S5, splitting the current project overview data according to the splitting model, dividing the current project overview data into different sub-project units, and performing accuracy evaluation on the split sub-project units; Step S6: for each of the split sub-project units, determine the equipment selection scheme in combination with the mapping relationship of the project type.

2. According to claim 1, the method for intelligent splitting of distribution network monomer projects based on K-means clustering algorithm is characterized in that: In step S2, the classification of the project overview data includes the following steps: The project overview data is classified into two parts, namely the transformer part and the line engineering part; The transformer part and the line engineering part are divided into Class A and Class B respectively. Class A is the same material but with different models, and Class B is the material with only one selection; Class A is further classified according to material type.

3. The method for intelligent splitting of distribution network monomer projects based on K-means clustering algorithm according to claim 1 is characterized in that: In step S3, the data cleaning and preprocessing of the engineering overview data includes the following steps: Carry out data cleaning and standardization on project profile data; According to the equipment mapping relationship, different types of equipment and materials in the processed engineering profile data are mapped into a unified category.

4. The method for intelligent splitting of distribution network monomer projects based on K-means clustering algorithm according to claim 1 is characterized in that: The step S4 comprises the following steps: Integrate the single project feature data with the project type mapping data to build a comprehensive data set; Extracting features from the data set, wherein the features include quantity, type and specification of the single engineering feature data; Select the K value and use the K-means algorithm to perform cluster analysis on the data set, divide the individual projects into different categories, and obtain the cluster analysis results; The results of cluster analysis are combined with the engineering type mapping data to construct a split model. The split model is expressed by the proportion of engineering types in each cluster. The proportion of each engineering type in each cluster is determined according to the number of samples in each cluster and the number of units in the engineering type mapping data, and a split plan is formulated accordingly.

5. According to claim 4, the method for intelligent splitting of distribution network monomer projects based on K-means clustering algorithm is characterized in that: The clustering of the data set using the K-means algorithm includes the following steps: Randomly initialize K cluster centers and assign each sample to the nearest cluster center; Update each cluster center to the average value of its member samples; Repeat the above steps until the cluster center no longer changes or the maximum number of iterations is reached; Use internal or external evaluation metrics to evaluate the quality of clustering results; Adjust the K value according to the evaluation results and re-perform clustering analysis until the optimal clustering effect is achieved.

6. The method for intelligent splitting of distribution network monomer projects based on K-means clustering algorithm according to claim 1 is characterized in that: The step S5 comprises the following steps: According to the results of the K-means clustering algorithm, each sample data is assigned to the corresponding cluster; For the sample data in each cluster, determine the project type to which it belongs according to the project type mapping data; According to the project type and the number of samples in the cluster, the current project profile data is divided into different sub-project units; The properties and characteristics of each sub-project unit are determined, wherein the properties and characteristics of the sub-project unit include project quantity, equipment, and implementation method.

7. The method for intelligent splitting of distribution network monomer projects based on K-means clustering algorithm according to any one of claims 1 to 6, characterized in that: The step S6 comprises the following steps: For each split sub-project unit, extract the engineering quantity, equipment requirements and implementation methods; According to the engineering type mapping relationship table, each sub-engineering unit is matched to the corresponding engineering type, and the equipment selection category to which it belongs is determined, and the equipment selection category includes category A and category B; For each project type and equipment selection category, determine the best equipment selection solution based on actual needs and project requirements.

8. A distribution network monomer project intelligent splitting device based on K-means clustering algorithm, characterized in that: include: The data acquisition module is used to obtain the engineering overview data of the single project in the project settlement and review phase, and the engineering overview data includes historical engineering overview data and current engineering overview data; A data classification module is used to classify the project overview data according to the preset mapping relationship between different project types and equipment to obtain project type mapping data; The data processing module is used to clean and preprocess the project profile data based on the project type mapping data, and to extract features based on the preset splitting requirements to obtain the feature data of the single project; The model building module is used to combine the single project feature data and project type mapping data to build a split model based on the K-means clustering algorithm; The data splitting module is used to split the current project overview data according to the splitting model, divide the current project overview data into different sub-project units, and conduct accuracy evaluation on the split sub-project units; The solution determination module is used to determine the equipment selection solution for each split sub-project unit in combination with the mapping relationship of the project type.

9. A computer device, characterized in that: It includes a processor, a memory and a bus, the memory stores machine-readable instructions executable by the processor, when the computer device is running, the processor and the memory communicate through the bus, and the processor executes the machine-readable instructions to perform the steps of the intelligent splitting method of distribution network monomer projects based on the K-means clustering algorithm as described in any one of claims 1-7.

10. A storage medium, characterized in that: The storage medium stores a computer program, which, when executed by a processor, executes the steps of the method for intelligently splitting a single-unit distribution network project based on a K-means clustering algorithm as described in any one of claims 1 to 7.

Images