CN112434470A - Riverway diversion port door water level data extension method, device, storage medium and equipment - Google Patents
Riverway diversion port door water level data extension method, device, storage medium and equipment Download PDFInfo
- Publication number
- CN112434470A CN112434470A CN202011396244.8A CN202011396244A CN112434470A CN 112434470 A CN112434470 A CN 112434470A CN 202011396244 A CN202011396244 A CN 202011396244A CN 112434470 A CN112434470 A CN 112434470A
- Authority
- CN
- China
- Prior art keywords
- support vector
- vector machine
- machine model
- water level
- diversion
- 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.)
- Granted
Links
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
- G06N20/00—Machine learning
- G06N20/10—Machine learning using kernel methods, e.g. support vector machines [SVM]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/12—Computing arrangements based on biological models using genetic models
- G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2113/00—Details relating to the application field
- G06F2113/08—Fluids
-
- 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)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- Health & Medical Sciences (AREA)
- Biophysics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Data Mining & Analysis (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Medical Informatics (AREA)
- Evolutionary Biology (AREA)
- Biomedical Technology (AREA)
- Geometry (AREA)
- Computational Linguistics (AREA)
- Genetics & Genomics (AREA)
- Physiology (AREA)
- Computer Hardware Design (AREA)
- Molecular Biology (AREA)
- General Health & Medical Sciences (AREA)
- Barrages (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to a method, a device, a storage medium and equipment for extending water level data of a river diversion port door. The invention aims to provide a method, a device, a storage medium and equipment for extending water level data of a river diversion port door. The technical scheme of the invention is as follows: a water level data extension method for a river diversion port door is characterized by comprising the following steps: s1, initializing an integrated support vector machine model, wherein the integrated support vector machine model comprises N individual support vector machine models, and the initialization content comprises basic attribute information, adjustable parameter information and variable maximum time lag information of the integrated support vector machine model; s2, establishing a relation between the river way diversion gate water level and related elements thereof based on an aggregate support vector machine model in the diversion gate water level monitoring period; s3, a reduced set support vector machine model; and S4, in the water level data missing period of the diversion gate, performing water level data extension of the diversion gate of the river channel by using a simplified set support vector machine model. The invention is suitable for the technical field of measurement and control.
Description
Technical Field
The invention relates to a method, a device, a storage medium and equipment for extending water level data of a river diversion port door. The method is suitable for the technical field of measurement and control.
Background
In the process that water in the river channel flows to the lower part of the terrain, the water breaks through the original shoreline under the action of flood or human activities to form a new diversion river channel, and the water flows into the main flow river channel again at the downstream. After the riverbed evolves for a long time, the diversion riverway can gradually develop and even replace the dominant position of the original riverway, and can also gradually shrink and even cut off. The knowledge of the information of the water level of the diversion river channel gate and the like is crucial to the knowledge of the water flow movement and the riverbed evolution law of the diversion river channel, and has a prominent effect on river flood control, shipping, drain arrangement, health maintenance of a river ecosystem and the like.
Under current river hydrology monitoring system, the river course reposition of redundant personnel mouth door water level begins the phenomenon that monitoring time is later, water level data series is shorter, for the reposition of redundant personnel river bed evolution trend of mastering long-time yardstick, can only rely on the indirect mode to acquire the mouth door water level information before executing survey:
the first indirect method is to numerically solve the water flow equation (such as the saint-wien equation or the two-dimensional shallow water equation) to obtain the continuous variation process of the water level at the outlet door. The method has physical foundation and accurate calculation result, but has obvious defects that the underwater topography of the river needs to be collected and the calculation performance requirement is high.
The second indirect method with application potential, namely, establishing the relation between the water level of the diversion gate and the related elements thereof by adopting a machine learning method, can be regarded as an alternative or supplement to the first method. The method only needs water level and flow monitoring data of a fixed station, and does not need river channel underwater topography required by the first mode. Furthermore, machine learning methods are typically much less computationally intensive than the first approach.
Disclosure of Invention
The technical problem to be solved by the invention is as follows: aiming at the existing problems, a riverway diversion port door water level data extension method, a riverway diversion port door water level data extension device, a storage medium and equipment are provided.
The technical scheme adopted by the invention is as follows: a water level data extension method for a river diversion port door is characterized by comprising the following steps:
s1, initializing an integrated support vector machine model, wherein the integrated support vector machine model comprises N individual support vector machine models, and the initialization content comprises basic attribute information, adjustable parameter information and variable maximum time lag information of the integrated support vector machine model;
s2, establishing a relation between the river way diversion gate water level and relevant elements thereof based on the integrated support vector machine model during the diversion gate water level monitoring period, wherein the relation comprises determining input and output of the integrated support vector machine model and optimizing the integrated support vector machine model;
the optimized set support vector machine model respectively optimizes each individual support vector machine model in the set support vector machine model by using a population-based heuristic algorithm, and an optimized object comprises adjustable parameter information and variable maximum time lag information;
s3, a reduced set support vector machine model;
and S4, in the water level data missing period of the diversion gate, performing water level data extension of the diversion gate of the river channel by using a simplified set support vector machine model.
Step S1 includes:
s101, initializing basic attribute information: generating basic attribute information A of the individual support vector machine model [ a ] in a random mode aiming at each individual support vector machine model in the set support vector machine model1,a2]；
Wherein a is1A base formula type for specifying an individual support vector machine model; a is2A kernel function type for specifying an individual support vector machine model;
s102, initializing adjustable parameter information: generating adjustable parameter information B ═ B of the individual support vector machine model in a random mode according to basic attribute information A of each individual support vector machine model in the set support vector machine model1,b2,b3]；
Wherein b is1Is a model cost coefficient; b2For model basic parameters, the parameter types are according to basic attribute information a1Determining; b3As kernel function parameters, parameter types are based on basic attribute information a2Determining;
s103, initializing the maximum time lag information of the variables: aiming at each individual support vector machine model in the set support vector machine model, generating variable maximum time lag information C ═ C of the individual support vector machine model in a random mode1,c2,c3]；
Wherein c is1Representing the maximum time lag of adjacent upstream stations of a diversion port door on a main stream river channel; c. C2Representing the maximum time lag of adjacent downstream stations of an upper diversion gate of the main stream river channel; c. C3Representing the maximum lag time of the diverted channel.
The step S2 includes:
s201, determining input and output of the set support vector machine model: for each individual support vector machine model of the set of support vector machine models, determining an input as
Output is as
Wherein Z1The water level of an adjacent station at the upstream of a diversion port door on a main stream riverway; z2The water level of an adjacent station at the downstream of a diversion port door on a main stream riverway; q is the flow of the diversion river; t is time; c. C1、c2And c3Maximum time lag information C of the variable from the individual support vector machine model;
is the water level of the shunt port door;
s202, optimizing a set support vector machine model: for each chromosome in the heuristic algorithm population, training an individual support vector machine model determined by basic attribute information A based on adjustable parameter information B and variable maximum lag time information C of each chromosome, wherein the training adopts a 10-fold cross validation mode, and the obtained cross validation error is used as a fitness value of the chromosome;
and after the optimization is completed, updating adjustable parameter information B and variable maximum lag time information C of each individual support vector machine model, and storing the model cross validation error.
Step S3 includes:
s301, preliminary simplification: for the optimized collective support vector machine model, only keeping a single individual support vector machine model with the minimum cross validation error in all the individual support vector machine models with consistent basic attribute information;
s302, secondary simplification: for all individual support vector machine models retained by the initial compaction, only n individual support vector machine models with the smallest cross validation error are retained.
Step S4 includes:
s401, inputting a support vector machine model of the tissue set: for each individual support vector machine model in the set support vector machine model, according to
A formal organization model input of, wherein c1、c2And c3The variable maximum time lag information C from the updated individual support vector machine model;
s402, applying a set support vector machine model: and operating each individual support vector machine model in the set support vector machine model to obtain n diversion port gate water level results, and performing weighted average on the water level results of all the individual support vector machine models to obtain a final diversion port gate water level sequence.
The utility model provides a river course reposition of redundant personnel mouth water level data epitaxy device which characterized in that includes:
the initialization module is used for initializing the integrated support vector machine model, the integrated support vector machine model comprises N individual support vector machine models, and the initialization content comprises basic attribute information, adjustable parameter information and variable maximum time lag information of the integrated support vector machine model;
the contact construction module is used for constructing a contact between the water level of the diversion gate of the river channel and the relevant elements thereof based on the integrated support vector machine model in the diversion gate water level monitoring period, and comprises determining the input and output of the integrated support vector machine model and optimizing the integrated support vector machine model; the optimized set support vector machine model respectively optimizes each individual support vector machine model in the set support vector machine model by using a population-based heuristic algorithm, and an optimized object comprises adjustable parameter information and variable maximum time lag information;
the model reduction module is used for reducing the set support vector machine model;
and the data extension module is used for carrying out watercourse diversion gate water level data extension by applying a simplified set support vector machine model in the diversion gate water level data missing period.
A storage medium having a computer program stored thereon for execution by a processor, the computer program comprising: the computer program when executed implements the steps of the method for extending the water level data of the river diversion port door.
The utility model provides a river course reposition of redundant personnel mouthful of door water level data epitaxy equipment, has memory and treater, and the computer program that has stored on the memory and can supply the treater to carry out which characterized in that: the computer program when executed implements the steps of the method for extending the water level data of the river diversion port door.
The invention has the beneficial effects that: the invention establishes an aggregate model based on an advanced machine learning method-a support vector machine, is used for establishing the relation between the water level of a diversion port door and the related elements thereof, namely the upstream and downstream water levels of the diversion port door on a main stream riverway and the flow of the diversion riverway, and applies the relation to the water level data missing time of the diversion port door, thereby realizing the extension of water level data. In addition, during the process of establishing the set model, the heuristic algorithm based on population is used for optimizing the maximum time lag of the adjustable parameters and the variables of the model.
According to the invention, only water level and flow monitoring data of a fixed station are needed, and the underwater topography of a river channel does not need to be collected, so that the demand on basic data is low; the calculation workload of the water level data extension of the diversion gate of the river channel can be greatly reduced, and the calculation speed can be obviously improved; the invention uses heuristic algorithm to carry out comprehensive optimization on the model and has the advantage of high calculation precision.
Drawings
FIG. 1 is a flow chart of an embodiment of a method.
FIG. 2 is a comparison graph of the water level result of the integrated support vector machine model and the measured water level during the water level monitoring period of the shunt opening in the embodiment.
FIG. 3 is an illustration of an epitaxial water level verification diagram of the integrated support vector machine model in an embodiment.
Detailed Description
The water level measurement duration of a diversion gate of a certain river is not long, the gate water level sequence length is only 4 years, and the upstream and downstream water levels of the diversion gate on a main stream river channel and the flow of the diversion river channel are continuously monitored for decades. In this embodiment, data extension is performed on the gate water level by using a river diversion gate water level data extension method, wherein the diversion gate water level and related data from the 2 nd year to the 4 th year are used for establishing a connection between the river diversion gate water level and related elements thereof, and the diversion gate water level in the 1 st year is used for verifying the extension water level, and the specific steps of the river diversion gate water level data extension method in this embodiment are described as follows (see fig. 1):
s1, initializing an aggregate support vector machine model, wherein the aggregate support vector machine model comprises 100 individual support vector machine models and is used for constructing the relation between the water level of the diversion gate of the river channel and the relevant elements thereof, the initialization content comprises basic attribute information, adjustable parameter information and variable maximum time lag information of the aggregate support vector machine model, and the process is as follows:
s101, initializing basic attribute information: generating basic attribute information A ═ a in a random manner for each individual support vector machine model in the set support vector machine model1,a2]；
Wherein a is1Type of base formula for specifying individual support vector machine model, a11 represents ε -SVR, a12 represents ν -SVR; a is2Type of kernel function for specifying individual support vector machine model, a21 denotes a linear kernel function, a2Generation 2Kernel function of table polynomial, a23 denotes the radial basis kernel function, a24 stands for sigmoid kernel;
s102, initializing adjustable parameter information: generating adjustable parameter information B ═ B in a random manner for each individual support vector machine model in the set support vector machine model based on the basic attribute information A thereof1,b2,b3]；
Wherein b is1Is a model cost coefficient; b2As basic parameters of the model, a11 then b2Is epsilon, a12 then b2V is; b3As kernel function parameters, a21 then b3Is null value, a22 then b3Is [ gamma, r, d]，a2B when becoming 33Is gamma, a2B is 43Is [ gamma, r]；
S103, initializing the maximum time lag information of the variables: generating variable maximum time lag information C ═ C for each individual support vector machine model in the set support vector machine model in a random mode1,c2,c3]；
Wherein c is1Represents the maximum time lag of adjacent upstream stations of the upper diversion gate of the main stream river channel, c2Represents the maximum time lag of adjacent downstream stations of an upper diversion gate of a main stream river channel, c3Representing the maximum lag time of the diverted channel.
S2, in the 2 nd to 4 th years of monitoring of the diversion gate water level, establishing the relation between the river diversion gate water level and the relevant elements thereof based on the set support vector machine model, including determining the input and output of the set support vector machine model and optimizing the set support vector machine model, and the process is as follows:
s201, determining input and output of the set support vector machine model: the related elements of the water level of the diversion port door comprise the upstream and downstream water levels of the diversion port door on the main stream river channel and the flow of the diversion river channel; for each individual support vector machine model of the set of support vector machine models, determining an input as
Output is as
Wherein Z1The water level of an adjacent station at the upstream of a diversion port door on a main stream riverway; z2The water level of an adjacent station at the downstream of a diversion port door on a main stream riverway; q is the flow of the diversion river; t is time; c. C1、c2And c3Maximum time lag information C of the variable from the individual support vector machine model;
is the water level of the shunt port door;
s202, optimizing a set support vector machine model: respectively optimizing each individual support vector machine model in the set support vector machine models by using a heuristic algorithm based on a population, wherein an optimized object comprises adjustable parameter information B and variable maximum time lag information C;
for each chromosome in the heuristic algorithm population, training an individual support vector machine model determined by basic attribute information A based on adjustable parameter information B and variable maximum lag time information C of each chromosome, wherein the training adopts a 10-fold cross validation mode, and the obtained cross validation error is used as a fitness value of the chromosome; and after the optimization is completed, updating adjustable parameter information B and variable maximum lag time information C of each individual support vector machine model, and storing the model cross validation error.
S3, the reduced set supports the vector machine model, including the primary reduction and the secondary reduction, the process is as follows:
s301, preliminary simplification: for the optimized collective support vector machine model, only keeping a single individual support vector machine model with the minimum cross validation error in all the individual support vector machine models with consistent basic attribute information;
s302, secondary simplification: for all the individual support vector machine models reserved in the preliminary reduction step, only reserving 4 individual support vector machine models with the minimum cross validation error;
the simplified set support vector machine model is applied to the forecast of the water level of the shunt gate in the 2 nd to 4 th years, the comparison condition of the obtained water level result and the measured water level in the same period is shown in figure 2, and it can be seen that the model has higher precision in the period and the water level error can be almost ignored.
S4, in the 1 st year of monitoring the water level of the diversion gate, performing river diversion gate water level data extension by applying an aggregate support vector machine model, wherein the river diversion gate water level data extension comprises organizing the input of the aggregate support vector machine model and applying the aggregate support vector machine model, and the process is as follows:
s401, inputting a support vector machine model of the tissue set: for each individual support vector machine model in the set support vector machine model, according to
A formal organization model input of, wherein c1、c2And c3The variable maximum time lag information C from the updated individual support vector machine model;
s402, applying a set support vector machine model: running each individual support vector machine model in the simplified set support vector machine model to obtain 4 diversion port gate water level results, and performing weighted average on the water level results of all the individual support vector machine models to obtain a final diversion port gate water level sequence for supplementing the diversion port gate water level in the data missing period; the comparison condition of the water level of the supplemented shunt opening door and the actually measured water level is shown in figure 3, so that the precision of the epitaxial water level is higher, and the error is at an acceptable level.
The embodiment also provides a water level data extension device of the river diversion gate, which comprises an initialization module, a connection construction module, a model simplification module and a data extension module.
In this example, the initialization module is configured to initialize the integrated support vector machine model, where the integrated support vector machine model includes 100 individual support vector machine models, and the initialization content includes basic attribute information, adjustable parameter information, and variable maximum time lag information of the integrated support vector machine model.
The contact construction module is used for constructing a contact between the water level of the river way diversion gate and the relevant elements thereof based on the integrated support vector machine model in the diversion gate water level monitoring period, and comprises determining the input and output of the integrated support vector machine model and optimizing the integrated support vector machine model; the optimized set support vector machine model respectively optimizes each individual support vector machine model in the set support vector machine model by using a heuristic algorithm based on a population, and an optimized object comprises adjustable parameter information and variable maximum time lag information.
The model reduction module is used for reducing the set support vector machine model. And the data extension module is used for carrying out watercourse diversion gate water level data extension by applying a simplified set support vector machine model in the diversion gate water level data missing period.
The present embodiment also provides a storage medium, on which a computer program executable by a processor is stored, where the computer program is executed to implement the steps of the method for extending the water level data of the diversion gate of the river channel according to the present embodiment.
The embodiment also provides a riverway diversion port door water level data extension device, which is provided with a memory and a processor, wherein the memory is stored with a computer program which can be executed by the processor, and the computer program is executed to implement the steps of the riverway diversion port door water level data extension method in the embodiment.
The above description is only of the preferred embodiments of the present invention, and it should be noted that: it will be apparent to those skilled in the art that various modifications and adaptations can be made without departing from the principles of the invention and these are intended to be within the scope of the invention.
Claims (8)
1. A water level data extension method for a river diversion port door is characterized by comprising the following steps:
s1, initializing an integrated support vector machine model, wherein the integrated support vector machine model comprises N individual support vector machine models, and the initialization content comprises basic attribute information, adjustable parameter information and variable maximum time lag information of the integrated support vector machine model;
s2, establishing a relation between the river way diversion gate water level and relevant elements thereof based on the integrated support vector machine model during the diversion gate water level monitoring period, wherein the relation comprises determining input and output of the integrated support vector machine model and optimizing the integrated support vector machine model;
the optimized set support vector machine model respectively optimizes each individual support vector machine model in the set support vector machine model by using a population-based heuristic algorithm, and an optimized object comprises adjustable parameter information and variable maximum time lag information;
s3, a reduced set support vector machine model;
and S4, in the water level data missing period of the diversion gate, performing water level data extension of the diversion gate of the river channel by using a simplified set support vector machine model.
2. The method for extending the water level data of the river diversion port door according to claim 1, wherein step S1 comprises:
s101, initializing basic attribute information: generating basic attribute information A of the individual support vector machine model [ a ] in a random mode aiming at each individual support vector machine model in the set support vector machine model1,a2]；
Wherein a is1A base formula type for specifying an individual support vector machine model; a is2A kernel function type for specifying an individual support vector machine model;
s102, initializing adjustable parameter information: generating adjustable parameter information B ═ B of the individual support vector machine model in a random mode according to basic attribute information A of each individual support vector machine model in the set support vector machine model1,b2,b3]；
Wherein b is1Is a model cost coefficient; b2For model basic parameters, the parameter types are according to basic attribute information a1Determining; b3As kernel function parameters, parameter types are based on basic attribute information a2Determining;
s103, initializing the maximum time lag information of the variables: aiming at each individual support vector machine model in the set support vector machine model, generating variable maximum time lag information C ═ C of the individual support vector machine model in a random mode1,c2,c3]；
Wherein c is1Representing the maximum time lag of adjacent upstream stations of a diversion port door on a main stream river channel; c. C2Representing the maximum time lag of adjacent downstream stations of an upper diversion gate of the main stream river channel; c. C3Representing the maximum lag time of the diverted channel.
3. The method for extending the water level data of the river diversion port door according to claim 1 or 2, wherein the step S2 comprises:
s201, determining input and output of the set support vector machine model: for each individual support vector machine model of the set of support vector machine models, determining an input as
Output is as
Wherein Z1The water level of an adjacent station at the upstream of a diversion port door on a main stream riverway; z2The water level of an adjacent station at the downstream of a diversion port door on a main stream riverway; q is the flow of the diversion river; t is time; c. C1、c2And c3Maximum time lag information C of the variable from the individual support vector machine model;
is the water level of the shunt port door;
s202, optimizing a set support vector machine model: for each chromosome in the heuristic algorithm population, training an individual support vector machine model determined by basic attribute information A based on adjustable parameter information B and variable maximum lag time information C of each chromosome, wherein the training adopts a 10-fold cross validation mode, and the obtained cross validation error is used as a fitness value of the chromosome;
and after the optimization is completed, updating adjustable parameter information B and variable maximum lag time information C of each individual support vector machine model, and storing the model cross validation error.
4. The method for extending the water level data of the river diversion port door according to claim 3, wherein the step S3 comprises:
s301, preliminary simplification: for the optimized collective support vector machine model, only keeping a single individual support vector machine model with the minimum cross validation error in all the individual support vector machine models with consistent basic attribute information;
s302, secondary simplification: for all individual support vector machine models retained by the initial compaction, only n individual support vector machine models with the smallest cross validation error are retained.
5. The method for extending the water level data of the river diversion port door according to claim 3, wherein the step S4 comprises:
s401, inputting a support vector machine model of the tissue set: for each individual support vector machine model in the set support vector machine model, according to
A formal organization model input of, wherein c1、c2And c3The variable maximum time lag information C from the updated individual support vector machine model;
s402, applying a set support vector machine model: and operating each individual support vector machine model in the set support vector machine model to obtain n diversion port gate water level results, and performing weighted average on the water level results of all the individual support vector machine models to obtain a final diversion port gate water level sequence.
6. The utility model provides a river course reposition of redundant personnel mouth water level data epitaxy device which characterized in that includes:
the initialization module is used for initializing the integrated support vector machine model, the integrated support vector machine model comprises N individual support vector machine models, and the initialization content comprises basic attribute information, adjustable parameter information and variable maximum time lag information of the integrated support vector machine model;
the contact construction module is used for constructing a contact between the water level of the diversion gate of the river channel and the relevant elements thereof based on the integrated support vector machine model in the diversion gate water level monitoring period, and comprises determining the input and output of the integrated support vector machine model and optimizing the integrated support vector machine model; the optimized set support vector machine model respectively optimizes each individual support vector machine model in the set support vector machine model by using a population-based heuristic algorithm, and an optimized object comprises adjustable parameter information and variable maximum time lag information;
the model reduction module is used for reducing the set support vector machine model;
and the data extension module is used for carrying out watercourse diversion gate water level data extension by applying a simplified set support vector machine model in the diversion gate water level data missing period.
7. A storage medium having a computer program stored thereon for execution by a processor, the computer program comprising: the computer program is executed to realize the steps of the riverway diversion port door water level data extension method in any one of claims 1-5.
8. The utility model provides a river course reposition of redundant personnel mouthful of door water level data epitaxy equipment, has memory and treater, and the computer program that has stored on the memory and can supply the treater to carry out which characterized in that: the computer program is executed to realize the steps of the riverway diversion port door water level data extension method in any one of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011396244.8A CN112434470B (en) | 2020-12-03 | 2020-12-03 | River channel diversion port door water level data extension method and device, storage medium and equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011396244.8A CN112434470B (en) | 2020-12-03 | 2020-12-03 | River channel diversion port door water level data extension method and device, storage medium and equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112434470A true CN112434470A (en) | 2021-03-02 |
| CN112434470B CN112434470B (en) | 2022-05-31 |
Family
ID=74691843
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011396244.8A Active CN112434470B (en) | 2020-12-03 | 2020-12-03 | River channel diversion port door water level data extension method and device, storage medium and equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112434470B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103729550A (en) * | 2013-12-18 | 2014-04-16 | 河海大学 | Multi-model integrated flood forecasting method based on propagation time clustering analysis |
| CN107949812A (en) * | 2015-06-29 | 2018-04-20 | 苏伊士集团 | For detecting the abnormal combined method in water distribution system |
| CN108563837A (en) * | 2018-03-21 | 2018-09-21 | 中国水利水电科学研究院 | A kind of the model parameter real-time correction method and system of alluvial stream Water-sand model |
| US20180373993A1 (en) * | 2017-06-23 | 2018-12-27 | University Of Alaska Fairbanks | Method Of Predicting Streamflow Data |
| CN110298498A (en) * | 2019-06-14 | 2019-10-01 | 水利部交通运输部国家能源局南京水利科学研究院 | A kind of Flood of small drainage area forecasting procedure for establishing data-driven with support vector machines |
| US20190316309A1 (en) * | 2018-04-17 | 2019-10-17 | One Concern, Inc. | Flood monitoring and management system |
-
2020
- 2020-12-03 CN CN202011396244.8A patent/CN112434470B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103729550A (en) * | 2013-12-18 | 2014-04-16 | 河海大学 | Multi-model integrated flood forecasting method based on propagation time clustering analysis |
| CN107949812A (en) * | 2015-06-29 | 2018-04-20 | 苏伊士集团 | For detecting the abnormal combined method in water distribution system |
| US20180373993A1 (en) * | 2017-06-23 | 2018-12-27 | University Of Alaska Fairbanks | Method Of Predicting Streamflow Data |
| CN108563837A (en) * | 2018-03-21 | 2018-09-21 | 中国水利水电科学研究院 | A kind of the model parameter real-time correction method and system of alluvial stream Water-sand model |
| US20190316309A1 (en) * | 2018-04-17 | 2019-10-17 | One Concern, Inc. | Flood monitoring and management system |
| CN110298498A (en) * | 2019-06-14 | 2019-10-01 | 水利部交通运输部国家能源局南京水利科学研究院 | A kind of Flood of small drainage area forecasting procedure for establishing data-driven with support vector machines |
Non-Patent Citations (1)
| Title |
|---|
| 桂梓玲 等: ""基于经验相关的城陵矶日流量模拟模型研究"", 《中国农村水利水电》, no. 01, 15 January 2019 (2019-01-15), pages 26 - 30 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112434470B (en) | 2022-05-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105139093A (en) | Method for forecasting flood based on Boosting algorithm and support vector machine | |
| CN107705556A (en) | A kind of traffic flow forecasting method combined based on SVMs and BP neural network | |
| US20210125200A1 (en) | Method and system for predicting medium-long term water demand of water supply network | |
| CN114254526B (en) | Method and system for evaluating carbon dioxide exchange capacity of lake water-gas interface | |
| EP4303785A1 (en) | Reservoir flow rate regulating method and apparatus, electronic device, and storage medium | |
| Huang et al. | Effect of Three Gorges Dam on Poyang Lake water level at daily scale based on machine learning | |
| CN108846423A (en) | Water quality prediction method and system | |
| JPWO2018078674A1 (en) | Simulation apparatus, simulation method and program | |
| Mohammad Ashrafi | Two-stage metaheuristic mixed integer nonlinear programming approach to extract optimum hedging rules for multireservoir systems | |
| CN116523086A (en) | Single well production dynamic prediction method based on long-short-term memory depth neural network | |
| CN116933619A (en) | Digital twin distribution network fault scene generation method and system based on reinforcement learning | |
| CN112016839A (en) | Flood disaster prediction and early warning method based on QR-BC-ELM | |
| KR20110034288A (en) | A method for predicting diametral creep of candu reactor pressure tubes | |
| CN112434470B (en) | River channel diversion port door water level data extension method and device, storage medium and equipment | |
| CN116029462B (en) | Training method of canal gate flow prediction model | |
| CN104731709A (en) | Software defect predicting method based on JCUDASA_BP algorithm | |
| CN113361818B (en) | Medium-and-long-term power generation optimization method and system for hydroelectric generating set | |
| CN115577903A (en) | Method, device, equipment and medium for evaluating influence of new energy on power grid peak regulation | |
| CN114861571A (en) | Dynamic boundary calculation method and device for river channel type reservoir and storage medium | |
| CN105701720A (en) | Method of assessing optimum depreciation life of electric power equipment and system thereof | |
| JP2005031821A (en) | Hydroelectric power station operation plan preparing device, method, and program | |
| CN116306033B (en) | Hydraulic regulation and control method for controlling overgrowth of submerged plant through flow fluctuation flushing | |
| CN112183728B (en) | Learning strategy generation method and system based on deep learning | |
| CN110707695B (en) | Transient power angle stability margin calculation method and system based on artificial intelligence | |
| CN113435473A (en) | Method and system for generating power grid simulation sample |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |