Method for measuring project resource consumption of overhead transmission line

Abstract

The invention relates to an overhead transmission line project resource consumption measuring method. The method comprises the following steps: collecting construction scene image data and preprocessing the image data; constructing a construction scene feature extraction model, extracting feature data of the construction scene image through the construction scene feature extraction model, and classifying the construction scene; collecting resource consumption data of different classification construction scenes and preprocessing the resource consumption data; constructing a resource consumption prediction model, inputting the resource consumption data of different types of construction scenes into the resource consumption prediction model for training, and predicting the resource consumption of each type of construction scene through the trained resource consumption prediction model; and constructing a consumption matrix based on the resource consumption prediction result of each type of construction scene, and optimizing the consumption matrix by taking the maximization of the resource utilization rate as a target to obtain the resource allocation quantity of each type of construction scene.

Description

Technical Field

[0001] The invention relates to a method for measuring resource consumption of an overhead power transmission line project, and belongs to the technical field of electric power engineering. Background Art

[0002] As an important part of the power system, the construction process of overhead transmission line projects runs through a variety of complex scenarios, including diverse terrains such as plains, hills, and mountains, as well as complex geological conditions such as loose sandstone, rock, and clay. With the continuous expansion and complexity of transmission line construction, how to scientifically manage human, material, and machine resources and optimize construction efficiency during the construction process has become an important challenge in engineering construction. However, traditional construction management methods usually rely on experience and rough statistics, lack of in-depth analysis and precise measurement of resource consumption characteristics in different scenarios, resulting in low construction efficiency and serious waste of resources, especially in complex terrain and harsh environments. This problem is particularly prominent.

[0003] In addition, the current transmission line construction is facing many new challenges, such as the increasingly tight construction period, strict requirements for environmental protection, and the increasing proportion of mechanized construction. Under complex geological conditions, there are significant differences in the consumption patterns of resources in different construction links (such as foundation excavation, material transportation, tower assembly, etc.). How to use modern technical means and combine the characteristics of construction scenes to achieve accurate measurement and dynamic optimization of resources is not only an important way to improve construction efficiency, but also the key to energy saving, consumption reduction, cost reduction and green construction. Therefore, building a resource consumption measurement method based on intelligent technology has important practical needs and strategic significance. Summary of the invention

[0004] In order to solve the above problems existing in the prior art, the present invention proposes a method for measuring resource consumption of overhead power transmission line projects.

[0005] The technical solution of the present invention is as follows:

[0006] In one aspect, the present invention provides a method for measuring resource consumption of an overhead power transmission line project, comprising the following steps:

[0007] Collect construction scene image data and pre-process the image data;

[0008] Construct a construction scene feature extraction model, input the preprocessed image data into the construction scene feature extraction model to extract feature data of the construction scene, and classify the construction scene based on the feature data of the construction scene;

[0009] Collect resource consumption data of different construction scenarios and pre-process the resource consumption data;

[0010] Construct a resource consumption prediction model, input the pre-processed resource consumption data of different classified construction scenes into the resource consumption prediction model for training, obtain a trained resource consumption prediction model, and predict the resource consumption of each type of construction scene through the trained resource consumption prediction model;

[0011] A consumption matrix is ​​constructed based on the resource consumption prediction results of each type of construction scenario, and the consumption matrix is ​​optimized with the goal of maximizing resource utilization to obtain the allocation of resources for each type of construction scenario.

[0012] As a preferred embodiment of the present invention, the construction scene feature extraction model is constructed based on a convolutional neural network.

[0013] As a preferred embodiment of the present invention, the feature data of the construction scene extracted by the construction scene feature extraction model is constructed into a feature vector, and the feature vector is classified by a K-means clustering algorithm, and each classification is regarded as a construction scene type;

[0014] The types of construction scenarios include temporary road construction, material transportation, foundation excavation, foundation concrete pouring, tower assembly and ground wire installation.

[0015] As a preferred implementation of the present invention, after sorting the resource consumption data, outliers are eliminated by using the interquartile range method, as shown in the following formula:

[0016] Q1-1.5·IQR≤x≤Q3+1.5·IQR

[0017] IQR=Q3-Q1

[0018] Where: Q1 represents the first quartile of resource consumption data; Q3 represents the third quartile of resource consumption data; x represents the normal value;

[0019] The resource consumption data after outliers are removed is then normalized.

[0020] As a preferred embodiment of the present invention, the resource consumption prediction model is constructed based on a neural network model of a multilayer perceptron, and adopts a mean square error loss function with a regularization term, as shown in the following formula:

[0021]

[0022] Where: L represents the loss function; I represents the number of predicted values; y i represents the i-th predicted value; represents the i-th actual value; λ represents the regularization parameter; J represents the total number of model neurons; w j represents the weight of the jth neuron.

[0023] As a preferred embodiment of the present invention, the consumption matrix R c The specific formula is as follows:

[0024]

[0025] Where: r mn Represents the predicted consumption of the nth resource in the mth type of construction scenario.

[0026] As a preferred embodiment of the present invention, the specific steps of optimizing the consumption matrix with the goal of maximizing resource utilization are as follows:

[0027] For any type of construction scenario, the target model is constructed as shown in the following formula:

[0028]

[0029] Among them: U r represents resource utilization; r i Indicates the consumption of the nth resource in this type of construction scenario; c i represents the cost of the nth resource; R i Indicates the amount of resources consumed by the nth resource in the construction of this type of construction scenario; C i It represents the total cost consumed by the cth resource in the construction of this type of construction scenario.

[0030] On the other hand, the present invention further provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the method described in any embodiment of the present invention is implemented.

[0031] In yet another aspect, the present invention further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method described in any embodiment of the present invention.

[0032] The present invention has the following beneficial effects:

[0033] 1. The present invention combines deep learning with cluster analysis to extract construction scene features, construct a resource consumption prediction model based on neural network, and achieve accurate prediction of resource consumption in each construction scene, providing data support for construction planning and resource optimization in complex scenes, improving construction efficiency, reducing resource waste, and providing technical support for the intelligent construction of transmission line projects. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 The figure is a flow chart of the method of the present invention. DETAILED DESCRIPTION

[0035] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0036] It should be understood that the step numbers used in this document are only for convenience of description and are not intended to limit the order in which the steps are executed.

[0037] It should be understood that the terms used in the present specification are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the present specification and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0038] The terms “include” and “comprising” indicate the presence of described features, integers, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.

[0039] The term "and / or" means and includes any and all possible combinations of one or more of the associated listed items.

[0040] Embodiment 1:

[0041] See also Figure 1 , a method for measuring resource consumption of overhead transmission line engineering, comprising the following steps:

[0042] Collect construction scene image data and pre-process the image data;

[0043] Construct a construction scene feature extraction model, input the preprocessed image data into the construction scene feature extraction model to extract feature data of the construction scene, and classify the construction scene based on the feature data of the construction scene;

[0044] Collect resource consumption data of different construction scenarios and pre-process the resource consumption data;

[0045] Construct a resource consumption prediction model, input the pre-processed resource consumption data of different classified construction scenes into the resource consumption prediction model for training, obtain a trained resource consumption prediction model, and predict the resource consumption of each type of construction scene through the trained resource consumption prediction model;

[0046] A consumption matrix is ​​constructed based on the resource consumption prediction results of each type of construction scenario, and the consumption matrix is ​​optimized with the goal of maximizing resource utilization to obtain the allocation of resources for each type of construction scenario.

[0047] As a preferred implementation of this embodiment, the construction scene feature extraction model is constructed based on a convolutional neural network to extract key features of the construction site image, such as road width, foundation aperture, tower material weight, etc.;

[0048] The ReLU activation function is used to perform nonlinear mapping on the extracted image features to ensure the sparsity of the construction features;

[0049] As a preferred implementation of this embodiment, the feature data of the construction scene extracted by the construction scene feature extraction model is constructed into a feature vector, and the feature vector is classified by a K-means clustering algorithm, and each classification is regarded as a construction scene type;

[0050] Construct a weight matrix of influencing factors of construction scenarios and determine the influence of different features on classification through feature importance analysis;

[0051] Evaluate the accuracy of deep learning models and optimize neural network hyperparameters through cross-validation methods;

[0052] The types of construction scenarios include temporary road construction, material transportation, foundation excavation, foundation concrete pouring, tower assembly and ground wire installation.

[0053] Define the key variables involved in temporary road construction, including road width W r , road length L r and geological condition parameter ρ g , and constructed as the average road feasibility model F r :

[0054]

[0055] Establish the basic elements of construction material transportation: transportation distance, material weight, and transportation equipment load capacity. By analyzing key indicators, propose optimization plans for material transportation plans.

[0056] Clarify the main parameters in the foundation excavation process, including the excavation aperture D h , Excavation depth H h and geological conditions e , and construct the excavation volume V n Calculation formula:

[0057]

[0058] Describe the calculation model of material proportion in the foundation concrete pouring process and define the concrete consumption Cq , cement dosage S c and sand and gravel ratio P s , the specific relationship is as follows:

[0059] C q =S c +P s α s

[0060] Where: α s Indicates the sand-gravel mixing ratio coefficient;

[0061] Study the force balance model of tower assembly construction, analyze the relationship between the force of the tower bottom node and the tower height and wind force, and propose a node stability optimization plan;

[0062] A collaborative optimization method combining mechanical equipment deployment and human resource allocation in overhead transmission line construction is proposed to form a key equipment and human resource allocation matrix.

[0063] Combined with the construction environment complexity evaluation index C e The overall construction scene complexity classification model is proposed, as shown in the following formula:

[0064]

[0065] Where: P i is the manpower and machinery consumption in each construction step; T i is the construction time of this step;

[0066] Through historical data regression analysis, the standard consumption range of each construction step is clarified, and a key element library of the overall construction process is constructed to provide a data basis for subsequent steps;

[0067] As a preferred implementation of this embodiment, the resource consumption data (including excavation volume, material transportation distance, equipment power, etc.) are sorted and then outliers are eliminated using the interquartile range method, as shown in the following formula:

[0068] Q1-1.5·IQR≤x≤Q3+1.5·IQR

[0069] IQR=Q3-Q1

[0070] Where: Q1 represents the first quartile of resource consumption data; Q3 represents the third quartile of resource consumption data; x represents the normal value;

[0071] The resource consumption data after outliers are removed is then normalized.

[0072] As a preferred implementation of this embodiment, the resource consumption prediction model is constructed based on a neural network model of a multilayer perceptron, and adopts a mean square error loss function that introduces a regularization term, as shown in the following formula:

[0073]

[0074] Where: L represents the loss function; I represents the number of predicted values; y i represents the i-th predicted value; represents the i-th actual value; λ represents the regularization parameter; J represents the total number of model neurons; w j represents the weight of the jth neuron, and introduces the L2 regularization term to focus on preventing overfitting problems in the foundation excavation scenario, which is highly sensitive to the prediction of geological parameters;

[0075] Mini-Batch Gradient Descent is used to update model parameters based on the time and energy consumption of mechanical equipment in foundation excavation scenarios.

[0076] Transportation cost C for material transportation scenario t and equipment load factor L c Establish the optimization formula:

[0077]

[0078] Where: f i It represents the single transport consumption coefficient;

[0079] In model training, the learning rate is adjusted dynamically, and a learning rate decay strategy is adopted to address the large volatility of construction tension equipment data during tower assembly.

[0080] The model hyperparameters are adjusted using the validation set loss value for the construction tension and installation length in the ground wire installation scenario;

[0081] Combined with the construction site records, the back propagation algorithm is used to update the model weights, focusing on optimizing the material ratio and construction time during the foundation concrete pouring process;

[0082] Add a Softmax activation function to the output layer to calculate the probability distribution of human, material and machine consumption in multi-classification scenarios;

[0083] Eliminate low-confidence prediction values ​​in the prediction, and eliminate values ​​with confidence values ​​lower than 0.7;

[0084] Through transfer learning, the model parameters of the foundation excavation scenario are transferred to the tower assembly stage in a similar environment, reducing the training time of the new model;

[0085] In view of the energy consumption of mechanical tension equipment in ground wire installation, a weighted strategy is introduced to give higher weights to highly complex construction environments (such as mountainous areas);

[0086] Use construction data to update the model in real time, optimize material transportation routes and manpower allocation plans, and ensure that the prediction results are consistent with the actual situation on site;

[0087] Combined with construction consumption forecast, resource distribution diagrams for six scenarios are generated to analyze the consumption characteristics of manpower, materials and machines in different scenarios;

[0088] For complex construction scenarios (such as mountain foundation excavation), a multi-task learning model is built to simultaneously predict construction time and mechanical equipment consumption;

[0089] The mechanical power and construction time data at the construction site are corrected through real-time monitoring data to improve the dynamic accuracy of the prediction.

[0090] As a preferred implementation of this embodiment, the consumption matrix R c The specific formula is as follows:

[0091]

[0092] Where: r mn Represents the predicted consumption of the nth resource in the mth type of construction scenario.

[0093] As a preferred implementation of this embodiment, the specific steps of optimizing the consumption matrix with the goal of maximizing resource utilization are as follows:

[0094] For any type of construction scenario, the target model is constructed as shown in the following formula:

[0095]

[0096] Among them: U r represents resource utilization; r i Indicates the consumption of the nth resource in this type of construction scenario; c i represents the cost of the nth resource; R i Indicates the amount of resources consumed by the nth resource in the construction of this type of construction scenario; C i It represents the total cost consumed by the cth resource in the construction of this type of construction scenario.

[0097] Finally, a labor, material and machine consumption measurement report for six major construction scenarios is generated, covering the entire process from road construction to ground wire installation, providing data support for construction planning.

[0098] Embodiment 2:

[0099] This embodiment provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method described in any embodiment of the present invention when executing the program.

[0100] Embodiment three:

[0101] This embodiment provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the method described in any embodiment of the present invention is implemented.

[0102] In the embodiments of the present application, "at least one" refers to one or more, and "more than one" refers to two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent the existence of A alone, the existence of A and B at the same time, and the existence of B alone. Among them, A and B can be singular or plural. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship. "At least one of the following" and similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one of a, b and c can be represented by: a, b, c, a and b, a and c, b and c, or a and b and c, where a, b, c can be single or multiple.

[0103] Those of ordinary skill in the art will appreciate that the various units and algorithm steps described in the embodiments disclosed herein can be implemented in a combination of electronic hardware, computer software, and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0104] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0105] In several embodiments provided in the present application, if any function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory; hereinafter referred to as: ROM), random access memory (Random Access Memory; hereinafter referred to as: RAM), disk or optical disk, and other media that can store program codes.

[0106] The above descriptions are merely embodiments of the present invention and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A method for measuring resource consumption of overhead transmission line projects, characterized in that: The following steps are involved: Collect construction scene image data and pre-process the image data; Construct a construction scene feature extraction model, input the preprocessed image data into the construction scene feature extraction model to extract feature data of the construction scene, and classify the construction scene based on the feature data of the construction scene; Collect resource consumption data of different construction scenarios and pre-process the resource consumption data; Construct a resource consumption prediction model, input the pre-processed resource consumption data of different classified construction scenes into the resource consumption prediction model for training, obtain a trained resource consumption prediction model, and predict the resource consumption of each type of construction scene through the trained resource consumption prediction model; A consumption matrix is ​​constructed based on the resource consumption prediction results of each type of construction scenario, and the consumption matrix is ​​optimized with the goal of maximizing resource utilization to obtain the allocation of resources for each type of construction scenario.

2. A method for measuring resource consumption of overhead power transmission line engineering according to claim 1, characterized in that: The construction scene feature extraction model is built based on a convolutional neural network.

3. A method for measuring resource consumption of overhead power transmission line engineering according to claim 2, characterized in that: The feature data of the construction scene extracted by the construction scene feature extraction model is constructed into a feature vector, and the feature vector is classified by a K-means clustering algorithm, and each classification is regarded as a construction scene type; The types of construction scenarios include temporary road construction, material transportation, foundation excavation, foundation concrete pouring, tower assembly and ground wire installation.

4. The method for measuring resource consumption of overhead power transmission line engineering according to claim 1, characterized in that: After sorting the resource consumption data, outliers are removed using the interquartile range method, as shown in the following formula: Q1-1.5·IQR≤x≤Q3+1.5·IQR IQR=Q3-Q1 Where: Q1 represents the first quartile of resource consumption data; Q3 represents the third quartile of resource consumption data; x represents the normal value; The resource consumption data after outliers are removed is then normalized.

5. The method for measuring resource consumption of overhead power transmission line engineering according to claim 1, characterized in that: The resource consumption prediction model is constructed based on a multi-layer perceptron neural network model, and adopts a mean square error loss function with a regularization term, as shown in the following formula: Where: L represents the loss function; I represents the number of predicted values; y i represents the i-th predicted value; represents the i-th actual value; λ represents the regularization parameter; J represents the total number of model neurons; w j represents the weight of the jth neuron.

6. The method for measuring resource consumption of overhead power transmission line engineering according to claim 1, characterized in that: The consumption matrix R c The specific formula is as follows: Where: r mn Represents the predicted consumption of the nth resource in the mth type of construction scenario.

7. A method for measuring resource consumption of overhead power transmission line engineering according to claim 6, characterized in that: The specific steps to optimize the consumption matrix with the goal of maximizing resource utilization are: For any type of construction scenario, the target model is constructed as shown in the following formula: Among them: U r represents resource utilization; r i Indicates the consumption of the nth resource in this type of construction scenario; c i represents the cost of the nth resource; R i Indicates the amount of resources consumed by the nth resource in the construction of this type of construction scenario; C i It represents the total cost of the nth resource consumed in the construction of this type of construction scenario.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the method according to any one of claims 1 to 7 is implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images