CN113868942A - Rapid prediction method for collapse peak flow of weir dam - Google Patents

Rapid prediction method for collapse peak flow of weir dam Download PDF

Info

Publication number
CN113868942A
CN113868942A CN202111042566.7A CN202111042566A CN113868942A CN 113868942 A CN113868942 A CN 113868942A CN 202111042566 A CN202111042566 A CN 202111042566A CN 113868942 A CN113868942 A CN 113868942A
Authority
CN
China
Prior art keywords
dam
weir
peak flow
data
damming
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
Application number
CN202111042566.7A
Other languages
Chinese (zh)
Inventor
李炎隆
王琳
薛一峰
苑鹏飞
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Xian University of Technology
Original Assignee
Xian University of Technology
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Xian University of Technology filed Critical Xian University of Technology
Priority to CN202111042566.7A priority Critical patent/CN113868942A/en
Publication of CN113868942A publication Critical patent/CN113868942A/en
Pending legal-status Critical Current

Links

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
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/10—Geometric CAD
    • G06F30/13—Architectural design, e.g. computer-aided architectural design [CAAD] related to design of buildings, bridges, landscapes, production plants or roads
    • 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
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2113/00—Details relating to the application field
    • G06F2113/08—Fluids

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Evolutionary Computation (AREA)
  • General Physics & Mathematics (AREA)
  • Geometry (AREA)
  • General Engineering & Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Computer Hardware Design (AREA)
  • Artificial Intelligence (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Software Systems (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Computational Linguistics (AREA)
  • Medical Informatics (AREA)
  • Biophysics (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • Mathematical Physics (AREA)
  • Health & Medical Sciences (AREA)
  • Biomedical Technology (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Evolutionary Biology (AREA)
  • Architecture (AREA)
  • Civil Engineering (AREA)
  • Structural Engineering (AREA)
  • Computational Mathematics (AREA)
  • Mathematical Analysis (AREA)
  • Mathematical Optimization (AREA)
  • Pure & Applied Mathematics (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention discloses a rapid prediction method for the collapse peak flow of a weir dam, which is implemented according to the following steps: step 1, collecting a damming body burst data sample containing damming body erosion degree and damming body soil particle size parameters; step 2, classifying the data samples collected in the step 1 according to the soil body particle size parameters of the weir plug body and the erosion degree; step 3, carrying out non-dimensionalization processing on the data samples collected in the step 1; step 4, performing radial basis function neural network model training on the data processed in the step 3; and 5, processing the dam body collapse data sample to be predicted in the step 3, and inputting the processed data sample into the model obtained in the step 4 to obtain the dam body collapse peak flow. The method solves the problems that the influence of the erosion degree of the dam body and the grain size of the soil body on the burst flow is not considered, the nonlinear relation among parameters is not considered, and the prediction precision is poor in the conventional prediction method, and can provide data support for the burst rescue of the barrier lake, the plan for defining the evacuation range and the like.

Description

Rapid prediction method for collapse peak flow of weir dam
Technical Field
The invention belongs to the technical field of hydraulic engineering, and relates to a rapid prediction method for the collapse peak flow of a weir plug.
Background
The rapid prediction of the collapse peak flow is very important in the collapse emergency rescue of the damming body. However, most of the existing prediction methods are based on a small amount of representative parameters, especially the classification of erosion degree of the damming body and the important influence of the grain size of the damming body soil body on the damming body burst are not considered, and a rapid prediction method for the damming body burst peak flow aiming at the comprehensive parameters is lacked. In the rapid prediction process of the collapse peak flow of the weir dam, if only individual characteristic parameters are adopted to simulate the peak flow, the defects of strong subjectivity, large data fluctuation and low accuracy exist. Meanwhile, the existing method does not classify the erosion degree of the weir plug body, does not consider the influence of the soil particle size of the weir plug body on the burst peak flow, and cannot accurately calculate the burst peak flow of the weir plug body. In addition, the existing method mostly adopts a linear regression method to fit a parameter model for calculation, only linear factors are considered in the method, and the nonlinear relation between each parameter and the burst flow is neglected. At present, a rapid prediction model of the collapse peak flow of the damming body is provided, wherein more comprehensive parameter information and a nonlinear fitting relation are considered simultaneously.
Disclosure of Invention
The invention aims to provide a rapid prediction method for the damming body burst peak flow, which overcomes the defects that the classification of the erosion degree of a damming body and the influence of the grain size of a damming body soil body on the burst flow are not considered in the conventional prediction method, and provides data support for damming lake burst rescue, a damming lake downstream evacuation range defining scheme, damming body burst flood inversion analysis and the like so as to obtain a more accurate result.
The technical scheme adopted by the invention is that the rapid prediction method for the collapse peak flow of the weir dam body is implemented according to the following steps:
step 1, collecting a dam body bursting data sample;
step 2, classifying the data samples collected in the step 1 according to erosion degree of the weir plugs;
step 3, carrying out data dimensionless processing on the data samples collected in the step 1;
step 4, performing radial basis function neural network model training on the data processed in the step 3;
and 5, processing the dam body collapse data sample to be predicted in the step 3, and inputting the processed data sample into the model obtained in the step 4 to obtain the dam body collapse peak flow.
The present invention is also characterized in that,
in the step 1, the damming body burst data sample comprises a damming body name, a damming body location, a burst time process, a dam height, a dam width, a dam body volume, a damming lake storage capacity, a burst depth, a damming body erosion degree, a damming body soil body particle size parameter and a burst peak flow.
The soil particle size parameters of the dam plug body comprise d30、d50、d90。
In the step 2, the erosion degree of the weir plug body is divided according to the soil body category of the weir plug body, and the erosion degree of the weir plug body is specifically as follows:
Figure BDA0003249893280000021
the specific process of the step 3 is as follows:
step 3.1, calculating the dam body shape coefficient A1The expression is:
Figure BDA0003249893280000022
in the formula (1), HdRepresents dam height, m; vdDenotes the volume of the dam body, 106m3；
Step 3.2, calculating the lake surface shape coefficient A2The expression is:
Figure BDA0003249893280000023
in the formula (2), S represents a dammed lake reservoir capacity, 106m3；
Step 3.3, calculating dam height breach depth ratio A3The expression is:
Figure BDA0003249893280000031
in the formula (3), HwRepresenting the breach depth, m;
step 3.4, calculating the height-dam width ratio A of the dam4The expression is:
Figure BDA0003249893280000032
in the formula (4), BdRepresenting the dam width, m;
step 3.5, calculating peak flow parameter A5The expression is:
Figure BDA0003249893280000033
in the formula (5), g represents the local gravitational acceleration, QpFor the damming of the weir crest value of flow, m3/s。
The specific process of the step 4 is as follows:
step 4.1, dividing the data samples classified in the step 2 into a training set, a testing set and a testing set;
step 4.2, respectively inputting the training set samples in each type of data into a classical three-layer neural network model for training to obtain three types of trained models, wherein the soil particle size d of the damming body30The particle diameter d of the soil body of the weir plug body50The particle diameter d of the soil body of the weir plug body90The parameters, the dam body shape coefficient, the lake surface shape coefficient, the dam height break mouth depth ratio and the dam height dam width ratio are taken as dimensionless variables and are put into an input layer of the classical three-layer neural network model, the peak flow parameter is taken as an output layer of the classical three-layer neural network model, and a radial basis function connecting the output layer and the hidden layer adopts a classical Gaussian function;
step 4.3, inputting the test set samples in each type of data into the trained network model corresponding to the step 4.2 to obtain verification data, and verifying by using a root mean square error test method, wherein the root mean square error expression is as follows:
Figure BDA0003249893280000034
in equation (7), RMSE represents the root mean square error, n represents the total number of samples in the test set, and QiIndicating the peak flow parameter corresponding to the ith sample,
Figure BDA0003249893280000035
representing the verification peak flow parameter corresponding to the ith sample;
setting a reference value
Figure BDA0003249893280000036
Such as
Figure BDA0003249893280000037
Finishing the training of the network model in the step 4.2 to obtain a trained network model; if it is
Figure BDA0003249893280000041
Returning to the step 4.2, and re-selecting the training times, the expansion constant and the number of the hidden layer units for re-training;
step 4.4, inputting the test set samples in each type of data into the corresponding trained network model obtained in step 4.3 for testing, and evaluating the precision of the trained network model by using a computational efficiency coefficient E, wherein the expression of the efficiency coefficient E is as follows:
Figure BDA0003249893280000042
in the formula (8), the reaction mixture is,
Figure BDA0003249893280000043
represents the mean of the peak flow parameter for all samples.
In step 4.1, each class of data samples is divided by 7:1.5:1.5, wherein 70% is the training set, 15% is the testing set, and 15% is the testing set.
In step 4.2, the expression of the classical gaussian function is:
Figure BDA0003249893280000044
in the formula, x represents an input layer vector, and in the present model, is a column vector composed of input layer parameters. c. CiRepresents the central parameter of each hidden layer and gamma represents the spreading constant of the basis function.
The specific process of the step 5 is as follows: collecting a data sample of the dam breach to be predicted, inputting the data sample into a tested model to obtain a peak flow parameter A5Obtaining the collapse peak flow Q of the weir plug body according to the formula (5)p。
The method has the advantages that the influence of erosion degree of the weir dam and grain size of the soil body of the weir dam on the burst is considered, the adopted parameters are comprehensive, and the nonlinear relation between the parameters and the burst peak flow is considered, so that the more scientific and accurate rapid prediction of the breach peak flow of the weir dam is carried out, the accuracy of the prediction result is higher, more objective and more reasonable, and high-precision data support and decision basis can be provided for works such as barrier lake burst rescue, barrier lake downstream evacuation range planning, barrier lake flood inversion analysis research and the like.
Detailed Description
The present invention will be described in detail with reference to the following embodiments.
The invention provides a rapid prediction method for the collapse peak flow of a weir dam, which is implemented according to the following steps:
step 1, collecting damming data samples of the damming body, including the damming body name, the damming body location, the damming time, the dam height, the dam width, the dam body volume, the damming lake storage capacity, the break depth, the damming body erosion degree and the damming body soil body particle size parameter (a parameter widely used in the field of rock and soil, including d)30、d50、d90As shown in table 1), burst peak flow;
TABLE 1 Barrier body soil grain size parameter
Figure BDA0003249893280000051
Step 2, classifying the data samples collected in the step 1 according to erosion degrees of the weir plugs, wherein the erosion degrees of the weir plugs are specifically classified into an extremely high erosion degree I, a high erosion degree II, a medium erosion degree III, a low erosion degree IV, an extremely low erosion degree V and a non-erosion degree according to soil body categories of the weir plugs as shown in Table 2;
TABLE 2 Weir plug erosion degree Classification
Figure BDA0003249893280000052
Step 3, carrying out data dimensionless processing on the data samples collected in the step 1;
step 3.1, calculating the dam body shape coefficient A1The expression is:
Figure BDA0003249893280000053
in the formula (1), HdRepresents dam height, m; vdDenotes the volume of the dam body, 106m3；
Step 3.2, calculating the lake surface shape coefficient A2The expression is:
Figure BDA0003249893280000061
in the formula (2), S represents a dammed lake reservoir capacity, 106m3；
Step 3.3, calculating dam height breach depth ratio A3The expression is:
Figure BDA0003249893280000062
in the formula (3), HwRepresenting the breach depth, m;
step 3.4, calculating the height-dam width ratio A of the dam4The expression is:
Figure BDA0003249893280000063
in the formula (4), BdRepresenting the dam width, m;
step 3.5, calculating peak flow parameter A5The expression is:
Figure BDA0003249893280000064
in the formula (5), g represents the local gravitational acceleration, QpFor the damming of the weir crest value of flow, m3/s；
Step 4, performing radial basis function neural network model training on the data processed in the step 3;
step 4.1, dividing the data samples classified in the step 2 into a training set, a testing set and a testing set;
dividing each type of data sample according to the ratio of 7:1.5:1.5, wherein 70% of the data samples are training sets, 15% of the data samples are inspection sets and 15% of the data samples are testing sets;
step 4.2, respectively inputting the training set samples in each type of data into a classical three-layer neural network model for training, wherein the particle size d of the soil body of the damming body30The particle diameter d of the soil body of the weir plug body50The particle diameter d of the soil body of the weir plug body90The parameters, the dam body shape coefficient, the lake surface shape coefficient, the dam height break mouth depth ratio and the dam height dam width ratio are taken as dimensionless variables and are put into an input layer of the classical three-layer neural network model, the peak flow parameter is taken as an output layer of the classical three-layer neural network model, a radial basis function connecting the output layer and the hidden layer adopts a classical Gaussian function, and the expression is as follows:
Figure BDA0003249893280000065
in the formula, x represents an input layer vector, and is a column vector formed by input layer parameters in the model; c. CiRepresenting the central parameters of the hidden layers, and gamma representing the expansion constant of the basis function;
according to the method, a Gaussian function is used as a radial basis function, and the erosion degree of the weir plug body and the influence of the grain size of the soil body of the weir plug body on the collapse flow of the weir plug body are considered;
step 4.3, inputting the test set samples in each type of data into the trained network model corresponding to the step 4.2 to obtain verification data, and verifying by using a root mean square error test method, wherein the root mean square error expression is as follows:
Figure BDA0003249893280000071
in equation (7), RMSE represents the root mean square error, n represents the total number of samples in the test set, and QiIndicating the peak flow parameter corresponding to the ith sample,
Figure BDA0003249893280000072
representing the verification peak flow parameter corresponding to the ith sample;
setting a reference value
Figure BDA0003249893280000073
Such as
Figure BDA0003249893280000074
Finishing the training of the network model in the step 4.2 to obtain a trained network model; if it is
Figure BDA0003249893280000075
Returning to the step 4.2, and re-selecting the training times, the expansion constant and the number of the hidden layer units for re-training;
step 4.4, inputting the test set samples in each type of data into the corresponding trained network model obtained in the step 4.3 for testing, and evaluating the precision of the model by using a calculation efficiency coefficient E, wherein the expression of the efficiency coefficient E is as follows:
Figure BDA0003249893280000076
in the formula (8), the reaction mixture is,
Figure BDA0003249893280000077
the mean value of the peak flow parameters of all samples is represented, and the efficiency coefficient E is closer to 1, which indicates that the fitting effect is better;
step 5, collecting data samples of the dam breach to be predicted, inputting the data samples into a tested model, and obtaining a peak flow parameter A5Obtaining the collapse peak flow Q of the weir plug body according to the formula (5)p。

Claims (9)

1. A rapid prediction method for the collapse peak flow of a weir dam is characterized by comprising the following steps:
step 1, collecting a dam body bursting data sample;
step 2, classifying the data samples collected in the step 1 according to erosion degree of the weir plugs;
step 3, carrying out data dimensionless processing on the data samples collected in the step 1;
step 4, performing radial basis function neural network model training on the data processed in the step 3;
and 5, processing the dam body collapse data sample to be predicted in the step 3, and inputting the processed data sample into the model obtained in the step 4 to obtain the dam body collapse peak flow.
2. The method for rapidly predicting the breakdown peak flow of the weir plug according to claim 1, wherein in the step 1, the weir plug breakdown data sample comprises a weir plug name, a weir plug location, a breakdown time, a dam height, a dam width, a dam volume, a weir plug lake reservoir capacity, a breach depth, a weir plug erosion degree, a weir plug soil body particle size parameter and the breakdown peak flow.
3. The method for rapidly predicting the collapse peak flow of the weir dam according to claim 2, wherein the soil particle size parameter of the weir dam comprises d30、d50、d90。
4. The method for rapidly predicting the collapse peak flow of the weir dam according to claim 1, wherein in the step 2, the erosion degree of the weir dam is divided according to the soil body category of the weir dam, and the method is specifically as follows:
Figure FDA0003249893270000011
5. the method for rapidly predicting the peak flow of the damming breakdown of the weir body according to claim 2, wherein the specific process of the step 3 is as follows:
step 3.1, calculating the dam body shape coefficient A1The expression is:
Figure FDA0003249893270000021
in the formula (1), HdRepresents dam height, m; vdDenotes the volume of the dam body, 106m3；
Step 3.2, calculating the lake surface shape coefficient A2The expression is:
Figure FDA0003249893270000022
in the formula (2), S represents a dammed lake reservoir capacity, 106m3；
Step 3.3, calculating dam height breach depth ratio A3The expression is:
Figure FDA0003249893270000023
in the formula (3), HwRepresenting the breach depth, m;
step 3.4, calculating the height-dam width ratio A of the dam4The expression is:
Figure FDA0003249893270000024
in the formula (4), BdRepresenting the dam width, m;
step 3.5, calculating peak flow parameter A5The expression is:
Figure FDA0003249893270000025
in the formula (5), g represents the local gravitational acceleration, QpFor the damming of the weir crest value of flow, m3/s。
6. The method for rapidly predicting the peak flow of the damming breakdown of the weir body according to claim 2, wherein the specific process of the step 4 is as follows:
step 4.1, dividing the data samples classified in the step 2 into a training set, a testing set and a testing set;
step 4.2, respectively inputting the training set samples in each type of data into a classical three-layer neural network model for training to obtain three types of trained models, wherein the soil particle size d of the damming body30The particle diameter d of the soil body of the weir plug body50The particle diameter d of the soil body of the weir plug body90The parameters, the dam body shape coefficient, the lake surface shape coefficient, the dam height break mouth depth ratio and the dam height dam width ratio are taken as dimensionless variables and are put into an input layer of the classical three-layer neural network model, the peak flow parameter is taken as an output layer of the classical three-layer neural network model, and a radial basis function connecting the output layer and the hidden layer adopts a classical Gaussian function;
step 4.3, inputting the test set samples in each type of data into the trained network model corresponding to the step 4.2 to obtain verification data, and verifying by using a root mean square error test method, wherein the root mean square error expression is as follows:
Figure FDA0003249893270000031
in equation (7), RMSE represents the root mean square error, n represents the total number of samples in the test set, and QiIndicating the peak flow parameter corresponding to the ith sample,
Figure FDA0003249893270000032
representing the verification peak flow parameter corresponding to the ith sample;
setting a reference value
Figure FDA0003249893270000033
Such as
Figure FDA0003249893270000034
Finishing the training of the network model in the step 4.2 to obtain a trained network model; if it is
Figure FDA0003249893270000035
Returning to the step 4.2, and re-selecting the training times, the expansion constant and the number of the hidden layer units for re-training;
step 4.4, inputting the test set samples in each type of data into the corresponding trained network model obtained in step 4.3 for testing, and evaluating the precision of the trained network model by using a computational efficiency coefficient E, wherein the expression of the efficiency coefficient E is as follows:
Figure FDA0003249893270000036
in the formula (8), the reaction mixture is,
Figure FDA0003249893270000037
represents the mean of the peak flow parameter for all samples.
7. The method for rapidly predicting the peak flow of the damming breakdown of the weir body according to claim 6, wherein in step 4.1, each class of data samples is divided into 7:1.5:1.5, wherein 70% is a training set, 15% is a testing set, and 15% is a testing set.
8. The method for rapidly predicting the peak flow of the damming body burst according to claim 6, wherein in step 4.2, the expression of the classical Gaussian function is as follows:
Figure FDA0003249893270000038
in the formula, x represents an input layer vector, and is a column vector formed by input layer parameters in the model; c. CiRepresents the central parameter of each hidden layer and gamma represents the spreading constant of the basis function.
9. The method for rapidly predicting the peak flow of the damming breakdown of the weir body according to claim 6, wherein the specific process of the step 5 is as follows: collecting a data sample of the dam breach to be predicted, inputting the data sample into a tested model to obtain a peak flow parameter A5Obtaining the collapse peak flow Q of the weir plug body according to the formula (5)p。
CN202111042566.7A 2021-09-07 2021-09-07 Rapid prediction method for collapse peak flow of weir dam Pending CN113868942A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111042566.7A CN113868942A (en) 2021-09-07 2021-09-07 Rapid prediction method for collapse peak flow of weir dam

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111042566.7A CN113868942A (en) 2021-09-07 2021-09-07 Rapid prediction method for collapse peak flow of weir dam

Publications (1)

Publication Number Publication Date
CN113868942A true CN113868942A (en) 2021-12-31

Family

ID=78989833

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111042566.7A Pending CN113868942A (en) 2021-09-07 2021-09-07 Rapid prediction method for collapse peak flow of weir dam

Country Status (1)

Country Link
CN (1) CN113868942A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113449879A (en) * 2021-06-28 2021-09-28 中国水利水电科学研究院 Method for integrating osmotic deformation characteristic discrimination and impermeability gradient prediction
CN116976221A (en) * 2023-08-10 2023-10-31 西安理工大学 Method for predicting damming body breaking peak flow based on erosion characteristics and storage medium

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113449879A (en) * 2021-06-28 2021-09-28 中国水利水电科学研究院 Method for integrating osmotic deformation characteristic discrimination and impermeability gradient prediction
CN116976221A (en) * 2023-08-10 2023-10-31 西安理工大学 Method for predicting damming body breaking peak flow based on erosion characteristics and storage medium
CN116976221B (en) * 2023-08-10 2024-05-17 西安理工大学 Method for predicting damming body breaking peak flow based on erosion characteristics and storage medium

Similar Documents

Publication Publication Date Title
CN113868942A (en) Rapid prediction method for collapse peak flow of weir dam
CN108829950B (en) Unconventional reservoir permeability evaluation method based on core image
CN110287516B (en) Comprehensive evaluation method for compressibility of horizontal fractured well of shale gas reservoir
CN111144055A (en) Method, device and medium for determining toxic heavy gas leakage concentration distribution in urban environment
CN112922582B (en) Gas well wellhead choke tip gas flow analysis and prediction method based on Gaussian process regression
CN114818363B (en) Urban deep drainage tunnel siltation risk assessment and prediction early warning method
CN110991054B (en) Method for simulating space-time migration and tendency distribution of organic pollutants
CN109190839B (en) Wind direction-fused intelligent rolling prediction method for wind speed along railway
CN114036838B (en) Vertical water temperature simulation method based on multilayer LSTM neural network
CN112597702B (en) Pneumatic modeling generation type confrontation network model training method based on radial basis function
CN112883635A (en) Tropical cyclone full-path simulation method based on random forest algorithm
CN113642666A (en) Active enhanced soft measurement method based on sample expansion and screening
Oertel Discharge coefficients of piano key weirs from experimental and numerical models
CN115290057B (en) Channel software row state monitoring system and method
CN110909466A (en) Method for improving calculation precision of differential pore sorting reservoir average capillary pressure curve
CN115564264A (en) Safety risk assessment method for dam break destructiveness of tailing pond
CN114154686A (en) Dam deformation prediction method based on ensemble learning
CN112884739B (en) Deep learning network-based method for rapidly detecting filling compactness of rock-fill body
CN108090269A (en) A kind of rubber for tire cross-head Optimal Design of Runner System method
CN115271154A (en) Nonlinear regression flood element prediction method based on polynomial and partial least square coupling
CN114021644A (en) Method for calculating regional representative underground water level based on K-means and de-clustering method
CN111062118B (en) Multilayer soft measurement modeling system and method based on neural network prediction layering
CN110110287A (en) A kind of probability box Sensitivity Analysis Method
CN110929377A (en) Morris method based beach hydrothermal migration influence sensitivity analysis method
Qian et al. Equity Evaluation of Global Countries based on the Expanded Theil index and Factor Analysis

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