CN113011633A - Overhead transmission line engineering cost prediction method, device and medium - Google Patents
Overhead transmission line engineering cost prediction method, device and medium Download PDFInfo
- Publication number
- CN113011633A CN113011633A CN202110162167.8A CN202110162167A CN113011633A CN 113011633 A CN113011633 A CN 113011633A CN 202110162167 A CN202110162167 A CN 202110162167A CN 113011633 A CN113011633 A CN 113011633A
- Authority
- CN
- China
- Prior art keywords
- cost
- transmission line
- overhead transmission
- project
- sample data
- 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.)
- Pending
Links
- 230000005540 biological transmission Effects 0.000 title claims abstract description 101
- 238000000034 method Methods 0.000 title claims abstract description 53
- 238000004364 calculation method Methods 0.000 claims abstract description 28
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 21
- 238000012549 training Methods 0.000 claims abstract description 20
- 238000012795 verification Methods 0.000 claims abstract description 5
- 238000010276 construction Methods 0.000 claims description 50
- 238000012216 screening Methods 0.000 claims description 9
- 238000012360 testing method Methods 0.000 claims description 9
- 238000005070 sampling Methods 0.000 claims description 5
- 238000004590 computer program Methods 0.000 claims description 3
- 238000003860 storage Methods 0.000 claims description 3
- 230000006870 function Effects 0.000 description 14
- 239000011159 matrix material Substances 0.000 description 9
- 239000000463 material Substances 0.000 description 8
- 230000008569 process Effects 0.000 description 5
- 230000004913 activation Effects 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 3
- 238000003066 decision tree Methods 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 3
- 238000010606 normalization Methods 0.000 description 3
- 229910000831 Steel Inorganic materials 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 238000013459 approach Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 239000010959 steel Substances 0.000 description 2
- 239000002023 wood Substances 0.000 description 2
- 239000000654 additive Substances 0.000 description 1
- 230000000996 additive effect Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 239000004566 building material Substances 0.000 description 1
- 125000004432 carbon atom Chemical group C* 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 239000011248 coating agent Substances 0.000 description 1
- 238000000576 coating method Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000002360 explosive Substances 0.000 description 1
- 239000012212 insulator Substances 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000012417 linear regression Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
- 239000004575 stone Substances 0.000 description 1
- 238000012876 topography Methods 0.000 description 1
- 230000001052 transient effect Effects 0.000 description 1
Images
Classifications
-
- 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
- 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
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- 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
-
- 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
-
- 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
- G06Q50/08—Construction
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- General Health & Medical Sciences (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Mathematical Physics (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Primary Health Care (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biomedical Technology (AREA)
- Development Economics (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a method, a device and a medium for predicting the engineering cost of an overhead transmission line, which comprises the following steps: constructing a sample library, and adding engineering data of the overhead transmission line in a preset historical time period into the sample library as sample data; carrying out discount calculation on the cost data in each sample data according to the historical cost, the current cost and the cost ratio of each cost index in the overhead transmission line project; performing model training and verification on the sample data after discount calculation according to an LSTM algorithm to obtain a prediction model; and inputting the engineering technical indexes of the overhead transmission line project to be predicted into the prediction model to obtain the cost prediction data of the overhead transmission line project. The invention ensures the accuracy of the prediction result and saves the prediction time.
Description
Technical Field
The invention relates to the field of transmission line engineering cost, in particular to a method, a device and a medium for predicting the engineering cost of an overhead transmission line.
Background
The investment construction of the power industry always plays a significant role in national economy in China. At present, the scale of power grid engineering construction in China is continuously increased, and the investment is also increased along with the increase. With the rapid development of networking, informatization and internet cloud technology, big data and artificial intelligence are developing in an 'explosive' manner, and project cost informatization is promoted to move to a new era, so that the method is particularly widely applied to various aspects such as prediction, trend analysis and the like.
The cost prediction of the overhead transmission line project is mainly used in the following two scenes:
1) in the planning stage, the project needs to be roughly estimated and then compiled into a planning library, the estimation is often rough, and most projects have larger difference with the actual cost.
2) In the pre-research stage, the feasibility of a newly-built line project is mainly subjected to technical and economic demonstration, the technical and economic comparison and selection of two or even more schemes is involved, and the key link for determining the project recommendation scheme is provided. The traditional method is to provide two or more proposals through discussion, roughly list the required materials of the project, and calculate the materials one by one, the whole process takes at least 2.5 days, which is time-consuming and labor-consuming.
Disclosure of Invention
The technical problem to be solved by the invention is as follows: aiming at the technical problems in the prior art, the invention provides a method, a device and a medium for predicting the engineering cost of an overhead transmission line, which ensure the accuracy of a prediction result and save the prediction time.
In order to solve the technical problems, the technical scheme provided by the invention is as follows:
a method for predicting the construction cost of an overhead transmission line comprises the following steps:
s1), constructing a sample library, and adding the engineering data of the overhead transmission line in a preset historical time period into the sample library as sample data;
s2) carrying out discount calculation on the cost data in each sample data according to the historical cost, the current cost and the cost ratio of each cost index in the overhead transmission line project;
s3) carrying out model training and verification on the sample data after discount calculation according to an LSTM algorithm to obtain a prediction model;
s4) inputting the engineering technical indexes of the overhead transmission line project to be predicted into the prediction model to obtain the cost prediction data of the overhead transmission line project.
Further, the specific step of step S2) includes:
s21) obtaining the cost data in each sample data, and calculating the cost ratio of each cost index in the overhead transmission line body project through subjective and objective combination empowerment;
s22) calculating the discount coefficient of the cost index in each year in a preset historical time period according to the historical cost and the current cost;
s23) aiming at the construction cost data in each sample data, carrying out discount calculation according to the construction time, the construction cost ratio of the overhead transmission line body construction cost, the construction cost ratio of each construction cost index in the overhead transmission line body construction cost and the discount coefficient of the construction cost index in the current year.
Further, the step S21) of calculating the cost ratio of each cost index in the overhead transmission line body project by the subjective and objective combination empowerment specifically includes: firstly, determining subjective weight vector W of each cost index by an analytic hierarchy processsiThen determining objective weight vector W of each cost index by entropy weight methodoiFinally, the weight vector W of each cost index is determined by subjective and objective combinationi。
Further, step S23) is preceded by a step of adjusting a cost ratio of the engineering project, specifically including: if the cost index with the discount coefficient of 1 in each year in the preset historical time period exists, the cost index is deleted, and the cost ratio of the rest cost indexes is recalculated.
Further, the specific step of step S3) includes:
s31) screening the engineering technical indexes of each sub-project in the overhead transmission line body project in the sample data;
s32) sampling the sample data to form a training set and a test set;
s33) adopting an LSTM algorithm, taking engineering technical indexes in a training set as input features, and training based on cost data after different sample data in the training set are converted and calculated to obtain a prediction model;
s34) inputting the sample data in the test set into the prediction model, judging whether the precision requirement is met, if so, outputting the prediction model, otherwise, returning to the step S32).
Further, in step S32), the data ratio of the training set and the test set is 7: 3.
Further, step S31) specifically includes: and sequentially selecting sample data in the sample library as current sample data, selecting one sub-project in the overhead transmission line body project of the current sample data as the current sub-project, and screening the engineering technical indexes of the current sub-project by adopting an elastic network algorithm until the sub-projects corresponding to all the sample data are selected.
Further, step S4) specifically includes: the method comprises the steps that a prediction model obtains engineering technical indexes of an overhead transmission line project to be predicted, sample data after discount calculation corresponding to at least one similar overhead transmission line project is matched from a sample library according to the engineering technical indexes, if the overhead transmission line project to be predicted is compared with the similar overhead transmission line project and has missing engineering technical indexes, a mode number is taken from the sample data after discount calculation corresponding to the similar overhead transmission line project and is used as a default value of the missing engineering technical indexes of the overhead transmission line project to be predicted, and cost prediction data of the overhead transmission line project are calculated according to the sample data after discount calculation corresponding to the similar overhead transmission line project and the supplemented engineering technical indexes of the overhead transmission line project to be predicted.
The invention also provides an overhead transmission line project cost prediction device, which comprises a computer device programmed or configured to execute the overhead transmission line project cost prediction method.
The invention also proposes a computer-readable storage medium storing a computer program programmed or configured to perform the overhead transmission line construction cost prediction method.
Compared with the prior art, the invention has the advantages that:
aiming at the problem that historical data does not have timeliness, cost data in overhead transmission line engineering data in a preset historical time period in a sample library is subjected to discount calculation according to historical cost, current cost and cost ratio of cost indexes to obtain sample data after discount calculation, and reliability of the data and accuracy of a prediction result are guaranteed by discounting the sample data after calculation.
Drawings
FIG. 1 is a schematic overall flow chart of an embodiment of the present invention.
FIG. 2 is a schematic diagram of steps of an embodiment of the present invention
FIG. 3 is a schematic exploded view of various cost indicators according to an embodiment of the present invention.
FIG. 4 is a schematic diagram of the operation of the prediction model according to the embodiment of the present invention.
Detailed Description
The invention is further described below with reference to the drawings and specific preferred embodiments of the description, without thereby limiting the scope of protection of the invention.
The main difficulty of how to realize accurate prediction lies in that: firstly, the fluctuation of market price and the rising of object price have great influence on the cost, the cost prediction is mainly carried out at present based on historical construction cost data, and the direct cost prediction based on the historical construction cost data inevitably leads to inaccurate prediction results; secondly, how to construct a project cost prediction model through historical project cost data and ensure the accuracy of project cost prediction.
As shown in fig. 1 and fig. 2, the invention provides a method for predicting the construction cost of an overhead transmission line, which comprises the following steps:
s1), constructing a sample library, and adding the engineering data of the overhead transmission line in a preset historical time period into the sample library as sample data;
s2) carrying out discount calculation on the cost data in each sample data according to the historical cost, the current cost and the cost ratio of each cost index in the overhead transmission line project;
s3) carrying out model training and verification on the sample data after discount calculation according to an LSTM algorithm to obtain a prediction model;
s4) inputting the engineering technical indexes of the overhead transmission line project to be predicted into the prediction model to obtain the cost prediction data of the overhead transmission line project.
According to the method, the construction cost data in the engineering data of the overhead transmission line in the preset historical time period are subjected to discount calculation to obtain the sample data after the discount calculation, so that the reliability of the data and the accuracy of the prediction result are ensured.
In step S1) of this embodiment, the preset historical period is specifically 5 years, that is, historical data of all overhead transmission line projects from 5 years ago to the current date are selected and added to the sample library, so that the data volume of the sample library is sufficient.
Step S2) of the present embodiment includes:
s21) obtaining the cost data in each sample data, and calculating the cost ratio of each cost index in the overhead transmission line body project cost indexes through subjective and objective combination empowerment;
s22) calculating the discount coefficient of the cost index in each year in a preset historical time period according to the historical cost and the current cost;
s23) aiming at the construction cost data in each sample data, carrying out discount calculation according to the construction time, the construction cost ratio of the overhead transmission line body construction cost, the construction cost ratio of each construction cost index in the overhead transmission line body construction cost and the discount coefficient of the construction cost index in the current year.
As shown in fig. 3, in step S21), it is found that the cost of the overhead transmission line project can be divided into two parts, namely overhead transmission line body project cost and other costs, by counting the cost data in all sample data in the sample database, and the cost of the overhead transmission line body project cost and the other costs account for 70% and 30% of the total cost, respectively, since the overhead transmission line body project cost relates to material and labor costs, which are not the same, the overhead transmission line body project cost needs to be discounted and calculated.
As shown in fig. 3, the overhead transmission line body engineering cost is classified into 9 cost indexes such as hardware, towers, wires, concrete, gravel, steel, labor cost, material cost, mechanical cost and the like according to the relevance of the cost indexes in the overhead transmission line body engineering cost, and the subjective weight vector W of each cost index is determined by an analytic hierarchy processsiThen determining objective weight vector W of each cost index by entropy weight methodoiFinally, the weight vector W of each cost index is determined by subjective and objective combinationi。
Determining subjective weight vector W of current cost index by analytic hierarchy processsThe method comprises the following specific steps:
A1) according to the target-criterion or index-scheme or object, establishing a hierarchical analysis structure model from top to bottom in a layered manner according to the relevant factors of the current cost index;
A2) constructing a judgment matrix by using a scaling method;
A3) calculating the subjective weight direction of the current cost indexQuantity WsThe method comprises the following specific steps:
A31) calculating the product m of each row element of the judgment matrixiThe functional expression is:
in the above formula, i is the row number of the judgment matrix, j is the column number of the judgment matrix, aijElements in the judgment matrix;
A33) for vectorPerforming normalization processing to obtain weight coefficientThe functional expression is:
in the above formula, j is the number of items;
vector Ws=[ws1,ws2,...,wsn]TThe subjective weight vector of the current cost index is obtained; the subjective weighting results of the cost indexes obtained by the steps are shown in the following table;
TABLE 1 analytic hierarchy Process determination of subjective weight results
A4) And (4) carrying out consistency check, if the consistency check is passed, outputting the subjective weight vector of the current cost index, otherwise, returning to the step A2) to reconstruct a judgment matrix, wherein the consistency check specifically comprises the following steps:
A41) calculating maximum characteristic lambda of characteristic vector of judgment matrixmax;
A42) And (3) calculating a consistency index CI, wherein the function expression is as follows:
in the above formula, n is the index number in the criterion layer of the judgment matrix;
A43) calculating a consistency ratio CR, and using a function expression as follows:
in the above formula, RI is an average random index obtained by querying a random consistency RI table.
Determining objective weight vector W of current cost index by entropy weight methodoThe method comprises the following specific steps:
B1) and (3) standardization: calculating the weight of each index in a criterion layer of the judgment matrix, firstly, carrying out standardization processing on each index in the criterion layer, and carrying out normalization by using an imminent street value method, wherein a function expression is as follows:
xi'=(xi-xmin)/(xmax-xmin) (6)
in the above formula, xiAnd x'iRespectively an original value and a standardized value of the ith index in the criterion layer; x is the number ofmaxAnd xminThe maximum value and the minimum value of the ith index are respectively;
B2) the entropy and the weight are calculated, and the specific steps comprise:
B21) calculating the weight of the j index of the ith item, wherein the function expression is as follows:
in the above formula, m is the number of indices in the j-th index, x'ijIs the value of the jth index of the ith item, y'ijIs the value of the jth item;
B22) and calculating the information entropy of the j index, wherein the function expression is as follows:
B23) calculating the weight of the j index, wherein the function expression is as follows:
in the above formula, n is the index number.
Then W iso=[wo1,wo2,...won]TAnd the weight vector is an objective weight vector of the current cost index.
The objective weight of each cost index obtained through the above steps is shown in the following table.
TABLE 2 entropy weight method to determine objective weights
The specific steps of determining the current cost index weight vector W by subjective and objective combination comprise: according to the additive integration method, the integrated weight vector obtained by the subjective and objective combination weighting method is represented as W ═ α Ws+βWoWherein alpha and beta are undetermined coefficients for weighting by subjective and objective combination. In this embodimentβi=(1-αi) The correction is carried out by adopting a Markov method,to obtainThen, normalization is carried out, and the obtained W is ═ W1,w2,...wn]The current cost index weight vector synthesized by the final analytic hierarchy process and the entropy weight process is obtained according to the steps, and the cost index weights are shown in the following table, and each cost index weight is the cost ratio of each cost index in the overhead transmission line body engineering cost.
TABLE 3 determination of weights for subjective and objective combinations
Step S22) of the present embodiment, the functional expression of the discount coefficient for each year in the preset history period is as follows:
in the above formula, PNewFor the current cost of manufacture, POld ageThe cost of the corresponding year in the preset historical time period.
The tower and the lead respectively obtain the cost of the corresponding year and calculate the discount coefficient of each year according to the relevant documents issued by the power department, such as the 'main equipment material information price'; the manufacturing cost of the corresponding year is obtained and the discount coefficient of each year is calculated according to the related documents published locally, such as the building material information price; the sum of the labor cost, the material cost and the mechanical cost is obtained according to related documents issued by the power department, such as 'notice of price level adjustment of annual price of budget estimate quota of power construction project', the cost of the corresponding year is obtained and the discount coefficient of each year is obtained by calculation, and the discount coefficient of each cost index is shown in the following table.
TABLE 4 reduction factor
Regarding the hardware cost, according to the relevant documents issued by the energy department, such as "budget price for device materials", we find that the price remains basically unchanged, so step S23) of this embodiment further includes a step of adjusting the cost ratio of the cost index, which specifically includes: if the cost index with the discount coefficient of 1 in each year in the preset historical time period exists, the cost index is deleted, the cost ratio of the rest cost indexes is recalculated, and various modes are provided for recalculating the cost ratio of the rest cost indexes corresponding to the cost index, such as downward rounding, upward rounding or recalculating the weight of each rest cost index in the total after the cost index is deleted.
As shown in fig. 3, the functional expression of the cost ratio of each cost index is as follows:
r=ri0·ri1 (11)
in the above formula, ri0Is the cost ratio of the overhead transmission line body engineering cost, ri1The cost of the overhead transmission line body engineering cost is the ratio of the cost index.
In step S23) of the present embodiment, for a single sample data, the function expression for discount calculation of cost data is as follows:
in the above formula, the first and second carbon atoms are,is the original cost data of the sample data rTower with a tower body、rThread、……rMachine for producing woodRespectively the cost ratio of each cost index, aTower with a tower body、aThread、……aMachine for producing woodRespectively the discount coefficient of each cost index in the year corresponding to the sample data.
Step S3) of the present embodiment includes:
s31) screening the engineering technical indexes of each sub-project in the overhead transmission line body project in the sample data;
s32) sampling the sample data to form a training set and a test set, wherein the sampling is carried out by adopting a replaced autonomous sampling method in the embodiment, and the data ratio of the training set to the test set is 7: 3;
s33) adopting an LSTM algorithm, taking engineering technical indexes in a training set as input features, and training based on cost data after different sample data in the training set are converted and calculated to obtain a prediction model;
s34) inputting the sample data in the test set into the prediction model, judging whether the precision requirement is met, if so, outputting the prediction model, otherwise, returning to the step S32).
The detailed operation process of the prediction model obtained by training the LSTM algorithm is shown in fig. 4, and includes the following steps:
C1) according to the hidden layer state h at the previous momentt-1And input feature x at the current timetCalculating the value f of the forgetting gatetSelecting the value f of forgetting to get information and forgetting to gatetThe function of (a) is expressed as follows:
ft=σ(Wf·[ht-1,xt]+bf) (13)
in the above formula, σ is the activation function, WfTo forget the weight of the door, bfFor forgetting door bias
C2) According to the hidden layer state h at the previous momentt-1And input feature x at the current timetCalculating the value i of the memory gatetAnd transient cell stateThe function is expressed as follows:
in the above formula, σ is the activation function, WiTo memorize the gate weight, WcAs cell state weight, biTo memorize the gate weights, bcBiasing for a cellular state;
C3) according to the value i of the memory gatetForgetting the value f of the doortTemporary cell stateLast moment state ct-1Calculating the cell state c at the current momenttThe function is expressed as follows:
C4) according to the hidden layer state h at the previous momentt-1Input feature x at the present timetCurrent time cell status ctCalculating the value o of the output gatetAnd the current time hidden layer state htAnd obtaining output prediction information, wherein the function expression is as follows:
in the above formula, σ is the activation function, WoTo output the gate weights, boIs an output gate bias.
In step S31) of this embodiment, the engineering technical indicators of each sub-project are obtained by screening from the following common engineering technical indicators by using an elastic network algorithm, as shown in the following table.
TABLE 5 engineering technical indices
Line length (fold down)Single-pass) | Geology |
Base number of tower | Topography |
Wire specification | Cross section of wire |
Ground wire specification | Wind speed |
Topographic proportions | Ice coating |
Conducting wire | Strain resistance ratio |
Tower material | Amount of the composition used |
Ground wire | Concrete and its production method |
Base steel | Earth and stone square |
Insulator | Construction site requisition and cleaning fee |
Secondary distance of transportation |
Because practical application scenarios of each overhead transmission line project are different, the cost prediction can be performed only by using a part of the engineering technical indexes, which has a large influence on the cost, so in order to improve the generation efficiency and the working efficiency of the prediction model, step S31) in this embodiment specifically includes: and sequentially selecting sample data in the sample library as current sample data, selecting one sub-project in the overhead transmission line body project of the current sample data as the current sub-project, and screening the engineering technical indexes of the current sub-project by adopting an elastic network algorithm until the sub-projects corresponding to all the sample data are selected.
The elastic network is a linear regression model using L1 and L2 priors as regularizers, and operates according to the following equation:
wherein alpha rho | w | calculation1A penalty term is imposed for L1,and the penalty term is L2, rho is a mixing ratio, alpha is an nonnegative regular parameter, and the complexity of the model is controlled.
The specific steps of screening the engineering technical indexes of the current sub-engineering by adopting the elastic network algorithm in the embodiment comprise:
D1) setting an interval of a parameter alpha corresponding to the technical index of the current project on the basis of sample data corresponding to the current sub-project, and acquiring an optimal parameter alpha value by adopting a grid search method;
D2) solving the elastic network by adopting an LARS method to obtain an error value corresponding to the parameter alpha, and the steps are as follows:
D21) judging independent variable xiThe degree of correlation with y, and using x with the maximum degree of correlationiApproaching y;
D22) when other variable xjHaving the same correlation for y, i.e. the residuals of both being equal, will be along xiAnd xjThe direction of the bisector of (a) approaches y;
D23) when a third variable x appearskThe y has the same degree of correlation and approaches to the y along the common angular bisector direction of the three variables;
D24) returning to the step D22) until the residual error is smaller than the preset threshold value or all the independent variable parameters are completely approximated;
D3) and comparing and analyzing error values corresponding to the parameters alpha, and selecting engineering technical indexes corresponding to the optimal error values as screening results.
Considering that the engineering technical indexes which can be provided in the planning stage are limited and often only include line length, voltage level, terrain and the like, the construction cost of the overhead transmission line project to be predicted after the missing engineering technical indexes are supplemented in step S4) of the embodiment is predicted, and the specific steps include: the method comprises the steps that a prediction model obtains engineering technical indexes of an overhead transmission line project to be predicted, sample data after discount calculation corresponding to at least one similar overhead transmission line project is matched from a sample library according to the engineering technical indexes, if the overhead transmission line project to be predicted is compared with the similar overhead transmission line project and has missing engineering technical indexes, a mode number is taken from the sample data after discount calculation corresponding to the similar overhead transmission line project and is used as a default value of the missing engineering technical indexes of the overhead transmission line project to be predicted, and cost prediction data of the overhead transmission line project are obtained through calculation according to the sample data corresponding to the similar overhead transmission line project and the supplemented engineering technical indexes of the overhead transmission line project to be predicted.
In order to verify the prediction accuracy, after the prediction model is obtained according to the LSTM algorithm, another two prediction models are respectively constructed according to the decision tree algorithm and the BP neural network algorithm in this embodiment, and then four untrained sample data in the sample library are selected to compare and analyze the three models, and the detailed contents are shown in table 6.
TABLE 6 comparison of project cost prediction errors for three algorithms
In conclusion, the LSTM algorithm is adopted to predict the engineering cost, the prediction error can be reduced to 0.0278, and the prediction effect is better compared with the prediction results of a decision tree and a BP neural network. The reason is as follows: the LSTM algorithm has low requirement on data quality and has better containment for missing information in verification data; meanwhile, the LSTM algorithm is based on a depth algorithm, is more suitable for engineering cost samples based on big data, and has better precision and robustness compared with a decision tree and a BP neural network.
The embodiment also provides an overhead transmission line construction cost prediction device which comprises a computer device, wherein the computer device is programmed or configured to execute the overhead transmission line construction cost prediction method.
The present embodiment also proposes a computer-readable storage medium storing a computer program programmed or configured to execute the overhead transmission line construction cost prediction method.
The foregoing is considered as illustrative of the preferred embodiments of the invention and is not to be construed as limiting the invention in any way. Although the present invention has been described with reference to the preferred embodiments, it is not intended to be limited thereto. Therefore, any simple modification, equivalent change and modification made to the above embodiments according to the technical spirit of the present invention should fall within the protection scope of the technical scheme of the present invention, unless the technical spirit of the present invention departs from the content of the technical scheme of the present invention.
Claims (10)
1. A method for predicting the construction cost of an overhead transmission line is characterized by comprising the following steps:
s1), constructing a sample library, and adding the engineering data of the overhead transmission line in a preset historical time period into the sample library as sample data;
s2) carrying out discount calculation on the cost data in each sample data according to the historical cost, the current cost and the cost ratio of each cost index in the overhead transmission line project;
s3) carrying out model training and verification on the sample data after discount calculation according to an LSTM algorithm to obtain a prediction model;
s4) inputting the engineering technical indexes of the overhead transmission line project to be predicted into the prediction model to obtain the cost prediction data of the overhead transmission line project.
2. The overhead transmission line construction cost prediction method according to claim 1, wherein the concrete step of the step S2) includes:
s21) obtaining the cost data in each sample data, and calculating the cost ratio of each cost index in the overhead transmission line body project through subjective and objective combination empowerment;
s22) calculating the discount coefficient of the cost index in each year in a preset historical time period according to the historical cost and the current cost;
s23) aiming at the construction cost data in each sample data, carrying out discount calculation according to the construction time, the construction cost ratio of the overhead transmission line body construction cost, the construction cost ratio of each construction cost index in the overhead transmission line body construction cost and the discount coefficient of the construction cost index in the current year.
3. The method for predicting the construction cost of the overhead transmission line project according to claim 2, wherein the step S21) of calculating the construction cost ratio of each construction cost index in the overhead transmission line body project through subjective and objective combination empowerment specifically comprises the following steps: firstly, determining subjective weight vector W of each cost index by an analytic hierarchy processsiThen determining objective weight vector W of each cost index by entropy weight methodoiFinally, the weight vector W of each cost index is determined by subjective and objective combinationi。
4. The overhead transmission line project cost prediction method of claim 2, characterized in that, before step S23), the method further comprises a step of adjusting the cost ratio of the project, specifically comprising: if the cost index with the discount coefficient of 1 in each year in the preset historical time period exists, the cost index is deleted, and the cost ratio of the rest cost indexes is recalculated.
5. The overhead transmission line construction cost prediction method according to claim 1, wherein the concrete step of the step S3) includes:
s31) screening the engineering technical indexes of each sub-project in the overhead transmission line body project in the sample data;
s32) sampling the sample data to form a training set and a test set;
s33) adopting an LSTM algorithm, taking engineering technical indexes in a training set as input features, and training based on cost data after different sample data in the training set are converted and calculated to obtain a prediction model;
s34) inputting the sample data in the test set into the prediction model, judging whether the precision requirement is met, if so, outputting the prediction model, otherwise, returning to the step S32).
6. The overhead transmission line construction cost prediction method according to claim 5, wherein in the step S32), the data ratio of the training set and the test set is 7: 3.
7. The overhead transmission line construction cost prediction method according to claim 5, wherein the step S31) specifically includes: and sequentially selecting sample data in the sample library as current sample data, selecting one sub-project in the overhead transmission line body project of the current sample data as the current sub-project, and screening the engineering technical indexes of the current sub-project by adopting an elastic network algorithm until the sub-projects corresponding to all the sample data are selected.
8. The overhead transmission line construction cost prediction method according to claim 1, wherein the step S4) specifically includes: the method comprises the steps that a prediction model obtains engineering technical indexes of an overhead transmission line project to be predicted, sample data after discount calculation corresponding to at least one similar overhead transmission line project is matched from a sample library according to the engineering technical indexes, if the overhead transmission line project to be predicted is compared with the similar overhead transmission line project and has missing engineering technical indexes, a mode number is taken from the sample data after discount calculation corresponding to the similar overhead transmission line project and is used as a default value of the missing engineering technical indexes of the overhead transmission line project to be predicted, and cost prediction data of the overhead transmission line project are calculated according to the sample data after discount calculation corresponding to the similar overhead transmission line project and the supplemented engineering technical indexes of the overhead transmission line project to be predicted.
9. An overhead transmission line construction cost prediction apparatus comprising a computer device programmed or configured to perform the overhead transmission line construction cost prediction method of any one of claims 1 to 8.
10. A computer readable storage medium storing a computer program programmed or configured to perform the overhead transmission line construction cost prediction method according to any one of claims 1 to 8.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110162167.8A CN113011633A (en) | 2021-02-05 | 2021-02-05 | Overhead transmission line engineering cost prediction method, device and medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110162167.8A CN113011633A (en) | 2021-02-05 | 2021-02-05 | Overhead transmission line engineering cost prediction method, device and medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN113011633A true CN113011633A (en) | 2021-06-22 |
Family
ID=76383904
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110162167.8A Pending CN113011633A (en) | 2021-02-05 | 2021-02-05 | Overhead transmission line engineering cost prediction method, device and medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113011633A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113807596A (en) * | 2021-09-18 | 2021-12-17 | 中国能源建设集团广东省电力设计研究院有限公司 | Management method and system for informatization project cost |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105930931A (en) * | 2016-04-22 | 2016-09-07 | 国网浙江省电力公司经济技术研究院 | Electric power engineering cost management method |
CN107067092A (en) * | 2016-11-25 | 2017-08-18 | 国网浙江省电力公司经济技术研究院 | A kind of extra-high voltage electric transmission and transformation construction costs combination forecasting method and prediction meanss |
CN108038616A (en) * | 2017-12-11 | 2018-05-15 | 中国能源建设集团陕西省电力设计院有限公司 | A kind of work transmission line analysis of prices method |
CN110245801A (en) * | 2019-06-19 | 2019-09-17 | 中国电力科学研究院有限公司 | A kind of Methods of electric load forecasting and system based on combination mining model |
CN110992113A (en) * | 2019-12-23 | 2020-04-10 | 国网湖北省电力有限公司 | Neural network intelligent algorithm-based project cost prediction method for capital construction transformer substation |
CN111222669A (en) * | 2018-11-27 | 2020-06-02 | 国网新疆电力有限公司经济技术研究院 | Overhead line cost prediction method and device |
CN111880099A (en) * | 2020-06-30 | 2020-11-03 | 国网浙江省电力有限公司电力科学研究院 | Method and system for predicting service life of battery monomer in energy storage power station |
-
2021
- 2021-02-05 CN CN202110162167.8A patent/CN113011633A/en active Pending
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105930931A (en) * | 2016-04-22 | 2016-09-07 | 国网浙江省电力公司经济技术研究院 | Electric power engineering cost management method |
US20170308934A1 (en) * | 2016-04-22 | 2017-10-26 | Economy Research Institute of State Grid Zhejiang Electric Power | Management method of power engineering cost |
CN107067092A (en) * | 2016-11-25 | 2017-08-18 | 国网浙江省电力公司经济技术研究院 | A kind of extra-high voltage electric transmission and transformation construction costs combination forecasting method and prediction meanss |
CN108038616A (en) * | 2017-12-11 | 2018-05-15 | 中国能源建设集团陕西省电力设计院有限公司 | A kind of work transmission line analysis of prices method |
CN111222669A (en) * | 2018-11-27 | 2020-06-02 | 国网新疆电力有限公司经济技术研究院 | Overhead line cost prediction method and device |
CN110245801A (en) * | 2019-06-19 | 2019-09-17 | 中国电力科学研究院有限公司 | A kind of Methods of electric load forecasting and system based on combination mining model |
CN110992113A (en) * | 2019-12-23 | 2020-04-10 | 国网湖北省电力有限公司 | Neural network intelligent algorithm-based project cost prediction method for capital construction transformer substation |
CN111880099A (en) * | 2020-06-30 | 2020-11-03 | 国网浙江省电力有限公司电力科学研究院 | Method and system for predicting service life of battery monomer in energy storage power station |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113807596A (en) * | 2021-09-18 | 2021-12-17 | 中国能源建设集团广东省电力设计研究院有限公司 | Management method and system for informatization project cost |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Garcia-Melon et al. | Farmland appraisal based on the analytic network process | |
Giustolisi et al. | Advances in data-driven analyses and modelling using EPR-MOGA | |
CN111401599B (en) | Water level prediction method based on similarity search and LSTM neural network | |
CN110288137B (en) | Road network level road infrastructure structure comprehensive maintenance decision method and system | |
CN107610021A (en) | The comprehensive analysis method of environmental variance spatial and temporal distributions | |
CN110059896A (en) | A kind of Prediction of Stock Index method and system based on intensified learning | |
CN112990500B (en) | Transformer area line loss analysis method and system based on improved weighted gray correlation analysis | |
Do et al. | AHP-based evaluation model for optimal selection process of patching materials for concrete repair: focused on quantitative requirements | |
CN106980910B (en) | Medium-and-long-term power load measuring and calculating system and method | |
Stanujkic | An extension of the MOORA method for solving fuzzy decision making problems | |
CN113822499B (en) | Train spare part loss prediction method based on model fusion | |
Vogt et al. | Selecting statistical indices for calibrating building energy models | |
CN110837939A (en) | Power grid multi-target project screening method and system | |
CN113011633A (en) | Overhead transmission line engineering cost prediction method, device and medium | |
CN112330030B (en) | System and method for predicting requirements of expansion materials | |
Mitchell et al. | Nowcasting Euro area GDP growth using Bayesian quantile regression | |
Xiao et al. | A novel compositional data model for predicting the energy consumption structures of Europe, Japan, and China | |
CN112288187A (en) | Big data-based electricity sales amount prediction method | |
CN104200283B (en) | A kind of long-medium term power load forecasting method based on factor primary attribute model | |
Safi et al. | Comparative study on forecasting accuracy among moving average models with simulation and PALTEL stock market data in Palestine | |
CN115374570A (en) | Multi-source weighted training set construction method for deformation prediction of engineering tunnel crossing | |
CN114595890A (en) | Ship spare part demand prediction method and system based on BP-SVR combined model | |
CN106127606B (en) | Method and device for processing oil and gas index data in exploration and development project | |
Hanapi et al. | Developed a hybrid sliding window and GARCH model for forecasting of crude palm oil prices in Malaysia | |
CN114881506A (en) | Heat supply demand load assessment method and system based on room temperature and IBA-LSTM |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210622 |
|
RJ01 | Rejection of invention patent application after publication |