CN113128125B - Method and device for predicting quantity of power transmission and transformation engineering material - Google Patents
Method and device for predicting quantity of power transmission and transformation engineering material Download PDFInfo
- Publication number
- CN113128125B CN113128125B CN202110447307.6A CN202110447307A CN113128125B CN 113128125 B CN113128125 B CN 113128125B CN 202110447307 A CN202110447307 A CN 202110447307A CN 113128125 B CN113128125 B CN 113128125B
- Authority
- CN
- China
- Prior art keywords
- engineering
- index
- transformation
- prediction model
- power transmission
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 239000000463 material Substances 0.000 title claims abstract description 118
- 230000005540 biological transmission Effects 0.000 title claims abstract description 98
- 230000009466 transformation Effects 0.000 title claims abstract description 98
- 238000000034 method Methods 0.000 title claims abstract description 37
- 239000013077 target material Substances 0.000 claims abstract description 30
- 238000005516 engineering process Methods 0.000 claims abstract description 23
- 238000012549 training Methods 0.000 claims abstract description 22
- 238000004364 calculation method Methods 0.000 claims abstract description 15
- 238000013528 artificial neural network Methods 0.000 claims description 28
- 238000013507 mapping Methods 0.000 claims description 10
- 238000012800 visualization Methods 0.000 claims description 7
- 238000005314 correlation function Methods 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 6
- 239000004035 construction material Substances 0.000 claims description 3
- 230000001902 propagating effect Effects 0.000 claims 2
- 238000012795 verification Methods 0.000 claims 1
- 238000005259 measurement Methods 0.000 abstract description 4
- 238000007405 data analysis Methods 0.000 abstract description 3
- 238000013461 design Methods 0.000 abstract description 3
- 238000012360 testing method Methods 0.000 abstract description 3
- 229910000831 Steel Inorganic materials 0.000 description 4
- 239000010959 steel Substances 0.000 description 4
- 239000004566 building material Substances 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 239000004567 concrete Substances 0.000 description 2
- 239000012212 insulator Substances 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 239000011248 coating agent Substances 0.000 description 1
- 238000000576 coating method Methods 0.000 description 1
- 239000002131 composite material Substances 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000004575 stone Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2465—Query processing support for facilitating data mining operations in structured databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/28—Databases characterised by their database models, e.g. relational or object models
- G06F16/284—Relational databases
- G06F16/285—Clustering or classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E40/00—Technologies for an efficient electrical power generation, transmission or distribution
- Y02E40/70—Smart grids as climate change mitigation technology in the energy generation sector
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Economics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Artificial Intelligence (AREA)
- Strategic Management (AREA)
- Mathematical Physics (AREA)
- Biophysics (AREA)
- General Business, Economics & Management (AREA)
- Computing Systems (AREA)
- Tourism & Hospitality (AREA)
- Molecular Biology (AREA)
- Marketing (AREA)
- Biomedical Technology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Hardware Design (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Development Economics (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Geometry (AREA)
- Medical Informatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Fuzzy Systems (AREA)
- Probability & Statistics with Applications (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- Primary Health Care (AREA)
Abstract
The application discloses a method and a device for predicting the quantity of transmission and transformation engineering materials, wherein the method for predicting the quantity of the transmission and transformation engineering materials comprises the following steps: analyzing historical power transmission and transformation project data and national quota documents, and determining a quota index influencing the quantity of the engineering material; analyzing the power transmission and transformation project data by combining the quota index and a big data technology, and constructing a material prediction model; training the model by using the power transmission and transformation project data, and verifying the material prediction model by using actual project data to obtain a target material quantity prediction model; and predicting the quantity of the electric transmission and transformation engineering material according to the target material quantity prediction model. According to the method, a large amount of power transmission and transformation project data are analyzed and a data analysis model is established according to a large data supporting technology, a power transmission and transformation project material prediction model based on large power data is formed through training, testing and optimizing of the large amount of data, material amount prediction under different design conditions of a power transmission and transformation project is achieved, and an important basis is provided for material amount measurement and calculation of the power transmission and transformation project.
Description
Technical Field
The application relates to the technical field of power transmission and transformation engineering, in particular to a method and a device for predicting the quantity of power transmission and transformation engineering materials.
Background
The estimation of the amount of transmission and transformation project material is a considerable weight in the whole project evaluation. Currently, for measuring and calculating the quantity of power transmission and transformation engineering materials, a large amount of manpower is used for collecting relevant engineering data, researching engineering schemes, selecting types and selecting materials, and meanwhile, a large amount of time is invested for measuring and calculating. The expert experience is different, certain subjective difference exists in the type selection and material selection process, meanwhile, certain calculation error risk exists in manual calculation, and the working efficiency is low.
Disclosure of Invention
The application provides a method and a device for predicting the quantity of power transmission and transformation engineering materials, which are used for solving the problems of subjectivity and low prediction efficiency in prediction of the quantity of the power transmission and transformation engineering materials in the prior art.
In order to solve the technical problem, the present application provides a method for predicting the material quantity of power transmission and transformation engineering, including: analyzing historical power transmission and transformation project data and national quota documents, and determining a quota index influencing the quantity of the engineering material; analyzing the power transmission and transformation project data by combining the quota index and a big data technology, and constructing a material prediction model; training the model by using the power transmission and transformation project data, and verifying the material prediction model by using the actual project data to obtain a target material quantity prediction model; and predicting the quantity of the transmission and transformation engineering materials according to the target material quantity prediction model.
Optionally, predicting the amount of the electric transmission and transformation engineering material according to the target material amount prediction model includes: integrating a material prediction model into a B/S architecture application system to realize visualization; and the prediction of the power transmission and transformation engineering material quantity is completed by inputting a limit index of a service system through one-key operation.
Optionally, training the model by using the power transmission and transformation engineering data, and verifying the material prediction model by using the actual project data to obtain a target material quantity prediction model, including: defining a neural network comprising a plurality of parameters capable of being updated, wherein the parameters comprise weight values; performing iterative computation on input data; processing input data through a multi-layer network structure; calculating a loss value, wherein the loss value is a difference value between the output value and the target value; and reversely transmitting the gradient to the parameters of the neural network, updating the weight values in the neural network according to an updating rule, and finally obtaining a target material quantity prediction model.
Optionally, analyzing the historical power transmission and transformation project data and the national quota literature, and determining a quota index affecting the quantity of the engineering material, including: constructed as followsDecoupling calculation is carried out on the target function:
in the formula, G iA For each engineering quantity index for the actual project data>
Is a corresponding quota index, wherein i represents the ith index, Δ G i For engineering quantity index correlation functions, x, requiring decoupling 1 ,x 2 ,…,x n The index influence parameters are index influence parameters which influence the engineering quantity indexes.
Optionally, classifying and clustering the index influence parameters to find common features includes: d = { o1, o2, …, on } represents a set of n objects, oi represents the ith object, and Cx represents the xth cluster; wherein i =1,2, …, n; x =1,2, …, k; n is the number of objects and k is the number of clusters; representing the similarity between object oi and object oj by sim (oi, oj); and if each cluster Cx is a rigid clustering result, carrying out nonlinear mapping by means of a neural network, and constructing a material prediction model by combining a big data technology.
In order to solve the above technical problem, the present application provides a power transmission and transformation engineering material quantity prediction apparatus, including: the quota index acquisition module is used for analyzing historical power transmission and transformation project data and national quota documents and determining a quota index influencing the quantity of the engineering material; the construction material prediction model module is used for analyzing the power transmission and transformation project data by combining the quota index and the big data technology and constructing a material prediction model; the model training module is used for training the model by using the power transmission and transformation engineering data and verifying the material prediction model by using the actual project data to obtain a target material quantity prediction model; and the prediction module is used for predicting the electric transmission and transformation engineering material quantity according to the target material quantity prediction model.
Optionally, the prediction module is further configured to: integrating a material prediction model into a B/S architecture application system to realize visualization; and the prediction of the transmission and transformation engineering material quantity is completed through one-key operation of the recording of the quota index of the service system.
Optionally, the model training module is further configured to: defining a neural network comprising a plurality of parameters capable of being updated, wherein the parameters comprise weight values; performing iterative computation on input data; processing input data through a multi-layer network structure; calculating a loss value, wherein the loss value is the difference between the output value and the target value; and reversely transmitting the gradient to parameters of the neural network, updating weight values in the neural network according to an updating rule, and finally obtaining a target material quantity prediction model.
Optionally, the quota index obtaining module is further configured to:
constructing the following objective function for decoupling calculation:
Optionally, the building material prediction model module is further configured to: classifying and clustering index influence parameters to find out common characteristics, comprising the following steps: d = { o1, o2, …, on } represents a set of n objects, oi represents the ith object, and Cx represents the xth cluster; wherein i =1,2, …, n; x =1,2, …, k; n is the number of objects and k is the number of clusters; representing the similarity between object oi and object oj by sim (oi, oj); and if each cluster Cx is a rigid clustering result, carrying out nonlinear mapping by means of a neural network, and constructing a material prediction model by combining a big data technology.
The application provides a method and a device for predicting transmission and transformation engineering material quantity, wherein the method for predicting the transmission and transformation engineering material quantity comprises the following steps: analyzing historical power transmission and transformation project data and national quota documents, and determining a quota index influencing the quantity of the engineering material; analyzing the power transmission and transformation project data by combining the quota index and the big data technology, and constructing a material prediction model; training the model by using the power transmission and transformation project data, and verifying the material prediction model by using the actual project data to obtain a target material quantity prediction model; and predicting the quantity of the electric transmission and transformation engineering material according to the target material quantity prediction model. According to the method, a large amount of power transmission and transformation project data are analyzed and a data analysis model is established according to a big data technology, a power transmission and transformation project material prediction model based on large electric power data is formed through training, testing and optimizing of a large amount of data, material quantity prediction under different design conditions of a power transmission and transformation project is achieved, and an important basis is provided for material quantity measurement and calculation of the power transmission and transformation project.
Drawings
In order to more clearly illustrate the technical solution of the present application, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings without creative efforts.
FIG. 1 is a schematic flow chart illustrating an embodiment of a method for predicting the amount of a transmission and transformation engineering material according to the present application;
FIG. 2 is a schematic illustration of a non-linear mapping by means of a neural network;
FIG. 3 is a schematic structural diagram of an embodiment of a device for predicting the amount of a transmission and transformation engineering material according to the present application;
fig. 4 is a schematic flow chart of another embodiment of the method for predicting the amount of the power transmission and transformation engineering material.
Detailed Description
In order to enable those skilled in the art to better understand the technical solution of the present application, the following detailed description is provided for a method and an apparatus for predicting the amount of transmission and transformation engineering material in accordance with the present application with reference to the accompanying drawings and the detailed description.
At present, the measurement and calculation of the material quantity of the power transmission and transformation engineering needs to be carried out through manpower: the engineering data is familiar, the types and specifications of the required materials are determined, and the materials are summarized and summed up step by step, a plurality of experts are required to be invested for large-scale analysis and accounting, a large amount of labor cost is invested, and the overall measuring and calculating efficiency is low.
The method and the device can find key influence indexes of the material quantity through big data, build a model based on big data technology, train the model by combining historical engineering data to obtain a stable prediction model, and can complete quick prediction of the required material quantity through input of key indexes of the power transmission and transformation engineering. The method comprises the following specific steps:
referring to fig. 1, fig. 1 is a schematic flow chart of an embodiment of a method for predicting the amount of transmission and transformation engineering materials. In this embodiment, the method may specifically include the following steps:
s110: and analyzing historical power transmission and transformation project data and national quota documents, and determining quota indexes influencing the quantity of the engineering materials.
The calculated indexes by analyzing the national quota literature (national net, south net) and the actual project engineering include but are not limited to: the system comprises a line length, a whole line tortuosity coefficient, a loop number, a wind speed, ice coating, an altitude, a wire model, a ground wire model, a flat ground, a hill, a mountain land, a mountain, a mountain ridge, a mud and marsh, a river network, a desert, a strain tower proportion, a pole tower number, a single-kilometer pole tower number, a straight line tower average call height, a strain tower average call height, a manpower distance, an automobile distance, a wire, a ground wire, a wire hanging hardware fitting, a grounding steel, a wire spacing rod, a vibration damper, a disc insulator, a composite insulator, a pole tower steel, a foundation steel, an anchor bolt (inserting angle steel), cast-in-place concrete, cast-in-place pile concrete, a cushion layer, an earth and stone square, a tower foundation land acquisition, house dismantling, a sheet forest area length, a body project, device material cost, a foundation project, a pole tower project, a grounding project, an overhead line project, an accessory project and an auxiliary project.
The method is characterized by combining a quota index and a big data technology, analyzing the power transmission and transformation engineering data, and constructing a material prediction model, wherein the method comprises the following steps: constructing the following objective function for decoupling calculation:
in the formula, G iA For each engineering quantity index for the actual project data>
Is a corresponding quota index, where i represents the ith index, Δ G i For engineering quantity index correlation functions requiring decoupling, x 1 ,x 2 ,…,x n The index influence parameters are index influence parameters which influence the engineering quantity indexes.
The calculation result shows that the correlation coefficient of the whole line tortuosity coefficient is 10%, the correlation coefficient of the loop number is 8%, the correlation coefficient of the single kilometer tower footing is 7%, the proportional correlation coefficient of the strain tower is 5%, the average breath height correlation coefficient is 2%, the main influence factor indexes with the correlation coefficient larger than 1% are main influence factor indexes, and the main influence factor indexes with the correlation coefficient larger than 1% are used as quota indexes for influencing the engineering material quantity.
Namely, the project quantity index of the national quota literature (national network, south network) and the actual project quantity index are used as dependent variables.
S120: and (4) analyzing the power transmission and transformation project data by combining the quota index and the big data technology, and constructing a material prediction model.
Classifying and clustering index influence parameters to find out common characteristics, comprising the following steps: d = { o1, o2, …, on } represents a set of n objects, oi represents the ith object, and Cx represents the xth cluster; wherein i =1,2, …, n; x =1,2, …, k; n is the number of objects and k is the number of clusters; representing the similarity between object oi and object oj by sim (oi, oj); and if each cluster Cx is a rigid clustering result, carrying out nonlinear mapping by means of a neural network, and constructing a material prediction model by combining a big data technology. As shown in fig. 2, fig. 2 is a schematic diagram of non-linear mapping by means of a neural network.
S130: and training the model by using the power transmission and transformation engineering data, and verifying the material prediction model by using the actual project data to obtain a target material quantity prediction model.
Training a model by using power transmission and transformation engineering data, and verifying a material prediction model by using actual project data to obtain a target material quantity prediction model, wherein the method comprises the following steps: defining a neural network comprising a plurality of parameters capable of being updated, wherein the parameters comprise weight values; performing iterative computation on input data; processing input data through a multi-layer network structure; calculating a loss value, wherein the loss value is the difference between the output value and the target value; and reversely transmitting the gradient to parameters of the neural network, updating weight values in the neural network according to an updating rule, and finally obtaining a target material quantity prediction model.
S140: and predicting the quantity of the electric transmission and transformation engineering material according to the target material quantity prediction model.
The method for predicting the electric transmission and transformation engineering material quantity according to the target material quantity prediction model comprises the following steps: integrating a material prediction model into a B/S architecture application system to realize visualization; and the prediction of the power transmission and transformation engineering material quantity is completed by inputting a limit index of a service system through one-key operation.
The embodiment provides a method for predicting the quantity of transmission and transformation engineering materials, which comprises the following steps: analyzing historical power transmission and transformation project data and national quota documents, and determining a quota index influencing the quantity of the engineering material; analyzing the power transmission and transformation project data by combining the quota index and a big data technology, and constructing a material prediction model; training the model by using the power transmission and transformation project data, and verifying the material prediction model by using the actual project data to obtain a target material quantity prediction model; and predicting the quantity of the electric transmission and transformation engineering material according to the target material quantity prediction model. According to the method, a large amount of power transmission and transformation project data are analyzed and a data analysis model is established according to a big data technology, a power transmission and transformation project material prediction model based on large electric power data is formed through training, testing and optimizing of a large amount of data, material quantity prediction under different design conditions of a power transmission and transformation project is achieved, and an important basis is provided for material quantity measurement and calculation of the power transmission and transformation project.
Based on the foregoing method for predicting the amount of electrical transmission and transformation engineering material, the present application provides a device for predicting the amount of electrical transmission and transformation engineering material, please refer to fig. 3, and fig. 3 is a schematic structural diagram of an embodiment of the device for predicting the amount of electrical transmission and transformation engineering material. The power transmission and transformation engineering material amount prediction apparatus 300 may include a quota index obtaining module 310, a building material prediction model module 320, a model training module 330, and a prediction module 340.
A quota index obtaining module 310, configured to analyze historical power transmission and transformation project data and national quota documents, and determine a quota index affecting the quantity of the engineering material; the construction material prediction model module 320 is used for analyzing the power transmission and transformation project data by combining the quota index and the big data technology and constructing a material prediction model; the model training module 330 is configured to train a model by using power transmission and transformation engineering data, and verify a material prediction model by using actual project data to obtain a target material quantity prediction model; and the prediction module 340 is used for predicting the electric transmission and transformation engineering material quantity according to the target material quantity prediction model.
Optionally, the prediction module 340 is further configured to: integrating a material prediction model into a B/S architecture application system to realize visualization; and the prediction of the power transmission and transformation engineering material quantity is completed by inputting a limit index of a service system through one-key operation.
Optionally, the model training module 330 is further configured to: defining a neural network comprising a plurality of parameters capable of being updated, wherein the parameters comprise weight values; performing iterative computation on input data; processing input data through a multi-layer network structure; calculating a loss value, wherein the loss value is the difference between the output value and the target value; and reversely transmitting the gradient to parameters of the neural network, updating weight values in the neural network according to an updating rule, and finally obtaining a target material quantity prediction model.
Optionally, the quota index obtaining module 310 is further configured to:
constructing the following objective function for decoupling calculation:
in the formula, G iA For each engineering quantity index of the actual project data,
Is a corresponding quota index, wherein i represents the ith index, Δ G i For engineering quantity index correlation functions, x, requiring decoupling 1 ,x 2 ,…,x n The index influence parameters are index influence parameters which influence the engineering quantity indexes. Wherein, the main influence factor index with the correlation coefficient more than 1 percent is used as the quota index for influencing the engineering material quantity.
Optionally, the building material prediction model module 320 is further configured to:
classifying and clustering index influence parameters to find out common characteristics, comprising the following steps:
d = { o1, o2, …, on } represents a set of n objects, oi represents the ith object, cx represents the xth cluster; wherein i =1,2, …, n; x =1,2, …, k; n is the number of objects and k is the number of clusters;
representing the similarity between object oi and object oj by sim (oi, oj);
and if each cluster Cx is a rigid clustering result, carrying out nonlinear mapping by means of a neural network, and constructing a material prediction model by combining a big data technology.
Finally, for example, please refer to fig. 4, wherein fig. 4 is a schematic flow chart of another embodiment of the method for predicting the amount of the transmission and transformation engineering material according to the present application.
In the embodiment, an objective function is constructed according to the historical data of the power transmission and transformation project and the national quota literature, and the objective function is analyzed and decoupled to obtain an index with a correlation coefficient larger than 1% as a quota index.
The material quantity prediction model is built by applying big data technology and nonlinear mapping technology, wherein the nonlinear mapping technology comprises classification, clustering and neural network.
The model is trained, and the training content can comprise a neural network, iterative computation, a multi-layer network structure and a back propagation gradient. And outputting the model when the fitting effect of the model reaches 99.9%, otherwise, continuing to optimize the model.
The output model is combined with a B/S visualization system, namely the model predicted material quantity can be output.
It is to be understood that the specific embodiments described herein are merely illustrative of the application and are not limiting of the application. In addition, for convenience of description, only a part of structures related to the present application, not all of the structures, are shown in the drawings. Step numbers used herein are also for convenience of description only and are not intended as limitations on the order in which steps may be performed. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
The terms "first", "second", etc. in this application are used to distinguish different objects, and are not used to describe a particular order. Furthermore, the terms "include" and "have," as well as any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those steps or elements listed, but may alternatively include other steps or elements not listed, or inherent to such process, method, article, or apparatus.
Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the application. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. It is explicitly and implicitly understood by one skilled in the art that the embodiments described herein can be combined with other embodiments.
The above description is only for the purpose of illustrating embodiments of the present application and is not intended to limit the scope of the present application, and all modifications of equivalent structures and equivalent processes, which are made by the contents of the specification and the drawings of the present application or are directly or indirectly applied to other related technical fields, are also included in the scope of the present application.
Claims (6)
1. A method for predicting the quantity of electric transmission and transformation engineering materials is characterized by comprising the following steps:
analyzing historical power transmission and transformation project data and national quota documents, and determining a quota index influencing the quantity of the engineering material, wherein the quota index comprises the following steps:
obtaining a project quantity index through historical power transmission and transformation project data and national quota documents;
constructing the following objective function for decoupling calculation:
in the formula, G iA Respective engineering quantity indexes, x, for actual project data iA Is the actual project data of the engineering quantity index i,
limit indexes, x, corresponding to each engineering quantity index i0 Is x iA Wherein i represents the ith index, Δ G i For engineering quantity index correlation functions requiring decoupling, Δ x i The correlation coefficient is the engineering quantity index i;
obtaining a correlation coefficient of the engineering quantity index through the decoupling calculation, and taking the engineering quantity index with the correlation coefficient larger than 1% as a quota index influencing the engineering material quantity;
and (3) analyzing the power transmission and transformation engineering data by combining the quota index influencing the engineering material quantity and a big data technology, and constructing a material prediction model, wherein the method comprises the following steps:
classifying and clustering the index influence parameters to find out common characteristics, comprising the following steps:
d = { o1, o2, …, on } represents a set of n objects, oi represents the ith object, and Cx represents the xth cluster; wherein i =1,2, …, n; x =1,2, …, k; n is the number of objects and k is the number of clusters;
representing the similarity between object oi and object oj by sim (oi, oj);
if each Cx cluster is a rigid clustering result, carrying out nonlinear mapping by means of a neural network, and constructing the material prediction model by combining a big data technology;
training a model by using the power transmission and transformation project data, and verifying the material prediction model by using actual project data to obtain a target material quantity prediction model;
and predicting the quantity of the transmission and transformation engineering materials according to the target material quantity prediction model.
2. The method for predicting the quantity of electric transmission and transformation engineering material according to claim 1, wherein the predicting the quantity of electric transmission and transformation engineering material according to the target material quantity prediction model comprises:
integrating the material prediction model into a B/S architecture application system to achieve visualization;
and completing the prediction of the power transmission and transformation engineering material quantity through the input one-key operation of the limit index of the service system.
3. The method for predicting the quantity of electric transmission and transformation engineering materials according to claim 1, wherein the training of the model by using the electric transmission and transformation engineering data and the verification of the material prediction model by using actual project data to obtain a target material quantity prediction model comprises the following steps:
defining a neural network comprising a plurality of updatable parameters, wherein the parameters include weight values; performing iterative computation on input data; processing the input data through a multi-layer network structure; calculating a loss value, wherein the loss value is a difference value between the output value and a target value; and reversely propagating the gradient to the parameters of the neural network, updating the weight values in the neural network according to an updating rule, and finally obtaining the target material quantity prediction model.
4. An electric transmission and transformation engineering material quantity prediction device is characterized by comprising:
the quota index acquisition module is used for analyzing historical power transmission and transformation project data and national quota documents and determining a quota index influencing the quantity of the engineering material; the method comprises the following steps:
obtaining a project quantity index through historical power transmission and transformation project data and national quota documents;
constructing the following objective function for decoupling calculation:
in the formula, G iA For each engineering quantity index, x, of the actual project data iA Is the actual project data of the engineering quantity index i,
limit indexes, x, corresponding to each engineering quantity index i0 Is x iA Wherein i represents the ith index, Δ G i For engineering quantity index correlation functions requiring decoupling, Δ x i The correlation coefficient of the engineering quantity index i is obtained;
obtaining a correlation coefficient of the engineering quantity index through the decoupling calculation, and taking the engineering quantity index with the correlation coefficient larger than 1% as a quota index influencing the engineering material quantity;
the construction material prediction model module is used for analyzing the power transmission and transformation project data by combining the quota index influencing the engineering material quantity and a big data technology to construct a material prediction model;
the build material prediction model module is further to:
classifying and clustering the index influence parameters to find out common characteristics, comprising the following steps:
d = { o1, o2, …, on } represents a set of n objects, oi represents the ith object, cx represents the xth cluster; wherein i =1,2, …, n; x =1,2, …, k; n is the number of objects and k is the number of clusters;
representing similarity between the object oi and the object oi by sim (oi, oi);
if each Cx cluster is a rigid clustering result, carrying out nonlinear mapping by means of a neural network, and constructing the material prediction model by combining a big data technology;
the model training module is used for training a model by using the power transmission and transformation project data and verifying the material prediction model by using actual project data to obtain a target material quantity prediction model;
and the prediction module is used for predicting the electric transmission and transformation engineering material quantity according to the target material quantity prediction model.
5. The electric transmission and transformation engineering material quantity prediction device according to claim 4, wherein the prediction module is further configured to:
integrating the material prediction model into a B/S architecture application system to achieve visualization;
and completing the prediction of the power transmission and transformation engineering material quantity through the input one-key operation of the limit index of the service system.
6. The electric transmission and transformation engineering material quantity prediction device according to claim 4, wherein the model training module is further configured to:
defining a neural network comprising a plurality of parameters capable of being updated, wherein the parameters include weight values; performing iterative computation on input data; processing the input data through a multi-layer network structure; calculating a loss value, wherein the loss value is a difference value between the output value and a target value; and reversely propagating the gradient to the parameters of the neural network, updating the weight values in the neural network according to an updating rule, and finally obtaining the target material quantity prediction model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110447307.6A CN113128125B (en) | 2021-04-23 | 2021-04-23 | Method and device for predicting quantity of power transmission and transformation engineering material |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110447307.6A CN113128125B (en) | 2021-04-23 | 2021-04-23 | Method and device for predicting quantity of power transmission and transformation engineering material |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113128125A CN113128125A (en) | 2021-07-16 |
| CN113128125B true CN113128125B (en) | 2023-04-07 |
Family
ID=76780397
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110447307.6A Active CN113128125B (en) | 2021-04-23 | 2021-04-23 | Method and device for predicting quantity of power transmission and transformation engineering material |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113128125B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105354371A (en) * | 2015-10-21 | 2016-02-24 | 江苏省电力公司 | GA-WNN based power transmission and transformation project construction cost prediction method |
| CN108921334A (en) * | 2018-06-15 | 2018-11-30 | 国家电网公司 | Engineering quantity control target determination method and device for extra-high voltage power transmission and transformation project |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105335818A (en) * | 2015-10-21 | 2016-02-17 | 江苏省电力公司 | Power transmission and transformation project cost risk assessment and forecasting method based on BP neural algorithm |
| CN105825351A (en) * | 2016-04-22 | 2016-08-03 | 国网浙江省电力公司经济技术研究院 | Post evaluation method and risk management and control method of construction cost of power transmission project |
| CN106203701A (en) * | 2016-07-06 | 2016-12-07 | 吴本刚 | A kind of power matching network builds material requirements prognoses system |
| CN108846578A (en) * | 2018-06-15 | 2018-11-20 | 国家电网公司 | Engineering management and control method for extra-high voltage power transmission and transformation engineering |
| CN111127246A (en) * | 2019-11-21 | 2020-05-08 | 国网福建省电力有限公司经济技术研究院 | An Intelligent Prediction Method of Transmission Line Engineering Cost |
| CN112446534B (en) * | 2020-11-09 | 2022-06-17 | 国网福建省电力有限公司 | A construction period prediction method and device for power transmission and transformation projects |
-
2021
- 2021-04-23 CN CN202110447307.6A patent/CN113128125B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105354371A (en) * | 2015-10-21 | 2016-02-24 | 江苏省电力公司 | GA-WNN based power transmission and transformation project construction cost prediction method |
| CN108921334A (en) * | 2018-06-15 | 2018-11-30 | 国家电网公司 | Engineering quantity control target determination method and device for extra-high voltage power transmission and transformation project |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113128125A (en) | 2021-07-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110851905B (en) | A calculation method of wind vibration coefficient of transmission tower under canyon micro-topography | |
| CN110362886B (en) | A safety assessment method for urban masonry dwellings based on uncertainty analysis | |
| CN109472283B (en) | Dangerous weather prediction method and device based on multiple incremental regression tree model | |
| CN109613611A (en) | Method and system for determining input seismic waves for seismic time-history analysis of structures | |
| CN109117954A (en) | Black smoker design optimization method based on hybrid radial base neural net | |
| CN113255035B (en) | Method for fusing monitoring data of small and medium-sized bridges | |
| CN116823172B (en) | Model optimization-based engineering cost assessment method and system | |
| CN111539842A (en) | Overhead transmission line icing prediction method based on meteorological and geographical environments | |
| CN109191408A (en) | Rapid Circulation Ground Meteorological fusion method, device and server | |
| CN108763164B (en) | Evaluation method for coal and gas outburst inversion similarity | |
| CN117035505A (en) | Technical economy assessment method and system based on slope type gravity energy storage | |
| CN113128125B (en) | Method and device for predicting quantity of power transmission and transformation engineering material | |
| CN117574493B (en) | Highway frozen soil range deformation identification method and system in permafrost region | |
| CN117335912B (en) | Spectrum intelligent sensing method and system | |
| CN103604553A (en) | Damaged cable/concentrated load recognition method on basis of angular displacement angle monitoring | |
| CN109800508A (en) | The calculation method and terminal device of the empty top plate thickness at rock-socketed piles end | |
| CN118278293B (en) | Highway construction safety protection system based on data analysis | |
| CN115829206A (en) | Risk assessment method for ground collapse caused by water supply and drainage pipeline | |
| CN115169243A (en) | GA-PSO-GLSSVM algorithm-based soil-rock composite stratum deep foundation pit deformation time sequence prediction method | |
| Xu et al. | A method for suspenders tension identification of bridges based on the spatio‐temporal correlation between the girder strain and suspenders tension | |
| CN112214825A (en) | Selection method for input seismic waves with complex structure and shock resistance vulnerability | |
| Bian et al. | Improved nonprobabilistic global optimal solution method and Its application in bridge reliability assessment | |
| CN118114445B (en) | Method, system, equipment and medium for determining tower foundation instability under extreme environments | |
| CN117094449B (en) | Construction window period forecasting system for construction site operation scene based on meteorological risk | |
| Kenéz et al. | Performance-based wind engineering assessment of a telecommunication mast utilizing Bayesian extreme wind velocity model |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |