CN116070520A - Construction method of water flow resistance prediction model, flow prediction method and device - Google Patents
Construction method of water flow resistance prediction model, flow prediction method and device Download PDFInfo
- Publication number
- CN116070520A CN116070520A CN202310097810.2A CN202310097810A CN116070520A CN 116070520 A CN116070520 A CN 116070520A CN 202310097810 A CN202310097810 A CN 202310097810A CN 116070520 A CN116070520 A CN 116070520A
- Authority
- CN
- China
- Prior art keywords
- water flow
- flow resistance
- sample
- resistance
- river channel
- 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
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 title claims abstract description 295
- 238000000034 method Methods 0.000 title claims abstract description 54
- 238000010276 construction Methods 0.000 title claims abstract description 36
- 238000012549 training Methods 0.000 claims abstract description 45
- 238000005259 measurement Methods 0.000 claims abstract description 16
- 238000012545 processing Methods 0.000 claims description 33
- 230000006870 function Effects 0.000 claims description 20
- 238000013528 artificial neural network Methods 0.000 claims description 18
- 239000002245 particle Substances 0.000 claims description 12
- 239000013049 sediment Substances 0.000 claims description 10
- 238000004422 calculation algorithm Methods 0.000 claims description 5
- 238000012876 topography Methods 0.000 claims description 5
- 125000004122 cyclic group Chemical group 0.000 claims description 3
- 230000007787 long-term memory Effects 0.000 claims description 3
- 230000006403 short-term memory Effects 0.000 claims description 3
- 238000013473 artificial intelligence Methods 0.000 abstract description 2
- 108091006146 Channels Proteins 0.000 description 148
- 238000004590 computer program Methods 0.000 description 17
- 238000010586 diagram Methods 0.000 description 14
- 230000015654 memory Effects 0.000 description 10
- 238000004891 communication Methods 0.000 description 8
- 238000004364 calculation method Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 4
- 239000002023 wood Substances 0.000 description 4
- 238000013461 design Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000005070 sampling Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000014509 gene expression Effects 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000010790 dilution Methods 0.000 description 1
- 239000012895 dilution Substances 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 230000005484 gravity Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000000691 measurement method Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000000917 particle-image velocimetry Methods 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 150000003839 salts Chemical class 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 239000004575 stone Substances 0.000 description 1
- 239000000758 substrate Substances 0.000 description 1
- 235000012773 waffles Nutrition 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
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/14—Force analysis or force optimisation, e.g. static or dynamic forces
-
- 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
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A10/00—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE at coastal zones; at river basins
- Y02A10/40—Controlling or monitoring, e.g. of flood or hurricane; Forecasting, e.g. risk assessment or mapping
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Evolutionary Computation (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biophysics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computer Hardware Design (AREA)
- Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Biomedical Technology (AREA)
- Geometry (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The disclosure provides a construction method of a water flow resistance prediction model, a flow prediction method and a flow prediction device, which can be applied to the technical field of artificial intelligence and the technical field of hydraulic engineering. The construction method comprises the following steps: obtaining a training sample, wherein the training sample comprises first sample river channel attribute information, second sample river channel attribute information and sample measurement resistance corresponding to the first sample river channel attribute information; inputting first sample river channel attribute information into a first water flow resistance prediction layer, and outputting first sample predicted resistance, wherein the first water flow resistance prediction layer is constructed based on a preset resistance formula; training an initial second water flow resistance prediction layer by using the second sample river channel attribute information, the first sample predicted resistance and the sample measured resistance to obtain a trained second water flow resistance prediction layer; and constructing a water flow resistance prediction model based on the first water flow resistance prediction layer and the second water flow resistance prediction layer.
Description
Technical Field
The disclosure relates to the technical field of artificial intelligence and the technical field of hydraulic engineering, in particular to a construction method, a flow prediction method, a device, equipment, a medium and a program product of a water flow resistance prediction model.
Background
The flood flow prediction has very important significance for the stable operation of hydraulic engineering facilities and the protection of natural disasters. The related art method for predicting the flow rate of the flood generally calculates the flow rate and the flow rate of the river using a resistance formula. However, the accuracy of prediction of river flow by the resistance formula method in the related art is generally low, and the accuracy requirement of flow prediction in the related application scene is difficult to meet.
Disclosure of Invention
In view of the foregoing, the present disclosure provides a method of constructing a water flow resistance prediction model, a flow prediction method, an apparatus, a device, a medium, and a program product.
According to a first aspect of the present disclosure, there is provided a method for constructing a water flow resistance prediction model, including:
obtaining a training sample, wherein the training sample comprises first sample river channel attribute information, second sample river channel attribute information and sample measurement resistance corresponding to the first sample river channel attribute information;
inputting the first sample river channel attribute information into a first water flow resistance prediction layer, and outputting a first sample predicted resistance, wherein the first water flow resistance prediction layer is constructed based on a preset resistance formula;
Training an initial second water flow resistance prediction layer by using the second sample river channel attribute information, the first sample predicted resistance and the sample measured resistance to obtain a trained second water flow resistance prediction layer; and
and constructing a water flow resistance prediction model based on the first water flow resistance prediction layer and the second water flow resistance prediction layer.
A second aspect of the present disclosure provides a traffic prediction method, including:
inputting river channel attribute information into a water flow resistance prediction model, and outputting predicted water flow resistance;
the water flow resistance prediction model is obtained by constructing the water flow resistance prediction model according to the construction method of the water flow resistance prediction model; the river channel attribute information comprises first river channel attribute information and second river channel attribute information, and the water flow resistance prediction model comprises a first water flow resistance prediction layer and a second water flow resistance prediction layer; the first water flow resistance prediction layer is suitable for processing the first river channel attribute information to obtain a first predicted resistance, the second water flow resistance prediction layer is suitable for processing the second river channel attribute information to obtain a second predicted resistance, and the predicted water flow resistance is obtained by processing the first predicted resistance and the second predicted resistance; and
And processing the predicted water flow resistance based on a preset flow formula to obtain the predicted flow of the river channel.
A third aspect of the present disclosure provides a construction apparatus of a water flow resistance prediction model, including:
the training sample acquisition module is used for acquiring a training sample, wherein the training sample comprises first sample river channel attribute information, second sample river channel attribute information and sample measurement resistance corresponding to the first sample river channel attribute information;
the first sample predicted resistance determining module is used for inputting the first sample river channel attribute information into a first water flow resistance predicting layer and outputting first sample predicted resistance, wherein the first water flow resistance predicting layer is constructed based on a preset resistance formula;
the training module is used for training the initial second water flow resistance prediction layer by using the second sample river channel attribute information, the first sample predicted resistance and the sample measured resistance to obtain a trained second water flow resistance prediction layer; and
and the construction module is used for constructing a water flow resistance prediction model based on the first water flow resistance prediction layer and the second water flow resistance prediction layer.
A fourth aspect of the present disclosure provides a flow prediction apparatus, comprising:
The resistance prediction module is used for inputting river channel attribute information into the water flow resistance prediction model and outputting predicted water flow resistance;
the water flow resistance prediction model is obtained by constructing the water flow resistance prediction model according to the construction method of the water flow resistance prediction model;
the river channel attribute information comprises first river channel attribute information and second river channel attribute information, and the water flow resistance prediction model comprises a first water flow resistance prediction layer and a second water flow resistance prediction layer;
the first water flow resistance prediction layer is suitable for processing the first river channel attribute information to obtain a first predicted resistance, the second water flow resistance prediction layer is suitable for processing the second river channel attribute information to obtain a second predicted resistance, and the predicted water flow resistance is obtained by processing the first predicted resistance and the second predicted resistance; and
and the flow prediction module is used for processing the predicted water flow resistance based on a preset flow formula to obtain the predicted flow of the river channel.
A fifth aspect of the present disclosure provides an electronic device, comprising: one or more processors; and a memory for storing one or more programs, wherein the one or more programs, when executed by the one or more processors, cause the one or more processors to perform the method described above.
A sixth aspect of the present disclosure also provides a computer readable storage medium having stored thereon executable instructions which, when executed by a processor, cause the processor to perform the above-described method.
A seventh aspect of the present disclosure also provides a computer program product comprising a computer program which, when executed by a processor, implements the above method.
According to the construction method, the flow prediction method, the device, the equipment, the medium and the program product of the water flow resistance prediction model, the first sample river channel attribute information is processed by using the first water flow resistance prediction layer constructed based on the preset resistance formula, the second water flow resistance prediction layer is obtained by training based on the obtained first sample prediction resistance, the second sample river channel attribute information and the sample measurement resistance, the second predicted water flow resistance output by the second water flow resistance prediction layer can be enabled to at least partially correct the prediction error between the first predicted water flow resistance and the actual water flow resistance output by the first water flow resistance prediction layer, and therefore the water flow resistance prediction model constructed based on the first water flow resistance prediction layer and the second water flow resistance prediction layer can be improved, and further the accuracy of the river flow prediction and/or the river flow rate prediction of a river channel can be improved.
Drawings
The foregoing and other objects, features and advantages of the disclosure will be more apparent from the following description of embodiments of the disclosure with reference to the accompanying drawings, in which:
FIG. 1 schematically illustrates an application scenario diagram of a traffic prediction method and apparatus according to an embodiment of the present disclosure;
FIG. 2 schematically illustrates a flow chart of a method of constructing a water flow resistance prediction model according to an embodiment of the present disclosure;
FIG. 3 schematically illustrates a flow chart of training an initial second water flow resistance prediction layer using second sample river channel attribute information, first sample predicted resistance, and sample measured resistance, in accordance with an embodiment of the present disclosure;
FIG. 4 schematically illustrates an application scenario diagram of a method of constructing a water flow resistance prediction model according to an embodiment of the present disclosure;
FIG. 5 schematically illustrates a flow chart of a flow prediction method according to an embodiment of the present disclosure;
FIG. 6 schematically shows a block diagram of a construction apparatus of a water flow resistance prediction model according to an embodiment of the present disclosure;
FIG. 7 schematically illustrates a block diagram of a flow prediction device according to an embodiment of the present disclosure;
fig. 8 schematically illustrates a block diagram of an electronic device adapted to implement a method of constructing a water flow resistance prediction model, a method of flow prediction according to an embodiment of the present disclosure.
Detailed Description
Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. It should be understood that the description is only exemplary and is not intended to limit the scope of the present disclosure. In the following detailed description, for purposes of explanation, numerous specific details are set forth in order to provide a thorough understanding of the embodiments of the present disclosure. It may be evident, however, that one or more embodiments may be practiced without these specific details. In addition, in the following description, descriptions of well-known structures and techniques are omitted so as not to unnecessarily obscure the concepts of the present disclosure.
The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the disclosure. The terms "comprises," "comprising," and/or the like, as used herein, specify the presence of stated features, steps, operations, and/or components, but do not preclude the presence or addition of one or more other features, steps, operations, or components.
All terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art unless otherwise defined. It should be noted that the terms used herein should be construed to have meanings consistent with the context of the present specification and should not be construed in an idealized or overly formal manner.
Where expressions like at least one of "A, B and C, etc. are used, the expressions should generally be interpreted in accordance with the meaning as commonly understood by those skilled in the art (e.g.," a system having at least one of A, B and C "shall include, but not be limited to, a system having a alone, B alone, C alone, a and B together, a and C together, B and C together, and/or A, B, C together, etc.).
In the technical scheme of the disclosure, the related data (such as including but not limited to personal information of a user) are collected, stored, used, processed, transmitted, provided, disclosed, applied and the like, all conform to the regulations of related laws and regulations, necessary security measures are adopted, and the public welcome is not violated.
The flood flow prediction has very important significance for the stable operation of hydraulic engineering facilities and the protection of natural disasters. The variation of the river width of the mountain river is large, and the variation of the river width of the river is large in influence on flood resistance law and flow prediction. Meanwhile, as flood is mostly generated in mountain areas with changeable geographical conditions and complex landform attributes, the method for predicting the flood flow or predicting the flood flow rate based on the resistance formula in the related technology is caused, the predicted result has larger error, the accuracy of the predicted result is lower, and the actual requirement is difficult to meet.
In view of this, embodiments of the present disclosure provide a method of constructing a water flow resistance prediction model, a flow prediction method, apparatus, device, medium, and program product. The construction method of the water flow resistance prediction model comprises the following steps: obtaining a training sample, wherein the training sample comprises first sample river channel attribute information, second sample river channel attribute information and sample measurement resistance corresponding to the first sample river channel attribute information; inputting first sample river channel attribute information into a first water flow resistance prediction layer, and outputting first sample predicted resistance, wherein the first water flow resistance prediction layer is constructed based on a preset resistance formula; training an initial second water flow resistance prediction layer by using the second sample river channel attribute information, the first sample predicted resistance and the sample measured resistance to obtain a trained second water flow resistance prediction layer; and constructing a water flow resistance prediction model based on the first water flow resistance prediction layer and the second water flow resistance prediction layer.
According to the embodiment of the disclosure, the first sample river channel attribute information is processed by using the first water flow resistance prediction layer constructed based on the preset resistance formula, and the second water flow resistance prediction layer is obtained by training based on the obtained first sample prediction resistance, the second sample river channel attribute information and the sample measurement resistance, so that the second predicted water flow resistance output by the second water flow resistance prediction layer at least partially corrects the prediction error between the first predicted water flow resistance and the real water flow resistance output by the first water flow resistance prediction layer, and the water flow resistance prediction model constructed based on the first water flow resistance prediction layer and the second water flow resistance prediction layer can improve the prediction precision of the water flow resistance of the river channel, and further realize the follow-up improvement of the accuracy of river channel flow prediction and/or river channel flow velocity prediction.
The embodiment of the disclosure also provides a flow prediction method, which comprises the following steps: inputting river channel attribute information into a water flow resistance prediction model, and outputting predicted water flow resistance; the water flow resistance prediction model is obtained by constructing the water flow resistance prediction model according to the construction method; the river channel attribute information comprises first river channel attribute information and second river channel attribute information, and the water flow resistance prediction model comprises a first water flow resistance prediction layer and a second water flow resistance prediction layer; the first water flow resistance prediction layer is suitable for processing the first river channel attribute information to obtain a first predicted resistance, and the second water flow resistance prediction layer is suitable for processing the second river channel attribute information to obtain a second predicted resistance, wherein the predicted water flow resistance is obtained by processing the first predicted resistance and the second predicted resistance; and processing the predicted water flow resistance based on a preset flow formula to obtain the predicted flow of the river channel.
Fig. 1 schematically illustrates an application scenario diagram of a traffic prediction method and apparatus according to an embodiment of the present disclosure.
As shown in fig. 1, an application scenario 100 according to this embodiment may include a first terminal device 101, a second terminal device 102, a third terminal device 103, a network 104, and a server 105. The network 104 is a medium used to provide a communication link between the first terminal device 101, the second terminal device 102, the third terminal device 103, and the server 105. The network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, among others.
The user may interact with the server 105 through the network 104 using at least one of the first terminal device 101, the second terminal device 102, the third terminal device 103, to receive or send messages, etc. Various communication client applications, such as a shopping class application, a web browser application, a search class application, an instant messaging tool, a mailbox client, social platform software, etc. (by way of example only) may be installed on the first terminal device 101, the second terminal device 102, and the third terminal device 103.
The first terminal device 101, the second terminal device 102, the third terminal device 103 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smartphones, tablets, laptop and desktop computers, and the like.
The server 105 may be a server providing various services, such as a background management server (by way of example only) providing support for websites browsed by the user using the first terminal device 101, the second terminal device 102, and the third terminal device 103. The background management server may analyze and process the received data such as the user request, and feed back the processing result (e.g., the web page, information, or data obtained or generated according to the user request) to the terminal device.
It should be noted that, the traffic prediction method provided by the embodiments of the present disclosure may be generally performed by the server 105. Accordingly, the traffic prediction device provided by the embodiments of the present disclosure may be generally disposed in the server 105. The traffic prediction method provided by the embodiments of the present disclosure may also be performed by a server or a server cluster that is different from the server 105 and is capable of communicating with the first terminal device 101, the second terminal device 102, the third terminal device 103, and/or the server 105. Accordingly, the traffic prediction apparatus provided by the embodiments of the present disclosure may also be provided in a server or a server cluster that is different from the server 105 and is capable of communicating with the first terminal device 101, the second terminal device 102, the third terminal device 103, and/or the server 105.
It should be understood that the number of terminal devices, networks and servers in fig. 1 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.
The construction method and the flow rate prediction method of the water flow resistance prediction model of the disclosed embodiment will be described in detail below with reference to the scenario described in fig. 1 through fig. 2 to 5.
Fig. 2 schematically illustrates a flowchart of a method of constructing a water flow resistance prediction model according to an embodiment of the present disclosure.
As shown in fig. 2, the method for constructing the water flow resistance prediction model of this embodiment includes operations S210 to S230.
In operation S210, a training sample including first sample channel attribute information, second sample channel attribute information, and sample measurement resistance corresponding to the first sample channel attribute information is acquired.
According to an embodiment of the present disclosure, the first sample river channel attribute information and the second sample river channel attribute information may be information characterizing various attribute types such as a water flow attribute of a river channel, a geological attribute of the river channel, a geographical attribute of the river channel, and the like. The first sample river channel attribute information may have the same attribute type or may have different attribute types, or the attribute types of the first sample river channel attribute information and the second sample river channel attribute information may have partially the same attribute type or partially different attribute types, which are not limited in the embodiments of the present disclosure, and may be selected by a person skilled in the art according to actual needs.
It should be appreciated that the first sample channel attribute information and the second sample channel attribute information may both belong to the same sample data set, which may correspond to a sample measurement resistance.
According to an embodiment of the present disclosure, the sample measured resistance may be resistance data obtained after measuring the water flow in the river channel, and the resistance data may be associated with the first sample river channel attribute information and the second sample river channel attribute information.
In operation S220, the first sample river channel attribute information is input to the first water flow resistance prediction layer, and the first sample predicted resistance is output, wherein the first water flow resistance prediction layer is constructed based on a preset resistance formula.
According to the embodiment of the disclosure, after the first sample river channel attribute information is input to the first water flow resistance prediction layer, the first sample river channel attribute information may be processed based on a preset resistance formula for constructing the first water flow resistance prediction layer, so as to obtain the first sample predicted resistance.
According to the embodiment of the present disclosure, the preset resistance formula may include a calculation formula for calculating the water flow resistance in the related art, and the embodiment of the present disclosure does not limit a specific formula type of the preset resistance formula, and a person skilled in the art may design according to actual requirements.
It should be noted that, the first sample river channel attribute information may be input to the first water flow resistance prediction layer after being processed based on the data preprocessing modes such as encoding and standardization, and the specific data type of the first sample river channel attribute information input to the first water flow resistance prediction layer is not limited in the embodiments of the present disclosure, and a person skilled in the art may design according to actual requirements.
In operation S230, an initial second water flow resistance prediction layer is trained using the second sample river channel attribute information, the first sample predicted resistance and the sample measured resistance, and a trained second water flow resistance prediction layer is obtained.
According to the embodiment of the disclosure, the parameters of the initial second water flow resistance prediction layer can be adjusted by training the initial second water flow resistance prediction layer, so that a trained second water flow resistance prediction layer is obtained.
In operation S240, a water flow resistance prediction model is constructed based on the first water flow resistance prediction layer and the second water flow resistance prediction layer.
According to the embodiment of the disclosure, the first water flow resistance prediction layer in the water flow resistance prediction model can be used for processing the first river channel attribute information, and the second water flow resistance prediction layer can be used for processing the second river channel attribute information, so that after the first predicted resistance and the second predicted resistance output by the first water flow resistance prediction layer and the second water flow resistance prediction layer are fused, the predicted resistance output by the water flow resistance prediction model can be obtained.
According to the embodiment of the disclosure, the first sample river channel attribute information is processed by using the first water flow resistance prediction layer constructed based on the preset resistance formula, and the second water flow resistance prediction layer is obtained by training based on the obtained first sample prediction resistance, the second sample river channel attribute information and the sample measurement resistance, so that the second predicted water flow resistance output by the second water flow resistance prediction layer at least partially corrects the prediction error between the first predicted water flow resistance and the real water flow resistance output by the first water flow resistance prediction layer, and the water flow resistance prediction model constructed based on the first water flow resistance prediction layer and the second water flow resistance prediction layer can improve the prediction precision of the water flow resistance of the river channel, and further realize the follow-up improvement of the accuracy of river channel flow prediction and/or river channel flow velocity prediction.
According to the embodiment of the disclosure, the first water flow resistance prediction layer is constructed based on a Frugsen resistance formula.
According to an embodiment of the present disclosure, the first sample channel attribute information includes at least one of:
river depth information of the river channel and river bed roughness information of the river channel.
The river bed roughness information of the river channel may include: silt particle size parameters of river channels; or the elevation parameters of the river bed profile of the river channel.
According to the embodiment of the present disclosure, the water flow resistance can be represented by a function including the water depth d and the river bed roughness k of the river channel. Therefore, the sediment grain diameter parameter D of the river channel can be based i The method comprises the steps of carrying out a first treatment on the surface of the Or the elevation parameter sigma of the river bed section of the river channel is quantized, so that the first sample prediction resistance of the river channel can be quantitatively calculated.
According to an embodiment of the present disclosure, the first water flow resistance prediction layer may be represented by the following formula (1), namely, the fraglen resistance formula.
In the formula (1), D represents the average water depth of the river reach in the river course, D 84 The particle size of the sediment corresponding to the 84 th percentile in the sediment in the river channel is expressed,representing the predicted resistance of the first sample.
According to an embodiment of the present disclosure, the first water flow resistance prediction layer may also be represented by the following formula (2).
In the formula (2), d represents the average water depth and sigma of the river reach in the river z,2d The standard deviation of the elevation of the central axis longitudinal section of the riverbed of the riverway is shown. Because the river is usually a natural river, the central axes of the river bed are not regularly arranged according to the central axes, after the first sample predicted resistance is calculated by the formula (2), the second water flow resistance predicted layer transfusion can be obtained based on trainingThe second sample prediction resistance is used for correcting the first prediction resistance of the first sample, so that the sample prediction water flow resistance generated based on the first sample prediction resistance and the second sample prediction resistance is more similar to the sample measurement resistance, the prediction error of the water flow resistance is reduced, and the technical effect of subsequently improving the prediction precision of the water flow rate and/or the water flow velocity of the river is further realized.
According to an embodiment of the present disclosure, the second sample river channel attribute information includes at least one of:
the river channel water flow attribute parameters, the river channel sediment particle diameter parameters, the river channel morphology parameters and the river channel geographic attribute parameters.
According to embodiments of the present disclosure, the water flow attribute parameters may include a water flow width of a river channel, a water surface width, a river width-depth ratio, a sampling manner of sampling water flow, a measuring technique manner of measuring water flow, and the like.
In accordance with embodiments of the present disclosure, the silt particle size parameter may include a representative particle size parameter of non-uniform silt, such as D 84 The sediment grain size corresponding to the 84 th percentile in the river channel can be represented.
According to embodiments of the present disclosure, the river topography parameters may include a river bed topography type of a river reach in the river, such as a shoal deep groove type, a flat bed type, a stepped deep pool type, a steep slope flyrock type, and the like. Accordingly, the second water flow resistance prediction layer can be input after corresponding parameters or codes are set for different river bed surface shape types. The parameter setting mode or the coding mode of the river morphology parameter is not limited in the embodiment of the disclosure, and a person skilled in the art can design according to actual requirements.
According to the embodiment of the disclosure, the geographic attribute parameters may include, but are not limited to, the geographic location of the river channel, and the like, and may also include the geographic attribute parameters of the dead wood, the plant distribution, and the like in the river channel.
Fig. 3 schematically illustrates a flow chart of training an initial second water flow resistance prediction layer using second sample channel property information, first sample predicted resistance, and sample measured resistance, in accordance with an embodiment of the present disclosure.
As shown in fig. 3, training the initial second water flow resistance prediction layer using the second sample river channel attribute information, the first sample predicted resistance, and the sample measured resistance in operation S230 may include operations S310 to S350.
In operation S310, a difference between the sample measured resistance and the first sample predicted resistance is calculated to obtain a sample target resistance.
In operation S320, the second sample river channel attribute information is input to the initial second water flow resistance prediction layer, and the second sample predicted resistance is output.
In operation S330, the second sample predicted resistance and the sample target resistance are processed based on the loss function, resulting in a loss value.
In operation S340, parameters of the initial second water flow resistance prediction layer are adjusted based on the loss value until the loss function converges.
In operation S350, a corresponding second water flow resistance prediction layer in the case where the loss function converges is determined as the trained second water flow resistance prediction layer.
According to the embodiment of the disclosure, the second water flow resistance prediction layer is constructed based on a neural network algorithm.
According to an embodiment of the present disclosure, the second water flow resistance prediction layer includes at least one of:
an artificial neural network layer, a cyclic neural network layer and a long-term and short-term memory neural network layer.
In one embodiment of the disclosure, the second water flow resistance prediction layer may be constructed based on an artificial neural network (Artificial Neural Network, ANN), thereby reducing the computational overhead of the second water flow resistance prediction layer and improving the computational efficiency.
According to the embodiment of the disclosure, the second water flow resistance prediction layer can be constructed based on the artificial neural network, so that the calculation complexity of the second water flow resistance prediction layer is reduced, and the calculation efficiency is improved.
Fig. 4 schematically illustrates an application scenario diagram of a method of constructing a water flow resistance prediction model according to an embodiment of the present disclosure.
As shown in fig. 4, the training samples in this embodiment may include first sample channel attribute information 411, second sample channel attribute information 412, and sample measurement resistance 413.
The first sample river attribute information 411 may include a water depth of the river and a sediment particle size parameter of the river. The second sample river channel attribute information 412 may include a water flow attribute parameter, a sediment particle size parameter, and a river channel profile parameter.
The untrained water flow resistance prediction model 420 may include a first water flow resistance prediction layer 421 and an initial second water flow resistance prediction layer 422 to which the first sample channel attribute information 411 and the second sample channel attribute information 412 are input, respectively. The initial second water flow resistance prediction layer 422 may be constructed based on an artificial neural network algorithm.
The first water flow resistance prediction layer 421 may be constructed based on a preset resistance formula, and the initial second water flow resistance prediction layer 422 may be constructed based on an artificial neural network. The first water flow resistance prediction layer 421 outputs a first sample prediction resistance 431, and accordingly, the initial second water flow resistance prediction layer 422 may output a second sample prediction resistance 432.
By calculating the difference between the sample measured resistance 413 and the first sample predicted resistance 431, a sample target resistance 441 may be obtained, and then the sample target resistance 441 and the second sample predicted resistance 432 may be input into the loss function 450, and the sample target resistance 441 and the second sample predicted resistance 432 may be processed based on the loss function 450, resulting in the loss value 461. The parameters of the initial second water flow resistance prediction layer 422 may then be iteratively adjusted by the loss value 461 until the loss function 450 converges. In the case of converging the loss function 450, the parameters of the initial second water flow resistance prediction layer 422 may be used as the parameters of the trained second water flow resistance prediction layer, thereby obtaining the trained second water flow resistance prediction layer. And further constructing a trained water flow resistance prediction model according to the trained second water flow resistance prediction layer and the first water flow resistance prediction two layer 421.
In this embodiment, the water surface width, the river width-depth ratio and the water flow sampling mode for the river can be used as waterStream attribute parameters. The silt particle size parameter may include a representative particle size parameter of non-uniform silt, e.g. D 16 、D 50 、D 50 /D 16 、D 84 /D 50 Wherein D is i The sediment grain size corresponding to the ith percentile in the river channel can be represented. The river topography parameters can comprise the gradient of the river, the width of the river and the length of the river, the bed surface topography of the river, the shrub distribution of the river, the shrub morphology and other shrub attributes.
For example, the first sample river attribute information 411 and/or the second sample river attribute information 412 may be assigned in the following manner to implement the data processing procedure of the subsequent first water flow resistance prediction layer 421 and/or the initial second water flow resistance prediction layer 422.
The geographical attribute parameters of the river course may include boolean variables such as sink or field, respectively set sink to 0 and field to 1. The geographical attribute parameter may include a distribution parameter of dead wood in the river channel, for example, 1 is set in the case where dead wood exists in the river channel, and 0 is set in the case where dead wood does not exist in the river channel.
The river morphology parameters can be set to be shallow deep groove=0, flat bed=1, step deep pool=2, and steep waffle stone=3.
The water flow attribute parameters may include a measurement technique for the water flow in the river channel, for example, may be set to be salt dilution measurement=0, water gauge measurement=1, adv (acoustic doppler point type flow meter, acoustic Doppler Current) =2, piv (Particle Image Velocimetry ) =3.
It should be noted that, before the second sample river channel attribute information 412 is input to the initial second water flow resistance prediction layer 422 constructed based on the artificial neural network algorithm, the second sample river channel attribute information 412 may be subjected to a normalization process, for example, a normalized value of each sample attribute parameter in the second sample river channel attribute information 412 is calculated, where the normalized value= (sample attribute parameter-sample attribute parameter mean)/sample attribute parameter standard deviation.
Fig. 5 schematically illustrates a flow chart of a flow prediction method according to an embodiment of the present disclosure.
As shown in fig. 5, the flow prediction method of this embodiment includes operations S510 to S520.
In operation S510, river channel attribute information is input to a water flow resistance prediction model, and predicted water flow resistance is output; the water flow resistance prediction model is obtained by constructing the water flow resistance prediction model according to the construction method; the river channel attribute information comprises first river channel attribute information and second river channel attribute information, and the water flow resistance prediction model comprises a first water flow resistance prediction layer and a second water flow resistance prediction layer; the first water flow resistance prediction layer is suitable for processing the first river channel attribute information to obtain first predicted resistance, and the second water flow resistance prediction layer is suitable for processing the second river channel attribute information to obtain second predicted resistance, wherein the predicted water flow resistance is obtained after the first predicted resistance and the second predicted resistance are processed.
In operation S520, the predicted water flow resistance is processed based on the preset flow formula to obtain the predicted flow of the river channel.
According to the embodiments of the present disclosure, the first river channel attribute information, the second river channel attribute information, the first predicted resistance and the second predicted resistance applied to the flow prediction method may have the same or corresponding technical attributes as the first sample river channel attribute information, the second sample river channel attribute information, the first sample predicted resistance and the second sample predicted resistance applied to the construction method of the water flow resistance prediction model in the above embodiments, respectively, and the embodiments of the present disclosure will not be repeated herein.
According to an embodiment of the present disclosure, predicting the water flow resistance may include calling an adder to add the first predicted resistance and the second predicted resistance to obtain a resistance value. By adding the second predicted resistance and the first predicted resistance, the error between the river resistance calculated by the resistance formula in the related technology and the real river resistance can be corrected, so that the obtained predicted water flow resistance is more similar to the real river resistance or the real water flow resistance, the error is reduced, the accuracy of the water flow resistance prediction is improved, and the prediction accuracy of the predicted flow is further improved.
According to the embodiment of the disclosure, the preset flow formula may include any formula in the prior art capable of calculating the flow based on the water flow resistance, and the embodiment of the disclosure does not limit the specific type of the preset flow formula, and a person skilled in the art may select the preset flow formula according to actual requirements.
In one embodiment of the present disclosure, the predicted flow rate of the river channel may be calculated based on the following formulas (3) and (4).
In the formulas (3) and (4), Q is the predicted flow of the river channel, and g is the gravity acceleration. D is the average water depth D of the river reach in the river course, w is the average river width of the river course, S is the river bed gradient,the predicted water flow resistance may be represented.
According to the embodiment of the disclosure, the predicted water flow resistance can be the sum of the first predicted resistance and the second predicted resistance, so that the second predicted resistance output by the second water flow resistance prediction layer is used as a correction value of the first predicted resistance, and the second predicted resistance is used for correcting the error between the first predicted resistance and the real water flow resistance, so that the technical problem of lower water flow resistance prediction precision in the related art is at least partially solved, and the technical effect of improving the prediction accuracy of the river flow speed and/or the river flow is realized.
Based on the construction method and the flow prediction method of the water flow resistance prediction model, the invention also provides a construction device and a flow prediction device of the resistance prediction model. The device will be described in detail below in connection with fig. 6 and 7.
Fig. 6 schematically shows a block diagram of a construction apparatus of a water flow resistance prediction model according to an embodiment of the present disclosure.
As shown in fig. 6, the construction apparatus 600 of the water flow resistance prediction model of this embodiment includes a training sample acquisition module 610, a first sample predicted resistance determination module 620, a training module 630, and a construction module 640.
The training sample acquiring module 610 is configured to acquire a training sample, where the training sample includes first sample river channel attribute information, second sample river channel attribute information, and sample measurement resistance corresponding to the first sample river channel attribute information.
The first sample predicted resistance determination module 620 is configured to input first sample river channel attribute information to a first water flow resistance prediction layer, and output a first sample predicted resistance, where the first water flow resistance prediction layer is configured based on a preset resistance formula.
The training module 630 is configured to train the initial second water flow resistance prediction layer by using the second sample river channel attribute information, the first sample predicted resistance and the sample measured resistance, and obtain a trained second water flow resistance prediction layer.
The construction module 640 is configured to construct a water flow resistance prediction model based on the first water flow resistance prediction layer and the second water flow resistance prediction layer.
According to an embodiment of the present disclosure, training module 630 includes: the system comprises a sample target resistance calculation unit, a second sample prediction resistance prediction unit, a loss value determination unit, a parameter adjustment unit and a second water flow resistance prediction layer determination unit.
The sample target resistance calculation unit is used for calculating the difference between the sample measured resistance and the first sample predicted resistance to obtain the sample target resistance.
The second sample prediction resistance prediction unit is used for inputting second sample river channel attribute information into the initial second water flow resistance prediction layer and outputting second sample prediction resistance.
The loss value determining unit is used for processing the second sample predicted resistance and the sample target resistance based on the loss function to obtain a loss value.
The parameter adjusting unit is used for adjusting the parameters of the initial second water flow resistance prediction layer based on the loss value until the loss function converges.
The second water flow resistance prediction layer determining unit is used for determining a corresponding second water flow resistance prediction layer under the condition that the loss function converges as a trained second water flow resistance prediction layer.
According to the embodiment of the disclosure, the first water flow resistance prediction layer is constructed based on a Frugsen resistance formula.
According to the embodiment of the disclosure, the second water flow resistance prediction layer is constructed based on a neural network algorithm.
According to an embodiment of the present disclosure, the second water flow resistance prediction layer includes at least one of:
an artificial neural network layer, a cyclic neural network layer and a long-term and short-term memory neural network layer.
According to an embodiment of the present disclosure, the first sample channel attribute information includes at least one of:
river depth information of the river channel and river bed roughness information of the river channel; the river bed roughness information of the river channel comprises: silt particle size parameters of river channels; or the elevation parameters of the river bed profile of the river channel.
According to an embodiment of the present disclosure, the second sample river channel attribute information includes at least one of:
the river channel water flow attribute parameters, the river channel sediment particle diameter parameters, the river channel morphology parameters and the river channel geographic attribute parameters.
Fig. 7 schematically shows a block diagram of a flow rate prediction device according to an embodiment of the present disclosure.
As shown in fig. 7, the flow rate prediction apparatus 700 of this embodiment includes a resistance prediction module 710 and a flow rate prediction module 720.
The resistance prediction module 710 is configured to input river channel attribute information into a water flow resistance prediction model, and output a predicted water flow resistance; the water flow resistance prediction model is obtained by constructing the water flow resistance prediction model according to the construction method; the river channel attribute information comprises first river channel attribute information and second river channel attribute information, and the water flow resistance prediction model comprises a first water flow resistance prediction layer and a second water flow resistance prediction layer; the first water flow resistance prediction layer is suitable for processing the first river channel attribute information to obtain first predicted resistance, and the second water flow resistance prediction layer is suitable for processing the second river channel attribute information to obtain second predicted resistance, wherein the predicted water flow resistance is obtained after the first predicted resistance and the second predicted resistance are processed.
The flow prediction module 720 is configured to process the predicted water flow resistance based on a preset flow formula to obtain a predicted flow of the river channel.
According to embodiments of the present disclosure, any of the training sample acquisition module 610, the first sample predicted resistance determination module 620, the training module 630, and the construction module 640, or any of the resistance prediction module 710 and the flow prediction module 720 may be combined in one module to be implemented, or any of the modules may be split into a plurality of modules. Alternatively, at least some of the functionality of one or more of the modules may be combined with at least some of the functionality of other modules and implemented in one module. According to embodiments of the present disclosure, at least one of the training sample acquisition module 610, the first sample predicted resistance determination module 620, the training module 630, and the building module 640, or the resistance prediction module 710 and the flow prediction module 720, may be implemented at least in part as hardware circuitry, such as a Field Programmable Gate Array (FPGA), a Programmable Logic Array (PLA), a system-on-chip, a system-on-substrate, a system-on-package, an Application Specific Integrated Circuit (ASIC), or in hardware or firmware in any other reasonable manner that integrates or packages the circuitry, or in any one of, or in any suitable combination of, three of software, hardware, and firmware. Alternatively, at least one of the training sample acquisition module 610, the first sample predicted resistance determination module 620, the training module 630, and the construction module 640, or the resistance prediction module 710 and the flow prediction module 720, may be at least partially implemented as computer program modules that, when executed, perform the corresponding functions.
Fig. 8 schematically illustrates a block diagram of an electronic device adapted to implement a method of constructing a water flow resistance prediction model, a method of flow prediction according to an embodiment of the present disclosure.
As shown in fig. 8, an electronic device 800 according to an embodiment of the present disclosure includes a processor 801 that can perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM) 802 or a program loaded from a storage section 808 into a Random Access Memory (RAM) 803. The processor 801 may include, for example, a general purpose microprocessor (e.g., a CPU), an instruction set processor and/or an associated chipset and/or a special purpose microprocessor (e.g., an Application Specific Integrated Circuit (ASIC)), or the like. The processor 801 may also include on-board memory for caching purposes. The processor 801 may include a single processing unit or multiple processing units for performing the different actions of the method flows according to embodiments of the disclosure.
In the RAM 803, various programs and data required for the operation of the electronic device 800 are stored. The processor 801, the ROM 802, and the RAM 803 are connected to each other by a bus 804. The processor 801 performs various operations of the method flow according to the embodiments of the present disclosure by executing programs in the ROM 802 and/or the RAM 803. Note that the program may be stored in one or more memories other than the ROM 802 and the RAM 803. The processor 801 may also perform various operations of the method flows according to embodiments of the present disclosure by executing programs stored in the one or more memories.
According to an embodiment of the present disclosure, the electronic device 800 may also include an input/output (I/O) interface 805, the input/output (I/O) interface 805 also being connected to the bus 804. The electronic device 800 may also include one or more of the following components connected to the I/O interface 805: an input portion 806 including a keyboard, mouse, etc.; an output portion 807 including a display such as a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and a speaker; a storage section 808 including a hard disk or the like; and a communication section 809 including a network interface card such as a LAN card, a modem, or the like. The communication section 809 performs communication processing via a network such as the internet. The drive 810 is also connected to the I/O interface 805 as needed. A removable medium 811 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 810 as needed so that a computer program read out therefrom is mounted into the storage section 808 as needed.
The present disclosure also provides a computer-readable storage medium that may be embodied in the apparatus/device/system described in the above embodiments; or may exist alone without being assembled into the apparatus/device/system. The computer-readable storage medium carries one or more programs which, when executed, implement methods in accordance with embodiments of the present disclosure.
According to embodiments of the present disclosure, the computer-readable storage medium may be a non-volatile computer-readable storage medium, which may include, for example, but is not limited to: a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this disclosure, a computer-readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. For example, according to embodiments of the present disclosure, the computer-readable storage medium may include ROM 802 and/or RAM 803 and/or one or more memories other than ROM 802 and RAM 803 described above.
Embodiments of the present disclosure also include a computer program product comprising a computer program containing program code for performing the methods shown in the flowcharts. The program code, when executed in a computer system, causes the computer system to perform the methods provided by embodiments of the present disclosure.
The above-described functions defined in the system/apparatus of the embodiments of the present disclosure are performed when the computer program is executed by the processor 801. The systems, apparatus, modules, units, etc. described above may be implemented by computer program modules according to embodiments of the disclosure.
In one embodiment, the computer program may be based on a tangible storage medium such as an optical storage device, a magnetic storage device, or the like. In another embodiment, the computer program may also be transmitted, distributed, and downloaded and installed in the form of a signal on a network medium, and/or from a removable medium 811 via a communication portion 809. The computer program may include program code that may be transmitted using any appropriate network medium, including but not limited to: wireless, wired, etc., or any suitable combination of the foregoing.
In such an embodiment, the computer program may be downloaded and installed from a network via the communication section 809, and/or installed from the removable media 811. The above-described functions defined in the system of the embodiments of the present disclosure are performed when the computer program is executed by the processor 801. The systems, devices, apparatus, modules, units, etc. described above may be implemented by computer program modules according to embodiments of the disclosure.
According to embodiments of the present disclosure, program code for performing computer programs provided by embodiments of the present disclosure may be written in any combination of one or more programming languages, and in particular, such computer programs may be implemented in high-level procedural and/or object-oriented programming languages, and/or assembly/machine languages. Programming languages include, but are not limited to, such as Java, c++, python, "C" or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, partly on a remote computing device, or entirely on the remote computing device or server. In the case of remote computing devices, the remote computing device may be connected to the user computing device through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computing device (e.g., connected via the Internet using an Internet service provider).
The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
Those skilled in the art will appreciate that the features recited in the various embodiments of the disclosure and/or in the claims may be provided in a variety of combinations and/or combinations, even if such combinations or combinations are not explicitly recited in the disclosure. In particular, the features recited in the various embodiments of the present disclosure and/or the claims may be variously combined and/or combined without departing from the spirit and teachings of the present disclosure. All such combinations and/or combinations fall within the scope of the present disclosure.
The embodiments of the present disclosure are described above. However, these examples are for illustrative purposes only and are not intended to limit the scope of the present disclosure. Although the embodiments are described above separately, this does not mean that the measures in the embodiments cannot be used advantageously in combination. The scope of the disclosure is defined by the appended claims and equivalents thereof. Various alternatives and modifications can be made by those skilled in the art without departing from the scope of the disclosure, and such alternatives and modifications are intended to fall within the scope of the disclosure.
Claims (10)
1. A construction method of a water flow resistance prediction model comprises the following steps:
obtaining a training sample, wherein the training sample comprises first sample river channel attribute information, second sample river channel attribute information and sample measurement resistance corresponding to the first sample river channel attribute information;
Inputting the first sample river channel attribute information into a first water flow resistance prediction layer, and outputting a first sample predicted resistance, wherein the first water flow resistance prediction layer is constructed based on a preset resistance formula;
training an initial second water flow resistance prediction layer by using the second sample river channel attribute information, the first sample predicted resistance and the sample measured resistance to obtain a trained second water flow resistance prediction layer; and
and constructing a water flow resistance prediction model based on the first water flow resistance prediction layer and the second water flow resistance prediction layer.
2. The construction method of claim 1, wherein training an initial second water flow resistance prediction layer using the second sample channel property information, the first sample predicted resistance, and the sample measured resistance comprises:
calculating the difference between the sample measured resistance and the first sample predicted resistance to obtain a sample target resistance;
inputting the second sample river channel attribute information into the initial second water flow resistance prediction layer, and outputting second sample predicted resistance;
processing the second sample predicted resistance and the sample target resistance based on a loss function to obtain a loss value;
Adjusting parameters of the initial second water flow resistance prediction layer based on the loss value until the loss function converges; and
and determining a second water flow resistance prediction layer corresponding to the condition that the loss function is converged as the trained second water flow resistance prediction layer.
3. The construction method according to claim 1, wherein the first water flow resistance prediction layer is constructed based on a fraxhlet resistance formula.
4. The construction method according to claim 1, wherein the second water flow resistance prediction layer is constructed based on a neural network algorithm.
5. The construction method according to claim 4, wherein the second water flow resistance prediction layer comprises at least one of:
an artificial neural network layer, a cyclic neural network layer and a long-term and short-term memory neural network layer.
6. The construction method according to claim 1, wherein the first sample river channel attribute information includes at least one of:
the method comprises the steps of water flow depth information of a river channel and river bed roughness information of the river channel;
the river bed roughness information of the river channel comprises:
the sediment grain diameter parameter of the river course; or alternatively
And the elevation parameters of the section of the river bed of the river channel.
7. The construction method according to claim 1, wherein the second sample river channel attribute information includes at least one of:
the river course rivers attribute parameter, the silt particle diameter parameter of river course, the river course topography parameter of river course, the geographical attribute parameter of river course.
8. A traffic prediction method, comprising:
inputting river channel attribute information into a water flow resistance prediction model, and outputting predicted water flow resistance;
wherein the water flow resistance prediction model is constructed according to the construction method of the water flow resistance prediction model according to any one of claims 1 to 7;
the river channel attribute information comprises first river channel attribute information and second river channel attribute information, and the water flow resistance prediction model comprises a first water flow resistance prediction layer and a second water flow resistance prediction layer;
the first water flow resistance prediction layer is suitable for processing the first river channel attribute information to obtain a first predicted resistance, the second water flow resistance prediction layer is suitable for processing the second river channel attribute information to obtain a second predicted resistance, and the predicted water flow resistance is obtained by processing the first predicted resistance and the second predicted resistance; and
And processing the predicted water flow resistance based on a preset flow formula to obtain the predicted flow of the river channel.
9. A construction device of a water flow resistance prediction model comprises:
the training sample acquisition module is used for acquiring a training sample, wherein the training sample comprises first sample river channel attribute information, second sample river channel attribute information and sample measurement resistance corresponding to the first sample river channel attribute information;
the first sample predicted resistance determining module is used for inputting the first sample river channel attribute information into a first water flow resistance predicting layer and outputting first sample predicted resistance, wherein the first water flow resistance predicting layer is constructed based on a preset resistance formula;
the training module is used for training an initial second water flow resistance prediction layer by using the second sample river channel attribute information, the first sample predicted resistance and the sample measured resistance to obtain a trained second water flow resistance prediction layer; and
and the construction module is used for constructing a water flow resistance prediction model based on the first water flow resistance prediction layer and the second water flow resistance prediction layer.
10. A flow prediction device, comprising:
the resistance prediction module is used for inputting river channel attribute information into the water flow resistance prediction model and outputting predicted water flow resistance;
Wherein the water flow resistance prediction model is constructed according to the construction method of the water flow resistance prediction model according to any one of claims 1 to 7;
the river channel attribute information comprises first river channel attribute information and second river channel attribute information, and the water flow resistance prediction model comprises a first water flow resistance prediction layer and a second water flow resistance prediction layer;
the first water flow resistance prediction layer is suitable for processing the first river channel attribute information to obtain a first predicted resistance, the second water flow resistance prediction layer is suitable for processing the second river channel attribute information to obtain a second predicted resistance, and the predicted water flow resistance is obtained by processing the first predicted resistance and the second predicted resistance; and
and the flow prediction module is used for processing the predicted water flow resistance based on a preset flow formula to obtain the predicted flow of the river channel.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310097810.2A CN116070520A (en) | 2023-01-20 | 2023-01-20 | Construction method of water flow resistance prediction model, flow prediction method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310097810.2A CN116070520A (en) | 2023-01-20 | 2023-01-20 | Construction method of water flow resistance prediction model, flow prediction method and device |
Publications (1)
Publication Number | Publication Date |
---|---|
CN116070520A true CN116070520A (en) | 2023-05-05 |
Family
ID=86183472
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310097810.2A Pending CN116070520A (en) | 2023-01-20 | 2023-01-20 | Construction method of water flow resistance prediction model, flow prediction method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116070520A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN118152990A (en) * | 2024-05-13 | 2024-06-07 | 山东省水文计量检定中心 | Online current measurement system for hydrologic tower |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111400973A (en) * | 2020-04-21 | 2020-07-10 | 中国水利水电科学研究院 | Method for constructing flow-water surface width relation curve based on hydrologic monitoring data |
CN111707343A (en) * | 2020-06-23 | 2020-09-25 | 北京经纬恒润科技有限公司 | Method and device for determining weight of vehicle |
CN112561132A (en) * | 2020-11-30 | 2021-03-26 | 西安科锐盛创新科技有限公司 | Water flow prediction model based on neural network |
CN112561134A (en) * | 2020-11-30 | 2021-03-26 | 西安科锐盛创新科技有限公司 | Neural network-based water flow prediction method and device and electronic equipment |
CN113361621A (en) * | 2021-06-18 | 2021-09-07 | 北京百度网讯科技有限公司 | Method and apparatus for training a model |
CN113507419A (en) * | 2021-07-07 | 2021-10-15 | 工银科技有限公司 | Training method of flow distribution model, and flow distribution method and device |
CN115544915A (en) * | 2022-10-13 | 2022-12-30 | 中国水利水电科学研究院 | Method for calculating resistance coefficient of river channel containing submerged flexible vegetation |
-
2023
- 2023-01-20 CN CN202310097810.2A patent/CN116070520A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111400973A (en) * | 2020-04-21 | 2020-07-10 | 中国水利水电科学研究院 | Method for constructing flow-water surface width relation curve based on hydrologic monitoring data |
CN111707343A (en) * | 2020-06-23 | 2020-09-25 | 北京经纬恒润科技有限公司 | Method and device for determining weight of vehicle |
CN112561132A (en) * | 2020-11-30 | 2021-03-26 | 西安科锐盛创新科技有限公司 | Water flow prediction model based on neural network |
CN112561134A (en) * | 2020-11-30 | 2021-03-26 | 西安科锐盛创新科技有限公司 | Neural network-based water flow prediction method and device and electronic equipment |
CN113361621A (en) * | 2021-06-18 | 2021-09-07 | 北京百度网讯科技有限公司 | Method and apparatus for training a model |
CN113507419A (en) * | 2021-07-07 | 2021-10-15 | 工银科技有限公司 | Training method of flow distribution model, and flow distribution method and device |
CN115544915A (en) * | 2022-10-13 | 2022-12-30 | 中国水利水电科学研究院 | Method for calculating resistance coefficient of river channel containing submerged flexible vegetation |
Non-Patent Citations (4)
Title |
---|
CHEN, XINGYU: "Rough Correlations: Meta-Analysis of Roughness Measures in Gravel Bed Rivers", WATER RESOURCES RESEARCH, vol. 56, no. 8, 10 November 2020 (2020-11-10) * |
王党伟;陈建国;傅旭东;: "山区河道水流阻力研究进展", 水利学报, no. 2, 15 December 2012 (2012-12-15) * |
陈新果;冷绪林;安云朋;张健;王会豪;宫敬;: "基于深度学习结构网络的输气管道水力预测模型", 油气田地面工程, no. 08, 20 August 2018 (2018-08-20), pages 52 - 57 * |
黄才安等: "均匀沙床面动床阻力计算的人工神经网络模型", 《水利学报》, vol. 40, no. 11, 15 November 2009 (2009-11-15), pages 1351 - 1356 * |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN118152990A (en) * | 2024-05-13 | 2024-06-07 | 山东省水文计量检定中心 | Online current measurement system for hydrologic tower |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109995884B (en) | Method and apparatus for determining precise geographic location | |
CN105787104B (en) | Method and device for acquiring user attribute information | |
Karahan et al. | A new nonlinear Muskingum flood routing model incorporating lateral flow | |
Aureli et al. | A GPU-accelerated shallow-water scheme for surface runoff simulations | |
CN112800915A (en) | Building change detection method, building change detection device, electronic device, and storage medium | |
Hwang et al. | Long-term damping characteristics of twin cable-stayed bridge under environmental and operational variations | |
CN115085196B (en) | Power load predicted value determination method, device, equipment and computer readable medium | |
US20160328498A1 (en) | Topology-Based Method to Assess the Environmental Impact of Deicing Sodium Chloride | |
CN116070520A (en) | Construction method of water flow resistance prediction model, flow prediction method and device | |
KR20200119732A (en) | Method and device for generating high-resolution ocean data | |
CN116029151B (en) | Water flow resistance prediction method, training method, flow prediction method and device | |
CN116258097A (en) | Method, device, electronic equipment and medium for updating hydrologic model | |
CN116028499A (en) | Detection information generation method, electronic device, and computer-readable medium | |
CN116155628B (en) | Network security detection method, training device, electronic equipment and medium | |
CN116977575A (en) | Data processing method, device and computer readable storage medium | |
CN113724229B (en) | Method and device for determining elevation difference and electronic equipment | |
Okwuashi et al. | Tide modelling using the Kalman filter | |
JP6717304B2 (en) | Prediction device, prediction system, prediction method and program | |
Li | Effects of analytical window and resolution on topographic relief derived using digital elevation models | |
CN114548364A (en) | Ground settlement prediction method, computing equipment and computer storage medium | |
CN114936664A (en) | Watershed non-point source pollution prediction method based on hybrid deep learning model | |
Guo et al. | Research on assimilation simulation of chlorophyll a concentrations in a virtual geographic environment | |
Maghrebi et al. | Investigation of stage‐discharge model performance for streamflow estimating: A case study of the Gono River, Japan | |
Jiang et al. | Application of Particle Swarm Optimization for Auto-Tuning of the Urban Flood Model | |
US20220327290A1 (en) | Method of training feature determination model, method of performing semantic analysis, and electronic device |
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 |